Search

Extreme weather and globalisation leave our climate vulnerable to invasion by alien species, which have negative impacts on the economy, biodiversity, and ecosystem services. Rapid and accurate identification is key to the control of invasive alien species. However, visually similar species hinder conservation efforts, for example hybrids within the Japanese Knotweed complex. We applied the novel method of ATR-FTIR spectroscopy combined with chemometrics (mathematics applied to chemical data) to historic herbarium samples, taking 1580 spectra in total. Samples included five species from within the interbreeding Japanese Knotweed complex (including three varieties of Japanese Knotweed), six hybrids and five species from the wider Polygonaceae family. Spectral data from herbarium specimens were analysed with several chemometric techniques: support vector machines (SVM) for differentiation between plant types, supported by ploidy levels; principal component analysis loadings and spectral biomarkers to explore differences between the highly invasive Reynoutria japonica var. japonica and its non-invasive counterpart Reynoutria japonica var. compacta; hierarchical cluster analysis (HCA) to investigate the relationship between plants within the Polygonaceae family, of the Fallopia, Reynoutria, Rumex and Fagopyrum genera. ATR-FTIR spectroscopy coupled with SVM successfully differentiated between plant type, leaf surface and geographical location, even in herbarium samples of varying age. Differences between Reynoutria japonica var. japonica and Reynoutria japonica var. compacta included the presence of two polysaccharides, glucomannan and xyloglucan, at higher concentrations in Reynoutria japonica var. japonica than Reynoutria japonica var. compacta. HCA analysis indicated that potential genetic linkages are sometimes masked by environmental factors; an effect that can either be reduced or encouraged by altering the input parameters. Entering the absorbance values for key wavenumbers, previously highlighted by principal component analysis loadings, favours linkages in the resultant HCA dendrogram corresponding to expected genetic relationships, whilst environmental associations are encouraged using the spectral fingerprint region. The ability to distinguish between closely related interbreeding species and hybrids, based on their spectral signature, raises the possibility of using this approach for determining the origin of Japanese knotweed infestations in legal cases where the clonal nature of plants currently makes this difficult and for the targeted control of species and hybrids. These techniques also provide a new method for supporting biogeographical studies.

Objectives We aimed to explore the synergistic combination of a topologically invariant Betti number (BN)-based signature and a biomarker for the accurate prediction of symptomatic (grade ≥2) radiation-induced pneumonitis (RP+) before stereotactic ablative radiotherapy (SABR) for lung cancer. Methods A total of 272 SABR cases with early-stage non-small cell lung cancer were chosen for this study. The occurrence of RP+ was predicted using a support vector machine (SVM) model trained with the combined features of the BN-based signature extracted from planning computed tomography (pCT) images and a pretreatment biomarker, serum Krebs von den Lungen-6 (BN+KL-6 model). In all, 242 (20 RP+ and 222 RP–(grade 1)) and 30 cases (8 RP+ and 22 RP–) were used for training and testing the model, respectively. The BN-based features were extracted from BN maps that characterize topologically invariant heterogeneous traits of potential RP+ lung regions on pCT images by applying histogram- and texture-based feature calculations to the maps. The SVM models were built to predict RP+ patients with a BN signature that was constructed based on the least absolute shrinkage and selection operator logistic regression model. The evaluation of the prediction models was performed based on the area under the receiver operating characteristic curves (AUCs) and accuracy in the test. The performance of the BN+KL-6 model was compared to the performance based on the BN, conventional original pCT, and wavelet decomposition (WD) models. Results The test AUCs obtained for the BN+KL-6, BN, pCT, and WD models were 0.825, 0.807, 0.642, and 0.545, respectively. The accuracies of the BN+KL-6, BN, pCT, and WD models were found to be 0.724, 0.708, 0.591, and 0.534, respectively. Conclusion This study demonstrated the comprehensive performance of the BN+KL-6 model for the prediction of potential RP+ patients before SABR for lung cancer.

To better prevent the potential risks in Internet-based Supply Chain Financing (SCF) products, this paper optimizes and evaluates the Internet-based SCF-oriented Credit Risk Evaluation (CRE) method. Firstly, this paper summarizes 12 risk factors of SCF business, establishes a Risk Assessment Index System (RAIS) with good consistency and stability; then, the principles of Backpropagation (BP) Neural Network (NN) is expounded together with Support Vector Machines (SVM) and Genetic Algorithm (GA) model. Consequently, a CRE model is implemented by the NN tools in MATLAB based on the collection of multiple groups of SCF-oriented risk assessment samples. Subsequently, the assessment samples are trained and tested. Finally, the SCF-oriented CRE model is proposed and verified. The results show that the BP-GA model has presented high prediction consistency with the actual classification. According to the comparison of classification results of SVM, BP model, and BP-GA model, the classification accuracy of test samples of the proposed Internet-based SCF-oriented CRE system using BP-GA model reaches 97.19%; the Type I and Type II error rate of the CRE system based on BP-GA model is 7.2% and 14.21%, respectively. Therefore, a suitable SCF-oriented CRE method is put forward for China’s commercial banks along with scientific and feasible suggestions to manage SCF-oriented credit risks more reasonably and effectively.

Human T-cell Leukemia Virus type-1 (HTLV-1) is an oncovirus that may cause two main life-threatening diseases including a cancer type named Adult T-cell Leukemia/Lymphoma (ATLL) and a neurological and immune disturbance known as HTLV-1 Associated Myelopathy/Tropical Spastic Paraparesis (HAM/TSP). However, a large number of the infected subjects remain as asymptomatic carriers (ACs). There is no comprehensive study that determines which dysregulated genes differentiate the pathogenesis routes toward ATLL or HAM/TSP. Therefore, two main algorithms including weighted gene co-expression analysis (WGCNA) and multi-class support vector machines (SVM) were utilized to find major gene players in each condition. WGCNA was used to find the highly co-regulated genes and multi-class SVM was employed to identify the most important classifier genes. The identified modules from WGCNA were validated in the external datasets. Furthermore, to find specific modules for ATLL and HAM/TSP, the non-preserved modules in another condition were found. In the next step, a model was constructed by multi-class SVM. The results revealed 467, 3249, and 716 classifiers for ACs, ATLL, and HAM/TSP, respectively. Eventually, the common genes between the WGCNA results and classifier genes resulted from multi-class SVM that also determined as differentially expressed genes, were identified. Through these step-wise analyses, PAIP1, BCAS2, COPS2, CTNNB1, FASLG, GTPBP1, HNRNPA1, RBBP6, TOP1, SLC9A1, JMY, PABPC3, and PBX1 were found as the possible critical genes involved in the progression of ATLL. Moreover, FBXO9, ZNF526, ERCC8, WDR5, and XRCC3 were identified as the conceivable major involved genes in the development of HAM/TSP. These genes can be proposed as specific biomarker candidates and therapeutic targets for each disease.

Phenotyping to quantify the total carotenoids content (TCC) is sensitive, time-consuming, tedious, and costly. The development of high-throughput phenotyping tools is essential for screening hundreds of cassava genotypes in a short period of time in the biofortification program. This study aimed to (i) use digital images to extract information on the pulp color of cassava roots and estimate correlations with TCC, and (ii) select predictive models for TCC using colorimetric indices. Red, green and blue images were captured in root samples from 228 biofortified genotypes and the difference in color was analyzed using L*, a*, b*, hue and chroma indices from the International Commission on Illumination (CIELAB) color system and lightness. Colorimetric data were used for principal component analysis (PCA), correlation and for developing prediction models for TCC based on regression and machine learning. A high positive correlation between TCC and the variables b* (r = 0.90) and chroma (r = 0.89) was identified, while the other correlations were median and negative, and the L* parameter did not present a significant correlation with TCC. In general, the accuracy of most prediction models (with all variables and only the most important ones) was high (R2 ranging from 0.81 to 0.94). However, the artificial neural network prediction model presented the best predictive ability (R2 = 0.94), associated with the smallest error in the TCC estimates (root-mean-square error of 0.24). The structure of the studied population revealed five groups and high genetic variability based on PCA regarding colorimetric indices and TCC. Our results demonstrated that the use of data obtained from digital image analysis is an economical, fast, and effective alternative for the development of TCC phenotyping tools in cassava roots with high predictive ability.

