Search

Intelligent connected vehicles (ICVs) constitute a transformative technology attracting immense research effort and holding great promise in providing road safety, transport efficiency, driving comfort, and eco-friendly mobility. As the driving environment becomes more and more “connected”, the manner in which an ICV is driven (driving style) can dynamically vary from time to time, due to the change in several parameters associated with personal traits and with the ICV’s surroundings. This necessitates fast and effective decisions to be made for a priori identifying the most appropriate driving style for an ICV. Accordingly, the main goal of this study is to present a novel, in-vehicle autonomous decision-making functionality, which enables ICVs to dynamically, transparently, and securely utilize the best available driving style (DS). The proposed functionality takes as input several parameters related to the driver’s personal characteristics and preferences, as well as the changing driving environment. A Naive Bayes learning classifier is applied for the cognitive nature of the presented functionality. Three scenarios, with regards to drivers with different personal preferences and to driving scenes with changing environment situations, are illustrated, showcasing the effectiveness of the proposed functionality.

Wearable devices continuously measure multiple physiological variables to inform users of health and behavior indicators. The computed health indicators must rely on informative signals obtained by processing the raw physiological variables with powerful noise- and artifacts-filtering algorithms. In this study, we aimed to elucidate the effects of signal processing techniques on the accuracy of detecting and discriminating physical activity (PA) and acute psychological stress (APS) using physiological measurements (blood volume pulse, heart rate, skin temperature, galvanic skin response, and accelerometer) collected from a wristband. Data from 207 experiments involving 24 subjects were used to develop signal processing, feature extraction, and machine learning (ML) algorithms that can detect and discriminate PA and APS when they occur individually or concurrently, classify different types of PA and APS, and estimate energy expenditure (EE). Training data were used to generate feature variables from the physiological variables and develop ML models (na&iuml, ve Bayes, decision tree, k-nearest neighbor, linear discriminant, ensemble learning, and support vector machine). Results from an independent labeled testing data set demonstrate that PA was detected and classified with an accuracy of 99.3%, and APS was detected and classified with an accuracy of 92.7%, whereas the simultaneous occurrences of both PA and APS were detected and classified with an accuracy of 89.9% (relative to actual class labels), and EE was estimated with a low mean absolute error of 0.02 metabolic equivalent of task (MET).The data filtering and adaptive noise cancellation techniques used to mitigate the effects of noise and artifacts on the classification results increased the detection and discrimination accuracy by 0.7% and 3.0% for PA and APS, respectively, and by 18% for EE estimation. The results demonstrate the physiological measurements from wristband devices are susceptible to noise and artifacts, and elucidate the effects of signal processing and feature extraction on the accuracy of detection, classification, and estimation of PA and APS.

In the derived approach, an analysis is performed on Twitter data for World Cup soccer 2014 held in Brazil to detect the sentiment of the people throughout the world using machine learning techniques. By filtering and analyzing the data using natural language processing techniques, sentiment polarity was calculated based on the emotion words detected in the user tweets. The dataset is normalized to be used by machine learning algorithms and prepared using natural language processing techniques like word tokenization, stemming and lemmatization, part-of-speech (POS) tagger, name entity recognition (NER), and parser to extract emotions for the textual data from each tweet. This approach is implemented using Python programming language and Natural Language Toolkit (NLTK). A derived algorithm extracts emotional words using WordNet with its POS (part-of-speech) for the word in a sentence that has a meaning in the current context, and is assigned sentiment polarity using the SentiWordNet dictionary or using a lexicon-based method. The resultant polarity assigned is further analyzed using na&iuml, ve Bayes, support vector machine (SVM), K-nearest neighbor (KNN), and random forest machine learning algorithms and visualized on the Weka platform. Na&iuml, ve Bayes gives the best accuracy of 88.17% whereas random forest gives the best area under the receiver operating characteristics curve (AUC) of 0.97.

We examine the significance of the predictive potential of EPI cystatin C (EPI CysC) in combination with NTproBNP, sodium, and potassium in the evaluation of renal function in patients with cardiorenal syndrome using standard mathematical classification models from the domain of artificial intelligence. The criterion for the inclusion of subjects with combined impairment of heart and kidney function in the study was the presence of newly discovered or previously diagnosed clinically manifest cardiovascular disease and acute or chronic kidney disease in different stages of evolution. In this paper, five standard classifiers from the field of machine learning were used for the analysis of the obtained data: ensemble of neural networks (MLP), ensemble of k-nearest neighbors (k-NN) and naive Bayes classifier, decision tree, and a classifier based on logistic regression. The results showed that in MLP, k-NN, and naive Bayes, EPI CysC had the highest predictive potential. Thus, our approach with utility classifiers recognizes the essence of the disorder in patients with cardiorenal syndrome and facilitates the planning of further treatment.

