Higher Classification Accuracy Rate Research Articles

A Peak-Finding Siamese Convolutional Neural Network (PF-SCNN) for Aero-Engine Hot Jet FT-IR Spectrum Classification

Aiming at solving difficulties related to aero-engine classification and identification, two telemetry Fourier transform infrared spectrometers are utilized to measure the infrared spectra of six types of aero-engine hot jets, and create a spectral data set, which is divided into a training set (80%), a validation set (10%), and a prediction set (10%). A peak-finding Siamese convolutional neural network (PF-SCNN) is used to match and classify the spectral data. During the training stage, the Siamese convolutional neural network (SCNN) is designed to extract spectral features and calculate the distance similarity. In order to improve the efficiency of the SCNN, a peak-finding method is introduced to extract the spectral peaks, which are used to train the model instead of the original spectral data. During the prediction stage, the trained model is used to calculate the similarity between the prediction set and the combined set of the training set and validation set, and the label of the most similar training data in each prediction set is used as the prediction label. The performance measures of the classification results include accuracy, precision, recall, confusion matrix, and F1-score. The experimental results show that the PF-SCNN can achieve a high classification accuracy rate of 99% and can complete the task of classifying the infrared spectra of aero-engine hot jets.

Artificial intelligence detects awareness of functional relation with the environment in 3 month old babies

A recent experiment probed how purposeful action emerges in early life by manipulating infants’ functional connection to an object in the environment (i.e., tethering an infant’s foot to a colorful mobile). Vicon motion capture data from multiple infant joints were used here to create Histograms of Joint Displacements (HJDs) to generate pose-based descriptors for 3D infant spatial trajectories. Using HJDs as inputs, machine and deep learning systems were tasked with classifying the experimental state from which snippets of movement data were sampled. The architectures tested included k-Nearest Neighbour (kNN), Linear Discriminant Analysis (LDA), Fully connected network (FCNet), 1D-Convolutional Neural Network (1D-Conv), 1D-Capsule Network (1D-CapsNet), 2D-Conv and 2D-CapsNet. Sliding window scenarios were used for temporal analysis to search for topological changes in infant movement related to functional context. kNN and LDA achieved higher classification accuracy with single joint features, while deep learning approaches, particularly 2D-CapsNet, achieved higher accuracy on full-body features. For each AI architecture tested, measures of foot activity displayed the most distinct and coherent pattern alterations across different experimental stages (reflected in the highest classification accuracy rate), indicating that interaction with the world impacts the infant behaviour most at the site of organism~world connection.

COVID19-ResCapsNet: A Novel Residual Capsule Network for COVID-19 Detection from Chest X-Ray Scans Images

In response to the urgent need for swift and accurate diagnosis of COVID-19 during the global pandemic, there has been a growing interest in leveraging advanced technology like deep learning for detection purposes. This project introduces a novel approach termed COVID19-ResCapsNet, which integrates deep neural networks with X-ray imaging data to predict the likelihood of COVID-19 onset in patients. The methodology comprises two key steps. Initially, features are extracted using an enhanced Residual feature extraction network, aimed at capturing crucial information from the X-ray images. Subsequently, multiple Capsule Networks are employed to discern between COVID-19 and non-COVID-19 cases. This hybrid model is assessed using two separate datasets of chest X-ray images: Dataset-1 containing 50 images and Dataset-2 containing 20 images. Remarkably, the proposed method achieves high classification accuracy rates of 0.9988 on Dataset-1 and 0.9933 on Dataset-2 for binary classification tasks. To validate its efficacy, the performance of the COVID19-ResCapsNet model is compared against various state-of-the-art pre-trained classification models. Additionally, the study investigates the impact of two crucial hyper parameters: optimizer selection and batch size. The findings underscore the effectiveness of the proposed COVID-19 detection model, suggesting its potential as a complementary tool in clinical settings for expedited and accurate diagnosis. Keywords: Deep learning, Capsule network, Residual network, COVID-19 detection.

