Search

Over the last decade, there has been growing interest in learning the mapping from structural connectivity (SC) to functional connectivity (FC) of the brain. The spontaneous fluctuations of the brain activity during the resting-state as captured by functional MRI (rsfMRI) contain rich non-stationary dynamics over a relatively fixed structural connectome. Among the modeling approaches, graph diffusion-based methods with single and multiple diffusion kernels approximating static or dynamic functional connectivity have shown promise in predicting the FC given the SC. However, these methods are computationally expensive, not scalable, and fail to capture the complex dynamics underlying the whole process. Recently, deep learning methods such as GraphHeat networks and graph diffusion have been shown to handle complex relational structures while preserving global information. In this paper, we propose a novel attention-based fusion of multiple GraphHeat networks (A-GHN) for mapping SC-FC. A-GHN enables us to model multiple heat kernel diffusion over the brain graph for approximating the complex Reaction Diffusion phenomenon. We argue that the proposed deep learning method overcomes the scalability and computational inefficiency issues but can still learn the SC-FC mapping successfully. Training and testing were done using the rsfMRI data of 1058 participants from the human connectome project (HCP), and the results establish the viability of the proposed model. On HCP data, we achieve a high Pearson correlation of 0.788 (Desikan-Killiany atlas with 87 regions) and 0.773 (AAL atlas with 86 regions). Furthermore, experiments demonstrate that A-GHN outperforms the existing methods in learning the complex nature of the structure-function relation of the human brain. [ABSTRACT FROM AUTHOR]

Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the limited information in features and the complex background. To further enhance the detection accuracy of small objects, this paper proposes an efficient single-shot detector with weight-based feature fusion (WFFA-SSD). First, a weight-based feature fusion block is designed to adaptively fuse information from several multi-scale feature maps. The feature fusion block can exploit contextual information for feature maps with large resolutions. Then, a context attention block is applied to reinforce the local region in the feature maps. Moreover, a pyramids aggregation block is applied to combine the two feature pyramids to classify and locate target objects. The experimental results demonstrate that the proposed WFFA-SSD achieves higher mean Average Precision (mAP) under the premise of ensuring real-time performance. WFFA-SSD increases the mAP of the car by 4.12% on the test set of the CARPK. [ABSTRACT FROM AUTHOR]

Pancreatic cancer is associated with higher mortality rates due to insufficient diagnosis techniques, often diagnosed at an advanced stage when effective treatment is no longer possible. Therefore, automated systems that can detect cancer early are crucial to improve diagnosis and treatment outcomes. In the medical field, several algorithms have been put into use. Valid and interpretable data are essential for effective diagnosis and therapy. There is much room for cutting-edge computer systems to develop. The main objective of this research is to predict pancreatic cancer early using deep learning and metaheuristic techniques. This research aims to create a deep learning and metaheuristic techniques-based system to predict pancreatic cancer early by analyzing medical imaging data, mainly CT scans, and identifying vital features and cancerous growths in the pancreas using Convolutional Neural Network (CNN) and YOLO model-based CNN (YCNN) models. Once diagnosed, the disease cannot be effectively treated, and its progression is unpredictable. That's why there's been a push in recent years to implement fully automated systems that can sense cancer at a prior stage and improve diagnosis and treatment. The paper aims to evaluate the effectiveness of the novel YCNN approach compared to other modern methods in predicting pancreatic cancer. To predict the vital features from the CT scan and the proportion of cancer feasts in the pancreas using the threshold parameters booked as markers. This paper employs a deep learning approach called a Convolutional Neural network (CNN) model to predict pancreatic cancer images. In addition, we use the YOLO model-based CNN (YCNN) to aid in the categorization process. Both biomarkers and CT image dataset is used for testing. The YCNN method was shown to perform well by a cent percent of accuracy compared to other modern techniques in a thorough review of comparative findings. [ABSTRACT FROM AUTHOR]

Throughout the pandemic era, COVID-19 was one of the remarkable unexpected situations over the past few years, but with the decentralization and globalization of efforts and knowledge, a successful vaccine-based control strategy was efficiently designed and applied worldwide. On the other hand, excused confusion and hesitation have widely impacted public health. This paper aims to reduce COVID-19 vaccine hesitancy taking into consideration the patient's medical history. The dataset used in this study is the Vaccine Adverse Event Reporting System (VAERS) dataset which was created as a corporation between the Food and Drug Administration (FDA) and Centers for Disease Control and Prevention (CDC) to gather reported side effects that may be caused by PFIEZER, JANSSEN, and MODERNA vaccines. In this paper, a Deep Learning (DL) model has been developed to identify the relationship between a certain type of COVID-19 vaccine (i.e. PFIEZER, JANSSEN, and MODERNA) and the adverse reactions that may occur in vaccinated patients. The adverse reactions under study are the recovery condition, possibility to be hospitalized, and death status. In the first phase of the proposed model, the dataset has been pre-proceesed, while in the second phase, the Pigeon swarm optimization algorithm is used to optimally select the most promising features that affect the performance of the proposed model. The patient's status after vaccination dataset is grouped into three target classes (Death, Hospitalized, and Recovered). In the third phase, Recurrent Neural Network (RNN) is implemented for both each vaccine type and each target class. The results show that the proposed model gives the highest accuracy scores which are 96.031% for the Death target class in the case of PFIEZER vaccination. While in JANSSEN vaccination, the Hospitalized target class has shown the highest performance with an accuracy of 94.7%. Finally, the model has the best performance for the Recovered target class in MODERNA vaccination with an accuracy of 97.794%. Based on the accuracy and the Wilcoxon Signed Rank test, we can conclude that the proposed model is promising for identifying the relationship between the side effects of COVID-19 vaccines and the patient's status after vaccination. The study displayed that certain side effects were increased in patients according to the type of COVID-19 vaccines. Side effects related to CNS and hemopoietic systems demonstrated high values in all studied COVID-19 vaccines. In the frame of precision medicine, these findings can support the medical staff to select the best COVID-19 vaccine based on the medical history of the patient. [ABSTRACT FROM AUTHOR]

As more documents appear on the Internet, it becomes important to detect malware within the documents. Malware of non-executables might be more dangerous because people usually open them without worrying about inherent danger. Recently, deep learning models are used to analyze byte streams of the non-executables for malware detection. Although they have shown successful results, they are commonly designed for stream-level detection, but not for file-level detection. In this paper, we propose a new method that aggregates the stream-level results to get file-level results for malware detection. We demonstrate its effectiveness by experimental results with our annotated dataset, and show that it gives performance gain of 3.37–5.89% of F1 scores. [ABSTRACT FROM AUTHOR]

This paper illustrates the results obtained by using pre-trained semantic segmentation deep learning models for the detection of archaeological sites within the Mesopotamian floodplains environment. The models were fine-tuned using openly available satellite imagery and vector shapes coming from a large corpus of annotations (i.e., surveyed sites). A randomized test showed that the best model reaches a detection accuracy in the neighborhood of 80%. Integrating domain expertise was crucial to define how to build the dataset and how to evaluate the predictions, since defining if a proposed mask counts as a prediction is very subjective. Furthermore, even an inaccurate prediction can be useful when put into context and interpreted by a trained archaeologist. Coming from these considerations we close the paper with a vision for a Human–AI collaboration workflow. Starting with an annotated dataset that is refined by the human expert we obtain a model whose predictions can either be combined to create a heatmap, to be overlaid on satellite and/or aerial imagery, or alternatively can be vectorized to make further analysis in a GIS software easier and automatic. In turn, the archaeologists can analyze the predictions, organize their onsite surveys, and refine the dataset with new, corrected, annotations. [ABSTRACT FROM AUTHOR]