In this study, three (3) neural networks (NN) were designed to discriminate between malignant (n = 78) and benign (n = 88) breast tumors using their respective attenuated total reflection Fourier transform infrared (ATR-FTIR) spectral data. A proposed NN-based sensitivity analysis was performed to determine the most significant IR regions that distinguished benign from malignant samples. The result of the NN-based sensitivity analysis was compared to the obtained results from FTIR visual peak identification. In training each NN models, a 10-fold cross validation was performed and the performance metrics–area under the curve (AUC), accuracy, positive predictive value (PPV), specificity rate (SR), negative predictive value (NPV), and recall rate (RR)–were averaged for comparison. The NN models were compared to six (6) machine learning models–logistic regression (LR), Naïve Bayes (NB), decision trees (DT), random forest (RF), support vector machine (SVM) and linear discriminant analysis (LDA)–for benchmarking. The NN models were able to outperform the LR, NB, DT, RF, and LDA for all metrics; while only surpassing the SVM in accuracy, NPV and SR. The best performance metric among the NN models was 90.48% ± 10.30% for AUC, 96.06% ± 7.07% for ACC, 92.18 ± 11.88% for PPV, 94.19 ± 10.57% for NPV, 89.04% ± 16.75% for SR, and 94.34% ± 10.54% for RR. Results from the proposed sensitivity analysis were consistent with the visual peak identification. However, unlike the FTIR visual peak identification method, the NN-based method identified the IR region associated with C–OH C–OH group carbohydrates as significant. IR regions associated with amino acids and amide proteins were also determined as possible sources of variability. In conclusion, results show that ATR-FTIR via NN is a potential diagnostic tool. This study also suggests a possible more specific method in determining relevant regions within a sample’s spectrum using NN.

With the development of economic integration, Beijing has become more closely connected with surrounding areas, which gradually formed the Beijing metropolitan area (BMA). The authors define the scope of BMA from two dimensions of space and time. BMA is determined to be the built-up area of Beijing and its surrounding 10 districts. Designed questionnaire survey the personal characteristics, family characteristics, and travel characteristics of residents from 10 districts in the surrounding BMA. The statistical analysis of questionnaires shows that the supply of public transportation is insufficient and cannot meet traffic demand. Further, the travel mode prediction model of Softmax regression machine learning algorithm for BMA (SRBM) is established. To further verify the prediction performance of the proposed model, the Multinomial Logit Model (MNL) and Support Vector Machine (SVM), model are introduced to compare the prediction accuracy. The results show that the constructed SRBM model exhibits high prediction accuracy, with an average accuracy of 88.35%, which is 2.83% and 18.11% higher than the SVM and MNL models, respectively. This article provides new ideas for the prediction of travel modes in the Beijing metropolitan area.

Versatile video coding (VVC) achieves enormous improvement over the advanced high efficiency video coding (HEVC) standard due to the adoption of the quadtree with nested multi-type tree (QTMT) partition structure and other coding tools. However, the computational complexity increases dramatically as well. To tackle this problem, we propose a decision tree accelerated coding tree units (CTU) partition algorithm for intra prediction in VVC. Firstly, specially designated image features are extracted to characterize the coding unit (CU) complexity. Then, the trained decision tree is employed to predict the partition results. Finally, based on our newly designed intra prediction framework, the partition process is early terminated or redundant partition modes are screened out. The experimental results show that the proposed algorithm could achieve around 52% encoding time reduction for various test video sequences on average with only 1.75% Bjontegaard delta bit rate increase compared with the reference test model VTM9.0 of VVC.

The cognitive approach to psychotherapy aims to change patients’ maladaptive schemas, that is, overly negative views on themselves, the world, or the future. To obtain awareness of these views, they record their thought processes in situations that caused pathogenic emotional responses. The schemas underlying such thought records have, thus far, been largely manually identified. Using recent advances in natural language processing, we take this one step further by automatically extracting schemas from thought records. To this end, we asked 320 healthy participants on Amazon Mechanical Turk to each complete five thought records consisting of several utterances reflecting cognitive processes. Agreement between two raters on manually scoring the utterances with respect to how much they reflect each schema was substantial (Cohen’s κ = 0.79). Natural language processing software pretrained on all English Wikipedia articles from 2014 (GLoVE embeddings) was used to represent words and utterances, which were then mapped to schemas using k-nearest neighbors algorithms, support vector machines, and recurrent neural networks. For the more frequently occurring schemas, all algorithms were able to leverage linguistic patterns. For example, the scores assigned to the Competence schema by the algorithms correlated with the manually assigned scores with Spearman correlations ranging between 0.64 and 0.76. For six of the nine schemas, a set of recurrent neural networks trained separately for each of the schemas outperformed the other algorithms. We present our results here as a benchmark solution, since we conducted this research to explore the possibility of automatically processing qualitative mental health data and did not aim to achieve optimal performance with any of the explored models. The dataset of 1600 thought records comprising 5747 utterances is published together with this article for researchers and machine learning enthusiasts to improve upon our outcomes. Based on our promising results, we see further opportunities for using free-text input and subsequent natural language processing in other common therapeutic tools, such as ecological momentary assessments, automated case conceptualizations, and, more generally, as an alternative to mental health scales.

CD36 (cluster of differentiation 36) is a membrane protein involved in lipid metabolism and has been linked to pathological conditions associated with metabolic disorders, such as diabetes and dyslipidemia. A case-control study was conducted and included 177 patients with type-2 diabetes mellitus (T2DM) and 173 control subjects to study the involvement of CD36 gene rs1761667 (G>A) and rs1527483 (C>T) polymorphisms in the pathogenesis of T2DM and dyslipidemia among Jordanian population. Lipid profile, blood sugar, gender and age were measured and recorded. Also, genotyping analysis for both polymorphisms was performed. Following statistical analysis, 10 different neural networks and machine learning (ML) tools were used to predict subjects with diabetes or dyslipidemia. Towards further understanding of the role of CD36 protein and gene in T2DM and dyslipidemia, a protein-protein interaction network and meta-analysis were carried out. For both polymorphisms, the genotypic frequencies were not significantly different between the two groups (p > 0.05). On the other hand, some ML tools like multilayer perceptron gave high prediction accuracy (≥ 0.75) and Cohen’s kappa (κ) (≥ 0.5). Interestingly, in K-star tool, the accuracy and Cohen’s κ values were enhanced by including the genotyping results as inputs (0.73 and 0.46, respectively, compared to 0.67 and 0.34 without including them). This study confirmed, for the first time, that there is no association between CD36 polymorphisms and T2DM or dyslipidemia among Jordanian population. Prediction of T2DM and dyslipidemia, using these extensive ML tools and based on such input data, is a promising approach for developing diagnostic and prognostic prediction models for a wide spectrum of diseases, especially based on large medical databases.

This study aims to investigate the influence of all the mixture components of high-performance concrete (HPC) on its early compressive strength, ranging from 1 to 14 days. To this purpose, a Gaussian Process Regression (GPR) algorithm was first constructed using a database gathered from the available literature. The database included the contents of cement, blast furnace slag (BFS), fly ash (FA), water, superplasticizer, coarse, fine aggregates, and testing age as input variables to predict the output of the problem, which was the early compressive strength. Several standard statistical criteria, such as the Pearson correlation coefficient, root mean square error and mean absolute error, were used to quantify the performance of the GPR model. To analyze the sensitivity and influence of the HPC mixture components, partial dependence plots analysis was conducted with both one-dimensional and two-dimensional. Firstly, the results showed that the GPR performed well in predicting the early strength of HPC. Second, it was determined that the cement content and testing age of HPC were the most sensitive and significant elements affecting the early strength of HPC, followed by the BFS, water, superplasticizer, FA, fine aggregate, and coarse aggregate contents. To put it simply, this research might assist engineers select the appropriate amount of mixture components in the HPC production process to obtain the necessary early compressive strength.