Research on Demagnetization Fault Diagnosis Method of Mine Cutting Permanent Magnet Synchronous Motor

To give timely and accurate diagnosis in the early stage of demagnetization failure for effective control and treatment, based on wavelet packet analysis, principal component analysis (PCA) dimensionality reduction, and least squares support vector machine(LSSVM), the extraction of features and the classification of demagnetization faults are completed. Since it is difficult to collect real data sets of demagnetization faults in practice, a two-dimensional finite element simulation model of permanent magnet synchronous motor (PMSM) under uniform demagnetization and partial demagnetization faults is established based on the Maxwell simulation platform. The wavelet packet analysis is used to extract the demagnetization feature of the A-phase current of the PMSM. Based on PCA dimensionality reduction, the dimensionality reduction of fault features is realized. The LSSVM is used to identify the fault and complete the fault classification. The simulation results show that the method has a high classification accuracy rate for demagnetization faults.

Automatic detection of epileptic seizure using machine learning-based IANFIS-LightGBM system

A sudden increase in electrical activity in the brain is a defining feature of one of the severe neurological diseases known as epilepsy. This abnormality appears as a seizure, and identifying seizures is an important field of research. An essential technique for examining the features of neurological issues brain activities, and epileptic seizures is electroencephalography (EEG). In EEG data, analyzing epileptic irregularities visually requires a lot of time from neurologists. For accurate detection of epileptic seizures, numerous scientific techniques have been used with EEG data, and most of these techniques have produced promising results. For EEG signal classification with a high classification accuracy rate, the present research proposes an enhanced machine learning-based epileptic seizure detection model. The present research provides a hybrid Improved Adaptive Neuro-Fuzzy Inference System (IANFIS)-Light Gradient Boosting Machine (LightGBM) technique for automatically detecting and diagnosing epilepsy from EEG data. The experimental findings were supported by EEG records made available by the German University of Bonn and scalp EEG data acquired at Children’s Hospital Boston. The suggested IANFIS-LightGBM, according to the results, offers the most significant classification accuracy ratings in both situations.

Generation and classification models of ultrasonic signals in aged cast austenitic stainless steel (CASS)

In this study, we attempted to generate new ultrasonic signals from thermally aged CASS specimens using a statistical-based model to augment the experimental data. A variational auto-encoder (VAE) model is adopted to generate the ultrasonic signals. To verify the quality of the generated data (signals), two ML algorithms (k-nearest neighbor and multi-layer perceptron algorithms) were used for classification with newly generated data for training and experimental data for testing. The results showed that new ultrasonic signals could be generated effectively with a small amount of experimental data, with the newly generated data showing features approximating those of the experimental data, indicating high classification accuracy rate for ultrasonic signals from aged CASS specimens. In addition, a sampling method for the generated model is suggested.

Combining data discretization and missing value imputation for incomplete medical datasets.

Data discretization aims to transform a set of continuous features into discrete features, thus simplifying the representation of information and making it easier to understand, use, and explain. In practice, users can take advantage of the discretization process to improve knowledge discovery and data analysis on medical domain problem datasets containing continuous features. However, certain feature values were frequently missing. Many data-mining algorithms cannot handle incomplete datasets. In this study, we considered the use of both discretization and missing-value imputation to process incomplete medical datasets, examining how the order of discretization and missing-value imputation combined influenced performance. The experimental results were obtained using seven different medical domain problem datasets: two discretizers, including the minimum description length principle (MDLP) and ChiMerge; three imputation methods, including the mean/mode, classification and regression tree (CART), and k-nearest neighbor (KNN) methods; and two classifiers, including support vector machines (SVM) and the C4.5 decision tree. The results show that a better performance can be obtained by first performing discretization followed by imputation, rather than vice versa. Furthermore, the highest classification accuracy rate was achieved by combining ChiMerge and KNN with SVM.