One of the most dangerous snake species is the "Egyptian cobra" which can kill a man in only 15 min. This paper uses deep learning techniques to identify the Egyptian cobra bite in an accurate manner based on an image of the marks of the bites. We build a dataset consisting of 500 images of cobra bites marks and 600 images of marks of other species of snakes that exist in Egypt. We utilize techniques such as multi-task learning, transfer learning and data augmentation to boost the generalization and accuracy of our model. We have achieved 90.9% of accuracy. We must keep the availability and accuracy of our model as much as possible. So, we utilize cloud and edge computing techniques to enhance the availability of our model. We have achieved 90.9% of accuracy, which is considered as an efficient result, not 100%, so it is normal for the system to perform sometimes wrong classifications. So, we suggest to re-train our model with the wrong predictions, whereas the edge computing units, where the classifier task is positioned, resend the wrong predictions to the cloud model, where the training process occurs, to retrain the model. This enhances the accuracy to the best level after a small period and increases the dataset size. We use the quantum particle swarm optimization technique to determine the optimal required number of edge nodes. [ABSTRACT FROM AUTHOR]

Adding hooked industrial steel fibers (ISF) to concrete boosts its tensile and flexural strength. However, the understanding of ISF's influence on the compressive strength (CS) behavior of concrete is still questioned by the scientific society. The presented paper aims to use machine learning (ML) and deep learning (DL) algorithms to predict the CS of steel fiber reinforced concrete (SFRC) incorporating hooked ISF based on the data collected from the open literature. Accordingly, 176 sets of data are collected from different journals and conference papers. Based upon the initial sensitivity analysis, the most influential parameters like water-to-cement (W/C) ratio and content of fine aggregates (FA) tend to decrease the CS of SFRC. Meanwhile, the CS of SFRC could be enhanced by increasing the amount of superplasticizer (SP), fly ash, and cement (C). The least contributing factors include the maximum size of aggregates (Dmax) and the length-to-diameter ratio of hooked ISFs (L/DISF). Several statistical parameters are also used as metrics to evaluate the performance of implemented models, such as coefficient of determination (R2), mean absolute error (MAE), and mean of squared error (MSE). Among different ML algorithms, convolutional neural network (CNN) with R2 = 0.928, RMSE = 5.043, and MAE = 3.833 shows higher accuracy. On the other hand, K-nearest neighbor (KNN) algorithm with R2 = 0.881, RMSE = 6.477, and MAE = 4.648 results in the weakest performance. [ABSTRACT FROM AUTHOR]

The coronavirus is caused by the infection of the SARS-CoV-2 virus: it represents a complex and new condition, considering that until the end of December 2019 this virus was totally unknown to the international scientific community. The clinical management of patients with the coronavirus disease has undergone an evolution over the months, thanks to the increasing knowledge of the virus, symptoms and efficacy of the various therapies. Currently, however, there is no specific therapy for SARS-CoV-2 virus, know also as Coronavirus disease 19, and treatment is based on the symptoms of the patient taking into account the overall clinical picture. Furthermore, the test to identify whether a patient is affected by the virus is generally performed on sputum and the result is generally available within a few hours or days. Researches previously found that the biomedical imaging analysis is able to show signs of pneumonia. For this reason in this paper, with the aim of providing a fully automatic and faster diagnosis, we design and implement a method adopting deep learning for the novel coronavirus disease detection, starting from computed tomography medical images. The proposed approach is aimed to detect whether a computed tomography medical images is related to an healthy patient, to a patient with a pulmonary disease or to a patient affected with Coronavirus disease 19. In case the patient is marked by the proposed method as affected by the Coronavirus disease 19, the areas symptomatic of the Coronavirus disease 19 infection are automatically highlighted in the computed tomography medical images. We perform an experimental analysis to empirically demonstrate the effectiveness of the proposed approach, by considering medical images belonging from different institutions, with an average time for Coronavirus disease 19 detection of approximately 8.9 s and an accuracy equal to 0.95. [ABSTRACT FROM AUTHOR]

Recent advances in deep learning realized accurate, robust detection of various types of objects including pedestrians on the road, defect regions in the manufacturing process, human organs in medical images, and dangerous materials passing through the airport checkpoint. Specifically, small object detection implemented as an embedded system is gaining increasing attention for autonomous vehicles, drone reconnaissance, and microscopic imagery. In this paper, we present a light-weight small object detection model using two plug-in modules: (1) high-resolution processing module (HRPM) and (2) sigmoid fusion module (SFM). The HRPM efficiently learns multi-scale features of small objects using a significantly reduced computational cost, and the SFM alleviates mis-classification errors due to spatial noise by adjusting weights on the lost small object information. Combination of HRPM and SFM significantly improved the detection accuracy with a low amount of computation. Compared with the original YOLOX-s model, the proposed model takes a two-times higher-resolution input image for higher mean average precision (mAP) using 57% model parameters and 71% computation in Gflops. The proposed model was tested using real drone reconnaissance images, and provided significant improvement in detecting small vehicles. [ABSTRACT FROM AUTHOR]

The tubule index is a vital prognostic measure in breast cancer tumor grading and is visually evaluated by pathologists. In this paper, a computer-aided patch-based deep learning tubule segmentation framework, named Tubule-U-Net, is developed and proposed to segment tubules in Whole Slide Images (WSI) of breast cancer. Moreover, this paper presents a new tubule segmentation dataset consisting of 30820 polygonal annotated tubules in 8225 patches. The Tubule-U-Net framework first uses a patch enhancement technique such as reflection or mirror padding and then employs an asymmetric encoder-decoder semantic segmentation model. The encoder is developed in the model by various deep learning architectures such as EfficientNetB3, ResNet34, and DenseNet161, whereas the decoder is similar to U-Net. Thus, three different models are obtained, which are EfficientNetB3-U-Net, ResNet34-U-Net, and DenseNet161-U-Net. The proposed framework with three different models, U-Net, U-Net++, and Trans-U-Net segmentation methods are trained on the created dataset and tested on five different WSIs. The experimental results demonstrate that the proposed framework with the EfficientNetB3 model trained on patches obtained using the reflection padding and tested on patches with overlapping provides the best segmentation results on the test data and achieves 95.33%, 93.74%, and 90.02%, dice, recall, and specificity scores, respectively. [ABSTRACT FROM AUTHOR]

Human monkeypox is a very unusual virus that can devastate society. Early identification and diagnosis are essential to treat and manage an illness effectively. Human monkeypox disease detection using deep learning models has attracted increasing attention recently. The virus that causes monkeypox may be passed to people, making it a zoonotic illness. The latest monkeypox epidemic has hit more than 40 nations. Computer-assisted approaches using Deep Learning techniques for automatically identifying skin lesions have shown to be a viable alternative in light of the fast proliferation and ever-growing problems of supplying PCR (Polymerase Chain Reaction) Testing in places with limited availability. In this research, we introduce a deep learning model for detecting human monkeypoxes that is accurate and resilient by tuning its hyper-parameters. We employed a mixture of convolutional neural networks and transfer learning strategies to extract characteristics from medical photos and properly identify them. We also used hyperparameter optimization strategies to fine-tune the Model and get the best possible results. This paper proposes a Yolov5 model-based method for differentiating between chickenpox and Monkeypox lesions on skin pictures. The Roboflow skin lesion picture dataset was subjected to three different hyperparameter tuning strategies: the SDG optimizer, the Bayesian optimizer, and Learning without Forgetting. The proposed Model had the highest classification accuracy (98.18%) when applied to photos of monkeypox skin lesions. Our findings show that the suggested Model surpasses the current best-in-class models and may be used in clinical settings for actual Human Monkeypox disease detection and diagnosis., (© 2023. Springer Nature Limited.)