The Cox proportional hazard model may predict whether an individual belonging to a given group would likely register an event of interest at a given time. However, the Cox model is limited by relatively strict statistical assumptions. In this study, we propose decomposing the time-to-event variable into “time” and “event” components and using the latter as a target variable for various machine-learning classification algorithms, which are almost assumption-free, unlike the Cox model. While the time component is continuous and is used as one of the covariates, i.e., input variables for various classification algorithms such as logistic regression, naïve Bayes classifiers, decision trees, random forests, and artificial neural networks, the event component is binary and thus may be modeled using these classification algorithms. Moreover, we apply the proposed method to predict a decrease or non-decrease of IgG and IgM blood antibodies against COVID-19 (SARS-CoV-2), respectively, below a laboratory cut-off, for a given individual at a given time point. Using train-test splitting of the COVID-19 dataset (n=663 individuals), models for the mentioned algorithms, including the Cox proportional hazard model, are learned and built on the train subsets while tested on the test ones. To increase robustness of the model performance evaluation, models’ predictive accuracies are estimated using 10-fold cross-validation on the split dataset. Even though the time-to-event variable decomposition might ignore the effect of individual data censoring, many algorithms show similar or even higher predictive accuracy compared to the traditional Cox proportional hazard model. In COVID-19 IgG decrease prediction, multivariate logistic regression (of accuracy 0.811), support vector machines (of accuracy 0.845), random forests (of accuracy 0.836), artificial neural networks (of accuracy 0.806) outperform the Cox proportional hazard model (of accuracy 0.796), while in COVID-19 IgM antibody decrease prediction, neither Cox regression nor other algorithms perform well (best accuracy is 0.627 for Cox regression). An accurate prediction of mainly COVID-19 IgG antibody decrease can help the healthcare system manage, with no need for extensive blood testing, to identify individuals, for instance, who could postpone boosting vaccination if new COVID-19 variant incomes or should be flagged as high risk due to low COVID-19 antibodies.

Simple Summary Monitoring animal activity in production systems is an important tool for obtaining information on health, production, and reproduction. In this study, we evaluated the use of accelerometers with different strategies to predict the grazing behavior of Nelore cattle. This research was conducted in an environment both more challenging and representative of the practices adopted in livestock production systems in Brazil. The results of this study showed that the use of the Random Forest algorithm, together with techniques for resampling the training data of the models, classified the studied behaviors with high accuracy, especially for important, and less frequent activities such as water consumption frequency. Abstract Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest.

The recent advance in information technology has created a new era named the Internet of Things (IoT). This new technology allows objects (things) to be connected to the Internet, such as smart TVs, printers, cameras, smartphones, smartwatches, etc. This trend provides new services and applications for many users and enhances their lifestyle. The rapid growth of the IoT makes the incorporation and connection of several devices a predominant procedure. Although there are many advantages of IoT devices, there are different challenges that come as network anomalies. In this research, the current studies in the use of deep learning (DL) in DDoS intrusion detection have been presented. This research aims to implement different Machine Learning (ML) algorithms in WEKA tools to analyze the detection performance for DDoS attacks using the most recent CICDDoS2019 datasets. CICDDoS2019 was found to be the model with best results. This research has used six different types of ML algorithms which are K_Nearest_Neighbors (K-NN), super vector machine (SVM), naïve bayes (NB), decision tree (DT), random forest (RF) and logistic regression (LR). The best accuracy result in the presented evaluation was achieved when utilizing the Decision Tree (DT) and Random Forest (RF) algorithms, 99% and 99%, respectively. However, the DT is better than RF because it has a shorter computation time, 4.53 s and 84.2 s, respectively. Finally, open issues for further research in future work are presented.

Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of “bad” paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models.

In the last decade, ground-level ozone exposure has led to a significant increase in environmental and health risks. Thus, it is essential to measure and monitor atmospheric ozone concentration levels. Specifically, recent improvements in machine learning (ML) processes, based on statistical modeling, have provided a better approach to solving these risks. In this study, we compare Naive Bayes, K-Nearest Neighbors, Decision Tree, Stochastic Gradient Descent, and Extreme Gradient Boosting (XGBoost) algorithms and their ensemble technique to classify ground-level ozone concentration in the El Paso-Juarez area. As El Paso-Juarez is a non-attainment city, the concentrations of several air pollutants and meteorological parameters were analyzed. We found that the ensemble (soft voting classifier) of algorithms used in this paper provide high classification accuracy (94.55%) for the ozone dataset. Furthermore, variables that are highly responsible for the high ozone concentration such as Nitrogen Oxide (NOx), Wind Speed and Gust, and Solar radiation have been discovered.