Improved Cyber Attack Detection Using MLB-FQS: A Novel Modified Lagrange Butterfly-based Fuzzy Quasi-Linear SVM Algorithm

With the rapid enhancement of communication and computer networks, internet-based technologies provide numerous convenient and accessible services to the public all over the world. Meanwhile, the types and number of cyber attacks have been increasing day by day and create a serious threat to secure most confidential data. Hence, securing data is considered a crucial task and nowadays intrusion detection system is one of the most effective and promising techniques to provide secure data by detecting malicious data. However, it becomes extremely hard in preventing the network system from attack due to imbalanced data that results in low detection and poor accuracy rates. Therefore, a novel intrusion detection mechanism is proposed to accurately detect cyber intrusion with high detection accuracy rate. The Intrusion detection mechanism comprises three significant phases namely the data pre-processing phase, the feature selection phase as well as attack detection phase. Various pre-processing techniques namely data normalization, data conversion as well as one-hot encoding process are utilized to provide an appropriate format that is suitable for analysis. In the feature selection phase, a Modified Lagrange Butterfly (MLB) optimization is employed to select optimal features for effective detection. Finally, a Fuzzy Quasi-Linear Support Vector Machine (FQL-SVM) classifier is employed to determine the network as two different types of classes namely the abnormal or malicious classes. After examining on malware dataset, the experimental analysis demonstrates a high classification accuracy rate of 98.41% which is better than other comparative techniques.

Text Classification of Mixed Model Based on Deep Learning

At present, deep learning has been widely used many fields, but the research on text classification is still relatively few. This paper makes full use of the good learning characteristics of deep learning, proposes a hybrid model based on deep learning, and designs a text classifier based on the hybrid model. This hybrid model uses two common deep learning models, sparse automatic encoder and deep confidence network, to mix. The hybrid model is mainly composed of three parts, the first two layers are constructed by sparse automatic encoder, the middle layer is a three-layer depth Convolutional Neural Network (CNN), and finally Softmax regression is used as the classification layer. In order to test the classification performance of the classifier based on deep learning hybrid model, relevant experiments were conducted on English data set 20Newsgroup and Chinese data set Fudan University Chinese Corpus. In the English text classification experiment, the classifier based on deep learning hybrid model is used to classify, and a high classification accuracy rate is obtained. In order to further verify the superiority of its performance, a comparative experiment with naive Bayes classifier, K-Nearest Neighbor (KNN) classifier and Support Vector Machine (SVM) classifier demonstrates that the classification effect of the classifier based on deep learning hybrid model is better than that of naive Bayes classifier, KNN classifier and support vector machine classifier. In the experiment of Chinese text classification, the Chinese corpus of Fudan University is tested, and a good classification effect is obtained. The influence of different parameter settings on the classification accuracy is discussed.

A Method on Classification and Recognition of Noisy Plant Images Based on Visual Domain Perception

At present, some achievements have been made in the research of plant leaf classification such as the introduction of artificial intelligence algorithm. But there are still some problems. First, the existing achievements do not consider the subjective perception mechanism and role of human visual system in leaf classification data labels. Second, the implementation of the deep learning algorithm completely depends on the computing power level of the high-cost machine hardware and the large-scale image database. Finally, these research results rarely consider the noise pollution of leaf image samples. In order to solve the above problems, the paper fully considered the subjective perception principle and characteristics of human vision system (HVS), and proposed a lightweight classification method of noisy plant leaves (LCM-NPLs) based on visual domain perception. First, the most suitable HVS front-end perception characteristics were applied to the physical visual processing of leaves. Then the plant leaves were denoised through the information processing mechanism of HVS back-end. The visual effect of regular and orderly plant leaves is obtained. Finally, the classification is realized by principal component analysis (PCA) and third-order nearest neighbor algorithm. The results of ablation contrast experiments show that the classification accuracy of the method in this paper is 82.50% for plant leaves in the presence of serious noise interference with PSNR of 10.2421, more than 90% for plant leaves with general noise pollution transmission with PSNR of more than 15.3759, and 98.33% for plant leaves of light pollution with PSNR of 20.5659. The proposed method has achieved very good results. The proposed method can not only accurately classify plant leaves in different growth periods, but also maintain a high classification accuracy rate in the presence of serious noise interference.