Surface-enhanced Raman spectroscopy (SERS), as a rapid, non-invasive and reliable spectroscopic detection technique, has promising applications in disease screening and diagnosis. In this paper, an annealed silver nanoparticles/porous silicon Bragg reflector (AgNPs/PSB) composite SERS substrate with high sensitivity and strong stability was prepared by immersion plating and heat treatment using porous silicon Bragg reflector (PSB) as the substrate. The substrate combines the five deep learning algorithms of the improved AlexNet, ResNet, SqueezeNet, temporal convolutional network (TCN) and multiscale fusion convolutional neural network (MCNN). We constructed rapid screening models for patients with primary Sjögren's syndrome (pSS) and healthy controls (HC), diabetic nephropathy patients (DN) and healthy controls (HC), respectively. The results showed that the annealed AgNPs/PSB composite SERS substrates performed well in diagnosing. Among them, the MCNN model had the best classification effect in the two groups of experiments, with an accuracy rate of 94.7% and 92.0%, respectively. Previous studies have indicated that the AgNPs/PSB composite SERS substrate, combined with machine learning algorithms, has achieved promising classification results in disease diagnosis. This study shows that SERS technology based on annealed AgNPs/PSB composite substrate combined with deep learning algorithm has a greater developmental prospect and research value in the early identification and screening of immune diseases and chronic kidney disease, providing reference ideas for non-invasive and rapid clinical medical diagnosis of patients., (© 2023. Springer Nature Limited.)

An increasing and aging patient population poses a growing burden on healthcare professionals. Automation of medical imaging diagnostics holds promise for enhancing patient care and reducing manpower required to accommodate an increasing patient-population. Deep learning, a subset of machine learning, has the potential to facilitate automated diagnostics, but commonly requires large-scaled labeled datasets. In medical domains, data is often abundant but labeling is a laborious and costly task. Active learning provides a method to optimize the selection of unlabeled samples that are most suitable for improvement of the model and incorporate them into the model training process. This approach proves beneficial when only a small number of labeled samples are available. Various selection methods currently exist, but most of them employ fixed querying schedules. There is limited research on how the timing of a query can impact performance in relation to the number of queried samples. This paper proposes a novel approach called dynamic querying, which aims to optimize the timing of queries to enhance model development while utilizing as few labeled images as possible. The performance of the proposed model is compared to a model trained utilizing a fully-supervised training method, and its effectiveness is assessed based on dataset size requirements and loss rates. Dynamic querying demonstrates a considerably faster learning curve in relation to the number of labeled samples used, achieving an accuracy of 70% using only 24 samples, compared to 82% for a fully-supervised model trained on the complete training dataset of 1017 images., (© 2023. Springer Nature Limited.)

An alarming number of fatalities caused by the COVID-19 pandemic has forced the scientific community to accelerate the process of therapeutic drug discovery. In this regard, the collaboration between biomedical scientists and experts in artificial intelligence (AI) has led to a number of in silico tools being developed for the initial screening of therapeutic molecules. All living organisms produce antiviral peptides (AVPs) as a part of their first line of defense against invading viruses. The Deep-AVPiden model proposed in this paper and its corresponding web app, deployed at https://deep-avpiden.anvil.app , is an effort toward discovering novel AVPs in proteomes of living organisms. Apart from Deep-AVPiden, a computationally efficient model called Deep-AVPiden (DS) has also been developed using the same underlying network but with point-wise separable convolutions. The Deep-AVPiden and Deep-AVPiden (DS) models show an accuracy of 90% and 88%, respectively, and both have a precision of 90%. Also, the proposed models were statistically compared using the Student's t-test. On comparing the proposed models with the state-of-the-art classifiers, it was found that they are much better than them. To test the proposed model, we identified some AVPs in the natural defense proteins of plants, mammals, and fishes and found them to have appreciable sequence similarity with some experimentally validated antimicrobial peptides. These AVPs can be chemically synthesized and tested for their antiviral activity., (© 2023. Springer Nature Limited.)

Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying chemicals across entire fields is both environmentally unsustainable and costly. Hence, precise localization and management of aphids are essential for targeted pesticide application. The paper primarily focuses on using deep learning models for detecting aphid clusters. We propose a novel approach for estimating infection levels by detecting aphid clusters. To facilitate this research, we have captured a large-scale dataset from sorghum fields, manually selected 5447 images containing aphids, and annotated each individual aphid cluster within these images. To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151,380 image patches. Then, we implemented and compared the performance of four state-of-the-art object detection models (VFNet, GFLV2, PAA, and ATSS) on the aphid dataset. Extensive experimental results show that all models yield stable similar performance in terms of average precision and recall. We then propose to merge close neighboring clusters and remove tiny clusters caused by cropping, and the performance is further boosted by around 17%. The study demonstrates the feasibility of automatically detecting and managing insects using machine learning models. The labeled dataset will be made openly available to the research community., (© 2023. Springer Nature Limited.)

Ultrasonic vocalizations (USVs) analysis represents a fundamental tool to study animal communication. It can be used to perform a behavioral investigation of mice for ethological studies and in the field of neuroscience and neuropharmacology. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and then processed by specific software, which help the operator to identify and characterize different families of calls. Recently, many automated systems have been proposed for automatically performing both the detection and the classification of the USVs. Of course, the USV segmentation represents the crucial step for the general framework, since the quality of the call processing strictly depends on how accurately the call itself has been previously detected. In this paper, we investigate the performance of three supervised deep learning methods for automated USV segmentation: an Auto-Encoder Neural Network (AE), a U-NET Neural Network (UNET) and a Recurrent Neural Network (RNN). The proposed models receive as input the spectrogram associated with the recorded audio track and return as output the regions in which the USV calls have been detected. To evaluate the performance of the models, we have built a dataset by recording several audio tracks and manually segmenting the corresponding USV spectrograms generated with the Avisoft software, producing in this way the ground-truth (GT) used for training. All three proposed architectures demonstrated precision and recall scores exceeding [Formula: see text], with UNET and AE achieving values above [Formula: see text], surpassing other state-of-the-art methods that were considered for comparison in this study. Additionally, the evaluation was extended to an external dataset, where UNET once again exhibited the highest performance. We suggest that our experimental results may represent a valuable benchmark for future works., (© 2023. The Author(s).)

Long short-term memory (LSTM) models provide high predictive performance through their ability to recognize longer sequences of time series data. More recently, bidirectional deep learning models (BiLSTM) have extended the LSTM capabilities by training the input data twice in forward and backward directions. In this paper, BiLSTM short term traffic forecasting models have been developed and evaluated using data from a calibrated micro-simulation model for a congested freeway in Melbourne, Australia. The simulation model was extensively calibrated and validated to a high degree of accuracy using field data collected from 55 detectors on the freeway. The base year simulation model was then used to generate loop detector data including speed, flow and occupancy which were used to develop and compare a number of LSTM models for short-term traffic prediction up to 60 min into the future. The modelling results showed that BiLSTM outperformed other predictive models for multiple prediction horizons for base year conditions. The simulation model was then adapted for future year scenarios where the traffic demand was increased by 25–100 percent to reflect potential future increases in traffic demands. The results showed superior performance of BiLSTM for multiple prediction horizons for all traffic variables. [ABSTRACT FROM AUTHOR]

Urban activities, particularly vehicle traffic, are contributing significantly to environmental pollution with detrimental effects on public health. The ability to anticipate air quality in advance is critical for public authorities and the general public to plan and manage these activities, which ultimately help in minimizing the adverse impact on the environment and public health effectively. Thanks to recent advancements in Artificial Intelligence and sensor technology, forecasting air quality is possible through the consideration of various environmental factors. This paper presents our novel solution for air quality prediction and its correlation with different environmental factors and urban activities, such as traffic density. To this aim, we propose a multi-modal framework by integrating real-time data from different environmental sensors and traffic density extracted from Closed Circuit Television footage. The framework effectively addresses data inconsistencies arising from sensor and camera malfunctions within a streaming dataset. The dataset exhibits real-world complexities, including abrupt camera or station activations/deactivations, noise interference, and outliers. The proposed system tackles the challenge of predicting air quality at locations having no sensors or experiencing sensor failures by training a joint model on the data obtained from nearby stations/sensors using a Particle Swarm Optimization (PSO)-based merit fusion of the sensor data. The proposed methodology is evaluated using various variants of the LSTM model including Bi-directional LSTM, CNN-LSTM, and Convolutions LSTM (ConvLSTM) obtaining an improvement of 48%, 67%, and 173% for short-term, medium-term, and long-term periods, respectively, over the ARIMA model. [ABSTRACT FROM AUTHOR]