We present a multi-modal genre recognition framework that considers the modalities audio, text, and image by features extracted from audio signals, album cover images, and lyrics of music tracks. In contrast to pure learning of features by a neural network as done in the related work, handcrafted features designed for a respective modality are also integrated, allowing for higher interpretability of created models and further theoretical analysis of the impact of individual features on genre prediction. Genre recognition is performed by binary classification of a music track with respect to each genre based on combinations of elementary features. For feature combination a two-level technique is used, which combines aggregation into fixed-length feature vectors with confidence-based fusion of classification results. Extensive experiments have been conducted for three classifier models (Naïve Bayes, Support Vector Machine, and Random Forest) and numerous feature combinations. The results are presented visually, with data reduction for improved perceptibility achieved by multi-objective analysis and restriction to non-dominated data. Feature- and classifier-related hypotheses are formulated based on the data, and their statistical significance is formally analyzed. The statistical analysis shows that the combination of two modalities almost always leads to a significant increase of performance and the combination of three modalities in several cases.

Earthquakes lead to enormous harm to life and assets. The ability to quickly assess damage across a vast area is crucial for effective disaster response. In recent years, social networks have demonstrated a lot of capability for improving situational awareness and identifying impacted areas. In this regard, this study proposed an approach that applied social media data for the earthquake damage assessment at the county, city, and 10 × 10 km grids scale using Naive Bayes, support vector machine (SVM), and deep learning classification algorithms. In this study, classification was evaluated using accuracy, precision, recall, and F-score metrics. Then, for understanding the message propagation behavior in the study area, temporal analysis based on classified messages was performed. In addition, variability of spatial topic concentration in three classification algorithms after the earthquake was examined using location quotation (LQ). A damage map based on the results of the classification of the three algorithms into three scales was created. For validation, confusion matrix metrics, Spearman’s rho, Pearson correlation, and Kendall’s tau were used. In this study, binary classification and multi-class classification have been done. Binary classification was used to classify messages into two classes of damage and non-damage so that their results could finally be used to estimate the earthquake damage. Multi-class classification was used to categorize messages to increase post-crisis situational awareness. In the binary classification, the SVM algorithm performed better in all the indices, gaining 71.22% accuracy, 81.22 F-measure, 79.08% accuracy, 85.62% precision, and 0.634 Kappa. In the multi-class classification, the SVM algorithm performed better in all the indices, gaining 90.25% accuracy, 88.58% F-measure, 84.34% accuracy, 93.26% precision, and 0.825 Kappa. Based on the results of the temporal analysis, most of the damage-related messages were reported on the day of the earthquake and decreased in the following days. Most of the messages related to infrastructure damages and injured, dead, and missing people were reported on the day of the earthquake. In addition, results of LQ indicated Napa as a center of the earthquake as the concentration of damage-related messages in all algorithms were based there. This indicates that our approach has been able to identify the damage well and has considered the earthquake center one of the most affected counties. The findings of the damage estimation showed that going away from the epicenter lowered the amount of damage. Based on the result of the validation of the estimated damage map with official data, the SVM performed better for damage estimation, followed by deep learning. In addition, at the county scale, algorithms showed better performance with Spearman’s rho of 0.8205, Pearson correlation of 0.5217, and Kendall’s tau of 0.6666.

In this article, we present the results of our experiments on sentiment and emotion recognition for English and Polish texts, aiming to work in the context of a therapeutic chatbot. We created a dedicated dataset by adding samples of neutral texts to an existing English-language emotion-labeled corpus. Next, using neural machine translation, we developed a Polish version of the English database. A bilingual, parallel corpus created in this way, named CORTEX (CORpus of Translated Emotional teXts), labeled with three sentiment polarity classes and nine emotion classes, was used for experiments on classification. We employed various classifiers: Naïve Bayes, Support Vector Machines, fastText, and BERT. The results obtained were satisfactory: we achieved the best scores for the BERT-based models, which yielded accuracy of over 90% for sentiment (3-class) classification and almost 80% for emotion (9-class) classification. We compared the results for both languages and discussed the differences. Both the accuracy and the F1-scores for Polish turned out to be slightly inferior to those for English, with the highest difference visible for BERT.

The proliferation of renewable energy sources distributed generation (RES-DG) into the grid results in time-varying inertia constant. To ensure the security of the grid under varying inertia, techniques for fast security assessment are required. In addition, considering the high penetration of RES-DG units into the modern grids, security prediction using varying grid features is crucial. The computation burden concerns of conventional time-domain security assessment techniques make it unsuitable for real-time security prediction. This paper, therefore, proposes a fast security monitoring model that includes security prediction and load shedding for security control. The attributes considered in this paper include the load level, inertia constant, fault location, and power dispatched from the renewable energy sources generator. An incremental Naïve Bayes algorithm is applied on the training dataset developed from the responses of the grid to transient stability simulations. An additive Gaussian process regression (GPR) model is proposed to estimate the load shedding required for the predicted insecure states. Finally, an algorithm based on the nodes’ security margin is proposed to determine the optimal node (s) for the load shedding. The average security prediction and load shedding estimation model training times are 1.2 s and 3 s, respectively. The result shows that the proposed model can predict the security of the grid, estimate the amount of load shed required, and determine the specific node for load shedding operation.

