Search

Simple Summary: Breast cancer is one of the leading causes of cancer death among women. Developing machine learning-based diagnosis models receives great attention from researchers and scientists using histopathology images. Deep learning (DL) algorithms automatically extract features from raw data through convolutional operations. The generalization of the DL models' results relies on large datasets, although they eliminate the expert knowledge in the feature extraction stage. This work aimed to compare the performance of the features extracted via deep learning and a knowledge-based approach in breast cancer detection from histopathology images. Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers. [ABSTRACT FROM AUTHOR]

Motivation Interpretable deep learning (DL) models that can provide biological insights, in addition to accurate predictions, are of great interest to the biomedical community. Recently, interpretable DL models that incorporate signaling pathways have been proposed for drug response prediction (DRP). While these models improve interpretability, it is unclear whether this comes at the cost of less accurate DRPs, or a prediction improvement can also be obtained. Results We comprehensively and systematically assessed four state-of-the-art interpretable DL models using three pathway collections to assess their ability in making accurate predictions on unseen samples from the same dataset, as well as their generalizability to an independent dataset. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. However, in most evaluation setups, the best performance was achieved using a black-box multilayer perceptron, and the performance of a random forests baseline was comparable to those of the interpretable models. Replacing the signaling pathways with randomly generated pathways showed a comparable performance for the majority of the models. Finally, the performance of all models deteriorated when applied to an independent dataset. These results highlight the importance of systematic evaluation of newly proposed models using carefully selected baselines. We provide different evaluation setups and baseline models that can be used to achieve this goal. Availability and implementation Implemented models and datasets are provided at https://doi.org/10.5281/zenodo.7787178 and https://doi.org/10.5281/zenodo.7101665 , respectively. [ABSTRACT FROM AUTHOR]

Approximately 65% of the worldwide adult population has experienced stress, affecting their daily routine at least once in the past year. Stress becomes harmful when it occurs for too long or is continuous (i.e., chronic), interfering with our performance, attention, and concentration. Chronic high stress contributes to major health issues such as heart disease, high blood pressure, diabetes, depression, and anxiety. Several researchers have focused on detecting stress through combining many features with machine/deep learning models. Despite these efforts, our community has not agreed on the number of features to identify stress conditions using wearable devices. In addition, most of the reported studies have been focused on person-specific training and testing. Thanks to our community's broad acceptance of wearable wristband devices, this work investigates a global stress detection model combining eight HRV features with a random forest (RF) algorithm. Whereas the model's performance is evaluated for each individual, the training of the RF model contains instances of all subjects (i.e., global training). We have validated the proposed global stress model using two open-access databases (the WESAD and SWELL databases) and their combination. The eight HRV features with the highest classifying power are selected using the minimum redundancy maximum relevance (mRMR) method, reducing the training time of the global stress platform. The proposed global stress monitoring model identifies person-specific stress events with an accuracy higher than 99% after a global training framework. Future work should be focused on testing this global stress monitoring framework in real-world applications. [ABSTRACT FROM AUTHOR]

Particulate matter (PM) in the air can cause various health problems and diseases in humans. In particular, the smaller size of PM 2.5 enable them to penetrate deep into the lungs, causing severe health impacts. Exposure to PM 2.5 can result in respiratory, cardiovascular, and allergic diseases, and prolonged exposure has also been linked to an increased risk of cancer, including lung cancer. Therefore, forecasting the PM 2.5 concentration in the surrounding is crucial for preventing these adverse health effects. This paper proposes a method for forecasting the PM 2.5 concentration after 1 h using bidirectional long short-term memory (Bi-LSTM). The proposed method involves selecting input variables based on the feature importance calculated by random forest, classifying the data to assign weight variables to reduce bias, and forecasting the PM 2.5 concentration using Bi-LSTM. To compare the performance of the proposed method, two case studies were conducted. First, a comparison of forecasting performance according to preprocessing. Second, forecasting performance between deep learning (long short-term memory, gated recurrent unit, and Bi-LSTM) and conventional machine learning models (multi-layer perceptron, support vector machine, decision tree, and random forest). In case study 1, The proposed method shows that the performance indices (RMSE: 3.98%p, MAE: 5.87%p, RRMSE: 3.96%p, and R 2 :0.72%p) are improved because weights are given according to the input variables before the forecasting is performed. In case study 2, we show that Bi-LSTM, which considers both directions (forward and backward), can effectively forecast when compared to conventional models (RMSE: 2.70, MAE: 0.84, RRMSE: 1.97, R 2 : 0.16). Therefore, it is shown that the proposed method can effectively forecast PM 2.5 even if the data in the high-concentration section is insufficient. [ABSTRACT FROM AUTHOR]

Cybersecurity has become one of the focuses of organisations. The number of cyberattacks keeps increasing as Internet usage continues to grow. As new types of cyberattacks continue to emerge, researchers focus on developing machine learning (ML)-based intrusion detection systems (IDS) to detect zero-day attacks. They usually remove some or all attack samples from the training dataset and only include them in the testing dataset when evaluating the performance. This method may detect unknown attacks; however, it does not reflect the long-term performance of the IDS as it only shows the changes in the type of attacks. In this work, we focused on evaluating the long-term performance of ML-based IDS. To achieve this goal, we proposed evaluating the ML-based IDS using a dataset created later than the training dataset. The proposed method can better assess the long-term performance as the testing dataset reflects the changes in the attack type and network infrastructure changes over time. We have implemented six of the most popular ML models, including decision tree (DT), random forest (RF), support vector machine (SVM), naïve Bayes (NB), artificial neural network (ANN), and deep neural network (DNN). These models are trained and tested with a pair of datasets with symmetrical classes. Our experiments using the CIC-IDS2017 and the CSE-CIC-IDS2018 datasets show that SVM and ANN are most resistant to overfitting. Our experiments also indicate that DT and RF suffer the most from overfitting, although they perform well on the training dataset. On the other hand, our experiments using the LUFlow dataset have shown that all models can perform well when the difference between the training and testing datasets is small. [ABSTRACT FROM AUTHOR]

Purpose: Hypercholesterolemia is a major risk factor for a wide range of cardiovascular diseases. Developing countries are more susceptible to hypercholesterolemia and its complications due to the increasing prevalence and the lack of adequate resources for conducting screening and/or prevention programs. Using machine learning techniques to identify factors contributing to hypercholesterolemia and developing predictive models can help early detection of hypercholesterolemia, especially in developing countries. Methods: Data from the nationwide 2016 STEPs study in Iran were used to identify socioeconomic, lifestyle, and metabolic risk factors associated with hypercholesterolemia. Furthermore, the predictive power of the identified risk factors was assessed using five commonly used machine learning algorithms (random forest; gradient boosting; support vector machine; logistic regression; artificial neural network) and 10-fold cross validation in terms of specificity, sensitivity, and the area under the receiver operating characteristic curve. Results: A total of 14,667 individuals were included in this study, of those 12.8% (n = 1879) had (undiagnosed) hypercholesterolemia. Based on multivariate logistic regression analysis the five most important risk factors for hypercholesterolemia were: older age (for the elderly group: OR = 2.243; for the middle-aged group: OR = 1.869), obesity-related factors including high BMI status (morbidly obese: OR = 1.884; obese: OR = 1.499; overweight: OR = 1.426) and AO (OR = 1.339), raised BP (hypertension: OR = 1.729; prehypertension: OR = 1.577), consuming fish once or twice per week (OR = 1.261), and having risky diet (OR = 1.163). Furthermore, all the five hypercholesterolemia prediction models achieved AUC around 0.62, and models based on random forest (AUC = 0.6282; specificity = 65.14%; sensitivity = 60.51%) and gradient boosting (AUC = 0.6263; specificity = 64.11%; sensitivity = 61.15%) had the optimal performance. Conclusion: The study shows that socioeconomic inequalities, unhealthy lifestyle, and metabolic syndrome (including obesity and hypertension) are significant predictors of hypercholesterolemia. Therefore controlling these factors is necessary to reduce the burden of hypercholesterolemia. Furthermore, machine learning algorithms such as random forest and gradient boosting can be employed for hypercholesterolemia screening and its timely diagnosis. Applying deep learning algorithms as well as techniques for handling the class overlap problem seems necessary to improve the performance of the models. [ABSTRACT FROM AUTHOR]