Enhancing IoT security is a corner stone for building trust in its technology and driving its growth. Limited resources and diversified nature of IoT devices make them vulnerable to attacks. Botnet attacks compromise the IoT systems and can pose significant security challenges. Numerous investigations have utilized machine learning and deep learning techniques to identify botnet attacks in IoT. However, achieving high detection accuracy with reasonable computational requirements is still a challenging research considering the particularity of IoT. This paper aims to analytically study the performance of the tree based machine learning in detecting botnet attacks for IoT ecosystems. Through an empirical study performed on a public botnet dataset of IoT environment, basic decision tree algorithm in addition to ensemble learning of different bagging and boosting algorithms are compared. The comparison covers two perspectives: IoT botnet detection capability and computational performance. Results demonstrated that the significant potential for the tree based ML algorithms in detecting network intrusions in IoT environments. The RF algorithm achieved the best performance for multi-class classification with accuracy rate of 0.999991. It achieved also the highest results in all other measures. [ABSTRACT FROM AUTHOR]

Deep learning techniques have proven to be effective in solving the facial emotion recognition (FER) problem. However, it demands a significant amount of supervision data which is often unavailable due to privacy and ethical concerns. In this paper, we present a novel approach for addressing the FER problem using multi-source transfer learning. The proposed method leverages the knowledge from multiple data sources of similar domains to inform the model on a related task. The approach involves the optimization of aggregate multivariate correlation among the source tasks trained on the source dataset, thus controlling the transfer of information to the target task. The hypothesis is validated on benchmark datasets for facial emotion recognition and image classification tasks, and the results demonstrate the effectiveness of the proposed method in capturing the group correlation among features, as well as being robust to negative transfer and performing well in few-shot multi-source adaptation. With respect to the state-of-the-art methods MCW and DECISION, our approach shows an improvement of 7% and ∼ 15% respectively. [ABSTRACT FROM AUTHOR]

Bats are a crucial component within ecosystems, providing valuable ecosystem services such as pollination and pest control. In practical conservation efforts, the classification and identification of bats are essential in order to develop effective conservation management programs for bats and their habitats. Traditionally, the identification of bats has been a manual and time-consuming process. With the development of artificial intelligence technology, the accuracy and speed of identification work of such fine-grained images as bats identification can be greatly improved. Bats identification relies on the fine features of their beaks and faces, so mining the fine-grained information in images is crucial to improve the accuracy of bats identification. This paper presents a deep learning-based model designed for the rapid and precise identification of common horseshoe bats (Chiroptera: Rhinolophidae: Rhinolophus) from Southern China. The model was developed by utilizing a comprehensive dataset of 883 high-resolution images of seven distinct Rhinolophus species which were collected during surveys conducted between 2010 and 2022. An improved EfficientNet model with an attention mechanism module is architected to mine the fine-grained appearance of these Rhinolophus. The performance of the model beat other classical models, including SqueezeNet, AlexNet, VGG16_BN, ShuffleNetV2, GoogleNet, ResNet50 and EfficientNet_B0, according to the predicting precision, recall, accuracy, F1-score. Our model achieved the highest identification accuracy of 94.22% and an F1-score of 0.948 with low computational complexity. Heat maps obtained with Grad-CAM show that our model meets the identification criteria of the morphology of Rhinolophus. Our study highlights the potential of artificial intelligence technology for the identification of small mammals, and facilitating fast species identification in the future. [ABSTRACT FROM AUTHOR]

This work proposes a new machine learning (ML)-based paradigm aiming to enhance the computational efficiency of non-equilibrium reacting flow simulations while ensuring compliance with the underlying physics. The framework combines dimensionality reduction and neural operators through a hierarchical and adaptive deep learning strategy to learn the solution of multi-scale coarse-grained governing equations for chemical kinetics. The proposed surrogate's architecture is structured as a tree, with leaf nodes representing separate neural operator blocks where physics is embedded in the form of multiple soft and hard constraints. The hierarchical attribute has two advantages: (i) It allows the simplification of the training phase via transfer learning, starting from the slowest temporal scales; (ii) It accelerates the prediction step by enabling adaptivity as the surrogate's evaluation is limited to the necessary leaf nodes based on the local degree of non-equilibrium of the gas. The model is applied to the study of chemical kinetics relevant for application to hypersonic flight, and it is tested here on pure oxygen gas mixtures. In 0- D scenarios, the proposed ML framework can adaptively predict the dynamics of almost thirty species with a maximum relative error of 4.5% for a wide range of initial conditions. Furthermore, when employed in 1- D shock simulations, the approach shows accuracy ranging from 1% to 4.5% and a speedup of one order of magnitude compared to conventional implicit schemes employed in an operator-splitting integration framework. Given the results presented in the paper, this work lays the foundation for constructing an efficient ML-based surrogate coupled with reactive Navier-Stokes solvers for accurately characterizing non-equilibrium phenomena in multi-dimensional computational fluid dynamics simulations. [ABSTRACT FROM AUTHOR]

Automated multi-organ segmentation plays an essential part in the computer-aided diagnostic (CAD) of chest X-ray fluoroscopy. However, developing a CAD system for the anatomical structure segmentation remains challenging due to several indistinct structures, variations in the anatomical structure shape among different individuals, the presence of medical tools, such as pacemakers and catheters, and various artifacts in the chest radiographic images. In this paper, we propose a robust deep learning segmentation framework for the anatomical structure in chest radiographs that utilizes a dual encoder–decoder convolutional neural network (CNN). The first network in the dual encoder–decoder structure effectively utilizes a pre-trained VGG19 as an encoder for the segmentation task. The pre-trained encoder output is fed into the squeeze-and-excitation (SE) to boost the network's representation power, which enables it to perform dynamic channel-wise feature calibrations. The calibrated features are efficiently passed into the first decoder to generate the mask. We integrated the generated mask with the input image and passed it through a second encoder–decoder network with the recurrent residual blocks and an attention the gate module to capture the additional contextual features and improve the segmentation of the smaller regions. Three public chest X-ray datasets are used to evaluate the proposed method for multi-organs segmentation, such as the heart, lungs, and clavicles, and single-organ segmentation, which include only lungs. The results from the experiment show that our proposed technique outperformed the existing multi-class and single-class segmentation methods. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is one of the main causes of blindness in people around the world. Early diagnosis and treatment of DR can be accomplished by organizing large regular screening programs. Still, it is difficult to spot diabetic retinopathy timely because the situation might not indicate signs in the primary stages of the disease. Due to a drastic increase in diabetic patients, there is an urgent need for efficient diabetic retinopathy detecting systems. Auto-encoders, sparse coding, and limited Boltzmann machines were used as a few past deep learning (DL) techniques and features for the classification of DR. Convolutional Neural Networks (CNN) have been identified as a promising solution for detecting and classifying DR. We employ the deep learning capabilities of efficient net batch normalization (BNs) pre-trained models to automatically acquire discriminative features from fundus images. However, we successfully achieved F1 scores above 80% on all efficient net BNs in the EYE-PACS dataset (calculated F1 score for DeepDRiD another dataset) and the results are better than previous studies. In this paper, we improved the accuracy and F1 score of the efficient net BNs pre-trained models on the EYE-PACS dataset by applying a Gaussian Smooth filter and data augmentation transforms. Using our proposed technique, we have achieved F1 scores of 84% and 87% for EYE-PACS and DeepDRiD. [ABSTRACT FROM AUTHOR]

