Automated oscillation detection and correction of fused wearable sensor signals using machine learning

Online social media is used to show the sentiments of different individuals about various subjects. Sentiment analysis or opinion mining has recently been considered as one of the highly dynamic research fields in natural language processing, Web mining, and machine learning. There has been a very limited amount of research that focuses on sentiment analysis in the Malay language. This study investigates how feature selection methods contribute to the improvement of Malay sentiment classification performance. Three supervised machine-learning classifiers and seven feature selection methods are used to conduct a series of experiments for the effective selection of the appropriate methods for the automatic sentiment classification of online Malay-written reviews. Findings show that the classifications of Malay sentiment improve using feature selections approaches. This work demonstrates that all feature reduction methods generally improve classifier performance. Support Vector Machine (SVM) approach provide the highest accuracy performance of features selection in order to classify Malay sentiment comparing with other classifications approaches such as PCA and CHI square. SVM records 87% as experimental accuracy result of feature selection.

The new phase in handling COVID-19 in Indonesia, called New Normal, gives various public perspectives regarding this policy. This study aims to analyze public sentiment towards the New Normal policy through an electronic news comment column. This study uses text data in the form of comments were collected from electronic news media sites, namely www.detik.com and www.kompas.com, and taken from the comments column on Instagram social media, namely the @detikcom account. Also, use FastText method to extract features by converting data into vector values and using three classification methods, Naive Bayes (NB), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). This study conducted a hyperparameter test to obtain the most optimal model. Testing the hyperparameters from FastText produces an optimal model with dimensions of 250, window size 8, epoch 1.000, and a learning rate of 0,0025. Hyperparameter testing was also carried out on the SVM and MLP classifiers. Hyperparameter testing of the SVM and MLP classifiers produces the most optimal model with the SVM method using the RBF kernel, C of 1.000, gamma of 10. In contrast, the MLP method uses the relu activation function, hidden size layer (250,250), adam optimizer, alpha 0,0001, and adaptive learning rate. The classification model was evaluated using K-fold cross-validation to produce an average f1score. The result is for the NB method 72,25% f1score, for the SVM method 92,21% f1score, and for the MLP method 90,75% f1score.

생물 및 의학계에서는 생물정보학(bioinformatics)의 데이터 중 혈청 단백질(proteome)에서 추출한 데이터가 질병의 진단에 관련된 정보를 가지고 있고, 이 데이터를 분류 분석함으로 질병을 조기에 진단 할 수 있다고 믿고 있다. 본 논문에서는 혈청 단백질(2-D PAGE: Two-dimensional polyacrylamide gel electrophoresis)로부터 암과 정상을 판별하는 새로운 복합분류기를 제안한다. 새로운 복합 분류기에서는 support vector machine(SVM)와 다층 퍼셉트론(multi-layer perceptron: MLP)와 k-최근 접 이웃(k-nearest neighbor: k-NN)분류기를 앙상블(ensemble) 방법으로 통합하는 동시에 다중 부스팅(boosting) 방법으로 각 분류기를 확장하여 부분류기(subclassifier)의 배열(array)으로서 복합분류기를 구성하였다. 각 부분류기에서는 최적 특성 집합 (feature set)을 탐색하기 위하여 유전 알고리즘(genetic algorithm: GA)를 적용하였다. 복합분류기의 성능을 측정하기 위하여 암연구에서 얻어진 임상 데이터를 복합분류기에 적용하였고 결과로서 단일 분류기 보다 높은 분류 정확도와 안정성을 보여 주었다. It is believed that the anomalies or diseases of human organs are identified by the analysis of the patterns. This paper proposes a new classification technique for the identification of cancer disease using the proteome patterns obtained from two-dimensional polyacrylamide gel electrophoresis(2-D PAGE). In the new classification method, three different classification methods such as support vector machine(SVM), multi-layer perceptron(MLP) and k-nearest neighbor(k-NN) are extended by multi-boosting method in an array of subclassifiers and the results of each subclassifier are merged by ensemble method. Genetic algorithm was applied to obtain optimal feature set in each subclassifier. We applied our method to empirical data set from cancer research and the method showed the better accuracy and more stable performance than single classifier.