The dimensionality of the spatially distributed channels and the temporal resolution of electroencephalogram (EEG) based brain-computer interfaces (BCI) undermine emotion recognition models. Thus, prior to modeling such data, as the final stage of the learning pipeline, adequate preprocessing, transforming, and extracting temporal (i.e., time-series signals) and spatial (i.e., electrode channels) features are essential phases to recognize underlying human emotions. Conventionally, inter-subject variations are dealt with by avoiding the sources of variation (e.g., outliers) or turning the problem into a subject-deponent. We address this issue by preserving and learning from individual particularities in response to affective stimuli. This paper investigates and proposes a subject-independent emotion recognition framework that mitigates the subject-to-subject variability in such systems. Using an unsupervised feature selection algorithm, we reduce the feature space that is extracted from time-series signals. For the spatial features, we propose a subject-specific unsupervised learning algorithm that learns from inter-channel co-activation online. We tested this framework on real EEG benchmarks, namely DEAP, MAHNOB-HCI, and DREAMER. We train and test the selection outcomes using nested cross-validation and a support vector machine (SVM). We compared our results with the state-of-the-art subject-independent algorithms. Our results show an enhanced performance by accurately classifying human affection (i.e., based on valence and arousal) by 16%–27% compared to other studies. This work not only outperforms other subject-independent studies reported in the literature but also proposes an online analysis solution to affection recognition.

Smartphone usage is nearly ubiquitous worldwide, and Android provides the leading open-source operating system, retaining the most significant market share and active user population of all open-source operating systems. Hence, malicious actors target the Android operating system to capitalize on this consumer reliance and vulnerabilities present in the system. Hackers often use confidential user data to exploit users for advertising, extortion, and theft. Notably, most Android malware detection tools depend on conventional machine-learning algorithms; hence, they lose the benefits of metaheuristic optimization. Here, we introduce a novel detection system based on optimizing the random vector functional link (RVFL) using the artificial Jellyfish Search (JS) optimizer following dimensional reduction of Android application features. JS is used to determine the optimal configurations of RVFL to improve classification performance. RVFL+JS minimizes the runtime of the execution of the optimized models with the best performance metrics, based on a dataset consisting of 11,598 multi-class applications and 471 static and dynamic features.

Leptospirosis is a zoonosis caused by the pathogenic bacterium Leptospira. The Microscopic Agglutination Test (MAT) is widely used as the gold standard for diagnosis of leptospirosis. In this method, diluted patient serum is mixed with serotype-determined Leptospiras, and the presence or absence of aggregation is determined under a dark-field microscope to calculate the antibody titer. Problems of the current MAT method are 1) a requirement of examining many specimens per sample, and 2) a need of distinguishing contaminants from true aggregates to accurately identify positivity. Therefore, increasing efficiency and accuracy are the key to refine MAT. It is possible to achieve efficiency and standardize accuracy at the same time by automating the decision making process. In this study, we built an automatic identification algorithm of MAT using a machine learning method to determine aggregation within microscopic images. The machine learned the features from 316 positive and 230 negative MAT images created with sera of Leptospira- infected (positive) and non-infected (negative) hamsters, respectively. In addition to the acquired original images, wavelet-transformed images were also considered as features. We utilized a support vector machine (SVM) as a proposed decision method. We validated the trained SVMs with 210 positive and 154 negative images. When the features were obtained from original or wavelet-transformed images, all negative images were misjudged as positive, and the classification performance was very low with sensitivity of 1 and specificity of 0. In contrast, when the histograms of wavelet coefficients were used as features, the performance was greatly improved with sensitivity of 0.99 and specificity of 0.99. We confirmed that the current algorithm judges the positive or negative of agglutinations in MAT images and gives the further possibility of automatizing MAT procedure.

Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users—pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups—for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.

In recent years, advancements in Internet and cloud technologies have led to a significant increase in electronic trading in which consumers make online purchases and transactions. This growth leads to unauthorized access to users’ sensitive information and damages the resources of an enterprise. Phishing is one of the familiar attacks that trick users to access malicious content and gain their information. In terms of website interface and uniform resource locator (URL), most phishing webpages look identical to the actual webpages. Various strategies for detecting phishing websites, such as blacklist, heuristic, Etc., have been suggested. However, due to inefficient security technologies, there is an exponential increase in the number of victims. The anonymous and uncontrollable framework of the Internet is more vulnerable to phishing attacks. Existing research works show that the performance of the phishing detection system is limited. There is a demand for an intelligent technique to protect users from the cyber-attacks. In this study, the author proposed a URL detection technique based on machine learning approaches. A recurrent neural network method is employed to detect phishing URL. Researcher evaluated the proposed method with 7900 malicious and 5800 legitimate sites, respectively. The experiments’ outcome shows that the proposed method’s performance is better than the recent approaches in malicious URL detection.

Gene expression profiles can be utilized in the diagnosis of critical diseases such as cancer. The selection of biomarker genes from these profiles is significant and crucial for cancer detection. This paper presents a framework proposing a two-stage multifilter hybrid model of feature selection for colon cancer classification. Colon cancer is being extremely common nowadays among other types of cancer. There is a need to find fast and an accurate method to detect the tissues, and enhance the diagnostic process and the drug discovery. This paper reports on a study whose objective has been to improve the diagnosis of cancer of the colon through a two-stage, multifilter model of feature selection. The model described deals with feature selection using a combination of Information Gain and a Genetic Algorithm. The next stage is to filter and rank the genes identified through this method using the minimum Redundancy Maximum Relevance (mRMR) technique. The final phase is to further analyze the data using correlated machine learning algorithms. This two-stage approach, which involves the selection of genes before classification techniques are used, improves success rates for the identification of cancer cells. It is found that Decision Tree, K-Nearest Neighbor, and Naïve Bayes classifiers had showed promising accurate results using the developed hybrid framework model. It is concluded that the performance of our proposed method has achieved a higher accuracy in comparison with the existing methods reported in the literatures. This study can be used as a clue to enhance treatment and drug discovery for the colon cancer cure.

Background Even though conceptually, Tuberculosis (TB) is almost always curable, it is currently the world’s leading infectious killer. Patients with pulmonary TB are the source of transmission. Approximately 23% of the world’s population is believed to be latently infected with TB bacteria, and 5–15% of them will progress at any point in time to develop the disease. There was a global diagnostic gap of 2.9 million between notifications of new cases and the estimated number of incident cases, and Indonesia carries the third-highest of this gap. Therefore, screening TB among the community is of great importance to prevent further transmission and infection. The electronic nose for screening TB (eNose-TB) project is initiated in Yogyakarta, Indonesia, to screen TB by breath test with an electronic-nose that is easy-to-use, point-of-care, does not expose patients to radiation, and can be produced at low cost. Methods/Design The objectives of the two-phase planned project are to: 1) investigate the potential of an eNose-TB as a screening tool in Indonesia, in comparison with screening with clinical symptoms and chest radiology, which are currently used as a standard, and 2) analyze the time and cost of a screening algorithm with eNose-TB to obtain additional case detection. A cross-sectional study will be conducted in the first phase to validate the eNose-TB. The validation phase will involve 395 presumptive TB patients in the Surakarta General Hospital, Central Java. In the second phase, a cross-sectional research will be conducted, involving 1,383 adults and children in the municipality of Yogyakarta and Kulon Progo district of Yogyakarta Province. Discussion The findings will provide data concerning the sensitivity and specificity of the eNose-TB as a screening tool for tuberculosis, and the time and cost analysis of a screening algorithm with the eNose. Trial registration NCT04567498; https://clinicaltrials.gov/.