Sentence-level sentiment analysis (SLSA) aims to identify the overall sentiment polarity conveyed in a given sentence. The state-of-the-art performance of SLSA has been achieved by deep learning models. However, depending on the i.i.d (independent and identically distributed) assumption, the performance of these deep learning models may fall short in real scenarios, where the distributions of training and target data are almost certainly different to some extent. In this paper, we propose a supervised solution based on the non-i.i.d paradigm of gradual machine learning (GML) for SLSA. It begins with some labeled observations, and gradually labels target instances in the order of increasing hardness by iterative knowledge conveyance. It leverages labeled samples for supervised deep feature extraction, and constructs a factor graph based on the extracted features to enable gradual knowledge conveyance. Specifically, it employs a polarity classifier to detect polarity similarity between close neighbors in an embedding space, and a separate binary semantic network to extract implicit polarity relations between arbitrary instances. Our extensive experiments on benchmark datasets show that the proposed approach achieves the state-of-the-art performance on all benchmark datasets. Our work clearly demonstrates that by leveraging DNN for feature extraction, GML can easily outperform the pure DNN solutions. [ABSTRACT FROM AUTHOR]

Air pollution is a leading cause of human diseases. Accurate air quality predictions are critical to human health. However, it is difficult to extract spatiotemporal features among complex spatiotemporal dependencies effectively. Most existing methods focus on constructing multiple spatial dependencies and ignore the systematic analysis of spatial dependencies. We found that besides spatial proximity stations, functional similarity stations, and temporal pattern similarity stations, the shared spatial dependencies also exist in the complete spatial dependencies. In this paper, we propose a novel deep learning model, the spatiotemporal adaptive attention graph convolution model, for city-level air quality prediction, in which the prediction of future short-term series of PM2.5 readings is preferred. Specifically, we encode multiple spatiotemporal dependencies and construct complete spatiotemporal interactions between stations using station-level attention. Among them, we design a Bi-level sharing strategy to extract shared inter-station relationship features between certain stations efficiently. Then we extract multiple spatiotemporal features with multiple decoders, which it is extracted from the complete spatial dependencies between stations. Finally, we fuse multiple spatiotemporal features with a gating mechanism for multi-step predictions. Our model achieves state-of-the-art experimental results in several real-world datasets. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. The most efficient supervised machine learning (ML)-based approaches for predicting human activity are based on a continuous stream of sensor data. Sensor data analysis for human activity recognition using conventional algorithms and deep learning (DL) models shows promising results, but evaluating their ambiguity in decision-making is still challenging. In order to solve these issues, the paper proposes a novel Wasserstein gradient flow legonet WGF-LN-based human activity recognition system. At first, the input data is pre-processed. From the pre-processed data, the features are extracted using Haar Wavelet mother- Symlet wavelet coefficient scattering feature extraction (HS-WSFE). After that, the interest features are selected from the extracted features using (Binomial Distribution integrated-Golden Eagle Optimization) BD-GEO. The important features are then post-processed using the scatter plot matrix method. Obtained post-processing features are finally given into the WGF-LN for classifying human activities. From these experiments, the results can be obtained and showed the efficacy of the proposed model. [ABSTRACT FROM AUTHOR]

Clinical studies from WHO have demonstrated that only 50–70% of patients adhere properly to prescribed drug therapy. Such adherence failure can impact therapeutic efficacy for the patients in question and compromises data quality around the population-level efficacy of the drug for the indications targeted. In this study, we applied various ensemble learning and deep learning models to predict medication adherence among patients. Our contribution to this endeavour involves targeting the problem of adherence prediction for a particularly challenging class of patients who self-administer injectable medication at home. Our prediction pipeline, based on event history, comprises a connected sharps bin which aims to help patients better manage their condition and improve outcomes. In other words, the efficiency of interventions can be significantly improved by prioritizing the patients who are most likely to be non-adherent. The collected data comprising a rich event feature set may be exploited for the purposes of predicting the status of the next adherence state for individual patients. This paper reports on how this concept can be realized through an investigation using a wide range of ensemble learning and deep learning models on a real-world dataset collected from such a system. The dataset investigated comprises 342,174 historic injection disposal records collected over the course of more than 5 years. A comprehensive comparison of different models is given in this paper. Moreover, we demonstrate that the selected best performer, long short-term memory (LSTM), generalizes well by deploying it in a true future testing dataset. The proposed end-to-end pipeline is capable of predicting patient failure in adhering to their therapeutic regimen with 77.35 % accuracy (Specificity: 78.28 %, Sensitivity: 76.42%, Precision: 77.87%,F1 score: 0.7714, ROC AUC: 0.8390). [ABSTRACT FROM AUTHOR]

The automatic segmentation of the pharyngeal airway space has many potential medical use, one of which is to help facilitate the creation of the Tubingen Palatal Plate. Therefore, it is of great importance to understand which methods are suitable for this task. Here, neural network based solutions available in the literature are compared to find the best methods. Neural network models were chosen to encompass a diverse landscape. Some models were taken from the general semantic segmentation literature, while others were taken from the medical or pharyngeal airway space segmentation literature. Some models are convolutional neural networks, while others are transformer-based model or a mix of both convolutional and transformer-based model. These models include 2d/3d U-Net, Deeplabv3, YOLOv8, Swinv2 UNETR, SegFormer, and 3D MRU-Net. Furthermore, additional strategies to enhance performance were also considered. These strategies consisted of training two separate networks in multiple stages as well leveraging unlabeled data to pretrain the neural networks before fine-tuning them on the labeled data. It was found that out of all the models considered here, the 2d U-Net performed the best achieving an average dice score of 0.9180 ± 0.0111. Out of all the strategies to enhance performance, only two strategies improve the actual results but only by a small margin. Therefore, these strategies can be consider if a small increase in performance is desired from the 2d U-Net at the expense of computational resource. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions. We demonstrate that baseline methods achieve comparable or superior performance compared to more complex models on survival predictions tasks. DL representation methods, however, are the most efficient to predict the gene essentiality of cell lines. We show that auto-encoders (AE) are consistently improved by techniques such as masking and multi-head training. Our results suggest that the impact of DL representations and of pretraining are highly task- and architecture-dependent, highlighting the need for adopting rigorous evaluation guidelines. These guidelines for robust evaluation are implemented in a pipeline made available to the research community. [ABSTRACT FROM AUTHOR]

Abstract Radar observation variables reflect the precipitation amount of strong convective precipitation processes, which accurate forecast is an important difficulty in weather forecasting. Current forecasting methods are mostly based on radar echo extrapolation, which has the insufficiency of input information and the ineffectiveness of model architecture. This paper presents a Bidirectional Long Short-Term Memory forecasting method for strong convective precipitation based on the attention mechanism and residual neural network (ResNet-Attention-BiLSTM). First, this paper uses ResNet to effectively extract the key information of extreme weather and solves the problem of regression to the mean of the prediction model by learning the residuals of the radar observation data. Second, this paper uses the attention mechanism to adaptively weight the fusion of the features to enhance the extraction of the important features of the precipitation image data. On this basis, this paper presents a novel spatio-temporal reasoning method for radar observations and establishes a precipitation forecasting model, which captures the past and future time-order relationship of the sequence data. Finally, this paper conducts experiments based on the real collected data of a strong convective precipitation process and compares its performance with the existing models, the mean absolute percentage error of this model was reduced by 15.94% (1 km), 18.72% (3 km), and 14.91% (7 km), and the coefficient of determination ( $$R^{2}$$ R 2 ) was increased by 10.89% (1 km), 9.61% (3 km), and 9.29% (7 km), which proves the state of the art and effectiveness of this forecasting model.