Use of Machine Learning Techniques in Soil Classification

In the design of reliable structures, the soil classification process is the first step, which involves costly and time-consuming work including laboratory tests. Machine learning (ML), which has wide use in many scientific fields, can be utilized for facilitating soil classification. This study aims to provide a concrete example of the use of ML for soil classification. The dataset of the study comprises 805 soil samples based on the soil drillings of the new Gayrettepe–Istanbul Airport metro line construction. The dataset has both missing data and class imbalance. In the data preprocessing stage, first, data imputation techniques were applied to deal with the missing data. Two different imputation techniques were tested, and finally, the data were imputed with the KNN imputer. Later, a balance was achieved with the synthetic minority oversampling technique (SMOTE). After the preprocessing, a series of ML algorithms were tested with 10-fold cross-validation. Unlike the studies conducted in previous research, new gradient-boosting methods such as XGBoost, LightGBM, and CatBoost were tested, high classification accuracy rates of up to +90% were observed, and a significant improvement in the accuracy of prediction (when compared with previous research) was achieved.

Dual Residual Denoising Autoencoder with Channel Attention Mechanism for Modulation of Signals

Aiming to address the problems of the high bit error rate (BER) of demodulation or low classification accuracy of modulation signals with a low signal-to-noise ratio (SNR), we propose a double-residual denoising autoencoder method with a channel attention mechanism, referred to as DRdA-CA, to improve the SNR of modulation signals. The proposed DRdA-CA consists of an encoding module and a decoding module. A squeeze-and-excitation (SE) ResNet module containing one residual connection is modified and then introduced into the autoencoder as the channel attention mechanism, to better extract the characteristics of the modulation signals and reduce the computational complexity of the model. Moreover, the other residual connection is further added inside the encoding and decoding modules to optimize the network degradation problem, which is beneficial for fully exploiting the multi-level features of modulation signals and improving the reconstruction quality of the signal. The ablation experiments prove that both the improved SE module and dual residual connections in the proposed method play an important role in improving the denoising performance. The subsequent experimental results show that the proposed DRdA-CA significantly improves the SNR values of eight modulation types in the range of -12 dB to 8 dB. Especially for 16QAM and 64QAM, the SNR is improved by 8.38 dB and 8.27 dB on average, respectively. Compared to the DnCNN denoising method, the proposed DRdA-CA makes the average classification accuracy increase by 67.59∼74.94% over the entire SNR range. When it comes to the demodulation, compared with the RLS and the DnCNN denoising algorithms, the proposed denoising method reduces the BER of 16QAM by an average of 63.5% and 40.5%, and reduces the BER of 64QAM by an average of 46.7% and 18.6%. The above results show that the proposed DRdA-CA achieves the optimal noise reduction effect.

Multifactor Authentication System Using Simplified EEG Brain–Computer Interface

This article proposes a scheme for multifactor authentication based on electroencephalography (EEG) signal analysis. A solution for EEG signal acquisition and recording of acquisition results has been implemented, a machine learning model has been developed and trained, then a classifier that determines the user's login procedure familiarity has been built, and a solution to carry out the described experiments has been implemented, in the form of a mobile application. Besides, a multifactor authentication system, based on the EEG signal combined with user image verification, using the brain–computer interface system with a single EEG electrode based on the NeuroSky MindWave device was proposed. Based on the defined scenarios, experiments were conducted, followed by a survey on the research group, and the obtained results were analyzed. In the case of an experiment related to login simulation, a high classification accuracy rate was obtained, both for the classifier itself (83.33%) and the proposed user authentication system (77.78%). Analyzing the results of the EEG signal recording used in the classification, it seems that the proposed solution is promising not only due to the high accuracy and a low false rejections rate but also through confirmed associations in the analysis of brain wave signal, corresponding to the results of research in the literature. A proposed multi-factor authentication system based on image selection and EEG analysis can be implemented in many areas as a modern solution in securing IT systems.

BMPA-TVSinV: A Binary Marine Predators Algorithm using time-varying sine and V-shaped transfer functions for wrapper-based feature selection