PHOTONAI is a high-level Python API designed to simplify and accelerate machine learning model development. It functions as a unifying framework allowing the user to easily access and combine algorithms from different toolboxes into custom algorithm sequences. It is especially designed to support the iterative model development process and automates the repetitive training, hyperparameter optimization and evaluation tasks. Importantly, the workflow ensures unbiased performance estimates while still allowing the user to fully customize the machine learning analysis. PHOTONAI extends existing solutions with a novel pipeline implementation supporting more complex data streams, feature combinations, and algorithm selection. Metrics and results can be conveniently visualized using the PHOTONAI Explorer and predictive models are shareable in a standardized format for further external validation or application. A growing add-on ecosystem allows researchers to offer data modality specific algorithms to the community and enhance machine learning in the areas of the life sciences. Its practical utility is demonstrated on an exemplary medical machine learning problem, achieving a state-of-the-art solution in few lines of code. Source code is publicly available on Github, while examples and documentation can be found at www.photon-ai.com.

Feature selection is an important task in big data analysis and information retrieval processing. It reduces the number of features by removing noise, extraneous data. In this paper, one feature subset selection algorithm based on damping oscillation theory and support vector machine classifier is proposed. This algorithm is called the Maximum Kendall coefficient Maximum Euclidean Distance Improved Gray Wolf Optimization algorithm (MKMDIGWO). In MKMDIGWO, first, a filter model based on Kendall coefficient and Euclidean distance is proposed, which is used to measure the correlation and redundancy of the candidate feature subset. Second, the wrapper model is an improved grey wolf optimization algorithm, in which its position update formula has been improved in order to achieve optimal results. Third, the filter model and the wrapper model are dynamically adjusted by the damping oscillation theory to achieve the effect of finding an optimal feature subset. Therefore, MKMDIGWO achieves both the efficiency of the filter model and the high precision of the wrapper model. Experimental results on five UCI public data sets and two microarray data sets have demonstrated the higher classification accuracy of the MKMDIGWO algorithm than that of other four state-of-the-art algorithms. The maximum ACC value of the MKMDIGWO algorithm is at least 0.5% higher than other algorithms on 10 data sets.

BackgroundAlcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to continue outpatient treatment, predicting and managing patients who might discontinue treatment becomes necessary. Accordingly, we developed a machine learning (ML) algorithm to predict which the risk of patients dropping out of outpatient treatment schemes.MethodsA total of 839 patients were selected out of 2,206 patients admitted for AUD in three hospitals under the Catholic Central Medical Center in Korea. We implemented six ML models—logistic regression, support vector machine, k-nearest neighbor, random forest, neural network, and AdaBoost—and compared the prediction performances thereof.ResultsAmong the six models, AdaBoost was selected as the final model for recommended use owing to its area under the receiver operating characteristic curve (AUROC) of 0.72. The four variables affecting the prediction based on feature importance were the length of hospitalization, age, residential area, and diabetes.ConclusionAn ML algorithm was developed herein to predict the risk of patients with AUD in Korea discontinuing outpatient treatment. By testing and validating various machine learning models, we determined the best performing model, AdaBoost, as the final model for recommended use. Using this model, clinicians can manage patients with high risks of discontinuing treatment and establish patient-specific treatment strategies. Therefore, our model can potentially enable patients with AUD to successfully complete their treatments by identifying them before they can drop out.

Abnormalities and defects that can cause lumbar spinal stenosis often occur in the Intervertebral Disc (IVD) of the patient’s lumbar spine. Their automatic detection and classification require an application of an image analysis algorithm on suitable images, such as mid-sagittal images or traverse mid-height intervertebral disc slices, as inputs. Hence the process of selecting and separating these images from other medical images in the patient’s set of scans is necessary. However, the technological progress in making this process automated is still lagging behind other areas in medical image classification research. In this paper, we report the result of our investigation on the suitability and performance of different approaches of machine learning to automatically select the best traverse plane that cuts closest to the half-height of an IVD from a database of lumbar spine MRI images. This study considers images features extracted using eleven different pre-trained Deep Convolution Neural Network (DCNN) models. We investigate the effectiveness of three dimensionality-reduction techniques and three feature-selection techniques on the classification performance. We also investigate the performance of five different Machine Learning (ML) algorithms and three Fully Connected (FC) neural network learning optimizers which are used to train an image classifier with hyperparameter optimization using a wide range of hyperparameter options and values. The different combinations of methods are tested on a publicly available lumbar spine MRI dataset consisting of MRI studies of 515 patients with symptomatic back pain. Our experiment shows that applying the Support Vector Machine algorithm with a short Gaussian kernel on full-length image features extracted using a pre-trained DenseNet201 model is the best approach to use. This approach gives the minimum per-class classification performance of around 0.88 when measured using the precision and recall metrics. The median performance measured using the precision metric ranges from 0.95 to 0.99 whereas that using the recall metric ranges from 0.93 to 1.0. When only considering the L3/L4, L4/L5, and L5/S1 classes, the minimum F1-Scores range between 0.93 to 0.95, whereas the median F1-Scores range between 0.97 to 0.99.

Diagnostic tests for hearing impairment not only determines the presence (or absence) of hearing loss, but also evaluates its degree and type, and provides physicians with essential data for future treatment and rehabilitation. Therefore, accurately measuring hearing loss conditions is very important for proper patient understanding and treatment. In current-day practice, to quantify the level of hearing loss, physicians exploit specialized test scores such as the pure-tone audiometry (PTA) thresholds and speech discrimination scores (SDS) as quantitative metrics in examining a patient’s auditory function. However, given that these metrics can be easily affected by various human factors, which includes intentional (or accidental) patient intervention, there are needs to cross validate the accuracy of each metric. By understanding a “normal” relationship between the SDS and PTA, physicians can reveal the need for re-testing, additional testing in different dimensions, and also potential malingering cases. For this purpose, in this work, we propose a prediction model for estimating the SDS of a patient by using PTA thresholds via a Random Forest-based machine learning approach to overcome the limitations of the conventional statistical (or even manual) methods. For designing and evaluating the Random Forest-based prediction model, we collected a large-scale dataset from 12,697 subjects, and report a SDS level prediction accuracy of 95.05% and 96.64% for the left and right ears, respectively. We also present comparisons with other widely-used machine learning algorithms (e.g., Support Vector Machine, Multi-layer Perceptron) to show the effectiveness of our proposed Random Forest-based approach. Results obtained from this study provides implications and potential feasibility in providing a practically-applicable screening tool for identifying patient-intended malingering in hearing loss-related tests.

Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients’ day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.

Accurate streamflow prediction plays a pivotal role in hydraulic project design, nonpoint source pollution estimation, and water resources planning and management. However, the highly non-linear relationship between rainfall and runoff makes prediction difficult with desirable accuracy. To improve the accuracy of monthly streamflow prediction, a seasonal Support Vector Regression (SVR) model coupled to the Soil and Water Assessment Tool (SWAT) model was developed for 13 subwatersheds in the Illinois River watershed (IRW), U.S. Terrain, precipitation, soil, land use and land cover, and monthly streamflow data were used to build the SWAT model. SWAT Streamflow output and the upstream drainage area were used as two input variables into SVR to build the hybrid SWAT-SVR model. The Calibration Uncertainty Procedure (SWAT-CUP) and Sequential Uncertainty Fitting-2 (SUFI-2) algorithms were applied to compare the model performance against SWAT-SVR. The spatial calibration and leave-one-out sampling methods were used to calibrate and validate the hybrid SWAT-SVR model. The results showed that the SWAT-SVR model had less deviation and better performance than SWAT-CUP simulations. SWAT-SVR predicted streamflow more accurately during the wet season than the dry season. The model worked well when it was applied to simulate medium flows with discharge between 5 m3 s-1 and 30 m3 s-1, and its applicable spatial scale fell between 500 to 3000 km2. The overall performance of the model on yearly time series is “Satisfactory”. This new SWAT-SVR model has not only the ability to capture intrinsic non-linear behaviors between rainfall and runoff while considering the mechanism of runoff generation but also can serve as a reliable regional tool for an ungauged or limited data watershed that has similar hydrologic characteristics with the IRW.