Advanced Metering Infrastructure (AMI) is the metering network of the smart grid that enables bidirectional communications between each consumer's premises and the provider's control center. The massive amount of data collected supports the real-time decision-making required for diverse applications. The communication infrastructure relies on different network types, including the Internet. This makes the infrastructure vulnerable to various attacks, which could compromise security or have devastating effects. However, traditional machine learning solutions cannot adapt to the increasing complexity and diversity of attacks. The objective of this paper is to develop an Anomaly Detection System (ADS) based on deep learning using the CIC-IDS2017 dataset. However, this dataset is highly imbalanced; thus, a two-step sampling technique: random under-sampling and the Synthetic Minority Oversampling Technique (SMOTE), is proposed to balance the dataset. The proposed system utilizes a multiple hidden layer Auto-encoder (AE) for feature extraction and dimensional reduction. In addition, an ensemble voting based on both Random Forest (RF) and Convolutional Neural Network (CNN) is developed to classify the multiclass attack categories. The proposed system is evaluated and compared with six different state-of-the-art machine learning and deep learning algorithms: Random Forest (RF), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGboost), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and bidirectional LSTM (biLSTM). Experimental results show that the proposed model enhances the detection for each attack class compared with the other machine learning and deep learning models with overall accuracy (98.29%), precision (99%), recall (98%), F¹ score (98%), and the UNDetection rate (UND) (8%). [ABSTRACT FROM AUTHOR]

The coronavirus is considered this century’s most disruptive catastrophe and global concern. This disease has prompted extreme social, psychological and economic impacts affecting millions of people around the globe. COVID-19 is transmitted from one infected person’s body to another through respiratory droplets. This virus proliferates when people breathe in air-contaminated space with droplets and microscopic airborne particles. This research aims to analyze automatic COVID-19 detection using machine learning techniques to build an intelligent web application. The dataset has been preprocessed by dropping null values, feature engineering, and synthetic oversampling (SMOTE) techniques. Next, we trained and evaluated different classifiers, i.e., logistic regression, random forest, decision tree, k-nearest neighbor, support vector machine (SVM), ensemble models (adaptive boosting and extreme gradient boosting) and deep learning (artificial neural network, convolutional neural network and long short-term memory) techniques. Explainable AI with the LIME framework has been applied to interpret the prediction results. The hybrid CNN-LSTM algorithm with the SMOTE approach performed better than the other models on the employed open-source dataset obtained from the Israeli Ministry of Health website, with 96.34% accuracy and a 0.98 F1 score. Finally, this model was chosen to deploy the proposed prediction system to a website, where users may acquire an instantaneous COVID-19 prognosis based on their symptoms. [ABSTRACT FROM AUTHOR]

As a result of the expansions that have taken place in the field of networking and the increase in the number of users of networks, there have recently been breakthroughs made in the techniques and methods used for network security. In this paper, a virtual private network (VPN) is proposed as a means of providing the necessary level of security for particular connections that span across vast networks. After the network performance metrics such as time delay and throughput have been accomplished, the suggested VPN is recommended for the purpose of assuring network security. In addition, artificial intelligence attack predictors and virtual private networks have been implemented with the purpose of preventing harmful activity within such connections. Using a wide variety of machine learning methods like Random Forests and Nave Bays, malicious assaults of any kind can be identified and thwarted in their tracks. Another technique for anticipating attacks is the use of an artificial neural network, which is a type of system that engages in deep learning and learns the behaviors of attacks while it is being trained so that it can then predict attacks. The results of this study demonstrate that the use of machine learning and artificial intelligence techniques can significantly improve the security and performance of virtual private networks and can effectively identify and prevent malicious attacks on networks. [ABSTRACT FROM AUTHOR]

This paper presents the development of physics-informed machine learning models for subsurface flows, specifically for determining pressure variation in the subsurface without the use of numerical modeling schemes. The numerical elliptic operator is replaced with a neural network operator and includes comparisons of several different machine learning models, along with linear regression, support vector regression, lasso, random forest regression, decision tree regression, light weight gradient boosting, eXtreme gradient boosting, convolution neural network, artificial neural network, and perceptron. The mean of absolute error of all models is compared, and error residual plots are used as a measure of error to determine the best-performing method. [ABSTRACT FROM AUTHOR]

With the advent of the Internet, the activities of individuals and businesses have expanded into the online realm. As a result, vulnerabilities that result in actual breaches can lead to data loss and program failure. The number of breaches is increasing every year, as is the number of vulnerabilities. To address this problem, current research focuses on the detection of vulnerabilities using static analysis techniques. To prevent the propagation of vulnerabilities, a new paradigm is needed to quickly detect vulnerabilities, analyze them, and take actions such as blocking or removing them. Recently, artificial intelligence algorithms such as deep learning have been introduced for vulnerability detection. In this paper, we propose a vulnerability detection model, V-CNN, which aims to detect CWE/CVE (Common Weakness Enumeration/Common Vulnerabilities and Exposures) using CNN (convolutional neural network). We trained CWE for deep learning and redefined vulnerabilities based on CWE. We propose an experimental algorithm to improve vulnerability detection. The accuracy of the proposed V-CNN model is 98%, which exceeds the 95% of the random forest model. Therefore, our V-CNN has excellent correctness detection performance in the field of vulnerability detection. The V-CNN vulnerability detection algorithm can be used instead of static analysis to detect various security vulnerabilities. [ABSTRACT FROM AUTHOR]

Firefighters face numerous challenges when entering burning structures to rescue trapped victims, assess the conditions of a residential structure, and extinguish the fire as quickly as possible. These challenges include extreme temperatures, smoke, toxic gases, explosions, and falling objects, which can hinder their efficiency and pose risks to their safety. Accurate information and data about the burning site can help firefighters make informed decisions about their duties and determine when it is safe to enter and evacuate, reducing the likelihood of casualties. This research presents unsupervised deep learning (DL) to classify the danger levels at a burning site and an autoregressive integrated moving average (ARIMA) prediction model to forecast temperature changes using the extrapolation of a random forest regressor. The DL classifier algorithms provide the chief firefighter with an awareness of the danger levels in the burning compartment. The prediction models forecast the rise in temperature from a height ranging from 0.6 m to 2.6 m and the changes in temperature over time at an altitude of 2.6 m. Predicting the temperature at this altitude is critical as the temperature increases faster with height, and elevated temperatures can weaken the building's structural material. We also investigated a new classification method using an unsupervised DL autoencoder artificial neural network (AE-ANN). The prediction data analytical approach included using the autoregressive integrated moving average (ARIMA) with random forest regression implementation. The proposed AE-ANN model, with an accuracy score of 0.869, did not perform as well compared to previous work, with an accuracy of 0.989, at achieving high accuracy scores for the classification task using the same dataset. However, the random forest regressor and our ARIMA models are analyzed and evaluated in this work, while other research has not utilized this dataset, even though it is open-sourced. However, the ARIMA model demonstrated remarkable predictions of the trends of temperature changes in a burning site. The proposed research aims to classify fire sites into dangerous levels and predict temperature progression using deep learning and predictive modeling techniques. This research's main contribution is using a random forest regressor and autoregressive integrated moving average models to predict temperature trends in burning sites. This research demonstrates the potential of using deep learning and predictive modeling to enhance firefighter safety and decision-making processes. [ABSTRACT FROM AUTHOR]