International audience; Persistent Pain after Spinal Surgery can be successfully addressed by Spinal Cord Stimulation (SCS). International guidelines strongly recommend that a lead trial be performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears that patient outcomes, WITH OR WITHOUT lead trial, are similar. In contrast, during trialing, infection rate drops drastically within time and can compromise the therapy. Using composite pain assessment experience and previous research, we hypothesized that ma-chine learning models could be robust screening tools and reliable predictors of long-term SCS efficacy. We developed several algorithms including logistic regression, Regularized Logistic Regression (RLR), naive Bayes classifier, artificial neural networks, random forest and gradient boosted trees to test this hypothesis and to perform internal and external validations, the objec-tive being to confront model predictions with lead trial results using a 1-year composite out-come from 103 patients. While almost all models have demonstrated superiority on lead trial-ing, the RLR model appears to represent the best compromise between complexity and inter-pretability in prediction of SCS efficacy. These results underscore the need to use AI based-predictive medicine, as a synergistic mathematical approach, aimed at helping implanters to optimize their clinical choices on daily practice.

This study proposes a method for diagnosing problems in truck ore transport operations in underground mines using four machine learning models (i.e., Gaussian naïve Bayes (GNB), k-nearest neighbor (kNN), support vector machine (SVM), and classification and regression tree (CART)) and data collected by an Internet of Things system. A limestone underground mine with an applied mine production management system (using a tablet computer and Bluetooth beacon) is selected as the research area, and log data related to the truck travel time are collected. The machine learning models are trained and verified using the collected data, and grid search through 5-fold cross-validation is performed to improve the prediction accuracy of the models. The accuracy of CART is highest when the parameters leaf and split are set to 1 and 4, respectively (94.1%). In the validation of the machine learning models performed using the validation dataset (1500), the accuracy of the CART was 94.6%, and the precision and recall were 93.5% and 95.7%, respectively. In addition, it is confirmed that the F1 score reaches values as high as 94.6%. Through field application and analysis, it is confirmed that the proposed CART model can be utilized as a tool for monitoring and diagnosing the status of truck ore transport operations.

The Surface Urban Heat Islands (SUHI) phenomenon has adverse environmental consequences on human activities, biophysical and ecological systems. In this study, Land Surface Temperature (LST) from Landsat and Sentinel-2 satellites is used to investigate the contribution of potential factors that generate the SUHI phenomenon. We employ Principal Component Analysis (PCA) and Multiple Linear Regression (MLR) techniques to model the main temporal and spatial SUHI patterns of Cartago, Colombia, for the period 2001–2020. We test and evaluate the performance of three different emissivity models to retrieve LST. The fractional vegetation cover model using Sentinel-2 data provides the best results with R2 = 0.78, while the ASTER Global Emissivity Dataset v3 and the land surface emissivity model provide R2 = 0.27 and R2 = 0.26, respectively. Our SUHI model reveals that the factors with the highest impact are the Normalized Difference Water Index (NDWI) and the Normalized Difference Build-up Index (NDBI). Furthermore, we incorporate a weighted Naïve Bayes Machine Learning (NBML) algorithm to identify areas prone to extreme temperatures that can be used to define and apply normative actions to mitigate the negative consequences of SUHI. Our NBML approach demonstrates the suitability of the new SUHI model with uncertainty within 95%, against the 88% given by the Support Vector Machine (SVM) approach.

Producción Científica, Radiomics, in combination with artificial intelligence, has emerged as a powerful tool for the development of predictive models in neuro-oncology. Our study aims to find an answer to a clinically relevant question: is there a radiomic profile that can identify glioblastoma (GBM) patients with short-term survival after complete tumor resection? A retrospective study of GBM patients who underwent surgery was conducted in two institutions between January 2019 and January 2020, along with cases from public databases. Cases with gross total or near total tumor resection were included. Preoperative structural multiparametric magnetic resonance imaging (mpMRI) sequences were pre-processed, and a total of 15,720 radiomic features were extracted. After feature reduction, machine learning-based classifiers were used to predict early mortality (

Most text classification systems use machine learning algorithms, among these, naïve Bayes and support vector machine algorithms adapted to handle text data afford reasonable performance. Recently, given developments in deep learning technology, several scholars have used deep neural networks (recurrent and convolutional neural networks) to improve text classification. However, deep learning-based text classification has not greatly improved performance compared to that of conventional algorithms. This is because a textual document is essentially expressed as a vector (only), albeit with word dimensions, which compromises the inherent semantic information, even if the vector is (appropriately) transformed to add conceptual information. To solve this `loss of term senses’ problem, we develop a concept-driven deep neural network based upon our semantic tensor space model. The semantic tensor used for text representation features a dependency between the term and the concept, we use this to develop three deep neural networks for text classification. We perform experiments using three standard document corpora, and we show that our proposed methods are superior to both traditional and more recent learning methods.