Purpose:There has been burgeoning interest in applying machine learning methods for predicting radiotherapy outcomes. However, the imbalanced ratio of a large number of variables to a limited sample size in radiation oncology constitutes a major challenge. Therefore, dimensionality reduction methods can be a key to success. The study investigates and contrasts the application of traditional machine learning methods and deep learning approaches for outcome modeling in radiotherapy. In particular, new joint architectures based on variational autoencoder (VAE) for dimensionality reduction are presented and their application is demonstrated for the prediction of lung radiation pneumonitis (RP) from a large-scale heterogeneous dataset.Methods:A large-scale heterogeneous dataset containing a pool of 230 variables including clinical factors (e.g., dose, KPS, stage) and biomarkers (e.g., single nucleotide polymorphisms (SNPs), cytokines and micro-RNAs) in a population of 106 non-small cell lung cancer (NSCLC) patients who received radiotherapy was used for modeling RP. 22 patients had grade 2 or higher RP. Four methods were investigated, including feature selection (case A) and feature extraction (case B) with traditional machine learning methods, a VAE-MLP joint architecture (case C) with deep learning and lastly, the combination of feature selection and joint-architecture (case D). For feature selection, Random forest (RF), Support Vector Machine (SVM) and multi-layer perceptron (MLP) were implemented to select relevant features. Specifically, each method was run for multiple times to rank features within several cross-validated (CV) resampled sets. A collection of ranking lists were then aggregated by top 5% and Kemeny graph methods to identify the final ranking for prediction. A synthetic minority oversampling technique (SMOTE) was applied to correct for class imbalance during this process. For deep learning, a VAE-MLP joint architecture where a VAE aimed for dimensionality reduction and an MLP aimed for classification was developed. In this architecture, reconstruction loss and prediction loss were combined into a single loss function to realize simultaneous training and weights were assigned to different classes to mitigate class imbalance. To evaluate the prediction performance and conduct comparisons, the area under receiver operating characteristic (ROC) curves (AUCs) were performed for nested CVs for both handcrafted feature selections and the deep learning approach. The significance of differences in AUCs was assessed using the DeLong test of U-statistics.Results:An MLP-based method using weight pruning (WP) feature selection yielded the best performance among the different hand-crafted feature selection methods (case A), reaching an AUC of 0.804 (95% CI: 0.761–0.823) with 29 top features. A VAE-MLP joint architecture (case C) achieved a comparable but slightly lower AUC of 0.781 (95% CI: 0.737–0.808) with the size of latent dimension being 2. The combination of handcrafted features (case A) and latent representation (case D) achieved a significant AUC improvement of 0.831 (95% CI: 0.805–0.863) with 22 features (p-value = 0.000642 compared with handcrafted features only (Case A) and p-value=0.000453 compared to VAE alone (Case C)) with an MLP classifier.Conclusion:The potential for combination of traditional machine learning methods and deep learning VAE techniques has been demonstrated for dealing with limited datasets in modeling radiotherapy toxicities. Specifically, latent variables from a VAE-MLP joint architecture are able to complement handcrafted features for the prediction of RP and improve prediction over either method alone.

Speech is the fastest and most natural method for human to communicate. This has led several researches to be done in the field of the interaction effects between human and machine. Hence, it is necessary to design machines which can intelligently recognize the emotion of a human voice. However, we are still far from having a natural interaction between the human and machine because machines cannot distinguish the emotion of the speaker. This has established a new field in the literature, namely the speech emotion recognition systems. The accuracy of these systems depends on various factors such as the number and type of the emotion manners as well as the feature selection and the classifier sort. In this paper, classification methods of the Neural Network (NN), Support Vector Machine (SVM), the combination of NN and SVM (NN-SVM), NN and SVM (NN-SVM), NN and C5.0 (NN-C5.0), C5.0 and SVM (SVM-C5.0), and finally the combination of NN, SVM, and C5.0 (NN-SVM-C5.0) have been verified, and their efficiencies in speech emotion recognition have been compared. The utilized features in this research include energy, power, Zero Crossing Rate (ZCR), pitch, and Mel-scale Frequency Cepstral Coefficients (MFCC). The presented results in this paper demonstrate that using the proposed NN-C5.0 classification method is more efficient in recognizing the emotion states-to the extent of 6%- to 30% depending on the number of emotions states-than SVM, NN, and other aforementioned combinations of classification methods.

Modeling IDS have been focused on improving detection model(s) in terms of (i) detection model design based on classification algorithm, clustering algorithm, and soft computing techniques such as Artificial Neural Networks (ANN), Hidden Markov Model (HMM), Support Vector Machines (SVM), K-means clustering, Fuzzy approaches and so on and (ii) feature selection through wrapper and filter approaches. However these approaches require large overhead due to heavy computations for both feature selection and cross validation method to minimize generalization errors. In addition selected feature set varies according to detection model so that they are inefficient for modeling lightweight IDS. Therefore this paper proposes a new approach to model lightweight Intrusion Detection System (IDS) based on a new feature selection approach named Correlation-based Hybrid Feature Selection (CBHFS) which is able to significantly decrease training and testing times while retaining high detection rates with low false positives rates as well as stable feature selection results. The experimental results on KDD 1999 intrusion detection datasets show the feasibility of our approach to enable one to modeling lightweight IDS.