Accurate information on dominant tree species and their spatial distribution in subtropical natural forests are key ecological monitoring factors for accurately characterizing forest biodiversity, depicting the tree competition mechanism and quantitatively evaluating forest ecosystem stability. In this study, the subtropical natural forest in northwest Yunnan province of China was selected as the study area. Firstly, an object-oriented multi-resolution segmentation (MRS) algorithm was used to segment individual tree crowns from the UAV RGB imagery and satellite multispectral imagery in the forests with different densities (low (547 n/ha), middle (753 n/ha) and high (1040 n/ha)), and parameters of the MRS algorithm were tested and optimized for accurately extracting the tree crown and position information of the individual tree. Secondly, the texture metrics of the UAV RGB imagery and the spectral metrics of the satellite multispectral imagery within the individual tree crown were extracted, and the random forest algorithm and three deep learning networks constructed in this study were utilized to classify the five dominant tree species. Finally, we compared and evaluated the performance of the random forest algorithm and three deep learning networks for dominant tree species classification using the field measurement data, and the influence of the number of training samples on the accuracy of dominant tree species classification using deep learning networks was investigated. The results showed that: (1) Stand density had little influence on individual tree segmentation using the object-oriented MRS algorithm. In the forests with different stand densities, the F1 score of individual tree segmentation based on satellite multispectral imagery was 71.3–74.7%, and that based on UAV high-resolution RGB imagery was 75.4–79.2%. (2) The overall accuracy of dominant tree species classification using the light-weight network MobileNetV2 (OA = 71.11–82.22%), residual network ResNet34 (OA = 78.89–91.11%) and dense network DenseNet121 (OA = 81.11–94.44%) was higher than that of the random forest algorithm (OA = 60.00–64.44%), among which DenseNet121 had the highest overall accuracy. Texture metrics improved the overall accuracy of dominant tree species classification. (3) For the three deep learning networks, the changes in overall accuracy of dominant tree species classification influenced by the number of training samples were 2.69–4.28%. [ABSTRACT FROM AUTHOR]

Applied computing and artificial intelligence methods have been attracting growing interest in recent years due to their effectiveness in solving technical problems. Hao et al. [[14]] present an unsupervised fault diagnosis methodology to leverage the generated MPCs of different working conditions to diagnose the actual unlabeled MPCs. The paper by Ainapure et al. [[17]] proposes a new cross-domain fault diagnosis method with enhanced robustness. The paper by Saeed et al. [[1]] proposes an approach to building an AutoML data-dependent CNN model (DeepPCANet) customized for DR screening automatically. [Extracted from the article]

Breast cancer is categorized as an aggressive disease, and it is one of the leading causes of death. Accurate survival predictions for both long-term and short-term survivors, when delivered on time, can help physicians make effective treatment decisions for their patients. Therefore, there is a dire need to design an efficient and rapid computational model for breast cancer prognosis. In this study, we propose an ensemble model for breast cancer survivability prediction (EBCSP) that utilizes multi-modal data and stacks the output of multiple neural networks. Specifically, we design a convolutional neural network (CNN) for clinical modalities, a deep neural network (DNN) for copy number variations (CNV), and a long short-term memory (LSTM) architecture for gene expression modalities to effectively handle multi-dimensional data. The independent models' results are then used for binary classification (long term > 5 years and short term < 5 years) based on survivability using the random forest method. The EBCSP model's successful application outperforms models that utilize a single data modality for prediction and existing benchmarks. [ABSTRACT FROM AUTHOR]

Among the different contactless techniques for medical diagnosis, hyperspectral imaging has gained relevance due to the high accuracy in tissues classification. Several techniques have been proposed to elaborate these images, ranging from traditional machine learning methods to deep learning algorithms. This paper evaluates three popular machine learning methods, namely Support Vector Machine (SVM), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) considering a dataset of hyperspectral skin cancer images. The study demonstrates that the proposed algorithms are suitable for medical hyperspectral data classification, particularly when considering a small dataset. [ABSTRACT FROM AUTHOR]

With the recent growth of the Internet, the volume of data has also increased. In particular, the increase in the amount of unstructured data makes it difficult to manage data. Classification is also needed in order to be able to use the data for various purposes. Since it is difficult to manually classify the ever-increasing volume data for the purpose of various types of analysis and evaluation, automatic classification methods are needed. In addition, the performance of imbalanced and multi-class classification is a challenging task. As the number of classes increases, so does the number of decision boundaries a learning algorithm has to solve. Therefore, in this paper, an improvement model is proposed using WordNet lexical ontology and BERT to perform deeper learning on the features of text, thereby improving the classification effect of the model. It was observed that classification success increased when using WordNet 11 general lexicographer files based on synthesis sets, syntactic categories, and logical groupings. WordNet was used for feature dimension reduction. In experimental studies, word embedding methods were used without dimension reduction. Afterwards, Random Forest (RF), Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) algorithms were employed to perform classification. These studies were then repeated with dimension reduction performed by WordNet. In addition to the machine learning model, experiments were also conducted with the pretrained BERT model with and without WordNet. The experimental results showed that, on an unstructured, seven-class, imbalanced dataset, the highest accuracy value of 93.77% was obtained when using our proposed model. [ABSTRACT FROM AUTHOR]

Face recognition technology has been widely used due to the convenience it provides. However, face recognition is vulnerable to spoofing attacks which limits its usage in sensitive application areas. This work introduces a novel face anti-spoofing system, FASS, that fuses results of two classifiers. One, random forest, uses the identified by us seven no-reference image quality features derived from face images and its results are fused with a deep learning classifier results that uses entire face images as input. Extensive experiments were performed to compare FASS with state-of-the-art anti-spoofing systems on five benchmark datasets: Replay-Attack, CASIA-MFSD, MSU-MFSD, OULU-NPU and SiW. The results show that FASS outperforms all face anti-spoofing systems based on image quality features and is also more accurate than many of the state-of-the-art systems based on deep learning. [ABSTRACT FROM AUTHOR]