The COVID-19 outbreak resulted in preventative measures and restrictions for Bangladesh during the summer of 2020—these unstable and stressful times led to multiple social problems (e.g., domestic violence and divorce). Globally, researchers, policymakers, governments, and civil societies have been concerned about the increase in domestic violence against women and children during the ongoing COVID-19 pandemic. In Bangladesh, domestic violence against women and children has increased during the COVID-19 pandemic. In this article, we investigated family violence among 511 families during the COVID-19 outbreak. Participants were given questionnaires to answer, for a period of over ten days; we predicted family violence using a machine learning-based model. To predict domestic violence from our data set, we applied random forest, logistic regression, and Naive Bayes machine learning algorithms to our model. We employed an oversampling strategy named the Synthetic Minority Oversampling Technique (SMOTE) and the chi-squared statistical test to, respectively, solve the imbalance problem and discover the feature importance of our data set. The performances of the machine learning algorithms were evaluated based on accuracy, precision, recall, and F-score criteria. Finally, the receiver operating characteristic (ROC) and confusion matrices were developed and analyzed for three algorithms. On average, our model, with the random forest, logistic regression, and Naive Bayes algorithms, predicted family violence with 77%, 69%, and 62% accuracy for our data set. The findings of this study indicate that domestic violence has increased and is highly related to two features: family income level during the COVID-19 pandemic and education level of the family members.

This paper presents an advanced computational approach to assess the risk of damage to masonry buildings subjected to negative kinematic impacts of underground mining exploitation. The research goals were achieved using selected tools from the area of artificial intelligence (AI) methods. Ultimately, two models of damage risk assessment were built using the Naive Bayes classifier (NBC) and Bayesian Networks (BN). The first model was used to compare results obtained using the more computationally advanced Bayesian network methodology. In the case of the Bayesian network, the unknown Directed Acyclic Graph (DAG) structure was extracted using Chow-Liu’s Tree Augmented Naive Bayes (TAN-CL) algorithm. Thus, one of the methods involving Bayesian Network Structure Learning from data (BNSL) was implemented. The application of this approach represents a novel scientific contribution in the interdisciplinary field of mining and civil engineering. The models created were verified with respect to quality of fit to observed data and generalization properties. The connections in the Bayesian network structure obtained were also verified with respect to the observed relations occurring in engineering practice concerning the assessment of the damage intensity to masonry buildings in mining areas. This allowed evaluation of the model and justified the utility of the conducted research in the field of protection of mining areas. The possibility of universal application of the Bayesian network, both in the case of damage prediction and diagnosis of its potential causes, was also pointed out.

Data driven methods are widely used for the development of Landslide Susceptibility Mapping (LSM). The results of these methods are sensitive to different factors, such as the quality of input data, choice of algorithm, sampling strategies, and data splitting ratios. In this study, five different Machine Learning (ML) algorithms are used for LSM for the Wayanad district in Kerala, India, using two different sampling strategies and nine different train to test ratios in cross validation. The results show that Random Forest (RF), K Nearest Neighbors (KNN), and Support Vector Machine (SVM) algorithms provide better results than Naïve Bayes (NB) and Logistic Regression (LR) for the study area. NB and LR algorithms are less sensitive to the sampling strategy and data splitting, while the performance of the other three algorithms is considerably influenced by the sampling strategy. From the results, both the choice of algorithm and sampling strategy are critical in obtaining the best suited landslide susceptibility map for a region. The accuracies of KNN, RF, and SVM algorithms have increased by 10.51%, 10.02%, and 4.98% with the use of polygon landslide inventory data, while for NB and LR algorithms, the performance was slightly reduced with the use of polygon data. Thus, the sampling strategy and data splitting ratio are less consequential with NB and algorithms, while more data points provide better results for KNN, RF, and SVM algorithms.