Abstract Building extraction aims to extract building pixels from remote sensing imagery, which plays a significant role in urban planning, dynamic urban monitoring, and many other applications. UNet3+ is widely applied in building extraction from remote sensing images. However, it still faces issues such as low segmentation accuracy, imprecise boundary delineation, and the complexity of network models. Therefore, based on the UNet3+ model, this paper proposes a 3D Joint Attention (3DJA) module that effectively enhances the correlation between local and global features, obtaining more accurate object semantic information and enhancing feature representation. The 3DJA module models semantic interdependence in the vertical and horizontal dimensions to obtain feature map spatial encoding information, as well as in the channel dimensions to increase the correlation between dependent channel graphs. In addition, a bottleneck module is constructed to reduce the number of network parameters and improve model training efficiency. Many experiments are conducted on publicly accessible WHU,INRIA and Massachusetts building dataset, and the benchmarks, BOMSC-Net, CVNet, SCA-Net, SPCL-Net, ACMFNet, MFCF-Net models are selected for comparison with the 3DJA-UNet3+ model proposed in this paper. The experimental results show that 3DJA-UNet3+ achieves competitive results in three evaluation indicators: overall accuracy, mean intersection over union, and F1-score. The code will be available at https://github.com/EnjiLi/3DJA-UNet3Plus .

Abstract In transportation, roads sometimes have cracks due to overloading and other reasons, which seriously affect driving safety, and it is crucial to identify and fill road cracks in time. Aiming at the defects of existing semantic segmentation models that have degraded the segmentation performance of road crack images and the standard convolution makes it challenging to capture the spatial and channel coupling relationship between pixels. It is difficult to differentiate crack pixels from background pixels in complex backgrounds; this paper proposes a semantic segmentation model for road cracks that combines channel-spatial convolution with the aggregation of frequency features. A new convolutional block is proposed to accurately identify cracked pixels by grouping spatial displacements and convolutional kernel weight dynamization while modeling pixel spatial relationships linked to channel features. To enhance the contrast of crack edges, a frequency domain feature aggregation module is proposed, which uses a simple windowing strategy to solve the problem of mismatch of frequency domain inputs and, at the same time, takes into account the effect of the frequency imaginary part on the features to model the deep frequency features effectively. Finally, a feature refinement module is designed to refine the semantic features to improve the segmentation accuracy. Many experiments have proved that the model proposed in this paper has better performance and more application potential than the current popular general model.

Plankton microorganisms play a huge role in the aquatic food web. Recently, it has been proposed to use plankton as a biosensor, since they can react to even minimal perturbations of the aquatic environment with specific physiological changes, which may lead to alterations in morphology and behavior. Nowadays, the development of high-resolution in-situ automatic acquisition systems allows the research community to obtain a large amount of plankton image data. Fundamental examples are the ZooScan and Woods Hole Oceanographic Institution (WHOI) datasets, comprising up to millions of plankton images. However, obtaining unbiased annotations is expensive both in terms of time and resources, and in-situ acquired datasets generally suffer from severe imbalance, with only a few images available for several species. Transfer learning is a popular solution to these challenges, with ImageNet1K being the most-used source dataset for pre-training. On the other hand, datasets like the ZooScan and the WHOI may represent a valuable opportunity to compare out-of-domain and large-scale plankton in-domain source datasets, in terms of performance for the task at hand.In this paper, we design three transfer learning pipelines for plankton image classification, with the aim of comparing in-domain and out-of-domain transfer learning on three popular benchmark plankton datasets. The general framework consists in fine-tuning a pre-trained model on a plankton target dataset. In the first pipeline, the model is pre-trained from scratch on a large-scale plankton dataset, in the second, it is pre-trained on large-scale natural image datasets (ImageNet1K or ImageNet22K), while in the third, a two-stage fine-tuning is implemented (ImageNet [Formula: see text] large-scale plankton dataset [Formula: see text] target plankton dataset). Our results show that an out-of-domain ImageNet22K pre-training outperforms the plankton in-domain ones, with an average boost in test accuracy of around 6%. In the next part of this work, we adopt three ImageNet22k pre-trained Vision Transformers and one ConvNeXt, obtaining results on par (or slightly superior) with the state-of-the-art, corresponding to the usage of CNN models ensembles, with a single model. Finally, we design and test an ensemble of our Vision Transformers and the ConvNeXt, outperforming the state-of-the-art existing works on plankton image classification on the three target datasets. To support scientific community contribution and further research, our implemented code is open-source and available at https://github.com/Malga-Vision/plankton_transfer ., (© 2023. The Author(s).)

Electronic coaching (eCoach) facilitates goal-focused development for individuals to optimize certain human behavior. However, the automatic generation of personalized recommendations in eCoaching remains a challenging task. This research paper introduces a novel approach that combines deep learning and semantic ontologies to generate hybrid and personalized recommendations by considering "Physical Activity" as a case study. To achieve this, we employ three methods: time-series forecasting, time-series physical activity level classification, and statistical metrics for data processing. Additionally, we utilize a naïve-based probabilistic interval prediction technique with the residual standard deviation used to make point predictions meaningful in the recommendation presentation. The processed results are integrated into activity datasets using an ontology called OntoeCoach, which facilitates semantic representation and reasoning. To generate personalized recommendations in an understandable format, we implement the SPARQL Protocol and RDF Query Language (SPARQL). We evaluate the performance of standard time-series forecasting algorithms [such as 1D Convolutional Neural Network Model (CNN1D), autoregression, Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU)] and classifiers [including Multilayer Perceptron (MLP), Rocket, MiniRocket, and MiniRocketVoting] using state-of-the-art metrics. We conduct evaluations on both public datasets (e.g., PMData) and private datasets (e.g., MOX2-5 activity). Our CNN1D model achieves the highest prediction accuracy of 97[Formula: see text], while the MLP model outperforms other classifiers with an accuracy of 74[Formula: see text]. Furthermore, we evaluate the performance of our proposed OntoeCoach ontology model by assessing reasoning and query execution time metrics. The results demonstrate that our approach effectively plans and generates recommendations on both datasets. The rule set of OntoeCoach can also be generalized to enhance interpretability., (© 2023. The Author(s).)

Infectious keratitis refers to a group of corneal disorders in which corneal tissues suffer inflammation and damage caused by pathogenic infections. Among these disorders, fungal keratitis (FK) and acanthamoeba keratitis (AK) are particularly severe and can cause permanent blindness if not diagnosed early and accurately. In Vivo Confocal Microscopy (IVCM) allows for imaging of different corneal layers and provides an important tool for an early and accurate diagnosis. In this paper, we introduce the IVCM-Keratitis dataset, which comprises of a total of 4001 sample images of AK and FK, as well as non-specific keratitis (NSK) and healthy corneas classes. We use this dataset to develop multiple deep-learning models based on Convolutional Neural Networks (CNNs) to provide automated assistance in enhancing the diagnostic accuracy of confocal microscopy in infectious keratitis. Densenet161 had the best performance among these models, with an accuracy, precision, recall, and F1 score of 93.55%, 92.52%, 94.77%, and 96.93%, respectively. Our study highlights the potential of deep learning models to provide automated diagnostic assistance for infectious keratitis via confocal microscopy images, particularly in the early detection of AK and FK. The proposed model can provide valuable support to both experienced and inexperienced eye-care practitioners in confocal microscopy image analysis, by suggesting the most likely diagnosis. We further demonstrate that these models can highlight the areas of infection in the IVCM images and explain the reasons behind their diagnosis by utilizing saliency maps, a technique used in eXplainable Artificial Intelligence (XAI) to interpret these models., (© 2023. The Author(s).)