The increase in the number of undesired SMS termed smishing message and the data imbalance problem has generated a great demand for the development of more reliable anti‐spam filters. State of the art machine learning approaches are being employed to recognize and separate spam messages. Most recent studies target message classification by using numerous properties and features of the words but fail to consider the circumstantial features like long‐range dependencies between the words that are extremely important in identifying smishing messages. The idea is to develop an intelligent model that will distinguish between smishing messages and ham messages, by adopting a combined approach of regular expression (Regex), machine learning (ML) and deep learning (DL) models. Regex rules are generated using the dataset's spam messages for the purpose of refining the dataset. Support vector machine (SVM), Multinomial Naive Bayes and Random Forest are included under machine learning models and long short‐term memory (LSTM), bidirectional long short‐term memory (Bi‐LSTM), stacked LSTM and stacked Bi‐LSTM are included under deep learning models. The comparison between machine learning models and deep learning models is also carried out based on the performance evaluation parameters namely accuracy, precision, recall and F1 score of the models. It is observed that deep learning models perform better than machine learning models and the introduction of a regular expression to the dataset increases the efficiency of both the deep learning models and machine learning models. [ABSTRACT FROM AUTHOR]

Depression is a serious mental health condition that may lead to poor mental and emotional functioning at work, at school and in the family causing the mental imbalance. In worst scenarios, depression may lead to severe anxiety or suicide. Hence, it is necessary to diagnose depression at early stages. This paper elaborates the development of a novel approach for a convolutional neural network model that can examine facial images from the recorded interview sessions to discover facial patterns that could indicate depression level. The user‐generated data helps to distinguish between different depressive groups with depression symptoms that can manifest people with various mental illnesses in different ways. In particular, we want to automatically predict the depression scale and differentiate depression from other mental disorders using the patient's psychiatric illness history and dynamic textual descriptions extracted from the user inputs. We apply the k‐nearest neighbour algorithm on the dynamic textual descriptors to make a linguistic analysis for classifying mental illness into different classes. We apply dimensionality reduction and regression using the Random Forest algorithm to predict the depression scale. The proposed framework is an extension to pre‐existing frameworks, replacing the handcrafted feature extraction technique with the deep feature extraction. The model performs 2.7% better than existing frameworks in facial detection and feature extraction. [ABSTRACT FROM AUTHOR]

Accurate stock price prediction has an important role in stock investment. Because stock price data are characterized by high frequency, nonlinearity, and long memory, predicting stock prices precisely is challenging. Various forecasting methods have been proposed, from classical time series methods to machine-learning-based methods, such as random forest (RF), recurrent neural network (RNN), convolutional neural network (CNN), Long Short-Term Memory (LSTM) neural networks and their variants, etc. Each method can reach a certain level of accuracy but also has its limitations. In this paper, a CNN-BiLSTM-Attention-based model is proposed to boost the accuracy of predicting stock prices and indices. First, the temporal features of sequence data are extracted using a convolutional neural network (CNN) and bi-directional long and short-term memory (BiLSTM) network. Then, an attention mechanism is introduced to fit weight assignments to the information features automatically; and finally, the final prediction results are output through the dense layer. The proposed method was first used to predict the price of the Chinese stock index—the CSI300 index and was found to be more accurate than any of the other three methods—LSTM, CNN-LSTM, CNN-LSTM-Attention. In order to investigate whether the proposed model is robustly effective in predicting stock indices, three other stock indices in China and eight international stock indices were selected to test, and the robust effectiveness of the CNN-BiLSTM-Attention model in predicting stock prices was confirmed. Comparing this method with the LSTM, CNN-LSTM, and CNN-LSTM-Attention models, it is found that the accuracy of stock price prediction is highest using the CNN-BiLSTM-Attention model in almost all cases. [ABSTRACT FROM AUTHOR]

Today, image classification methods are widely utilized on agricultural products or in agricultural applications. However, many of these methods based on traditional approaches remain unsatisfactory in terms of obtaining effective results. Within this context, this study aimed to classify lentil images by machine learning algorithms, a current and effective method. In line with this purpose, first of all, a camera system was prepared primarily and a dataset was created by recording lentil grains at 225 × 225 resolution via this system. The dataset contains a total of 33,938 data obtained from 3 lentil species as green, yellow, and red. SqueezeNet, InceptionV3, DeepLoc, and VGG16 architectures, among the CNN methods, were used in order to extract features from the recorded images. Lastly, Artificial Neural Network (ANN), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AB), and Decision Tree (DT) algorithms were utilized with the aim of creating models for lentil images' classification. The classification success of the created machine learning models was calculated and the results were analyzed. The highest classification success with the deep features obtained from the SqueezeNet model, 99.80%, was achieved in the ANN algorithm. The results also revealed that grain size and shape features in image classification can yield much more detailed and precise data than can be obtained practically with manual quality assessment. [ABSTRACT FROM AUTHOR]

Crime is hard to anticipate since it occurs at random and can occur anywhere at any moment, making it a difficult issue for any society to address. By analyzing and comparing eight known prediction models: Naive Bayes, Stacking, Random Forest, Lazy:IBK, Bagging, Support Vector Machine, Convolutional Neural Network, and Locally Weighted Learning - this study proposed an improved deep learning crime prediction model using convolutional neural networks and the xgboost algorithm to predict crime. The major goal of this research is to provide an improved crime prediction model based on previous criminal records. Using the Boston crime dataset, where our larceny crime dataset was extracted, exploratory data analysis (EDA) is used to uncover patterns and explain trends in crimes. The performance of the proposed model on the basis of accuracy, recall, and f-measure was 100% outperforming the other models used in this study. The analysis of the proposed model and prediction can aid security services in making better use of their resources, anticipating crime at a certain time, and serving the society better. [ABSTRACT FROM AUTHOR]

Accurate and reliable measurement of key biological parameters during penicillin fermentation is of great significance for improving penicillin production. In this research context, a new hybrid soft sensor model method based on RF-IHHO-LSTM (random forest-improved​ Harris hawks optimization-long short-term memory) is proposed for penicillin fermentation processes. Firstly, random forest (RF) is used for feature selection of the auxiliary variables for penicillin. Next, improvements are made for the Harris hawks optimization (HHO) algorithm, including using elite opposition-based learning strategy (EOBL) in initialization to enhance the population diversity, and using golden sine algorithm (Gold-SA) in the search strategy to make the algorithm accelerate convergence. Then the long short-term memory (LSTM) network is constructed to build a soft sensor model of penicillin fermentation processes. Finally, the hybrid soft sensor model is used to the Pensim platform in simulation experimental research. The simulation test results show that the established soft sensor model, with high accuracy of measurement and good effect, can meet the actual requirements of engineering. • RF is used for feature selection of the auxiliary variables for penicillin fermentation process. • Elite opposition-based learning and Golden sine algorithm are used to improve HHO. • The improved HHO algorithm is introduced to optimize the LSTM network. • The effectiveness of the proposed method was confirmed through case studies using real datasets. [ABSTRACT FROM AUTHOR]

Tunnel fan is critical fire-fighting equipment, and its safe and stable operation is very important for the efficiency and safety of tunnel traffic. Existing studies commonly train the fault diagnosis methods with the goal of minimizing mean error which ignores the difference between classes in feature distribution. To solve the problem of inaccurate prediction caused by mean error evaluation, this paper presents a non-neural deep learning model, namely hierarchical cascade forest, which has three characteristics: (1) A hierarchical cascade structure is constructed, of which the output comes from each layer; (2) Each fault class is evaluated and recognized independently, the result of fault classes that are easy to distinguish is output earlier; (3) A confidence-based threshold estimate method is proposed in HCF and used to improve the training method to increase the reliability of HCF. Based on these, HCF improves the cascade forest structure and implements the proper matching of different depth of feature and fault patterns. The effect of HCF is verified through experiments based on the tunnel fans testing rig. Experimented results show that, compared to Deep Forest, the accuracy of HCF increases by 0.6% to 10.8%, and the training time of HCF is reduced 33.24%. • A cascaded forest-based hierarchical framework is proposed for intelligent fault diagnosis. • A novel confidence is defined to evaluate the credibility of the accuracy threshold. • The efficiency of HCF is improved through the hierarchical output structure. • The proposed method is verified on two real mechanical fault datasets. [ABSTRACT FROM AUTHOR]