The feature selection problem is one of the pre-processing mechanisms to find the optimal subset of features from a dataset. The search space of the problem will exponentially grow when the number of features increases. Hence, the feature selection problem is classified as an NP-hard problem, and exact algorithms cannot find the optimal subset at a reasonable time. As a result, approximate algorithms like meta-heuristic algorithms are extensively applied to solve the problem. The feature selection problem is a discrete (binary) optimization problem; consequently, a discrete meta-algorithm can be employed to find the optimal subset of features. One of the recently introduced meta-heuristic algorithms is Marine Predator Algorithm (MPA), which has shown good solutions to many continuous optimization problems. In this study, a novel Binary Marine Predator Algorithm using Time-Varying Sine and V-shaped transfer functions (BMPA-TVSinV) is proposed to find the optimal subset of features in datasets. The proposed algorithm applies two new time-varying transfer functions to convert the continuous search space to the binary one. These transfer functions considerably improve the performance of BMPA-TVSinV. Several well-known datasets with high-dimensional features and three coronavirus disease (COVID-19) datasets have been selected to compare the results of BMPA-TVSinV with some recently introduced binary meta-heuristic algorithms for the feature selection problem. The results show the superiority of BMPA-TVSinV in achieving high classification accuracy and feature reduction rate. The source code of BMPA-TVSinV for feature selection problem is publicly available at https://www.mathworks.com/matlabcentral/fileexchange/115315-bmpa-tvsinv-a-binary-metaheuristic-for-feature-selection.

An effective detection method for wheat mold based on ultra weak luminescence

It is widely known that mold is one of important indices in assessing the quality of stored wheat. First, mold will decrease the quality of wheat kernels; the wheat kernels infected by mold can produce secondary metabolites, such as aflatoxins, ochratoxin A, zearalenone, fumonisins and so on. Second, the mycotoxins metabolized by mycetes are extremely harmful to humans; once the food or feed is made of by those wheat kernels infected by mold, it will cause serious health problems on human beings as well as animals. Therefore, the effective and accurate detection of wheat mold is vitally important to evaluate the storage and subsequent processing quality of wheat kernels. However, traditional methods for detecting wheat mold mainly rely on biochemical methods, which always involve complex and long pretreatment processes, and waste part of wheat samples for each detection. In view of this, this paper proposes a type of eco-friendly and nondestructive wheat mold detection method based on ultra weak luminescence. The specific implementation process is as follows: firstly, ultra weak luminescence signals of the healthy and the moldy wheat subsamples are measured by a photon analyzer; secondly, the approximate entropy and multiscale approximate entropy are introduced as the main classification features separately; finally, the detection model has been established based on the support vector machine in order to classify two types of wheat subsamples. The receiver operating characteristic curve of the newly established detection model shows that the highest classification accuracy rate can reach 93.1%, which illustrates that our proposed detection model is feasible and promising for detecting wheat mold.

Automatic Events Recognition in Low SNR Microseismic Signals of Coal Mine Based on Wavelet Scattering Transform and SVM

The technology of microseismic monitoring, the first step of which is event recognition, provides an effective method for giving early warning of dynamic disasters in coal mines, especially mining water hazards, while signals with a low signal-to-noise ratio (SNR) usually cannot be recognized effectively by systematic methods. This paper proposes a wavelet scattering decomposition (WSD) transform and support vector machine (SVM) algorithm for discriminating events of microseismic signals with a low SNR. Firstly, a method of signal feature extraction based on WSD transform is presented by studying the matrix constructed by the scattering decomposition coefficients. Secondly, the microseismic events intelligent recognition model built by operating a WSD coefficients calculation for the acquired raw vibration signals, shaping a feature vector matrix of them, is outlined. Finally, a comparative analysis of the microseismic events and noise signals in the experiment verifies that the discriminative features of the two can accurately be expressed by using wavelet scattering coefficients. The artificial intelligence recognition model developed based on both SVM and WSD not only provides a fast method with a high classification accuracy rate, but it also fits the online feature extraction of microseismic monitoring signals. We establish that the proposed method improves the efficiency and the accuracy of microseismic signals processing for monitoring rock instability and seismicity.

Identifying gene expression-based biomarkers in online learning environments.

