Search

Personality reflects how people can behave in different situations and affects their decisions. Analyzing personality is useful in many fields, for example in the prediction of performance in a job. Emotion recognition is another important research topic due to the wide spread of social media. People express their feeling in form of Facebook posts, tweeter real reactions, and shares. Understanding both personality and emotions from the written text is much easier when it comes to humans. However, this task is impossible with the huge amount of data spread all other social media. The use of machine learning algorithms for personality and emotion recognition from text data is a new research field. In this paper, we propose an enhanced recognition system for personality recognition and emotion recognition. The proposed enhanced recognition system is composed of four main modules, namely data acquisition module, data preprocessing module, personality recognition module, and emotion recognition module. Several machine learning algorithms are used for the multiclass classification process. Gray wolf optimization (GWO) algorithm is used for hyperparameter optimization, while group GWO (GGWO) algorithm is used for feature selection. The proposed model could achieve an accuracy of 99.99% using the random forest algorithm for personality detection and 88.06% using a decision tree for emotion recognition, which outperforms other state-of-the-art studies. We can profit from social media despite some of its drawbacks by understanding people's emotions through their tweets, posts, etc. For instance, before someone commits suicide, we can tell what their intentions are. Most suicide committers, according to recent studies, leave suicide notes on their social media accounts, and these letters need to be taken seriously. [ABSTRACT FROM AUTHOR]

Severe air pollution poses a significant threat to public safety and human health. Predicting future air quality conditions is crucial for implementing pollution control measures and guiding residents' activity choices. However, traditional single-module machine learning models suffer from long training times and low prediction accuracy. To improve the accuracy of air quality forecasting, this paper proposes a ISSA–LSTM model-based approach for predicting the air quality index (AQI). The model consists of three main components: random forest (RF) and mRMR, improved sparrow search algorithm (ISSA), and long short-term memory network (LSTM). Firstly, RF–mRMR is used to select the influential variables affecting AQI, thereby enhancing the model's performance. Next, ISSA algorithm is employed to optimize the hyperparameters of LSTM, further improving the model's performance. Finally, LSTM model is utilized to predict AQI concentrations. Through comparative experiments, it is demonstrated that the ISSA–LSTM model outperforms other models in terms of RMSE and R2, exhibiting higher prediction accuracy. The model's predictive performance is validated across different time steps, demonstrating minimal prediction errors. Therefore, the ISSA–LSTM model is a viable and effective approach for accurately predicting AQI. [ABSTRACT FROM AUTHOR]

This paper promotes better life quality and lifestyle for patients. We attain this goal by creating a mobile application that analyses patient's medical records, such as diabetes, hypertension, and chronic kidney diseases. Then, we implement the system to diagnose patients with chronic conditions using machine learning techniques. Machine learning classifiers are used in this paper to decide whether a person has any chronic diseases. The investigated diseases are hypertension, diabetes, and chronic kidney disease. Four datasets were used to build the classifying models. Orange3 from Anaconda-Navigator, a data mining tool, was used to test machine learning algorithms. The study findings revealed the superiority of the tree algorithm with 100% accuracy for hypertension; it was the highest outcome for both males and females using Orange3. The highest precision, which is 100%, is observed by SVM, k-NN, decision trees, logistic regression, and CART for hypertension males' data collection. In comparison, the highest precision is 100% in SVM, MLP, decision tree, random forest, logistic regression, and CART for the female dataset. We conclude that the two datasets for the same diseases share mostly the same algorithm accuracy. For kidneys, the Random Forest algorithm produced 100% accuracy, which is the highest value among other algorithms. For diabetes, neural networks have attested the best accuracy. It was 76.3%, yet the accuracy increased slightly as the kNN algorithm showed 83% accuracy. [ABSTRACT FROM AUTHOR]