Global carbon fluxes describe the carbon exchange between land and atmosphere. However, already available global carbon fluxes datasets have not been adjusted by the available site data and deep learning tools. In this work, a global carbon fluxes dataset (named as GCFD) of gross primary productivity (GPP), terrestrial ecosystem respiration (RECO), and net ecosystem exchange (NEE) has been developed via a deep learning based convolutional neural network (CNN) model. The dataset has a spatial resolution of 1 km at three time steps per month from January 1999 to June 2020. Flux measurements were used as a training target while remote sensing of vegetation conditions and meteorological data were used as predictors. The results showed that CNN could outperform other commonly used machine learning methods such as random forest (RF) and artificial neural network (ANN) by leading to satisfactory performance with R2 values of the validation stage as 0.82, 0.72 and 0.62 for GPP, RECO, and NEE modelling, respectively. Thus, CNN trained using reanalysis meteorological data and remote sensing data was chosen to produce the global dataset. GCFD showed higher accuracy and more spatial details than some other global carbon flux datasets with reasonable spatial pattern and temporal variation. GCFD is also in accordance with vegetation conditions detected by remote sensing. Owing to the obtained results, GCFD can be a useful reference for various meteorological and ecological analyses and modelling, especially when high resolution carbon flux maps are required. [ABSTRACT FROM AUTHOR]

Traditional Chinese medicine (TCM) has been practiced for thousands of years with clinical efficacy. Natural products and their effective agents such as artemisinin and paclitaxel have saved millions of lives worldwide. Artificial intelligence is being increasingly deployed in TCM. By summarizing the principles and processes of deep learning and traditional machine learning algorithms, analyzing the application of machine learning in TCM, reviewing the results of previous studies, this study proposed a promising future perspective based on the combination of machine learning, TCM theory, chemical compositions of natural products, and computational simulations based on molecules and chemical compositions. In the first place, machine learning will be utilized in the effective chemical components of natural products to target the pathological molecules of the disease which could achieve the purpose of screening the natural products on the basis of the pathological mechanisms they target. In this approach, computational simulations will be used for processing the data for effective chemical components, generating datasets for analyzing features. In the next step, machine learning will be used to analyze the datasets on the basis of TCM theories such as the superposition of syndrome elements. Finally, interdisciplinary natural product-syndrome research will be established by unifying the results of the two steps outlined above, potentially realizing an intelligent artificial intelligence diagnosis and treatment model based on the effective chemical components of natural products under the guidance of TCM theory. This perspective outlines an innovative application of machine learning in the clinical practice of TCM based on the investigation of chemical molecules under the guidance of TCM theory. [ABSTRACT FROM AUTHOR]

Introduction and methodology: Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs). It has been hypothesised that QSAR models struggle to predict ACs and that ACs thus form a major source of prediction error. However, the AC-prediction power of modern QSAR methods and its quantitative relationship to general QSAR-prediction performance is still underexplored. We systematically construct nine distinct QSAR models by combining three molecular representation methods (extended-connectivity fingerprints, physicochemical-descriptor vectors and graph isomorphism networks) with three regression techniques (random forests, k-nearest neighbours and multilayer perceptrons); we then use each resulting model to classify pairs of similar compounds as ACs or non-ACs and to predict the activities of individual molecules in three case studies: dopamine receptor D2, factor Xa, and SARS-CoV-2 main protease. Results and conclusions: Our results provide strong support for the hypothesis that indeed QSAR models frequently fail to predict ACs. We observe low AC-sensitivity amongst the evaluated models when the activities of both compounds are unknown, but a substantial increase in AC-sensitivity when the actual activity of one of the compounds is given. Graph isomorphism features are found to be competitive with or superior to classical molecular representations for AC-classification and can thus be employed as baseline AC-prediction models or simple compound-optimisation tools. For general QSAR-prediction, however, extended-connectivity fingerprints still consistently deliver the best performance amongs the tested input representations. A potential future pathway to improve QSAR-modelling performance might be the development of techniques to increase AC-sensitivity. [ABSTRACT FROM AUTHOR]

Drug combinations can be the prime strategy for increasing the initial treatment options in cancer therapy. However, identifying the combinations through experimental approaches is very laborious and costly. Notably, in vitro and/or in vivo examination of all the possible combinations might not be plausible. This study presented a novel computational approach to predicting synergistic drug combinations. Specifically, the deep neural network-based binary classification was utilized to develop the model. Various physicochemical, genomic, protein–protein interaction and protein-metabolite interaction information were used to predict the synergy effects of the combinations of different drugs. The performance of the constructed model was compared with shallow neural network (SNN), k-nearest neighbors (KNN), random forest (RF), support vector machines (SVMs), and gradient boosting classifiers (GBC). Based on our findings, the proposed deep neural network model was found to be capable of predicting synergistic drug combinations with high accuracy. The prediction accuracy and AUC metrics for this model were 92.21% and 97.32% in tenfold cross-validation. According to the results, the integration of different types of physicochemical and genomics features leads to more accurate prediction of synergy in cancer drugs. [ABSTRACT FROM AUTHOR]

After graphene was first exfoliated in 2004, research worldwide has focused on discovering and exploiting its distinctive electronic, mechanical, and structural properties. Application of the efficacious methodology used to fabricate graphene, mechanical exfoliation followed by optical microscopy inspection, to other analogous bulk materials has resulted in many more two-dimensional (2D) atomic crystals. Despite their fascinating physical properties, manual identification of 2D atomic crystals has the clear drawback of low-throughput and hence is impractical for any scale-up applications of 2D samples. To combat this, recent integration of high-performance machine-learning techniques, usually deep learning algorithms because of their impressive object recognition abilities, with optical microscopy have been used to accelerate and automate this traditional flake identification process. However, deep learning methods require immense datasets and rely on uninterpretable and complicated algorithms for predictions. Conversely, tree-based machine-learning algorithms represent highly transparent and accessible models. We investigate these tree-based algorithms, with features that mimic color contrast, for automating the manual inspection process of exfoliated 2D materials (e.g., MoSe2). We examine their performance in comparison to ResNet, a famous Convolutional Neural Network (CNN), in terms of accuracy and the physical nature of their decision-making process. We find that the decision trees, gradient boosted decision trees, and random forests utilize physical aspects of the images to successfully identify 2D atomic crystals without suffering from extreme overfitting and high training dataset demands. We also employ a post-hoc study that identifies the sub-regions CNNs rely on for classification and find that they regularly utilize physically insignificant image attributes when correctly identifying thin materials. [ABSTRACT FROM AUTHOR]