Gene expression-based classifiers are often developed using historical data by training a model on a small set of patients and a large set of features. Models trained in such a way can be afterwards applied for predicting the output for new unseen patient data. However, very often the accuracy of these models starts to decrease as soon as new data is fed into the trained model. This problem, known as concept drift, complicates the task of learning efficient biomarkers from data and requires special approaches, different from commonly used data mining techniques. Here, we propose an online ensemble learning method to continually validate and adjust gene expression-based biomarker panels over increasing volume of data. We also propose a computational solution to the problem of feature drift where gene expression signatures used to train the classifier become less relevant over time. A benchmark study was conducted to classify the breast tumors into known subtypes by using a large-scale transcriptomic dataset (∼3500 patients), which was obtained by combining two datasets: SCAN-B and TCGA-BRCA. Remarkably, the proposed strategy improves the classification performances of gold-standard biomarker panels (e.g. PAM50, OncotypeDX and Endopredict) by adding features that are clinically relevant. Moreover, test results show that newly discovered biomarker models can retain a high classification accuracy rate when changing the source generating the gene expression profiles. github.com/UEFBiomedicalInformaticsLab/OnlineLearningBD. Supplementary data are available at Bioinformatics Advances online.

The research of EEG feature extraction and classification for subjects with different organizational commitment

With the development of EEG analysis technology, researchers have gradually explored the correlation between personality trait (such as Big Five personality) and EEG. However, there are still many challenges in model construction. In this paper, we tried to classify the people with different organizational commitment personality trait through EEG. Firstly, we organized the participants to complete the organizational commitment questionnaire and recorded their resting state EEG. We divided 10 subjects into two classes (positive and negative) according to the questionnaire scores. Then, various EEG features including power spectral density, microstate, functional brain network and nonlinear features from segmented EEG sample were extracted as the input of different machine learning classifiers. Next, several evaluation metrics were used to evaluate the results of the cross-validation experiment. Finally, the results show that the EEG power in α band, the weighted clustering coefficient of functional brain network and the Permutation Entropy of EEG are relatively good features for this classification task. Furthermore, the highest classification accuracy rate can reach 79.9% with 0.87 AUC (the area under the ROC). The attempts in this paper may serve as the basis for our future research.

Investigating the Performance of Wearable Motion Sensors on recognizing falls and daily activities via machine learning

With sensor-based wearable technologies, high precision monitoring and recognition of human physical activities in real time is becoming more critical to support the daily living requirements of the elderly. The use of sensor technologies, including accelerometers (A), gyroscopes (G), and magnetometers (M) is mostly encountered in work focused on assistive technology, ambient intelligence, context-aware systems, gait and motion analysis, sports science, and fall detection. The classification performance of four sensor type combinations is investigated through the use of four machine learning algorithms: support vector machines (SVMs), Manhattan k-nearest neighbor classifier (M.k-NN), subspace linear discriminant analysis (SLDA), and ensemble bagged decision tree (EBDT). In this context, a large dataset containing 2520 tests performed by 14 volunteers containing 16 activities of daily living (ADLs) and 20 falls was employed. In binary (fall vs. ADL) and multi-class activity (36 activities) recognition, the highest classification accuracy rate was obtained by the SVM (99.96%) and M.k-NN (95.27%) classifiers, respectively, with the AM sensor type combination in both cases. We also made our dataset publicly available to lay the groundwork for new research.

Application and comparison of deep learning approaches for upper limb functionality evaluation based on multi-modal inertial data

Nowadays, stroke survivors usually can regain their limb function through rehabilitation training prescribed by physicians. With the development of technologies such as the Internet of Things, artificial intelligence and the rapid increase in research in the field of digital health, a growing number of cutting-edge research focuses on sustaining medical services with digital technologies. In addition, some new approaches have been widely taken in rehabilitation. In the process of upper limb rehabilitation training for stroke survivors, this paper collects a series of inertial sensing time series data through the data collection mechanism. This paper utilizes Dynamic Time Warping-K-NearestNeighbor (DTW-KNN), Long Short-Term Memory (LSTM) neural network and Gated Recurrent Unit (GRU) neural network to process and analyze the time series data of rehabilitation actions, and finally realize the classification and evaluation of different completion situations of various upper limb rehabilitation actions. The experimental results show that the classification accuracy of DTW-KNN under different completion situations of the three upper limb rehabilitation actions are 72.2%, 47.2%, and 69.4%, respectively, while the corresponding classification accuracy of LSTM is 97.2%, 94.4% and 91.7%. LSTM also has significant advantages over DTW-KNN in terms of classification time. In addition, GRU not only has a high classification accuracy rate similar to LSTM, but also has a slight advantage over LSTM in classification time.