Poverty is a glaring issue in the twenty-first century, even after concerted efforts of organizations to eliminate the same. Predicting poverty using machine learning can offer practical models for facilitating the process of elimination of poverty. This paper uses Multidimensional Poverty Index Data from the Oxford Poverty and Human Development Initiative across the years 2019 and 2021 to make predictions of multidimensional poverty before and during the pandemic. Several poverty indicators under health, education and living standards are taken into consideration. The work implements several data analysis techniques like feature correlation and selection, and graphical visualizations to answer research questions about poverty. Various machine learning, such as Multiple Linear Regression, Decision Tree Regressor, Random Forest Regressor, XGBoost, AdaBoost, Gradient Boosting, Linear Support Vector Regressor (SVR), Ridge Regression, Lasso Regression, ElasticNet Regression, and K-Nearest Neighbor Regression algorithm, have been implemented to predict poverty across four datasets on a national and a subnational level. Regularization is used to increase the performance of the models, and cross-validation is used for estimation. Through a rigorous analysis and comparison of different models, this work identifies important poverty determinants and concludes that overall, Ridge Regression model performs the best with the highest R2 score. [ABSTRACT FROM AUTHOR]

Predicting students' performance during their years of academic study has been investigated tremendously. It offers important insights that can help and guide institutions to make timely decisions and changes leading to better student outcome achievements. In the post-COVID-19 pandemic era, the adoption of e-learning has gained momentum and has increased the availability of online related learning data. This has encouraged researchers to develop machine learning (ML)-based models to predict students' performance during online classes. The study presented in this paper, focuses on predicting student performance during a series of online interactive sessions by considering a dataset collected using digital electronics education and design suite. The dataset tracks the interaction of students during online lab work in terms of text editing, a number of keystrokes, time spent in each activity, etc., along with the exam score achieved per session. Our proposed prediction model consists of extracting a total of 86 novel statistical features, which were semantically categorized in three broad categories based on different criteria: (1) activity type, (2) timing statistics, and (3) peripheral activity count. This set of features were further reduced during the feature selection phase and only influential features were retained for training purposes. Our proposed ML model aims to predict whether a student's performance will be low or high. Five popular classifiers were used in our study, namely: random forest (RF), support vector machine, Naïve Bayes, logistic regression, and multilayer perceptron. We evaluated our model under three different scenarios: (1) 80:20 random data split for training and testing, (2) fivefold cross-validation, and (3) train the model on all sessions but one which will be used for testing. Results showed that our model achieved the best classification accuracy performance of 97.4% with the RF classifier. We demonstrated that, under similar experimental setup, our model outperformed other existing studies. [ABSTRACT FROM AUTHOR]

Parkinson's disease, which affects the neurological system of patients, is the second most common neurodegenerative ailment after Alzheimer's disease. Parkinson's disease is most common in adults over sixty and advances slowly. Parkinson's disease symptoms are mild in the early stages and may go unnoticed, but as the disease advances, the symptoms get more severe, and its diagnosis at an early stage is not easy. Recent studies have revealed that alterations in speech or voice distortion can be used to diagnose Parkinson's disease, because it develops as an early symptom in Parkinson's disease patients. The authors propose a technique for detecting Parkinson's disease using speech signals in this paper. As feature selection plays a vital role during classification, the authors have proposed a hybrid MIRFE feature selection approach based on mutual information gain and recursive feature elimination methods. A Parkinson's disease classification dataset consisting of 756 voice measures of 252 individuals was used in this study. The proposed feature selection approach is compared with the five standard feature selection methods by random forest and XGBoost classifier. The proposed MIRFE approach selects 40 features out of 754 features, with a feature reduction ratio of 94.69%. An accuracy of 93.88% and an area under the curve (AUC) of 0.978 are obtained by the proposed system, which is higher than some recent work. [ABSTRACT FROM AUTHOR]

Nowadays, embedded systems are comprised of heterogeneous multi-core architectures, i.e., CPUs and GPUs. If the application is mapped to an appropriate processing core, then these architectures provide many performance benefits to applications. Typically, programmers map sequential applications to CPU and parallel applications to GPU. The task mapping becomes challenging because of the usage of evolving and complex CPU- and GPU-based architectures. This paper presents an approach to map the OpenCL application to heterogeneous multi-core architecture by determining the application suitability and processing capability. The classification is achieved by developing a machine learning-based device suitability classifier that predicts which processor has the highest computational compatibility to run OpenCL applications. In this paper, 20 distinct features are proposed that are extracted by using the developed LLVM-based static analyzer. In order to select the best subset of features, feature selection is performed by using both correlation analysis and the feature importance method. For the class imbalance problem, we use and compare synthetic minority over-sampling method with and without feature selection. Instead of hand-tuning the machine learning classifier, we use the tree-based pipeline optimization method to select the best classifier and its hyper-parameter. We then compare the optimized selected method with traditional algorithms, i.e., random forest, decision tree, Naïve Bayes and KNN. We apply our novel approach on extensively used OpenCL benchmarks, i.e., AMD and Polybench. The dataset contains 653 training and 277 testing applications. We test the classification results using four performance metrics, i.e., F-measure, precision, recall and R 2 . The optimized and reduced feature subset model achieved a high F-measure of 0.91 and R 2 of 0.76. The proposed framework automatically distributes the workload based on the application requirement and processor compatibility. [ABSTRACT FROM AUTHOR]