Apples damaged by black root mold (BRM) lose moisture, vitamins, and minerals as well as carry dangerous toxins. Determination of the infection degree can allow for customized use of apples, reduce financial losses, and ensure food safety. In this study, red-green-blue (RGB) imaging and hyperspectral imaging (HSI) are combined to detect the infection degree of BRM in apple fruits. First, RGB and HSI images of healthy, mildly, moderately, and severely infected fruits are measured, and those with effective wavelengths (EWs) are screened from HSI by random frog. Second, the statistic and network features of images are extracted by using color moment and convolutional neural network. Meanwhile, random forest (RF), K-nearest neighbor, and support vector machine are used to construct classification models with the above two features of RGB and HSI images of EWs. Optimal results with the 100% accuracy of training set and 96% accuracy of prediction set are obtained by RF with the statistic and network features of the two images, outperforming the other cases. The proposed method furnishes an accurate and effective solution for determining the BRM infection degree in apples. [ABSTRACT FROM AUTHOR]

A method for training and white boxing of deep learning (DL) binary decision trees (BDT), random forest (RF) as well as mind maps (MM) based on graph neural networks (GNN) is proposed. By representing DL, BDT, RF, and MM as graphs, these can be trained by GNN. These learning architectures can be optimized through the proposed method. The proposed method allows representation of the architectures with matrices because the learning architecture can be expressed with graphs. These matrices and graphs are visible, which makes the learning processes visible, and therefore, more accountable. Some examples are shown here to highlight the usefulness of the proposed method, in particular, for learning processes and for ensuring the accountability of DL together with improvement in network architecture. [ABSTRACT FROM AUTHOR]

The Quick UDP Internet Connections (QUIC) protocol provides advantages over traditional TCP, but its encryption functionality reduces the visibility for operators into network traffic. Many studies deploy machine learning and deep learning algorithms on QUIC traffic classification. However, standalone machine learning models are subject to overfitting and poor predictability in complex network traffic environments. Deep learning on the other hand requires a huge dataset and intensive parameter fine-tuning. On the contrary, ensemble techniques provide reliability, better prediction, and robustness of the trained model, thereby reducing the chance of overfitting. In this paper, we approach the QUIC network traffic classification problem by utilizing five different ensemble machine learning techniques, namely: Random Forest, Extra Trees, Gradient Boosting Tree, Extreme Gradient Boosting Tree, and Light Gradient Boosting Model. We used the publicly available dataset with five different services such as Google Drive, YouTube, Google Docs, Google Search, and Google Music. The models were trained using a different number of features on different scenarios and evaluated using several performance metrics. The results show that Extreme Gradient Boosting Tree and Light Gradient Boosting Model outperform the other models and achieve one of the highest results among the state-of-the-art models found in the literature with a simpler model and features. [ABSTRACT FROM AUTHOR]

Circuit simulation has become increasingly significant in circuit design with the development of very large scale integration, and direct current (DC) analysis, which serves as the basis of circuit behavior analysis, is the foundation for nonlinear electronic circuit simulation. Among the several continuation algorithms for DC analysis, pseudo-transient analysis (PTA) methods have gained great success. However, PTA tends to be computationally intensive without a proper time-step control method. In order to improve this problem, we propose a novel time-step control method enhanced by advanced deep learning in this paper. Specifically, a coarse and fine-grained hybrid sampling strategy is introduced to find the optimal time step, which resolves the problem that the optimal time step has no precise definition in PTA theory. After that, a long short-term memory (LSTM) network, with the ability to process temporal information, can be employed to learn the optimal time-step control method based on feature selection and a two-stage data preprocessing strategy, which accelerates DC analysis. Furthermore, random forest (RF) is also used to evaluate feature importance, which can achieve feature selection with reduced dimensions, thereby speeding up the network's training speed and improving the accuracy of prediction. Experimental results demonstrate a significant speedup: up to 61.32 times. [ABSTRACT FROM AUTHOR]

Extraction of associations of singular nucleotide polymorphism (SNP) and phenotypes from biomedical literature is a vital task in BioNLP. Recently, some methods have been developed to extract mutation-diseases affiliations. However, no accessible method of extracting associations of SNP-phenotype from content considers their degree of certainty. In this paper, several machine learning methods were developed to extract ranked SNP-phenotype associations from biomedical abstracts and then were compared to each other. In addition, shallow machine learning methods, including random forest, logistic regression, and decision tree and two kernel-based methods like subtree and local context, a rule-based and a deep CNN-LSTM-based and two BERT-based methods were developed in this study to extract associations. Furthermore, the experiments indicated that although the used linguist features could be employed to implement a superior association extraction method outperforming the kernel-based counterparts, the used deep learning and BERT-based methods exhibited the best performance. However, the used PubMedBERT-LSTM outperformed the other developed methods among the used methods. Moreover, similar experiments were conducted to estimate the degree of certainty of the extracted association, which can be used to assess the strength of the reported association. The experiments revealed that our proposed PubMedBERT–CNN-LSTM method outperformed the sophisticated methods on the task. [ABSTRACT FROM AUTHOR]

The numerical simulation and slope stability prediction are the focus of slope disaster research. Recently, machine learning models are commonly used in the slope stability prediction. However, these machine learning models have some problems, such as poor nonlinear performance, local optimum and incomplete factors feature extraction. These issues can affect the accuracy of slope stability prediction. Therefore, a deep learning algorithm called Long short-term memory (LSTM) has been innovatively proposed to predict slope stability. Taking the Ganzhou City in China as the study area, the landslide inventory and their characteristics of geotechnical parameters, slope height and slope angle are analyzed. Based on these characteristics, typical soil slopes are constructed using the Geo-Studio software. Five control factors affecting slope stability, including slope height, slope angle, internal friction angle, cohesion and volumetric weight, are selected to form different slope and construct model input variables. Then, the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors. Each slope stability coefficient and its corresponding control factors is a slope sample. As a result, a total of 2160 training samples and 450 testing samples are constructed. These sample sets are imported into LSTM for modelling and compared with the support vector machine (SVM), random forest (RF) and convolutional neural network (CNN). The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features. Furthermore, LSTM has a better prediction performance for slope stability compared to SVM, RF and CNN models. [ABSTRACT FROM AUTHOR]

Objective: We aimed to develop a robust framework to model the complex association between clinical features and traumatic brain injury (TBI) risk in children under age two, and identify significant features to derive clinical decision rules for triage decisions. Methods: In this retrospective study, four frequently used machine learning models, i.e., support vector machine (SVM), random forest (RF), deep neural network (DNN), and XGBoost (XGB), were compared to identify significant clinical features from 24 input features associated with the TBI risk in children under age two under the permutation feature importance test (PermFIT) framework by using the publicly available data set from the Pediatric Emergency Care Applied Research Network (PECARN) study. The prediction accuracy was determined by comparing the predicted TBI status with the computed tomography (CT) scan results since CT scan is the gold standard for diagnosing TBI. Results: At a significance level of p = 0.05 , DNN, RF, XGB, and SVM identified 9, 1, 2, and 4 significant features, respectively. In a comparison of accuracy (Accuracy), the area under the curve (AUC), and the precision-recall area under the curve (PR-AUC), the permutation feature importance test for DNN model was the most powerful framework for identifying significant features and outperformed other methods, i.e., RF, XGB, and SVM, with Accuracy, AUC, and PR-AUC as 0.915, 0.794, and 0.974, respectively. Conclusion: These results indicate that the PermFIT-DNN framework robustly identifies significant clinical features associated with TBI status and improves prediction performance. The findings could be used to inform the development of clinical decision tools designed to inform triage decisions. [ABSTRACT FROM AUTHOR]

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, and so forth on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment-pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the downward SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2021, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, namely multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset in an attempt of improving the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations and known algorithms based on machine learning methods for estimating downward SW flux using remote sensing (MODIS) imagery. The estimates of downward SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site. [ABSTRACT FROM AUTHOR]