Tissue engineering and gene therapy strategies offer new ways to repair permanent damage to mechanosensory hair cells (MHCs) by differentiating human Wharton’s Jelly cells (HWJCs). Conventionally, these strategies require the classification of each cell as differentiated or undifferentiated. Automated classification tools, however, may serve as a novel method to rapidly classify these cells. In this paper, images from previous work, where HWJCs were differentiated into MHC-like cells, were examined. Various cell features were extracted from these images, and those which were pertinent to classification were identified. Different machine learning models were then developed, some using all extracted data and some using only certain features. To evaluate model performance, the area under the curve (AUC) of the receiver operating characteristic curve was primarily used. This paper found that limiting algorithms to certain features consistently improved performance. The top performing model, a voting classifier model consisting of two logistic regressions, a support vector machine, and a random forest classifier, obtained an AUC of 0.9638. Ultimately, this paper illustrates the viability of a novel machine learning pipeline to automate the classification of undifferentiated and differentiated cells. In the future, this research could aid in automated strategies that determine the viability of MHC-like cells after differentiation.

Fin-tech is an emerging field, inspiring revolutionary innovations in the financial field. It may initiate the evolutionary episode of the financial research, where volatility forecasting is a crucial topic in finance. For forecasting volatility, GARCH model is a prevailing model, however, further improvement of the GARCH model is still challenging. In this paper, we demonstrate how Fintech can play a part in volatility forecasting by employing a metaheuristic procedure called Genetic Programming. On the basis, we are able to develop a new volatility forecasting model, which can beat GARCH family models (including GARCH, IGARCH and TGARCH models) in a significant way. Since genetic programming is an evolutionary algorithm based on the principles of natural selection, this innovative work will be a breakthrough point in the financial area. The innovation of this paper demonstrates how GP technology can be applied in the financial field, attempting to explore the volatility forecasting area from the combination of new technology and finance, known as fintech. More importantly, when the formula of volatility forecasting is unknown as we introduce a new factor, namely, the liquidity factor, we unveil that how GP method can be helpful in determining the specific volatility forecasting model format. We thereby exhibit the liquidity effects on volatility forecasting filed from the fintech perspective.

This study proposes a reliable computer-aided framework to identify gait fluctuations associated with a wide range of degenerative neuromuscular disease (DNDs) and health conditions. Investigated DNDs included amyotrophic lateral sclerosis (ALS), Parkinson’s disease (PD), and Huntington’s disease (HD). We further performed a statistical and classification comparison elucidating the discriminative capability of different gait signals, including vertical ground reaction force (VGRF), stride duration, stance duration, and swing duration. Feature representation of these gait signals was based on statistical amplitude quantification using the root mean square (RMS), variance, kurtosis, and skewness metrics. We investigated various decision tree (DT) based ensemble methods such as bagging, adaptive boosting (AdaBoost), random under-sampling boosting (RUSBoost), and random subspace to tackle the challenge of multi-class classification. Experimental results showed that AdaBoost ensembling provided a 6.49%, 0.78%, 2.31%, and 2.72% prediction rate improvement for the VGRF, stride, stance, and swing signals, respectively. The proposed approach achieved the highest classification accuracy of 99.17%, sensitivity of 98.23%, and specificity of 99.43%, using the VGRF-based features and the adaptive boosting classification model. This work demonstrates the effective capability of using simple gait fluctuation analysis and machine learning approaches to detect DNDs. Computer-aided analysis of gait fluctuations provides a promising advent to enhance clinical diagnosis of DNDs.

Brain tumor is not most common, but truculent type of cancer. Therefore, correct prediction of its aggressiveness nature at an early stage would influence the treatment strategy. Although several diagnostic methods based on different modalities exist, a pre-operative method for determining tumor malignancy state still remains as an active research area. In this regard, the paper presents a new method for the assessment of tumor grades using conventional MR sequences namely, T1, T1 with contrast enhancement, T2 and FLAIR. The proposed method for tumor gradation is mainly based on feature extraction using multiresolution image analysis and classification using support vector machine. Since the wavelet features of different tumor subregions, obtained from single MR sequence, do not carry equally important information, a wavelet fusion technique is proposed based on the texture information content of each voxel. The concept of texture gradient, used in the proposed algorithm, fuses the wavelet coefficients of the given MR sequences. The feature vector is then derived from the co-occurrence of fused wavelet coefficients. As each wavelet subband contains distinct detail information, a novel concept of multispectral co-occurrence of wavelet coefficients is introduced to capture the spatial correlation among different subbands. It enables to convey more informative features to characterize the tumor type. The effectiveness of the proposed method is analyzed, with respect to six classification performance indices, on BRATS 2012 and BRATS 2014 data sets. The classification accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve assessed by the ten-fold cross-validation are 91.3%, 96.8%, 66.7%, 92.4%, 88.4%, and 92.0%, respectively, on real brain MR data.

Academic institutions need to maintain publication lists for thousands of faculty and other scholars. Automated tools are essential to minimize the need for direct feedback from the scholars themselves who are practically unable to commit necessary effort to keep the data accurate. In relying exclusively on clustering techniques, author disambiguation applications fail to satisfy key use cases of academic institutions. Algorithms can perfectly group together a set of publications authored by a common individual, but, for them to be useful to an academic institution, they need to programmatically and recurrently map articles to thousands of scholars of interest en masse. Consistent with a savvy librarian’s approach for generating a scholar’s list of publications, identity-driven authorship prediction is the process of using information about a scholar to quantify the likelihood that person wrote certain articles. ReCiter is an application that attempts to do exactly that. ReCiter uses institutionally-maintained identity data such as name of department and year of terminal degree to predict which articles a given scholar has authored. To compute the overall score for a given candidate article from PubMed (and, optionally, Scopus), ReCiter uses: up to 12 types of commonly available, identity data; whether other members of a cluster have been accepted or rejected by a user; and the average score of a cluster. In addition, ReCiter provides scoring and qualitative evidence supporting why particular articles are suggested. This context and confidence scoring allows curators to more accurately provide feedback on behalf of scholars. To help users to more efficiently curate publication lists, we used a support vector machine analysis to optimize the scoring of the ReCiter algorithm. In our analysis of a diverse test group of 500 scholars at an academic private medical center, ReCiter correctly predicted 98% of their publications in PubMed.

Effective soil spectral band selection and modeling methods can improve modeling accuracy. To establish a hyperspectral prediction model of soil organic matter (SOM) content, this study investigated a forested Eucalyptus plantation in Huangmian Forest Farm, Guangxi, China. The Ranger and Lasso algorithms were used to screen spectral bands. Subsequently, models were established using four algorithms: partial least squares regression, random forest (RF), a support vector machine, and an artificial neural network (ANN). The optimal model was then selected. The results showed that the modeling accuracy was higher when band selection was based on the Ranger algorithm than when it was based on the Lasso algorithm. ANN modeling had the best goodness of fit, and the model established by RF had the most stable modeling results. Based on the above results, a new method is proposed in this study for band selection in the early phase of soil hyperspectral modeling. The Ranger algorithm can be applied to screen the spectral bands, and ANN or RF can then be selected to construct the prediction model based on different datasets, which is applicable to establish the prediction model of SOM content in red soil plantations. This study provides a reference for the remote sensing of soil fertility in forests of different soil types and a theoretical basis for developing portable equipment for the hyperspectral measurement of SOM content in forest habitats.

Pregnancy is a complicated and long procedure during one or more offspring development inside a woman. A short period of oxygen shortage after birth is quite normal for most babies and does not threaten their health. However, if babies have to suffer from a long period of oxygen shortage, then this condition is an indication of pathological fetal intolerance, which probably causes their death. The identification of the pathological fetal intolerance from the physical oxygen shortage is one of the important clinical problems in obstetrics for a long time. The clinical syndromes typically manifest five symptoms that indicate that the baby may suffer from fetal intolerance. At present, liquid biopsy combined with high-throughput sequencing or mass spectrum techniques provides a quick approach to detect real-time alteration in the peripheral blood at multiple levels with the rapid development of molecule sequencing technologies. Gene methylation is functionally correlated with gene expression; thus, the combination of gene methylation and expression information would help in screening out the key regulators for the pathogenesis of fetal intolerance. We combined gene methylation and expression features together and screened out the optimal features, including gene expression or methylation signatures, for fetal intolerance prediction for the first time. In addition, we applied various computational methods to construct a comprehensive computational pipeline to identify the potential biomarkers for fetal intolerance dependent on the liquid biopsy samples. We set up qualitative and quantitative computational models for the prediction for fetal intolerance during pregnancy. Moreover, we provided a new prospective for the detailed pathological mechanism of fetal intolerance. This work can provide a solid foundation for further experimental research and contribute to the application of liquid biopsy in antenatal care.