Topic Modeling is a statistical process, which derives the latent themes from extensive collections of text. Three approaches to topic modeling exist, namely, unsupervised, semi-supervised and supervised. In this work, we develop a supervised topic model for an Amharic corpus. We also investigate the effect of stemming on topic detection on Term Frequency Inverse Document Frequency (TF-IDF) features, Latent Dirichlet Allocation (LDA) features and a combination of these two feature sets using four supervised machine learning tools, that is, Support Vector Machine (SVM), Naive Bayesian (NB), Logistic Regression (LR), and Neural Nets (NN). We evaluate our approach using an Amharic corpus of 14,751 documents of ten topic categories. Both qualitative and quantitative analysis of results show that our proposed supervised topic detection outperforms with an accuracy of 88% by SVM using state-of-the-art-approach TF-IDF word features with the application of the Synthetic Minority Over-sampling Technique (SMOTE) and with no stemming operation. The results show that text features with stemming slightly improve the performance of the topic classifier over features with no stemming.

In modern times, ensuring social security has become the prime concern for security administrators. The widespread and recurrent use of social media sites is creating a huge risk for the lives of the general people, as these sites are frequently becoming potential sources of the organization of various types of immoral events. For protecting society from these dangers, a prior detection system which can effectively detect events by analyzing these social media data is essential. However, automating the process of event detection has been difficult, as existing processes must account for diverse writing styles, languages, dialects, post lengths, and et cetera. To overcome these difficulties, we developed an effective model for detecting events, which, for our purposes, were classified as either protesting, celebrating, religious, or neutral, using Bengali and Banglish Facebook posts. At first, the collected posts’ text were processed for language detection, and then, detected posts were pre-processed using stopwords removal and tokenization. Features were then extracted from these pre-processed texts using three sub-processes: filtering, phrase matching of specific events, and sentiment analysis. The collected features were ultimately used to train our Bernoulli Naive Bayes classification model, which was capable of detecting events with 90.41% accuracy (for Bengali-language posts) and 70% (for the Banglish-form posts). For evaluating the effectiveness of our proposed model more precisely, we compared it with two other classifiers: Support Vector Machine and Decision Tree.

In recent years, different variants of the botnet are targeting government, private organizations and there is a crucial need to develop a robust framework for securing the IoT (Internet of Things) network. In this paper, a Hadoop based framework is proposed to identify the malicious IoT traffic using a modified Tomek-link under-sampling integrated with automated Hyper-parameter tuning of machine learning classifiers. The novelty of this paper is to utilize a big data platform for benchmark IoT datasets to minimize computational time. The IoT benchmark datasets are loaded in the Hadoop Distributed File System (HDFS) environment. Three machine learning approaches namely naive Bayes (NB), K-nearest neighbor (KNN), and support vector machine (SVM) are used for categorizing IoT traffic. Artificial immune network optimization is deployed during cross-validation to obtain the best classifier parameters. Experimental analysis is performed on the Hadoop platform. The average accuracy of 99% and 90% is obtained for BoT_IoT and ToN_IoT datasets. The accuracy difference in ToN-IoT dataset is due to the huge number of data samples captured at the edge layer and fog layer. However, in BoT-IoT dataset only 5% of the training and test samples from the complete dataset are considered for experimental analysis as released by the dataset developers. The overall accuracy is improved by 19% in comparison with state-of-the-art techniques. The computational times for the huge datasets are reduced by 3–4 hours through Map Reduce in HDFS.

This research proposes a new feature extraction algorithm using aggregated user engagements on social media in order to achieve demographics and personality discovery tasks. Our proposed framework can discover seven essential attributes, including gender identity, age group, residential area, education level, political affiliation, religious belief, and personality type. Multiple feature sets are developed, including comment text, community activity, and hybrid features. Various machine learning algorithms are explored, such as support vector machines, random forest, multi-layer perceptron, and naïve Bayes. An empirical analysis is performed on various aspects, including correctness, robustness, training time, and the class imbalance problem. We obtained the highest prediction performance by using our proposed feature extraction algorithm. The result on personality type prediction was 87.18%. For the demographic attribute prediction task, our feature sets also outperformed the baseline at 98.1% for residential area, 94.7% for education level, 92.1% for gender identity, 91.5% for political affiliation, 60.6% for religious belief, and 52.0% for the age group. Moreover, this paper provides the guideline for the choice of classifiers with appropriate feature sets.

Background: The aim of this study is to explore an objective approach that aids the diagnosis of bipolar disorder (BD), based on optical coherence tomography (OCT) data which are analyzed using artificial intelligence. Methods: Structural analyses of nine layers of the retina were analyzed in 17 type I BD patients and 42 controls, according to the areas defined by the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The most discriminating variables made up the feature vector of several automatic classifiers: Gaussian Naive Bayes, K-nearest neighbors and support vector machines. Results: BD patients presented retinal thinning affecting most layers, compared to controls. The retinal thickness of the parafoveolar area showed a high capacity to discriminate BD subjects from healthy individuals, specifically for the ganglion cell (area under the curve (AUC) = 0.82) and internal plexiform (AUC = 0.83) layers. The best classifier showed an accuracy of 0.95 for classifying BD versus controls, using as variables of the feature vector the IPL (inner nasal region) and the INL (outer nasal and inner inferior regions) thickness. Conclusions: Our patients with BD present structural alterations in the retina, and artificial intelligence seem to be a useful tool in BD diagnosis, but larger studies are needed to confirm our findings.