Accurate prediction of a newborn's birth weight (BW) is a crucial determinant to evaluate the newborn's health and safety. Infants with low BW (LBW) are at a higher risk of serious short- and long-term health outcomes. Over the past decade, machine learning (ML) techniques have shown a successful breakthrough in the field of medical diagnostics. Various automated systems have been proposed that use maternal features for LBW prediction. However, each proposed system uses different maternal features for LBW classification and estimation. Therefore, this paper provides a detailed setup for BW estimation and LBW classification. Multiple subsets of features were combined to perform predictions with and without feature selection techniques. Furthermore, the synthetic minority oversampling technique was employed to oversample the minority class. The performance of 30 ML algorithms was evaluated for both infant BW estimation and LBW classification. Experiments were performed on a self-created dataset with 88 features. The dataset was obtained from 821 women from three hospitals in the United Arab Emirates. Different performance metrics, such as mean absolute error and mean absolute percent error, were used for BW estimation. Accuracy, precision, recall, F-scores, and confusion matrices were used for LBW classification. Extensive experiments performed using five-folds cross validation show that the best weight estimation was obtained using Random Forest algorithm with mean absolute error of 294.53 g while the best classification performance was obtained using Logistic Regression with SMOTE oversampling techniques that achieved accuracy, precision, recall and F1 score of 90.24%, 87.6%, 90.2% and 0.89, respectively. The results also suggest that features such as diabetes, hypertension, and gestational age, play a vital role in LBW classification. [ABSTRACT FROM AUTHOR]

Several organizations are implementing large-scale Internet of Things (IoT)-based ecosystems, such as Industrial IoT (IIoT). Such systems are vulnerable to new threats and intrusions because of the nature of their networks. It is necessary to secure such systems by developing feature selection integrated with robust machine learning models. In this paper, a two-phase IIoT traffic prediction model is built for detecting normal and anomalous IIoT behavior. The system is divided into two phases. In the first phase, multi-objective non-dominated sorting with whale optimization approach (MNSWOA) and ideal point method (IPM) is implemented for feature selection. The key quality attributes are retrieved for effective classification. In the second phase, the feature selection results are sent to the random forest (RF) classifier for traffic prediction. Experimental results on IIoT datasets, namely CTU-13, AWID and Gas–Water show that the proposed technique MNSWOA–IPM–RF obtains enhanced performance in terms of accuracy, true positive rate, true negative rate and area under the ROC curve. Also, comparisons indicate that the proposed MNSWOA–IPM–RF model has superior results than benchmark multi-objective optimization techniques. [ABSTRACT FROM AUTHOR]

In today's world, the growth of computer networks is exponential as networking is an essential part of the latest technologies like Internet of Things (IoT), cloud computing, edge computing, etc., with the adoption of new technologies; security has become an important issue for such techniques. These networks need to be saved from a wide range of available attacks. In the literature, many intrusion detection systems (IDS) are used to detect such attacks. IDS can be signature based or anomaly based. The signature-based method can only detect a well-known attack while anomaly-based methods can detect new attacks but suffers from low performance. IDS with a potential anomaly detection mechanism to improve the performance is highly desirable. For the reasons mentioned above, this paper proposed an anomaly-based IDS with novel hybrid ensemble classification method based on grouping of the network traffic. The groups are created based on the services or protocol used by the network traffic. After grouping of network traffic, wrapper-based sequential feature selection (SFS) with random forest (RF) classifier is used to select optimal features and perform classification in each group. Furthermore, to validate the performance of the proposed model for service-based and protocol-based grouping approach, UNSW-NB15 and NSL-KDD datasets are used, respectively. The result shows that the proposed approach outperforms the existing feature selection approaches with high accuracy, precision, and F-score for both the datasets. [ABSTRACT FROM AUTHOR]