Fruit quality attributes are important factors for designing a market for agricultural goods and commodities. Support vector regression (SVR), MLR, and ANN models were established to predict the mass of ber fruits (Ziziphus mauritiana Lamk.) based on the axial dimensions of the fruit from manual measurements of fruit length, minor fruit diameter, and maximum fruit diameter of four ber cultivars. The precision and accuracy of the established models were assessed given their predicted values. The results revealed that using the validation dataset, the developed ANN (R2 = 0.9771; root mean square error [RMSE] = 1.8479 g) and SVR (R2 = 0.9947; RMSE = 1.8814 g) models produced better results when predicting ber fruit mass than those obtained by the MLR model (R2 = 0.4614; RMSE = 11.3742 g). In estimating ber fruit mass, the established SVR and ANN models produced more precise prediction values than those produced by the MLR model; however, the performance differences between the SVR and ANN models were not clear.

Background and objective Dynamic muscle fascicle length measurements through B-mode ultrasound have become popular for the non-invasive physiological insights they provide regarding musculoskeletal structure-function. However, current practices typically require time consuming post-processing to track muscle length changes from B-mode images. A real-time measurement tool would not only save processing time but would also help pave the way toward closed-loop applications based on feedback signals driven by in vivo muscle length change patterns. In this paper, we benchmark an approach that combines traditional machine learning (ML) models with B-mode ultrasound recordings to obtain muscle fascicle length changes in real-time. To gauge the utility of this framework for ‘in-the-loop’ applications, we evaluate accuracy of the extracted muscle length change signals against time-series’ derived from a standard, post-hoc automated tracking algorithm. Methods We collected B-mode ultrasound data from the soleus muscle of six participants performing five defined ankle motion tasks: (a) seated, constrained ankle plantarflexion, (b) seated, free ankle dorsi/plantarflexion, (c) weight-bearing, calf raises (d) walking, and then a (e) mix. We trained machine learning (ML) models by pairing muscle fascicle lengths obtained from standardized automated tracking software (UltraTrack) with the respective B-mode ultrasound image input to the tracker, frame-by-frame. Then we conducted hyperparameter optimizations for five different ML models using a grid search to find the best performing parameters for a combination of high correlation and low RMSE between ML and UltraTrack processed muscle fascicle length trajectories. Finally, using the global best model/hyperparameter settings, we comprehensively evaluated training-testing outcomes within subject (i.e., train and test on same subject), cross subject (i.e., train on one subject, test on another) and within/direct cross task (i.e., train and test on same subject, but different task). Results Support vector machine (SVM) was the best performing model with an average r = 0.70 ±0.34 and average RMSE = 2.86 ±2.55 mm across all direct training conditions and average r = 0.65 ±0.35 and average RMSE = 3.28 ±2.64 mm when optimized for all cross-participant conditions. Comparisons between ML vs. UltraTrack (i.e., ground truth) tracked muscle fascicle length versus time data indicated that ML tracked images reliably capture the salient qualitative features in ground truth length change data, even when correlation values are on the lower end. Furthermore, in the direct training, calf raises condition, which is most comparable to previous studies validating automated tracking performance during isolated contractions on a dynamometer, our ML approach yielded 0.90 average correlation, in line with other accepted tracking methods in the field. Conclusions By combining B-mode ultrasound and classical ML models, we demonstrate it is possible to achieve real-time tracking of human soleus muscle fascicles across a number of functionally relevant contractile conditions. This novel sensing modality paves the way for muscle physiology in-the-loop applications that could be used to modify gait via biofeedback or unlock novel wearable device control techniques that could enable restored or augmented locomotion performance.

Phoneme pronunciations are usually considered as basic skills for learning a foreign language. Practicing the pronunciations in a computer-assisted way is helpful in a self-directed or long-distance learning environment. Recent researches indicate that machine learning is a promising method to build high-performance computer-assisted pronunciation training modalities. Many data-driven classifying models, such as support vector machines, back-propagation networks, deep neural networks and convolutional neural networks, are increasingly widely used for it. Yet, the acoustic waveforms of phoneme are essentially modulated from the base vibrations of vocal cords, and this fact somehow makes the predictors collinear, distorting the classifying models. A commonly-used solution to address this issue is to suppressing the collinearity of predictors via partial least square regressing algorithm. It allows to obtain high-quality predictor weighting results via predictor relationship analysis. However, as a linear regressor, the classifiers of this type possess very simple topology structures, constraining the universality of the regressors. For this issue, this paper presents an heterogeneous phoneme recognition framework which can further benefit the phoneme pronunciation diagnostic tasks by combining the partial least square with support vector machines. A French phoneme data set containing 4830 samples is established for the evaluation experiments. The experiments of this paper demonstrates that the new method improves the accuracy performance of the phoneme classifiers by 0.21 - 8.47% comparing to state-of-the-arts with different data training data density.

Previous studies have shown that functional mobility, along with other physical functions, decreases with advanced age. However, it is still unclear which domains of functioning (body structures, body functions, and activities) are most closely related to functional mobility. This study used machine learning classification to predict the rankings of Timed Up and Go tests based on the results of four assessments (soft lean mass, FEV1/FVC, knee extension torque, and one-leg standing time). We tested whether assessment results for each level could predict functional mobility assessments in older adults. Using support vector machines for machine learning classification, we verified that the four assessments of each level could classify functional mobility. Knee extension torque (from the body function domain) was the most closely related assessment. Naturally, the classification accuracy rate increased with a larger number of assessments as explanatory variables. However, knee extension torque remained the highest of all assessments. This extended to all combinations (of 2–3 assessments) that included knee extension torque. This suggests that resistance training may help protect individuals suffering from age-related declines in functional mobility.

Artificial intelligence (AI) is emerging as a technology at the center of many political, economic, and societal debates. This paper formulates a new AI patent search strategy and applies this to provide a landscape analysis of AI innovation dynamics and technology evolution. The paper uses patent analyses, network analyses, and source path link count algorithms to examine AI spatial and temporal trends, cooperation features, cross-organization knowledge flow and technological routes. Results indicate a growing yet concentrated, non-collaborative and multi-path development and protection profile for AI patenting, with cross-organization knowledge flows based mainly on interorganizational knowledge citation links.

Much of the current research on supervised modelling is focused on maximizing outcome prediction accuracy. However, in engineering disciplines, an arguably more important goal is that of feature extraction, the identification of relevant features associated with the various outcomes. For instance, in microbial communities, the identification of keystone species can often lead to improved prediction of future behavioral shifts. This paper proposes a novel feature extractor based on Deep Learning, which is largely agnostic to underlying assumptions regarding the training data. Starting from a collection of microbial species abundance counts, the Deep Learning model first trains itself to classify the selected distinct habitats. It then identifies indicator species associated with the habitats. The results are then compared and contrasted with those obtained by traditional statistical techniques. The indicator species are similar when compared at top taxonomic levels such as Domain and Phylum, despite visible differences in lower levels such as Class and Order. More importantly, when our estimated indicators are used to predict final habitat labels using simpler models (such as Support Vector Machines and traditional Artificial Neural Networks), the prediction accuracy is improved. Overall, this study serves as a preliminary step that bridges modern, black-box Machine Learning models with traditional, domain expertise-rich techniques.