This paper presents a simple method for detecting both biotic and abiotic stress in plants. Stress levels are measured based on the increase in nutrient uptake by plants as a mechanism of self-defense when under stress. A continuous electrical resistance measurement was used to estimate the rate of change of nutrients in agarose as the growth medium for Cicer arietinum (Chickpea) seeds. To determine the concentration of charge carriers in the growth medium, Drude's model was used. For identifying anomalies and forecasting plant stress, two experiments were conducted and outliers were found in electrical resistance and relative changes in carrier concentration. Anomaly in the first iteration was detected by applying k-Nearest Neighbour, One Class Support Vector Machine and Local Outlier Factor in unsupervised mode on electrical resistance data. In the second iteration, the neural network-based Long Short Term Memory method was used on the relative change in the carrier concentration data. As a result of the change in resistance of growth media during stress, nutrient concentrations shifted by 35%, as previously reported. Farmers who cater to small communities around them and are most affected by local and global stress factors can use this method of forecasting., (© 2023. The Author(s).)

This paper presents methods of decomposition of musculoskeletal structures from radiographs into multiple individual muscle and bone structures. While existing solutions require dual-energy scan for the training dataset and are mainly applied to structures with high-intensity contrast, such as bones, we focused on multiple superimposed muscles with subtle contrast in addition to bones. The decomposition problem is formulated as an image translation problem between (1) a real X-ray image and (2) multiple digitally reconstructed radiographs, each of which contains a single muscle or bone structure, and solved using unpaired training based on the CycleGAN framework. The training dataset was created via automatic computed tomography (CT) segmentation of muscle/bone regions and virtually projecting them with geometric parameters similar to the real X-ray images. Two additional features were incorporated into the CycleGAN framework to achieve a high-resolution and accurate decomposition: hierarchical learning and reconstruction loss with the gradient correlation similarity metric. Furthermore, we introduced a new diagnostic metric for muscle asymmetry directly measured from a plain X-ray image to validate the proposed method. Our simulation and real-image experiments using real X-ray and CT images of 475 patients with hip diseases suggested that each additional feature significantly enhanced the decomposition accuracy. The experiments also evaluated the accuracy of muscle volume ratio measurement, which suggested a potential application to muscle asymmetry assessment from an X-ray image for diagnostic and therapeutic assistance. The improved CycleGAN framework can be applied for investigating the decomposition of musculoskeletal structures from single radiographs., (© 2023. The Author(s).)

Heart disease remains the major cause of death, despite recent improvements in prediction and prevention. Risk factor identification is the main step in diagnosing and preventing heart disease. Automatically detecting risk factors for heart disease in clinical notes can help with disease progression modeling and clinical decision-making. Many studies have attempted to detect risk factors for heart disease, but none have identified all risk factors. These studies have proposed hybrid systems that combine knowledge-driven and data-driven techniques, based on dictionaries, rules, and machine learning methods that require significant human effort. The National Center for Informatics for Integrating Biology and Beyond (i2b2) proposed a clinical natural language processing (NLP) challenge in 2014, with a track (track2) focused on detecting risk factors for heart disease risk factors in clinical notes over time. Clinical narratives provide a wealth of information that can be extracted using NLP and Deep Learning techniques. The objective of this paper is to improve on previous work in this area as part of the 2014 i2b2 challenge by identifying tags and attributes relevant to disease diagnosis, risk factors, and medications by providing advanced techniques of using stacked word embeddings. The i2b2 heart disease risk factors challenge dataset has shown significant improvement by using the approach of stacking embeddings, which combines various embeddings. Our model achieved an F1 score of 93.66% by using BERT and character embeddings (CHARACTER-BERT Embedding) stacking. The proposed model has significant results compared to all other models and systems that we developed for the 2014 i2b2 challenge., (© 2023. The Author(s).)

Evaluation of tool wear is vital in manufacturing system, since early detections on worn-out condition can ensure workpiece quality, improve machining efficiency. With the development of intelligent manufacturing, tool wear prediction technology plays an increasingly important role. However, traditional tool wear prediction methods rely on experience and knowledge of experts and are labor-extensive. Deep learning provides an effective way to extract features of raw data and establish the mapping relationship between features and targets automatically. In this paper, a new local-feature and global-dependency based tool wear prediction method is proposed. It is a hybrid approach combining manual features with automatic features. Firstly, an enhanced CNN network is designed and applied on the transformed wavelet scalogram to learn the local single-scale specific features and multi-scale correlation features automatically. Secondly, sequence of local feature vectors combining manual features with automatic features are fed into multi-layer LSTM step by step for the global dependency. A fully connected layer is then trained to predict tool wear. Finally, two statistics are proposed to illustrate the overall prediction performance and generalization ability of the model. An experiment illustrates the effectiveness of our proposed method under multiple working conditions. [ABSTRACT FROM AUTHOR]

As an effective approach to perceive environments, acoustic scene classification (ASC) has received considerable attention in the past few years. Generally, ASC is deemed a challenging task due to subtle differences between various classes of environmental sounds. In this paper, we propose a novel approach to perform accurate classification based on the aggregation of spatial–temporal features extracted from a multi-branch three-dimensional (3D) convolution neural network (CNN) model. The novelties of this paper are as follows. First, we form multiple frequency-domain representations of signals by fully utilizing expert knowledge on acoustics and discrete wavelet transformations (DWT). Secondly, we propose a novel 3D CNN architecture featuring residual connections and squeeze-and-excitation attentions (3D-SE-ResNet) to effectively capture both long-term and short-term correlations inherent in environmental sounds. Thirdly, an auxiliary supervised branch based on the chromatogram of the original signal is incorporated in the proposed architecture to alleviate overfitting risks by providing supplementary information to the model. The performance of the proposed multi-input multi-feature 3D-CNN architecture is numerically evaluated on a typical large-scale dataset in the 2019 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2019) and is shown to obtain noticeable performance gains over the state-of-the-art methods in the literature. [ABSTRACT FROM AUTHOR]

The triage process in emergency departments (EDs) relies on the subjective assessment of medical practitioners, making it unreliable in certain aspects. There is a need for a more accurate and objective algorithm to determine the urgency of patients. This paper explores the application of advanced data-synthesis algorithms, machine learning (ML) algorithms, and ensemble models to predict patient mortality. Patients predicted to be at risk of mortality are in a highly critical condition, signifying an urgent need for immediate medical intervention. This paper aims to determine the most effective method for predicting mortality by enhancing the F1 score while maintaining high area under the receiver operating characteristic curve (AUC) score. This study used a dataset of 7325 patients who visited the Yonsei Severance Hospital's ED, located in Seoul, South Korea. The patients were divided into two groups: patients who deceased in the ED and patients who didn't. Various data-synthesis techniques, such as SMOTE, ADASYN, CTGAN, TVAE, CopulaGAN, and Gaussian Copula, were deployed to generate synthetic patient data. Twenty two ML models were then utilized, including tree-based algorithms like Decision tree, AdaBoost, LightGBM, CatBoost, XGBoost, NGBoost, TabNet, which are deep neural network algorithms, and statistical algorithms such as Support Vector Machine, Logistic Regression, Random Forest, k-nearest neighbors, and Gaussian Naive Bayes, as well as Ensemble Models which use the results from the ML models. Based on 21 patient information features used in the pandemic influenza triage algorithm (PITA), the models explained previously were applied to aim for the prediction of patient mortality. In evaluating ML algorithms using an imbalanced medical dataset, conventional metrics like accuracy scores or AUC can be misleading. This paper emphasizes the importance of using the F1 score as the primary performance measure, focusing on recall and specificity in detecting patient mortality. The highest-ranked model for predicting mortality utilized the Gaussian Copula data-synthesis technique and the CatBoost classifier, achieving an AUC of 0.9731 and an F1 score of 0.7059. These findings highlight the effectiveness of machine learning algorithms and data-synthesis techniques in improving the prediction performance of mortality in EDs. [ABSTRACT FROM AUTHOR]