As the amount of content that is created on social media is constantly increasing, more and more opinions and sentiments are expressed by people in various subjects. In this respect, sentiment analysis and opinion mining techniques can be valuable for the automatic analysis of huge textual corpora (comments, reviews, tweets etc.). Despite the advances in text mining algorithms, deep learning techniques, and text representation models, the results in such tasks are very good for only a few high-density languages (e.g., English) that possess large training corpora and rich linguistic resources, nevertheless, there is still room for improvement for the other lower-density languages as well. In this direction, the current work employs various language models for representing social media texts and text classifiers in the Greek language, for detecting the polarity of opinions expressed on social media. The experimental results on a related dataset collected by the authors of the current work are promising, since various classifiers based on the language models (naive bayesian, random forests, support vector machines, logistic regression, deep feed-forward neural networks) outperform those of word or sentence-based embeddings (word2vec, GloVe), achieving a classification accuracy of more than 80%. Additionally, a new language model for Greek social media has also been trained on the aforementioned dataset, proving that language models based on domain specific corpora can improve the performance of generic language models by a margin of 2%. Finally, the resulting models are made freely available to the research community.

The paper elaborates on how text analysis influences classification—a key part of the spam-filtering process. The authors propose a multistage meta-algorithm for checking classifier performance. As a result, the algorithm allows for the fast selection of the best-performing classifiers as well as for the analysis of higher-dimensionality data. The last aspect is especially important when analyzing large datasets. The approach of cross-validation between different datasets for supervised learning is applied in the meta-algorithm. Three machine-learning methods allowing a user to classify e-mails as desirable (ham) or potentially harmful (spam) messages were compared in the paper to illustrate the operation of the meta-algorithm. The used methods are simple, but as the results showed, they are powerful enough. We use the following classifiers: k-nearest neighbours (k-NNs), support vector machines (SVM), and the naïve Bayes classifier (NB). The conducted research gave us the conclusion that multinomial naïve Bayes classifier can be an excellent weapon in the fight against the constantly increasing amount of spam messages. It was also confirmed that the proposed solution gives very accurate results.

COVID-19 is a community-acquired infection with symptoms that resemble those of influenza and bacterial pneumonia. Creating an infection control policy involving isolation, disinfection of surfaces, and identification of contagions is crucial in eradicating such pandemics. Incorporating social distancing could also help stop the spread of community-acquired infections like COVID-19. Social distancing entails maintaining certain distances between people and reducing the frequency of contact between people. Meanwhile, a significant increase in the development of different Internet of Things (IoT) devices has been seen together with cyber-physical systems that connect with physical environments. Machine learning is strengthening current technologies by adding new approaches to quickly and correctly solve problems utilizing this surge of available IoT devices. We propose a new approach using machine learning algorithms for monitoring the risk of COVID-19 in public areas. Extracted features from IoT sensors are used as input for several machine learning algorithms such as decision tree, neural network, naïve Bayes classifier, support vector machine, and random forest to predict the risks of the COVID-19 pandemic and calculate the risk probability of public places. This research aims to find vulnerable populations and reduce the impact of the disease on certain groups using machine learning models. We build a model to calculate and predict the risk factors of populated areas. This model generates automated alerts for security authorities in the case of any abnormal detection. Experimental results show that we have high accuracy with random forest of 97.32%, with decision tree of 94.50%, and with the naïve Bayes classifier of 99.37%. These algorithms indicate great potential for crowd risk prediction in public areas.

This paper presents an automatic classification of plastic material’s inorganic pigment using terahertz spectroscopy and convolutional neural networks (CNN). The plastic materials were placed between the THz transmitter and receiver, and the acquired THz signals were classified using a supervised learning approach. A THz frequency band between 0.1–1.2 THz produced a one-dimensional (1D) vector that is almost impossible to classify directly using supervised learning. This paper proposes a novel pre-processing of 1D THz data that transforms 1D data into 2D data, which are processed efficiently using a convolutional neural network. The proposed pre-processing algorithm consists of four steps: peak detection, envelope extraction, and a down-sampling procedure. The last main step introduces the windowing with spectrum dilatation that reorders 1D data into 2D data that can be considered as an image. The spectrum dilation techniques ensure the classifier’s robustness by suppressing measurement bias, reducing the complexity of the THz dataset with negligible loss of accuracy, and speeding up the network classification. The experimental results showed that the proposed approach achieved high accuracy using a CNN classifier, and outperforms 1D classification of THz data using support vector machine, naive Bayes, and other popular classification algorithms.