Obstructive sleep apnea (OSA) is a common chronic sleep disorder that disrupts breathing during sleep and is associated with many other medical conditions, including hypertension, coronary heart disease, and depression. Clinically, the standard for diagnosing OSA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of OSA diagnosis in public health sectors. Therefore, electrocardiogram (ECG)-based methods for OSA detection have been proposed to automate the polysomnography procedure and reduce its discomfort. So far, most of the proposed approaches rely on feature engineering, which calls for advanced expert knowledge and experience. This paper proposes a novel fused-image-based technique that detects OSA using only a single-lead ECG signal. In the proposed approach, a convolutional neural network extracts features automatically from images created with one-minute ECG segments. The proposed network comprises 37 layers, including four residual blocks, a dense layer, a dropout layer, and a soft-max layer. In this study, three time–frequency representations, namely the scalogram, the spectrogram, and the Wigner–Ville distribution, were used to investigate the effectiveness of the fused-image-based approach. We found that blending scalogram and spectrogram images further improved the system’s discriminative characteristics. Seventy ECG recordings from the PhysioNet Apnea-ECG database were used to train and evaluate the proposed model using 10-fold cross validation. The results of this study demonstrated that the proposed classifier can perform OSA detection with an average accuracy, recall, and specificity of 92.4%, 92.3%, and 92.6%, respectively, for the fused spectral images.

Vehicle ownership modeling and prediction is a crucial task in the transportation planning processes which, traditionally, uses statistical models in the modeling process. However, with the advancement in computing power of computers and Artificial Intelligence, Machine Learning (ML) algorithms are becoming an alternative or a complement to the statistical models in modeling the transportation planning processes. Although the application of ML algorithms to the transportation planning processes—like mode choice, and traffic forecasting and demand modeling—have received much attention in research and abound in literature, scanty attention is paid to its application to vehicle ownership modeling especially in the context of small to medium cities in developing countries. Therefore, this study attempts to fill this gap by modeling vehicle ownership in the Greater Tamale Area (GTA), a typically small to medium city in Ghana. Using a cross sectional survey of formal sectors workers, data was collected between June–August 2018. The study applied nine different ML classification algorithms to the dataset using 10-fold cross-validation technique/s and the Cohen-Kappa static/statistic to evaluate the predictive performance of each of the algorithms, and the Permutation Feature Importance to examine the features that contribute significantly to the prediction of vehicle ownership in GTA. The results showed that Linear Support Vector Classification (LinearSVC) classifier performed well in comparison with the other classifiers with regards to the overall predictive ability of the classifiers. In terms of class predictions, K- Nearest Neighbors (KNN) classifier performs well for no-vehicle class whiles Linear Support Vector Classification (LinearSVC) and GaussianNB classifiers performs well for motorcycle ownership. LinearSVC and Logistic Regression classifiers performed well on the car ownership class. Also, the results indicated that travel mode choice, average monthly income, average travel distance to workplace, average monthly expenditure on transport, duration of travel to workplace, occupational rank, age, household size and marital status were significant in predicting vehicle ownership for most of the classifiers. These findings could help policies makers carve out strategies that would reduce vehicle ownership but improve personal mobility.

Computational methods have been widely used in drug design. The recent developments in machine learning techniques and the ever-growing chemical and biological databases are fertile ground for discoveries in this area. In this study, we evaluated the performance of Deep Learning models in comparison to Random Forest, and Support Vector Regression for predicting the biological activity (pIC50) of ALK-5 inhibitors as candidates to treat cancer. The generalization power of the models was assessed by internal and external validation procedures. A deep neural network model obtained the best performance in this comparative study, achieving a coefficient of determination of 0.658 on the external validation set with mean square error and mean absolute error of 0.373 and 0.450, respectively. Additionally, the relevance of the chemical descriptors for the prediction of biological activity was estimated using Permutation Importance. We can conclude that the forecast model obtained by the deep neural network is suitable for the problem and can be employed to predict the biological activity of new ALK-5 inhibitors.

Video games have become a ubiquitous part of demographically diverse cultures. Numerous studies have focused on analyzing the cognitive aspects involved in game playing that could help provide an optimal gaming experience level by improving video game design. To this end, we present a framework for classifying the game player’s expertise level using wearable electroencephalography (EEG) headset. We hypothesize that expert/novice players’ brain activity is different, which can be classified using the frequency domain features extracted from EEG signals of the game player. A systematic channel reduction approach is presented using a correlation-based attribute evaluation method. This approach identifies two significant EEG channels, i.e., AF3 and P7, from the Emotiv EPOC headset’s fourteen channels. The features extracted from these EEG channels contribute the most to the video game player’s expertise level classification. This finding is validated by performing statistical analysis (t-test) over the extracted features. Moreover, among multiple classifiers used, K-nearest neighbor is the best classifier in classifying the game player’s expertise level with up to 98.04% classification accuracy.Author summaryTehmina Hafeez ROLES Investigation, Writing – original draft * E-mail: tehminamalik.52@gmail.com AFFILIATION Department of Computer Engineering, University of Engineering and Technology, Taxila, 47050, Pakistan.Sanay Muhammad Umar Saeed (Corresponding author) ROLES Conceptualization, Writing – review editing * E-mail: sanay.muhammad@uettaxila.edu.pk AFFILIATION Department of Computer Engineering, University of Engineering and Technology, Taxila, 47050, Pakistan.Aamir Arsalan ROLES Methodology, Writing – review editing * E-mail: aamir.arsalan@uettaxila.edu.pk AFFILIATION Department of Computer Engineering, University of Engineering and Technology, Taxila, 47050, Pakistan.Syed Muhammad Anwar ROLES Validation, Writing – review editing * E-mail: s.anwar@uettaxila.edu.pk AFFILIATION Department of Software Engineering, University of Engineering and Technology, Taxila, 47050, Pakistan.Muhammad Usman Ashraf (Corresponding author) ROLES Validation, Writing – review editing * E-mail: usman.ashraf@skt.umt.edu.pk AFFILIATION Department of Computer Science, University of management and Technology, Lahore (Sialkot), 51040, Pakistan.Khalid Alsubhi ROLES Conceptualization, Writing – review editing AFFILIATION Department of Computer Science, King Abdul Aziz University, Jeddah, Saudi Arabia.

Objective In stroke survivors, a treatment-resistant problem is inability to volitionally differentiate upper limb wrist extension versus flexion. When one intends to extend the wrist, the opposite occurs, wrist flexion, rendering the limb non-functional. Conventional therapeutic approaches have had limited success in achieving functional recovery of patients with chronic and severe upper extremity impairments. Functional magnetic resonance imaging (fMRI) neurofeedback is an emerging strategy that has shown potential for stroke rehabilitation. There is a lack of information regarding unique blood-oxygenation-level dependent (BOLD) cortical activations uniquely controlling execution of wrist extension versus uniquely controlling wrist flexion. Therefore, a first step in providing accurate neural feedback and training to the stroke survivor is to determine the feasibility of classifying (or differentiating) brain activity uniquely associated with wrist extension from that of wrist flexion, first in healthy adults. Approach We studied brain signal of 10 healthy adults, who performed wrist extension and wrist flexion during fMRI data acquisition. We selected four types of analyses to study the feasibility of differentiating brain signal driving wrist extension versus wrist flexion, as follows: 1) general linear model (GLM) analysis; 2) support vector machine (SVM) classification; 3) ‘Winner Take All’; and 4) Relative Dominance. Results With these four methods and our data, we found that few voxels were uniquely active during either wrist extension or wrist flexion. SVM resulted in only minimal classification accuracies. There was no significant difference in activation magnitude between wrist extension versus flexion; however, clusters of voxels showed extension signal > flexion signal and other clusters vice versa. Spatial patterns of activation differed among subjects. Significance We encountered a number of obstacles to obtaining clear group results in healthy adults. These obstacles included the following: high variability across healthy adults in all measures studied; close proximity of uniquely active voxels to voxels that were common to both the extension and flexion movements; in general, higher magnitude of signal for the voxels common to both movements versus the magnitude of any given uniquely active voxel for one type of movement. Our results indicate that greater precision in imaging will be required to develop a truly effective method for differentiating wrist extension versus wrist flexion from fMRI data.