Background - Many factors affect student performance such as the individual's background, habits, absenteeism and social activities. Using these factors, corrective actions can be determined to improve their performance. This study looks into the effects of these factors in predicting student performance from a data mining approach. This study presents a data mining approach in identify significant factors and predict student performance, based on two datasets collected from two secondary schools in Portugal. Methods - In this study, two datasets collected from two secondary schools in Portugal. First, the data used in the study is augmented to increase the sample size by merging the two datasets. Following that, data pre-processing is performed and the features are normalized with linear scaling to avoid bias on heavy weighted attributes. The selected features are then assigned into four groups comprising of student background, lifestyle, history of grades and all features. Next, Boruta feature selection is performed to remove irrelevant features. Finally, the classification models of Support Vector Machine (SVM), Naïve Bayes (NB), and Multilayer Perceptron (MLP) origins are designed and their performances evaluated. Results - The models were trained and evaluated on an integrated dataset comprising 1044 student records with 33 features, after feature selection. The classification was performed with SVM, NB and MLP with 60-40 and 50-50 train-test splits and 10-fold cross validation. GridSearchCV was applied to perform hyperparameter tuning. The performance metrics were accuracy, precision, recall and F1-Score. SVM obtained the highest accuracy with scores of 77%, 80%, 91% and 90% on background, lifestyle, history of grades and all features respectively in 50-50 train-test splits for binary classification (pass or fail). SVM also obtained highest accuracy for five class classification (grade A, B, C, D and F) with 39%, 38%, 73% and 71% for the four categories respectively.

Background - Many factors affect student performance such as the individual’s background, habits, absenteeism and social activities. Using these factors, corrective actions can be determined to improve their performance. This study looks into the effects of these factors in predicting student performance from a data mining approach. This study presents a data mining approach in identify significant factors and predict student performance, based on two datasets collected from two secondary schools in Portugal. Methods – In this study, two datasets are augmented to increase the sample size by merging them. Following that, data pre-processing is performed and the features are normalized with linear scaling to avoid bias on heavy weighted attributes. The selected features are then assigned into four groups comprising of student background, lifestyle, history of grades and all features. Next, Boruta feature selection is performed to remove irrelevant features. Finally, the classification models of Support Vector Machine (SVM) , Naïve Bayes (NB) , and Multilayer Perceptron (MLP) origins are designed and their performances evaluated. Results - The models were trained and evaluated on an integrated dataset comprising 1044 student records with 33 features, after feature selection. The classification was performed with SVM, NB and MLP with 60-40 and 50-50 train-test splits and 10-fold cross validation. GridSearchCV was applied to perform hyperparameter tuning. The performance metrics were accuracy, precision, recall and F1-Score. SVM obtained the highest accuracy with scores of 77%, 80%, 91% and 90% on background, lifestyle, history of grades and all features respectively in 50-50 train-test splits for binary levels classification . SVM also obtained highest accuracy for five levels classification with 39%, 38%, 73% and 71% for the four categories respectively. The results show that the history of grades form significant influence on the student performance.

Knowledge discovery using neural approach for SME’s credit risk analysis problem in Turkey

Recently, available data has increased explosively in both number of samples and dimensionality. The huge number of high dimensional data generates the presence of noisy, redundant and irrelevant dimensions. Such dimensions can increase the time and computational cost in the learning process and even degenerate the performance of learning tasks. One of the ways to reduce dimensionality is by Feature Selection (FS). The aim of this paper is study the feature selection based on expert knowledge and traditional methods (filter, wrapper and embedded) and analyze their performance in classification tasks. Three datasets related to cancer domain in humans were used for feature selection: Breast Cancer (BC), Primary Tumor (PT) and Central Nervous System (CNS). C4.5, K-Nearest Neighbors, Support Vector Machine and Multi Layer Perceptron were trained with the best subset of features for each cancer dataset. The subset of features selected by the wrapper method presents the best average accuracy in the datasets BC and PT, while the subset of features selected by the embedded method reaches the highest average accuracy in the CNS dataset.

Cancer survival classification using integrated data sets and intermediate information.

Emotion recognition plays a pivotal role in advancing Human-Computer Interaction (HCI) by enabling systems to understand and respond to human emotional states. Among various modalities, Speech Emotion Recognition (SER) stands out as a non-invasive, cost-effective, and temporally efficient approach for detecting emotions. This study leverages the RAVDESS dataset, which provides high-quality audio recordings for emotion classification. The proposed methodology involves preprocessing audio signals to remove noise, extracting temporal and spectral features in both time and frequency domains, and implementing machine learning models for multi-class emotion classification. The study evaluates and compares the performance of several classification models, including Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Decision Trees (DT). Experimental results demonstrate promising accuracy levels, highlighting the potential of these machine learning techniques in SER. This research contributes to the integration of SER within Brain-Computer Interfaces (BCI) and other emotion-aware applications, paving the way for enhanced interactive systems. Keywords – Speech Emotion Recognition -Machine Learning - Random Forest -Multilayer Perceptron - Support Vector Machine - Convolutional Neural Networks - Decision Tree - RAVDESS Dataset