Diabetic retinopathy (DR) and glaucoma can both be incurable if they are not detected early enough. Therefore, ophthalmologists worldwide are striving to detect them by personally screening retinal fundus images. However, this procedure is not only tedious, subjective, and labor-intensive, but also error-prone. Worse yet, it may not even be attainable in some countries where ophthalmologists are in short supply. A practical solution to this complicated problem is a computer-aided diagnosis (CAD) system—the objective of this work. We propose an accurate system to detect at once any of the two diseases from retinal fundus images. The accuracy stems from two factors. First, we calculate a large set of hybrid features belonging to three groups: first-order statistics (FOS), higher-order statistics (HOS), and histogram of oriented gradient (HOG). Then, these features are skillfully reduced using a genetic algorithm scheme that selects only the most relevant and significant of them. Finally, the selected features are fed to a classifier to detect one of three classes: DR, glaucoma, or normal. Four classifiers are tested for this job: decision tree (DT), naive Bayes (NB), k-nearest neighbor (kNN), and linear discriminant analysis (LDA). The experimental work, conducted on three publicly available datasets, two of them merged into one, shows impressive performance in terms of four standard classification metrics, each computed using k-fold crossvalidation for added credibility. The highest accuracy has been provided by DT—96.67% for DR, 100% for glaucoma, and 96.67% for normal.

Heart disease, one of the main reasons behind the high mortality rate around the world, requires a sophisticated and expensive diagnosis process. In the recent past, much literature has demonstrated machine learning approaches as an opportunity to efficiently diagnose heart disease patients. However, challenges associated with datasets such as missing data, inconsistent data, and mixed data (containing inconsistent missing data both as numerical and categorical) are often obstacles in medical diagnosis. This inconsistency led to a higher probability of misprediction and a misled result. Data preprocessing steps like feature reduction, data conversion, and data scaling are employed to form a standard dataset—such measures play a crucial role in reducing inaccuracy in final prediction. This paper aims to evaluate eleven machine learning (ML) algorithms—Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Naive Bayes (NB), Support Vector Machine (SVM), XGBoost (XGB), Random Forest Classifier (RF), Gradient Boost (GB), AdaBoost (AB), Extra Tree Classifier (ET)—and six different data scaling methods—Normalization (NR), Standscale (SS), MinMax (MM), MaxAbs (MA), Robust Scaler (RS), and Quantile Transformer (QT) on a dataset comprising of information of patients with heart disease. The result shows that CART, along with RS or QT, outperforms all other ML algorithms with 100% accuracy, 100% precision, 99% recall, and 100% F1 score. The study outcomes demonstrate that the model’s performance varies depending on the data scaling method.

Children’s healthcare is a relevant issue, especially the prevention of domestic accidents, since it has even been defined as a global health problem. Children’s activity classification generally uses sensors embedded in children’s clothing, which can lead to erroneous measurements for possible damage or mishandling. Having a non-invasive data source for a children’s activity classification model provides reliability to the monitoring system where it is applied. This work proposes the use of environmental sound as a data source for the generation of children’s activity classification models, implementing feature selection methods and classification techniques based on Bayesian networks, focused on the recognition of potentially triggering activities of domestic accidents, applicable in child monitoring systems. Two feature selection techniques were used: the Akaike criterion and genetic algorithms. Likewise, models were generated using three classifiers: naive Bayes, semi-naive Bayes and tree-augmented naive Bayes. The generated models, combining the methods of feature selection and the classifiers used, present accuracy of greater than 97% for most of them, with which we can conclude the efficiency of the proposal of the present work in the recognition of potentially detonating activities of domestic accidents.

The paper aims to emphasize the advantages of several advanced statistical and data mining techniques when applied to the dense literature on corruption measurements and determinants. For this purpose, we used all seven waves of the World Values Survey and we employed the Naive Bayes technique in SQL Server Analysis Services 2016, the LASSO package together with logit and melogit regressions with raw coefficients in Stata 16. We further conducted different types of tests and cross-validations on the wave, country, gender, and age categories. For eliminating multicollinearity, we used predictor correlation matrices. Moreover, we assessed the maximum computed variance inflation factor (VIF) against a maximum acceptable threshold, depending on the model’s R squared in Ordinary Least Square (OLS) regressions. Our main contribution consists of a methodology for exploring and validating the most important predictors of the risk associated with bribery tolerance. We found the significant role of three influences corresponding to questions about attitudes towards the property, authority, and public services, and other people in terms of anti-cheating, anti-evasion, and anti-violence. We used scobit, probit, and logit regressions with average marginal effects to build and test the index based on these attitudes. We successfully tested the index using also risk prediction nomograms and accuracy measurements (AUCROC &gt, 0.9).