Melanoma is one of the deadliest types of skin cancer that leads to death if not diagnosed early. Many skin lesions are similar in the early stages, which causes an inaccurate diagnosis. Accurate diagnosis of the types of skin lesions helps dermatologists save patients' lives. In this paper, we propose hybrid systems based on the advantages of fused CNN models. CNN models receive dermoscopy images of the ISIC 2019 dataset after segmenting the area of lesions and isolating them from healthy skin through the Geometric Active Contour (GAC) algorithm. Artificial neural network (ANN) and Random Forest (Rf) receive fused CNN features and classify them with high accuracy. The first methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid models CNN-ANN and CNN-RF. CNN models (AlexNet, GoogLeNet and VGG16) receive lesions area only and produce high depth feature maps. Thus, the deep feature maps were reduced by the PCA and then classified by ANN and RF networks. The second methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid CNN-ANN and CNN-RF models based on the features of the fused CNN models. It is worth noting that the features of the CNN models were serially integrated after reducing their high dimensions by Principal Component Analysis (PCA). Hybrid models based on fused CNN features achieved promising results for diagnosing dermatoscopic images of the ISIC 2019 data set and distinguishing skin cancer from other skin lesions. The AlexNet-GoogLeNet-VGG16-ANN hybrid model achieved an AUC of 94.41%, sensitivity of 88.90%, accuracy of 96.10%, precision of 88.69%, and specificity of 99.44%. [ABSTRACT FROM AUTHOR]

Automatic price appraisal is a relatively new feature in e-commerce sites that aims to help sellers and buyers with price suggestions. To this end, we explore the problem of predicting prices from public online car listings. A listing usually contains the car specification along with a description in the form of unstructured text. We leverage these structured and unstructured information for predicting prices by combining them in a neural network model. Our model has a fully-connected neural branch for handling structured data that learn patterns from the tabular attributes; and another branch that models interactions between the tabular attributes and textual description by employing a co-attention mechanism. The combined outputs of these branches are fed into a regression layer that predicts the car price. The latent representation of the car listings, as mapped by the intermediate layers of the learned model, can be used as a feature set by any regression algorithm to perform car price prediction. This learned feature encodes to a vector the relevant aspects of the car listing, as demonstrated by our experiments. We evaluate our solution in a dataset that was built by scraping multiple car classifieds websites. Our findings show that: (1) our network achieved lower prediction errors than the evaluated regressors using the same input features; (2) by using our learned representation, the regressors surpassed their performance using the original feature mapping; and (3) more competitive algorithms, such as LightGBM and Random Forest, using the raw features, are outperformed by simple linear models using our embeddings. [ABSTRACT FROM AUTHOR]

Digital healthcare combined with telemedicine services in the form of convergence with digital technology and AI is developing rapidly. Digital healthcare research is being conducted on many conditions including shock. However, the causes of shock are diverse, and the treatment is very complicated, requiring a high level of medical knowledge. In this paper, we propose a shock detection method based on the correlation between shock and data extracted from hemodynamic monitoring equipment. From the various parameters expressed by this equipment, four parameters closely related to patient shock were used as the input data for a machine learning model in order to detect the shock. Using the four parameters as input data, that is, feature values, a random forest-based ensemble machine learning model was constructed. The value of the mean arterial pressure was used as the correct answer value, the so called label value, to detect the patient's shock state. The performance was then compared with the decision tree and logistic regression model using a confusion matrix. The average accuracy of the random forest model was 92.80%, which shows superior performance compared to other models. We look forward to our work playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult cases of shock. [ABSTRACT FROM AUTHOR]

Background: During the Covid-19 period, the government made policies dealing with it. Policies issued by the government invited public opinion as a form of public reaction to these policies. The easiest way to find out the public's response is through Twitter's social media. However, Twitter data have limitations. There is a mix between facts and personal opinions. It is necessary to distinguish between these. Opinions expressed by the public can be both positive and negative, so correlation is needed to link opinions and their emotions. Objective: This study discusses sentiment and emotion detection to understand public opinion accurately. Sentiment and emotion are analyzed using Pearson correlation to determine the correlation. Methods: The datasets were about public opinion of Covid-19 retrieved from Twitter. The data were annotated into sentiment and emotion using Pearson correlation. After the annotation process, the data were preprocessed. Afterward, single model classification was carried out using machine learning methods (Support Vector Machine, Random Forest, Naïve Bayes) and deep learning method (Bidirectional Encoder Representation from Transformers). The classification process was focused on accuracy and F1-score evaluation. Results: There were three scenarios for determining sentiment and emotion, namely the factor of aspect-based and correlationbased, without those factors, and aspect-based sentiment only. The scenario using the two aforementioned factors obtained an accuracy value of 97%, while an accuracy of 96% was acquired without them. Conclusion: The use of aspect and correlation with Pearson correlation has helped better understand public opinion regarding sentiment and emotion more accurately. [ABSTRACT FROM AUTHOR]

Kinematic motion detection aims to determine a person's actions based on activity data. Human kinematic motion detection has many valuable applications in health care, such as health monitoring, preventing obesity, virtual reality, daily life monitoring, assisting workers during industry manufacturing, caring for the elderly. Computer vision-based activity recognition is challenging due to problems such as partial occlusion, background clutter, appearance, lighting, viewpoint, and changes in scale. Our research aims to detect human kinematic motions such as walking or running using smartphones' sensor data within a high-performance framework. An existing dataset based on smartphones' gyroscope and accelerometer sensor values is utilized for the experiments in our study. Sensor exploratory data analysis was conducted in order to identify valuable patterns and insights from sensor values. The six hyperparameters, tunned artificial indigence-based machine learning, and deep learning techniques were applied for comparison. Extensive experimentation showed that the ensemble learning-based novel ERD (ensemble random forest decision tree) method outperformed other state-of-the-art studies with high-performance accuracy scores. The proposed ERD method combines the random forest and decision tree models, which achieved a 99% classification accuracy score. The proposed method was successfully validated with the k-fold cross-validation approach. [ABSTRACT FROM AUTHOR]