Smart monitoring and surveillance systems have become one of the fundamental areas in the context of security applications in Smart Cities. In particular, video surveillance for Human Activity Recognition (HAR) applied to the recognition of potential offenders and to the detection and prevention of violent acts is a challenging task that is still undergoing. This paper presents a method based on deep learning for face recognition at a distance for security applications. Due to the absence of available datasets on face recognition at a distance, a methodology to generate a reliable dataset that relates the distance of the individuals from the camera, the focal length of the image sensors and the size in pixels of the target face is introduced. To generate the extended dataset, the Georgia Tech Face and Quality Dataset for Distance Faces databases were chosen. Our method is then tested and applied to a set of commercial image sensors for surveillance cameras using this dataset. The system achieves an average accuracy above 99% for several sensors and allows to calculate the maximum distance for a sensor to get the required accuracy in the recognition, which could be crucial in security applications in smart cities. [ABSTRACT FROM AUTHOR]

Electron energy loss spectroscopy (EELS) is a well established technique in electron microscopy that yields information on the elemental content of a sample in a very direct manner. One of the persisting limitations of EELS is the requirement for manual identification of core-loss edges and their corresponding elements. This can be especially bothersome in spectrum imaging, where a large amount of spectra are recorded when spatially scanning over a sample area. This paper introduces a synthetic dataset with 736,000 labeled EELS spectra, computed from available generalized oscillator strength tables, that represents 107 K, L, M or N core-loss edges and 80 chemical elements. Generic lifetime broadened peaks are used to mimic the fine structure due to band structure effects present in experimental core-loss edges. The proposed dataset is used to train and evaluate a series of neural network architectures, being a multilayer perceptron, a convolutional neural network, a U-Net, a residual neural network, a vision transformer and a compact convolutional transformer. An ensemble of neural networks is used to further increase performance. The ensemble network is used to demonstrate fully automated elemental mapping in a spectrum image, both by directly mapping the predicted elemental content and by using the predicted content as input for a physical model-based mapping. [ABSTRACT FROM AUTHOR]

In this paper, a novel technique for detecting female breast anomalous tissues is presented and validated through numerical simulations. The technique, to a high degree, resembles X-ray mammography; however, instead of using X-rays for obtaining images of the breast, low-frequency electromagnetic fields are leveraged. To capture breast impressions, a metasurface, which can be thought of as analogous to X-rays film, has been employed. To achieve deep and sufficient penetration within the breast tissues, the source of excitation is a simple narrow-band dipole antenna operating at 200 MHz. The metasurface is designed to operate at the same frequency. The detection mechanism is based on comparing the impressions obtained from the breast under examination to the reference case (healthy breasts) using machine learning techniques. Using this system, not only would it be possible to detect tumors (benign or malignant), but one can also determine the location and size of the tumors. Remarkably, deep learning models were found to achieve very high classification accuracy. [ABSTRACT FROM AUTHOR]

The mining of open pit mines is widespread in China, and there are many cases of landslide accidents. Therefore, the problem of slope stability is highlighted. The stability of the slope is a factor that directly affects the mining efficiency and the safety of the entire mining process. According to the statistics, there is a 15 percent chance of finding landslide risk in China's large-scale mines. And due to the expansion of the mining scale of the enterprise, the problem of slope stability has become increasingly obvious, which has become a major subject in the study of open-pit mine engineering. In order to better predict the slope stability coefficient, this study takes a mine in China as a case to deeply discuss the accuracy of different algorithms in the stability calculation, and then uses a deep learning algorithm to study the stability under rainfall conditions. The change of the coefficient and the change of the stability coefficient before and after the slope treatment are experimentally studied with the displacement of the monitoring point. The result shows that the safety coefficient calculated by the algorithm in this paper is about 7% lower than that of the traditional algorithm. In the slope stability analysis before treatment, the safety factor calculated by the algorithm in this paper is 1.086, and the algorithm in this paper is closer to reality. In the stability analysis of the slope after treatment, the safety factor calculated by the algorithm in this paper is 1.227, and the stability factor meets the requirements of the specification. It also shows that the deep learning algorithm effectively improves the efficiency of the slope stability factor prediction and improves security during project development. [ABSTRACT FROM AUTHOR]

In the field of machine intelligence and ubiquitous computing, there has been a growing interest in human activity recognition using wearable sensors. Over the past few decades, researchers have extensively explored learning-based methods to develop effective models for identifying human behaviors. Deep learning algorithms, known for their powerful feature extraction capabilities, have played a prominent role in this area. These algorithms can conveniently extract features that enable excellent recognition performance. However, many successful deep learning approaches have been built upon complex models with multiple hyperparameters. This paper examines the current research on human activity recognition using deep learning techniques and discusses appropriate recognition strategies. Initially, we employed multiple convolutional neural networks to determine an effective architecture for human activity recognition. Subsequently, we developed a hybrid convolutional neural network that incorporates a channel attention mechanism. This mechanism enables the network to capture deep spatio-temporal characteristics in a hierarchical manner and distinguish between different human movements in everyday life. Our investigations, using the UCI-HAR, WISDM, and IM-WSHA datasets, demonstrated that our proposed model, which includes cross-channel multi-size convolution transformations, outperformed previous deep learning architectures with accuracy rates of 98.92%, 98.80%, and 98.45% respectively. These results indicate that the suggested model surpasses state-of-the-art approaches in terms of overall accuracy, as supported by the research findings. [ABSTRACT FROM AUTHOR]

Exposure to alcohol content in media increases alcohol consumption and related harm. With exponential growth of media content, it is important to use algorithms to automatically detect and quantify alcohol exposure. Foundation models such as Contrastive Language-Image Pretraining (CLIP) can detect alcohol exposure through Zero-Shot Learning (ZSL) without any additional training. In this paper, we evaluated the ZSL performance of CLIP against a supervised algorithm called Alcoholic Beverage Identification Deep Learning Algorithm Version-2 (ABIDLA2), which is specifically trained to recognise alcoholic beverages in images, across three tasks. We found ZSL achieved similar performance compared to ABIDLA2 in two out of three tasks. However, ABIDLA2 outperformed ZSL in a fine-grained classification task in which determining subtle differences among alcoholic beverages (including containers) are essential. We also found that phrase engineering is essential for improving the performance of ZSL. To conclude, like ABIDLA2, ZSL with little phrase engineering can achieve promising performance in identifying alcohol exposure in images. This makes it easier for researchers, with little or no programming background, to implement ZSL effectively to obtain insightful analytics from digital media. Such analytics can assist researchers and policy makers to propose regulations that can prevent alcohol exposure and eventually prevent alcohol consumption. [ABSTRACT FROM AUTHOR]

This paper presents a new strategy to generate synthetic samples containing casting defects. Four samples of Inconel 100 containing casting defects such as shrinkages and pores have been characterized using X-ray tomography and are used as reference for this application. Shrinkages are known to be tortuous in shape and more detrimental for the mechanical properties of materials, especially metal fatigue, whereas pores can be of two types: broken shrinkage pores with arbitrary shape and gaseous pores of spherical shape. For the generation of synthetic samples, an integrated module of Spatial Point Pattern (SPP) analysis and deep learning techniques such as Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNNs) are used. The SPP analysis describes the spatial distributions of casting defects in material space, whereas GANs and CNNs generate a defect of arbitrary morphology very close to real defects. SPP analysis reveals the existence of two different void nucleation mechanisms during metal solidification associated to shrinkages and pores. Our deep learning model successfully generates casting defects with defect size ranging from 100 µm to 1.5 mm and of very realistic shapes. The entire synthetic microstructure generation process respects the global defect statistics of reference samples and the generated samples are validated by statistically comparing with real samples. [ABSTRACT FROM AUTHOR]