Keeping an eye on pedestrians as they navigate through a scene, surveillance cameras are everywhere. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This multi-label problem is extremely challenging even for human observers and has rightly garnered attention from the computer vision community. Towards a solution to this problem, in this paper, we adopt trainable Gabor wavelets (TGW) layers and cascade them with a convolution neural network (CNN). Whereas other researchers are using fixed Gabor filters with the CNN, the proposed layers are learnable and adapt to the dataset for a better recognition. We propose a two-branch neural network where mixed layers, a combination of the TGW and convolutional layers, make up the building block of our deep neural network. We test our method on twoo challenging publicly available datasets and compare our results with state of the art.

Running-in is an important and relatively complicated process. The surface morphology prior to running-in affects the surface morphology following the running-in process, which in turn influences the friction and wear characteristics of the workpiece. Therefore, the establishment of a model for running-in surface morphology prediction is important to investigate the process and optimize the surface design. Black-box models based on machine learning have robust complex object simulation performance. In this paper, five common machine learning methods are applied to establish running-in modeling performance based on surface morphology parameters. The support vector machine has the best model performance. The change law of the surface morphology parameters is obtained based on model testing, and the surface morphology optimization is explored. When better oil storage capacity is required, the recommendation is to increase the Sq, Sdq and Sk surface parameter values while setting medium Sdc and Sdr surface parameter values. When a lower coefficient of friction (COF) is required, Sdc and Sdr should be decreased, and Sq and Sdq should be increased. When better support performance is required, Sdc, Sdq, and Sdr should be increased. This article provides a solution to establish a link between surface design and functional performance in the steady wear stage, further filling the gap in quality monitoring of lifecycles.

Background Primary immunodeficiency diseases represent an expanding set of heterogeneous conditions which are difficult to recognize clinically. Diagnostic rates outside of the newborn period have not changed appreciably. This concern underscores a need for novel methods of disease detection. Objective We built a Bayesian network to provide real-time risk assessment about primary immunodeficiency and to facilitate prescriptive analytics for initiating the most appropriate diagnostic work up. Our goal is to improve diagnostic rates for primary immunodeficiency and shorten time to diagnosis. We aimed to use readily available health record data and a small training dataset to prove utility in diagnosing patients with relatively rare features. Methods We extracted data from the Texas Children’s Hospital electronic health record on a large population of primary immunodeficiency patients (n = 1762) and appropriately-matched set of controls (n = 1698). From the cohorts, clinically relevant prior probabilities were calculated enabling construction of a Bayesian network probabilistic model(PI Prob). Our model was constructed with clinical-immunology domain expertise, trained on a balanced cohort of 100 cases-controls and validated on an unseen balanced cohort of 150 cases-controls. Performance was measured by area under the receiver operator characteristic curve (AUROC). We also compared our network performance to classic machine learning model performance on the same dataset. Results PI Prob was accurate in classifying immunodeficiency patients from controls (AUROC = 0.945; p Conclusion Artificial intelligence methods can classify risk for primary immunodeficiency and guide management. PI Prob enables accurate, objective decision making about risk and guides the user towards the appropriate diagnostic evaluation for patients with recurrent infections. Probabilistic models can be trained with small datasets underscoring their utility for rare disease detection given appropriate domain expertise for feature selection and network construction.

We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.Author SummaryRecently, quantitative-phase imaging (QPI) has demonstrated the ability to elucidate novel parameters of cellular physiology and metabolism without the need for fluorescent staining. Here, we apply label-free, low photo-toxicity QPI to yeast cells in order to identify lipid droplets (LDs), an important organelle with key implications in human health and biofuel development. Because QPI yields low specificity, we explore the use of modern machine learning methods to rapidly identify intracellular LDs with high discriminatory power and accuracy. In recent years, machine learning has demonstrated exceptional abilities to recognize and segment objects in biomedical imaging, remote sensing, and other areas. Trained machine learning classifiers can be combined with QPI within high-throughput analysis pipelines, allowing for efficient and accurate identification and quantification of cellular components. Non-invasive, accurate and high-throughput classification of these organelles will accelerate research and improve our understanding of cellular functions with beneficial applications in biofuels, biomedicine, and more.

Objectives To propose a novel robust radiogenomics approach to the identification of epidermal growth factor receptor (EGFR) mutations among patients with non-small cell lung cancer (NSCLC) using Betti numbers (BNs). Materials and methods Contrast enhanced computed tomography (CT) images of 194 multi-racial NSCLC patients (79 EGFR mutants and 115 wildtypes) were collected from three different countries using 5 manufacturers’ scanners with a variety of scanning parameters. Ninety-nine cases obtained from the University of Malaya Medical Centre (UMMC) in Malaysia were used for training and validation procedures. Forty-one cases collected from the Kyushu University Hospital (KUH) in Japan and fifty-four cases obtained from The Cancer Imaging Archive (TCIA) in America were used for a test procedure. Radiomic features were obtained from BN maps, which represent topologically invariant heterogeneous characteristics of lung cancer on CT images, by applying histogram- and texture-based feature computations. A BN-based signature was determined using support vector machine (SVM) models with the best combination of features that maximized a robustness index (RI) which defined a higher total area under receiver operating characteristics curves (AUCs) and lower difference of AUCs between the training and the validation. The SVM model was built using the signature and optimized in a five-fold cross validation. The BN-based model was compared to conventional original image (OI)- and wavelet-decomposition (WD)-based models with respect to the RI between the validation and the test. Results The BN-based model showed a higher RI of 1.51 compared with the models based on the OI (RI: 1.33) and the WD (RI: 1.29). Conclusion The proposed model showed higher robustness than the conventional models in the identification of EGFR mutations among NSCLC patients. The results suggested the robustness of the BN-based approach against variations in image scanner/scanning parameters.

In power system networks, automatic fault diagnosis techniques of switchgears with high accuracy and less time consuming are important. In this work, classification of abnormal location in switchgears is proposed using hybrid gravitational search algorithm (GSA)-artificial intelligence (AI) techniques. The measurement data were obtained from ultrasound, transient earth voltage, temperature and sound sensors. The AI classifiers used include artificial neural network (ANN) and support vector machine (SVM). The performance of both classifiers was optimized by an optimization technique, GSA. The advantages of GSA classification on AI in classifying the abnormal location in switchgears are easy implementation, fast convergence and low computational cost. For performance comparison, several well-known metaheuristic techniques were also applied on the AI classifiers. From the comparison between ANN and SVM without optimization by GSA, SVM yields 2% higher accuracy than ANN. However, ANN yields slightly higher accuracy than SVM after combining with GSA, which is in the range of 97%-99% compared to 95%-97% for SVM. On the other hand, GSA-SVM converges faster than GSA-ANN. Overall, it was found that combination of both AI classifiers with GSA yields better results than several well-known metaheuristic techniques.

Taxi order demand prediction is of tremendous importance for continuous upgrading of an intelligent transportation system to realise city-scale and personalised services. An accurate short-term taxi demand prediction model in both spatial and temporal relations can assist a city pre-allocate its resources and facilitate city-scale taxi operation management in a megacity. To address problems similar to the above, in this study, we proposed a multi-zone order demand prediction model to predict short-term taxi order demand in different zones at city-scale. A two-step methodology was developed, including order zone division and multi-zone order prediction. For the zone division step, the K-means++ spatial clustering algorithm was used, and its parameter k was estimated by the between–within proportion index. For the prediction step, six methods (backpropagation neural network, support vector regression, random forest, average fusion-based method, weighted fusion-based method, and k-nearest neighbour fusion-based method) were used for comparison. To demonstrate the performance, three multi-zone weighted accuracy indictors were proposed to evaluate the order prediction ability at city-scale. These models were implemented and validated on real-world taxi order demand data from a three-month consecutive collection in Shenzhen, China. Experiment on the city-scale taxi demand data demonstrated the superior prediction performance of the multi-zone order demand prediction model with the k-nearest neighbour fusion-based method based on the proposed accuracy indicator.