With simple connectivity and fast-growing demand of smart devices and networks, IoT has become more prone to cyber attacks. In order to detect and prevent cyber attacks in IoT networks, intrusion detection system (IDS) plays a crucial role. However, most of the existing IDS have dimensionality curse that reduces overall IoT systems efficiency. Hence, it is important to remove repetitive and irrelevant features while designing effective IDS. Motivated from aforementioned challenges, this paper presents an intelligent cyber attack detection system for IoT network using a novel hybrid feature reduced approach. This technique first performs feature ranking using correlation coefficient, random forest mean decrease accuracy and gain ratio to obtain three different feature sets. Then, features are combined using a suitably designed mechanism (AND operation), to obtain single optimized feature set. Finally, the obtained reduced feature set is fed to three well-known machine learning algorithms such as random forest, K-nearest neighbor and XGBoost for detection of cyber attacks. The efficiency of the proposed cyber attack detection framework is evaluated using NSL-KDD and two latest IoT-based datasets namely, BoT-IoT and DS2OS. Performance of the proposed framework is evaluated and compared with some recent state-of-the-art techniques found in literature, in terms of accuracy, detection rate (DR), precision and F1 score. Performance analysis using these three datasets shows that the proposed model has achieved DR up to 90%–100%, for most of the attack vectors that has close similarity to normal behaviors and accuracy above 99%. [ABSTRACT FROM AUTHOR]

Energy being a precious resource needs to be mindfully utilized, so that efficiency is achieved and its wastage is curbed. Globally, multi-storeyed buildings are the biggest energy consumers. A large portion of energy within a building is consumed to maintain the desired temperature for the comfort of occupants. For this purpose, heating load and cooling load requirements of the building need to be met. These requirements should be minimized to reduce energy consumption and optimize energy usage. Some characteristics of buildings greatly affect the heating load and cooling load requirements. This paper presented a systematic approach for analysing various factors of a building playing a vital role in energy consumption, followed by the algorithmic approaches of traditional machine learning and modern ensemble learning for energy consumption prediction in residential buildings. The results revealed that ensemble techniques outperform machine learning techniques with an appreciable margin. The accuracy of predicting heating load and cooling load, respectively, with multiple linear regression was 88.59% and 85.26%, with support vector regression was 82.38% and 89.32%, with K-nearest neighbours was 91.91% and 94.47%. The accuracy achieved with ensemble techniques was comparatively better—99.74% and 94.79% with random forests, 99.73% and 96.22% with gradient boosting machines, 99.75% and 95.94% with extreme gradient boosting. [ABSTRACT FROM AUTHOR]

The aim of this study is to propose a high-accuracy and high-efficiency sleep staging algorithm using single-channel electroencephalograms (EEGs). The process consists four parts: signal preprocessing, feature extraction, feature selection, and classification algorithms. In the preconditioning of EEG, wavelet function and IIR filter are used for noise reduction. In feature selection, 15 feature algorithms in time domain, time-frequency domain, and nonlinearity are selected to obtain 30 feature parameters. Feature selection is very important for eliminating irrelevant and redundant features. Feature selection algorithms as Fisher score, Sequential Forward Selection (SFS), Sequential Floating Forward Selection (SFFS), and Fast Correlation-Based Filter Solution (FCBF) were used. The paper establishes a new ensemble learning algorithm based on stacking model. The basic layers are k-Nearest Neighbor (KNN), Random Forest (RF), Extremely Randomized Trees (ERT), Multi-layer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost) and the second layer is a Logistic regression. Comparing classification of RF, Gradient Boosting Decision Tree (GBDT), and XGBoost, the accuracies and kappa coefficients are 96.67% and 0.96 using the proposed method. It is higher than other classification algorithms.The results show that the proposed method can accurately sleep staging using single-channel EEG and has a high ability to predict sleep staging. Graphical abstract. [ABSTRACT FROM AUTHOR]