Uncertainty in renewable energy generation, energy consumption, and electricity prices, as well as transmission congestion, pose a number of problems in modern power grids, necessitating stability on the supply, grid, and demand sides. Grid‐side stability can be achieved by dynamic line rating (DLR) forecasting, which reliably predicts the overall current carrying potential of overhead transmission lines. Long short‐term memory proved beneficiary in this field, owing to its ability to learn highly variable and uncertain data. To empower this network to tackle the non‐stationary nature of meteorological parameters, a novel machine learning (ML) architecture based on Dagging technique is proposed and tested on the data collected from a 400 kV overhead transmission line. Simulation results corroborate that the proposed Dagging‐based stacked LSTM can successfully handle the non‐stationary issue and outperform the decomposition‐based technique, as the state‐of‐the‐art algorithm, for various forecasting horizons. The results confirm the generalizability of models with an application in forecasting DLR over the line without utilizing additional sensors and communication networks. Moreover, the proposed model is compared to several ML architectures, including support vector machines (SVM), random forest (RF), and multi‐layer perceptron (MLP) in a comprehensive benchmark study. The introduced algorithm outperforms MLP by 3.4%, RF by 9.4%, and SVM by 6.7% in terms of average prediction accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Sciences Institute is the property of Lublin University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The combination of multi-temporal images and deep learning is an efficient way to obtain accurate crop distributions and so has drawn increasing attention. However, few studies have compared deep learning models with different architectures, so it remains unclear how a deep learning model should be selected for multi-temporal crop classification, and the best possible accuracy is. To address this issue, the present work compares and analyzes a crop classification application based on deep learning models and different time-series data to exploit the possibility of improving crop classification accuracy. Using Multi-temporal Sentinel-2 images as source data, time-series classification datasets are constructed based on vegetation indexes (VIs) and spectral stacking, respectively, following which we compare and evaluate the crop classification application based on time-series datasets and five deep learning architectures: (1) one-dimensional convolutional neural networks (1D-CNNs), (2) long short-term memory (LSTM), (3) two-dimensional-CNNs (2D-CNNs), (4) three-dimensional-CNNs (3D-CNNs), and (5) two-dimensional convolutional LSTM (ConvLSTM2D). The results show that the accuracy of both 1D-CNN (92.5%) and LSTM (93.25%) is higher than that of random forest (~ 91%) when using a single temporal feature as input. The 2D-CNN model integrates temporal and spatial information and is slightly more accurate (94.76%), but fails to fully utilize its multi-spectral features. The accuracy of 1D-CNN and LSTM models integrated with temporal and multi-spectral features is 96.94% and 96.84%, respectively. However, neither model can extract spatial information. The accuracy of 3D-CNN and ConvLSTM2D models is 97.43% and 97.25%, respectively. The experimental results show limited accuracy for crop classification based on single temporal features, whereas the combination of temporal features with multi-spectral or spatial information significantly improves classification accuracy. The 3D-CNN and ConvLSTM2D models are thus the best deep learning architectures for multi-temporal crop classification. However, the ConvLSTM architecture combining recurrent neural networks and CNNs should be further developed for multi-temporal image crop classification. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has become widely adopted in businesses, organizations, and daily lives. They are usually characterized by transferring and processing sensitive data. Attackers have exploited this prospect of IoT devices to compromise user data's integrity and confidentiality. Considering the dynamic nature of the attacks, artificial intelligence (AI)-based techniques incorporating machine learning (ML) are promising techniques for identifying such attacks. However, the dataset being utilized features engineering techniques, and the kind of classifiers play significant roles in how accurate AI-based predictions are. Therefore, for the IoT environment, there is a need to contribute more to this context by evaluating different AI-based techniques on datasets that effectively capture the environment's properties. In this paper, we evaluated various ML models with the consideration of both binary and multiclass classification models validated on a new dedicated IoT dataset. Moreover, we investigated the impact of different features engineering techniques including correlation analysis and information gain. The experimental work conducted on bagging, k-nearest neighbor (KNN), J48, random forest (RF), logistic regression (LR), and multi-layer perceptron (MLP) models revealed that RF achieved the highest performance across all experiment sets, with a receiver operating characteristic (ROC) of 99.9%. [ABSTRACT FROM AUTHOR]

The growing use of the Internet of Things (IoT) in smart applications necessitates improved security monitoring of IoT components. The security of such components is monitored using intrusion detection systems which run machine learning (ML) algorithms to classify access attempts as anomalous or normal. However, in this case, one of the issues is the large length of the data feature vector that any ML or deep learning technique implemented on resource-constrained intelligent nodes must handle. In this paper, the problem of selecting an optimal-feature set is investigated to reduce the curse of data dimensionality. A two-layered approach is proposed: the first tier makes use of a random forest while the second tier uses a hybrid of gray wolf optimizer (GWO) and the particle swarm optimizer (PSO) with the k-nearest neighbor as the wrapper method. Further, differential weight distribution is made to the local-best and global-best positions in the velocity equation of PSO. A new metric, i.e., the reduced feature to accuracy ratio (RFAR), is introduced for comparing various works. Three data sets, namely, NSLKDD, DS2OS and BoTIoT, are used to evaluate and validate the proposed work. Experiments demonstrate improvements in accuracy up to 99.44%, 99.44% and 99.98% with the length of the optimal-feature vector equal to 9, 4 and 8 for the NSLKDD, DS2OS and BoTIoT data sets, respectively. Furthermore, classification improves for many of the individual classes of attacks: denial-of-service (DoS) (99.75%) and normal (99.52%) for NSLKDD, malicious control (100%) and DoS (68.69%) for DS2OS, and theft (95.65%) for BoTIoT. [ABSTRACT FROM AUTHOR]

For the last 40 years, actigraphy or wearable accelerometry has provided an objective, low-burden and ecologically valid approach to assess real-world sleep and circadian patterns, contributing valuable data to epidemiological and clinical insights on sleep and sleep disorders. The proper use of wearable technology in sleep research requires validated algorithms that can derive sleep outcomes from the sensor data. Since the publication of the first automated scoring algorithm by Webster in 1982, a variety of sleep algorithms have been developed and contributed to sleep research, including many recent ones that leverage machine learning and / or deep learning approaches. However, it remains unclear how these algorithms compare to each other on the same data set and if these modern data science approaches improve the analytical validity of sleep outcomes based on wrist-worn acceleration data. This work provides a systematic evaluation across 8 state-of-the-art sleep algorithms on a common sleep data set with polysomnography (PSG) as ground truth. Despite the inclusion of recently published complex algorithms, simple regression-based and heuristic algorithms demonstrated slightly superior performance in sleep-wake classification and sleep outcome estimation. The performance of complex machine learning and deep learning models seem to suffer from poor generalization. This independent and systematic analytical validation of sleep algorithms provides key evidence on the use of wearable digital health technologies for sleep research and care. [ABSTRACT FROM AUTHOR]

Authorities and policymakers in Korea have recently prioritized improving fire prevention and emergency response. Governments seek to enhance community safety for residents by constructing automated fire detection and identification systems. This study examined the efficacy of YOLOv6, a system for object identification running on an NVIDIA GPU platform, to identify fire-related items. Using metrics such as object identification speed, accuracy research, and time-sensitive real-world applications, we analyzed the influence of YOLOv6 on fire detection and identification efforts in Korea. We conducted trials using a fire dataset comprising 4000 photos collected through Google, YouTube, and other resources to evaluate the viability of YOLOv6 in fire recognition and detection tasks. According to the findings, YOLOv6's object identification performance was 0.98, with a typical recall of 0.96 and a precision of 0.83. The system achieved an MAE of 0.302%. These findings suggest that YOLOv6 is an effective technique for detecting and identifying fire-related items in photos in Korea. Multi-class object recognition using random forests, k-nearest neighbors, support vector, logistic regression, naive Bayes, and XGBoost was performed on the SFSC data to evaluate the system's capacity to identify fire-related objects. The results demonstrate that for fire-related objects, XGBoost achieved the highest object identification accuracy, with values of 0.717 and 0.767. This was followed by random forest, with values of 0.468 and 0.510. Finally, we tested YOLOv6 in a simulated fire evacuation scenario to gauge its practicality in emergencies. The results show that YOLOv6 can accurately identify fire-related items in real time within a response time of 0.66 s. Therefore, YOLOv6 is a viable option for fire detection and recognition in Korea. The XGBoost classifier provides the highest accuracy when attempting to identify objects, achieving remarkable results. Furthermore, the system accurately identifies fire-related objects while they are being detected in real-time. This makes YOLOv6 an effective tool to use in fire detection and identification initiatives. [ABSTRACT FROM AUTHOR]