This paper defines two major data sets 1) from wearable inertial measurement sensors and 2) wearable ECG SHIMMER™ sensors. The first dataset is devised to benchmark techniques dealing with human behavior analysis based on multimodal inertial measurement wearable SHIMMER™ sensors unit during research studies “Fall Detection System for the Elderly Based on the Classification of Shimmer Sensor Prototype Data” [2] and “A novel fall detection algorithm for elderly using SHIMMER wearable sensors” [3]. The SHIMMER inertial sensor is a lightweight sensing device, incorporated with tri-axial accelerometer, a tri-axial gyroscope and tri-axial magnetometer, mounted on the waist of the subjects. The second dataset is developed to assess the feasibility of using SHIMMER™ wearable third generation ECG sensors for identification of basic heart anomalies by remote ECG analysis. The experimental protocol was carried out according to the Timed Up and Go (TUG) test [1], which is mainly used in fall detection and fall risk assessment systems specially designed for elderly. Three daily life activities such as standing still, walking and sitting on chair and getup were performed along with fall activity in controlled environment. This dataset is available on Data in Brief Dataverse [4] and a data repository [5].

This study compares single and hybrid soft computing models for estimating daily solar radiation flux for two scenarios. Scenario I developed single soft computing models, including multilayer perceptron (MLP), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), and multivariate adaptive regression splines (MARS), for estimating daily solar radiation flux at two stations from the USA and South Korea. The MLP model was used to evaluate the effect of factors controlling daily solar radiation flux. Using different combinations of controlling factors as input, the MLP and SVM models, based on evaluation measures, were found to be superior to the ANFIS and MARS models at Big Bend station, USA. In addition, the MLP, SVM, and MARS models performed better than did the ANFIS model at Incheon station, South Korea. Scenario II combined the discrete wavelet transform (DWT) and single soft computing models (e.g., MLP and SVM) for improved performance using 4-input combination. The wavelet-based MLP (WMLP) and SVM (WSVM) models were superior to other single soft computing models (MLP, SVM, ANFIS, and MARS) at two stations. Taylor diagrams, violin plots and point density plots were also utilized to examine the similarity between the observed and estimated solar radiation flux values. Results showed that scenarios I and II can be alternatives for estimating daily solar radiation flux based on different meteorological information, such as peninsular and continental conditions.

Recently, a high dimensional classification framework has been proposed to introduce spatial and anatomical priors in support vector machine (SVM) optimization scheme for brain image analysis. However, classical SVM has to convert 3D discrete brain images naturally represented by higher-order tensors to one-dimensional vectors in order to meet the input requirements. This traditional method destroys the natural structure and correlation in the original data, and generates high dimensional vectors. In this manuscript, the method is improved by a modified support tensor machine (STM) algorithm to make full use of spatial prior and the inherent information of tensor. The new approach reduces memory requirements and computational complexity significantly, and it is comparably demonstrated by experimental results on classification of Alzheimer patients and elderly controls. Introduction Alzheimer disease (AD) is the most prevalent neurodegenerative dementia in worldwide, and thus prevention and early accurate diagnosis of AD is increasingly crucial. In the last few years, support vector machine (SVM) methods for AD subject classification have become an incredibly active research topic. In the related work, SVM approach, as same as feature selection and extraction, has been taking the specificity of neuroimaging data into account. As an example, a frame work is proposed in [1] to include spatial and anatomical priors into SVM by using regularization operators, and it indicates a flexible way to model various types of proximity. However, for the purpose of satisfying the input requirements of classical SVM, 3D discrete brain images naturally represented by higher-order tensors have to convert to vectors in advance. This conversion breaks the inherent structure and correlation in the original data, and easily produces high dimensional vectors and leads to a poor performance in time complexity and space complexity. In order to improve above method including spatial prior of 3D discrete brain images in SVM, a new method is proposed in this manuscript to maintain the natural structure in the original tensor data and include spatial prior of all frontal slices of the tensors in STM [2]. To illustrate the improvement, we apply the proposed method to classification of 299 subjects, 137 AD patients and 162 cognitively normal (CN) controls, as the same study population in [3]. It can be observed that the proposed method reduces size of memory requested and the time complexity significantly and produces better classification performances. Spatial prior in SVM SVM is a supervised learning algorithm introduced by Vapnik and performs classification by mapping the data into higher dimensional space [4]. Let (xs, ys), s∈1,...,S be a training set of instance-labeled pairs, xs∈Ω, ys∈{-1,1} and Ω is the input space, then SVM optimization problem can be written as: