Neural Network Based Classification Model Research Articles

Low-power adaptive sampling electronic nose system with a Radon transform-based convolutional neural network for optimized gas recognition

The electronic nose (E-nose) systems provide great promise in capturing information about the identity of gaseous chemical analytes as well as their temporal variation. However, the regular and dense sampling events of the E-nose often lead to a substantial amount of redundancy in the temporal structure, which in turn limits their application in efficiency-sensitive scenarios such as advanced robotics and the Internet of Things. Herein, we introduce a novel operating mechanism for E-noses, which dynamically adjusts the time interval of operation to reduce power consumption and information content through an adaptive sampling mechanism. Three strategic schemes with different operating principles are presented to implement this mechanism: the accurate scheme targets the optimized discrimination accuracy, the vague scheme is oriented toward power-sensitive scenarios, and the balanced scheme aims to balance cost and benefit. In order to ensure that the adaptively sampled inhomogeneous data can be compatible with each other, we further propose an algorithm based on the Radon transform that can convert non-uniform time series with timestamp information into the same size tensor. Finally, we designed a convolutional neural network-based classification model for gaseous chemical analytes, providing guidance on scheme and parameter selection with an accuracy of up to 99 % and power savings of up to 96 %. Overall, this work provides a novel solution to optimize temporal redundancy in E-nose systems and a generalized approach to the corresponding deep-learning data processing.

Distinguishing methicillin-resistant Staphylococcus aureus from methicillin-sensitive strains by combining Fe3O4 magnetic nanoparticle-based affinity mass spectrometry with a machine learning strategy

Pathogenic bacteria, including drug-resistant variants such as methicillin-resistant Staphylococcus aureus (MRSA), can cause severe infections in the human body. Early detection of MRSA is essential for clinical diagnosis and proper treatment, considering the distinct therapeutic strategies for methicillin-sensitive S. aureus (MSSA) and MRSA infections. However, the similarities between MRSA and MSSA properties present a challenge in promptly and accurately distinguishing between them. This work introduces an approach to differentiate MRSA from MSSA utilizing matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS) in conjunction with a neural network-based classification model. Four distinct strains of S. aureus were utilized, comprising three MSSA strains and one MRSA strain. The classification accuracy of our model ranges from ~ 92 to ~ 97% for each strain. We used deep SHapley Additive exPlanations to reveal the unique feature peaks for each bacterial strain. Furthermore, Fe3O4 MNPs were used as affinity probes for sample enrichment to eliminate the overnight culture and reduce the time in sample preparation. The limit of detection of the MNP-based affinity approach toward S. aureus combined with our machine learning strategy was as low as ~ 8 × 103 CFU mL−1. The feasibility of using the current approach for the identification of S. aureus in juice samples was also demonstrated.Graphical

A prognostic model and pre-discharge predictors of post-COVID-19 syndrome after hospitalization for SARS-CoV-2 infection.

Post-COVID-19 syndrome (PCS) has been increasingly recognized as an emerging problem: 50% of patients report ongoing symptoms 1 year after acute infection, with most typical manifestations (fatigue, dyspnea, psychiatric and neurological symptoms) having potentially debilitating effect. Early identification of high-risk candidates for PCS development would facilitate the optimal use of resources directed to rehabilitation of COVID-19 convalescents. To study the in-hospital clinical characteristics of COVID-19 survivors presenting with self-reported PCS at 3 months and to identify the early predictors of its development. 221 hospitalized COVID-19 patients underwent symptoms assessment, 6-min walk test, and echocardiography pre-discharge and at 1 month; presence of PCS was assessed 3 months after discharge. Unsupervised machine learning was used to build a SANN-based binary classification model of PCS development. PCS at 3 months has been detected in 75% patients. Higher symptoms level in the PCS group was not associated with worse physical functional recovery or significant echocardiographic changes. Despite identification of a set of pre-discharge predictors, inclusion of parameters obtained at 1 month proved necessary to obtain a high accuracy model of PCS development, with inputs list including age, sex, in-hospital levels of CRP, eGFR and need for oxygen supplementation, and level of post-exertional symptoms at 1 month after discharge (fatigue and dyspnea in 6MWT and MRC Dyspnea score). Hospitalized COVID-19 survivors at 3 months were characterized by 75% prevalence of PCS, the development of which could be predicted with an 89% accuracy using the derived neural network-based classification model.

Potential cyber threats of adversarial attacks on autonomous driving models

Autonomous Vehicles (CAVs) are currently seen as a viable alternative to traditional vehicles. However, CAVs will face serious cyber threats because many components of the driving system are based on machine learning models and are vulnerable to adversary attacks. We have reviewed the scientific literature and highlighted the main types of disruptive attacks on autonomous driving models that pose potential threats to CAVs. In this paper, we have compiled a dataset with traffic sign images obtained from public sources. We made experiments in which we distorted the original images and used them to train deep neural network-based classification models. The experiments demonstrated a possible threat to traffic sign recognition by autonomous vehicles. This work can give researchers and engineers a better understanding of the current state and trends in CAV security for their future use.

1D-CNN 기반 LIB 상태 진단 시스템 개발

LIB (Lithium Ion Battery) has been widely utilized in various fields due to its high energy density and long usage cycle, and is particularly actively applied as a power source for unmanned vehicles. LIBs deteriorate with repeated charge/discharge cycles, reducing usable capacity, and the LIB’s power performance is determined by the available capacity. Therefore, in order to smoothly supply power to unmanned vehicles, LIBs with guaranteed available capacity must be used. In this paper, we propose a learning-based LIB status diagnosis system to effectively determine the available capacity of LIB. The proposed system is constructed using a convolutional neural network-based classification model, extracts and synthesizes features from diagnostic data, and outputs LIB status diagnosis results. The state of the LIB is defined as three states depending on the operating conditions of the vehicle and the available capacity of the LIB, and diagnostic data is generated based on the time-series discharge data to effectively reflect the deterioration characteristics of the LIB. To verify the performance of the proposed state diagnosis system, model training and verification are conducted using random discharge data and confusion matrix, and the results are analyzed.

Classification of Monkeypox Images Using LIME-Enabled Investigation of Deep Convolutional Neural Network.

In this research, we demonstrate a Deep Convolutional Neural Network-based classification model for the detection of monkeypox. Monkeypox can be difficult to diagnose clinically in its early stages since it resembles both chickenpox and measles in symptoms. The early diagnosis of monkeypox helps doctors cure it more quickly. Therefore, pre-trained models are frequently used in the diagnosis of monkeypox, because the manual analysis of a large number of images is labor-intensive and prone to inaccuracy. Therefore, finding the monkeypox virus requires an automated process. The large layer count of convolutional neural network (CNN) architectures enables them to successfully conceptualize the features on their own, thereby contributing to better performance in image classification. The scientific community has recently articulated significant attention in employing artificial intelligence (AI) to diagnose monkeypox from digital skin images due primarily to AI's success in COVID-19 identification. The VGG16, VGG19, ResNet50, ResNet101, DenseNet201, and AlexNet models were used in our proposed method to classify patients with monkeypox symptoms with other diseases of a similar kind (chickenpox, measles, and normal). The majority of images in our research are collected from publicly available datasets. This study suggests an adaptive k-means clustering image segmentation technique that delivers precise segmentation results with straightforward operation. Our preliminary computational findings reveal that the proposed model could accurately detect patients with monkeypox. The best overall accuracy achieved by ResNet101 is 94.25%, with an AUC of 98.59%. Additionally, we describe the categorization of our model utilizing feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which provides a more in-depth understanding of particular properties that distinguish the monkeypox virus.

Convolutional Neural Network-Based Classification Model of Corn Leaf Disease

The decline in corn production can affect the continuity of food grown in society, especially in Indonesia, which is a country with a high level of corn consumers. Several factors cause a decrease in the production of corn plants, one of which is unhealthy plants so that their growth slows down and even makes the corn plants not bear fruit or are damaged. Therefore, a system is needed that can identify diseases in corn plants so that appropriate treatment can be carried out as early as possible to prevent severe damage to corn plants. With this research, the system can be built by utilizing machine learning in building a classification system using the Convolutional Neural Network (CNN) algorithm with a dataset of corn leaf images taken from farmers' fields in the Madura Region with four target classes namely healthy, gray leaf spot, blight, and common rust. Testing was carried out using several CNN architectural models such as SqueezeNet, AlexNet, ResNet-101, ResNet-50, and ResNet-18. The parameters used were 5 epochs with 100 iterations, a learning rate of 0.0001, using Adam optimization, and a data distribution of 70% for training data and 30% for testing data. The test results obtained in classifying corn images using the Convolutional Neural Network method with the ResNet-50 architecture provide a very good accuracy value of 95.59%.

Embeddings for Automatic Short Answer Grading: A Scoping Review

Automatic grading of short answers is an important task in computer-assisted assessment (CAA). Recently, embeddings, as semantic-rich textual representations, have been increasingly used to represent short answers and predict the grade. Despite the recent trend of applying embeddings in automatic short answer grading (ASAG), there are no systematic reviews of literature reporting on their usage. Therefore, following the PRISMA-ScR guidelines, this scoping review summarises relevant literature on the use of embeddings in ASAG, and reports on the current state of the art in that research area and on the identified knowledge gaps. We searched seven research databases for the relevant journal, conference, and workshop papers published from 2016 to July 2021. The inclusion criteria were based on the type of publication, its venue ranking, study focus, and evaluation methods. Upon the full-text screening, 17 articles were included in the scoping review. Among these, most of the articles used word embeddings, mainly to estimate the similarity of student and model answers using the cosine similarity measure or to initialise a neural network-based classification model. The contribution of embeddings to the performance of ASAG models compared to non-embedding features is inconclusive. Models employing embeddings were mostly evaluated on four public ASAG datasets using earlier ASAG methods as baselines. We summarise the reported evaluation results and draw conclusions on the performance of the state-of-the-art ASAG models.

Biomedical Text Classification Using Augmented Word Representation Based on Distributional and Relational Contexts.

Due to the increasing use of information technologies by biomedical experts, researchers, public health agencies, and healthcare professionals, a large number of scientific literatures, clinical notes, and other structured and unstructured text resources are rapidly increasing and being stored in various data sources like PubMed. These massive text resources can be leveraged to extract valuable knowledge and insights using machine learning techniques. Recent advancement in neural network-based classification models has gained popularity which takes numeric vectors (aka word representation) of training data as the input to train classification models. Better the input vectors, more accurate would be the classification. Word representations are learned as the distribution of words in an embedding space, wherein each word has its vector and the semantically similar words based on the contexts appear nearby each other. However, such distributional word representations are incapable of encapsulating relational semantics between distant words. In the biomedical domain, relation mining is a well-studied problem which aims to extract relational words, which associates distant entities generally representing the subject and object of a sentence. Our goal is to capture the relational semantics information between distant words from a large corpus to learn enhanced word representation and employ the learned word representation for various natural language processing tasks such as text classification. In this article, we have proposed an application of biomedical relation triplets to learn word representation through incorporating relational semantic information within the distributional representation of words. In other words, the proposed approach aims to capture both distributional and relational contexts of the words to learn their numeric vectors from text corpus. We have also proposed an application of the learned word representations for text classification. The proposed approach is evaluated over multiple benchmark datasets, and the efficacy of the learned word representations is tested in terms of word similarity and concept categorization tasks. Our proposed approach provides better performance in comparison to the state-of-the-art GloVe model. Furthermore, we have applied the learned word representations to classify biomedical texts using four neural network-based classification models, and the classification accuracy further confirms the effectiveness of the learned word representations by our proposed approach.

Time Series Artificial Neural Network based Classification Model for Asset Trading Strategy

Best daily trading strategy is meaningful to investors to obtain the maximum return. Financial market plays a key role in the social development. Sufficient funds are of great significance to promote the development of all sectors of society. From the perspective of investors, their purpose is to obtain the maximum income through investing assets in the market. At the same time, the benefit of investors can attract more investors and funds. However, there are huge risks in investment in financial markets. This is mainly because the changes of assets' prices are very complex, and traders cannot predict the changes of assets' prices. Therefore, it is of great significance for investors to determine the trading behavior according to the historical data of asset's price. Aiming at the problem of asset investment strategy, we study from three aspects: asset value accounting, optimal investment strategy and investment decision prediction. A novel method is proposed to represent trading action based on asset state, which represents the current asset state through a 0-1 variable. Then, the change of state indicates the occurrence of transaction. Based on this variable, we propose an evaluation model of the total value of the asset on every day. By maximizing the value of the combination, we establish an optimization model and the Genetic Algorithm (GA) is used to search the best investment combination. Using the prior information of the price, we first solve the combination of asset states of the investor corresponding to the best trading strategy. Then, taking the sequence of states as the supervision information, an Artificial Neural Network (ANN) based classification model for asset state prediction is established. The historical data of Bitcoin daily price is used to predict the asset state on the current day, to realize the decision-making of daily trading strategy. Extensive experiments have been conducted, and the experimental results verify our model can effectively find potential pattern for asset investment and achieve good profits based on the predict investment decisions.

A Novel Affective Analysis System Modeling Method Integrating Affective Cognitive Model and Bi-LSTM Neural Network.

The severity of mental health issues among college students has increased over the past few years, having a significant negative impact on not only their academic performance but also on their families and even society as a whole. Therefore, one of the pressing issues facing college administrators right now is finding a method that is both scientific and useful for determining the mental health of college students. In pace with the advancement of Internet technology, the Internet has become an important communication channel for contemporary college students. As one of the main forces in the huge Internet population, college students are at the stage of growing knowledge and being most enthusiastic about new things, and they like to express their opinions and views on study life and social issues and are brave to express their emotions. These subjective text data often contain some affective tendencies and psychological characteristics of college students, and it is beneficial to dig out their affective tendencies to further understand what they think and expect and to grasp their mental health as early as possible. In order to address the issue of assessing the mental health of college students, this study makes an effort to use public opinion data from the university network and suggests a college student sentiment analysis model based on the OCC affective cognitive model and Bi-LSTM neural network. In order to label three different types of positive, negative, and neutral sentiment on the microblog text of college network public opinion, we first design a sentiment rule system based on the OCC affective cognition elicitation mechanism. In order to effectively and automatically identify the sentiment state of college students in the network public opinion, this study uses a Bi-LSTM neural network to classify the preprocessed college network public opinion data. Finally, this study performs comparison experiments to confirm the validity of the Bi-LSTM neural network sentiment recognition algorithm and the accuracy of the OCC sentiment rule labeling system. The findings show that the college student sentiment recognition effect of the model is significantly enhanced when the OCC sentiment rule system is used to label the college network public opinion data set as opposed to the naturally labeled data set. In contrast to SVM and other classification models like CNN and LSTM, the Bi-LSTM neural network-based classification model achieves more satisfactory classification results in the recognition of college opinion sentiment.

Electrocardiogram signal classification using VGGNet: a neural network based classification model

Electrocardiogram signal classification using VGGNet: a neural network based classification model

On the reliability of deep learning-based classification for Alzheimer's disease: Multi-cohorts, multi-vendors, multi-protocols, and head-to-head validation.

Structural changes in the brain due to Alzheimer’s disease dementia (ADD) can be observed through brain T1-weighted magnetic resonance imaging (MRI) images. Many ADD diagnostic studies using brain MRI images have been conducted with machine-learning and deep-learning models. Although reliability is a key in clinical application and applicability of low-resolution MRI (LRMRI) is a key to broad clinical application, both are not sufficiently studied in the deep-learning area. In this study, we developed a 2-dimensional convolutional neural network-based classification model by adopting several methods, such as using instance normalization layer, Mixup, and sharpness aware minimization. To train the model, MRI images from 2,765 cognitively normal individuals and 1,192 patients with ADD from the Samsung medical center cohort were exploited. To assess the reliability of our classification model, we designed external validation in multiple scenarios: (1) multi-cohort validation using four additional cohort datasets including more than 30 different centers in multiple countries, (2) multi-vendor validation using three different MRI vendor subgroups, (3) LRMRI image validation, and finally, (4) head-to-head validation using ten pairs of MRI images from ten individual subjects scanned in two different centers. For multi-cohort validation, we used the MRI images from 739 subjects from the Alzheimer’s Disease Neuroimaging Initiative cohort, 125 subjects from the Dementia Platform of Korea cohort, 234 subjects from the Premier cohort, and 139 subjects from the Gachon University Gil Medical Center. We further assessed classification performance across different vendors and protocols for each dataset. We achieved a mean AUC and classification accuracy of 0.9868 and 0.9482 in 5-fold cross-validation. In external validation, we obtained a comparable AUC of 0.9396 and classification accuracy of 0.8757 to other cross-validation studies in the ADNI cohorts. Furthermore, we observed the possibility of broad clinical application through LRMRI image validation by achieving a mean AUC and classification accuracy of 0.9404 and 0.8765 at cross-validation and AUC and classification accuracy of 0.8749 and 0.8281 at the ADNI cohort external validation.

Hierarchical Clustering and Deep Learning for Short-Term Load Forecasting with Influenced Factors

Stable and reliable electricity is one of the essential things that must be maintained by the transmission system operator (TSO). That can be achieved when the TSO is able to set the balance between demand and production. To maintain the balance between production and demand, TSO should estimate how much demand must be served. In order to do that, the next day short-term load forecasting is an essential step that TSO should be done. Generally, load forecasting can be done through conventional techniques such as least square, time series, etc. However, this method has been sought over time as the electricity demand is increasing significantly over the years. Hence, this paper proposed another approach for short-term load forecasting using Deep Neural Networks, widely known as Long Short-Term Memory (LSTM). In addition, this paper clusters historical electrical loads to obtain similar patterns into several clusters before forecasting. We also explored other influence factors in the observed days, such as weather conditions and the human activity cycle represented by holidays, in a neural network-based classification model to predict the targeted clusters of electrical loads. East Java sub-system is used as the test system to investigate the efficacy of the proposed load forecasting method. From the simulation results, it is found that the proposed method could provide a better forecast on all indicators compared to the conventional method, as indicated by MaxAPE and MAPE are around 4,91% and 2,02%, while the RMSE is 112,08 MW. 

A classification model based on depthwise separable convolutional neural network to identify rice plant diseases

<p><span>Every year a number of rice diseases cause major damage to crop around the world. Early and accurate prediction of various rice plant diseases has been a major challenge for farmers and researchers. Recent developments in the convolutional neural networks (CNNs) have made image processing techniques more convenient and precise. Motivated from that in this research, a depthwise separable convolutional neural network based classification model has been proposed for identifying 12 types of rice plant diseases. Also, 8 different state-of-the-art convolution neural network model has been fine-tuned specifically for identifying the rice plant diseases and their performance has been evaluated. The proposed model performs considerably well in contrast to existing state-of-the-art CNN architectures. The experimental analysis indicates that the proposed model can correctly diagnose rice plant diseases with a validation and testing accuracy of 96.5% and 95.3% respectively while having a substantially smaller model size.</span></p>

A deep learning approach for classification and diagnosis of Parkinson’s disease

Deep learning grabs a center attraction in industries, deep learning techniques are having great potential and recently these potentials are applied to healthcare problems, including computer-aided detection/diagnosis, disease prediction. Deep learning techniques are playing an important role in the classification and prediction of the diseases. The popularity of deep learning approaches is because of their ability to handle a large amount of data related to the patients with accuracy, reliability in a short span of time. However, the practitioners may take time in analyzing and generating the reports. In this paper, we have proposed a Deep Neural Network-based classification model for the classification of Parkinson’s disease. Our proposed method is one such good example giving faster and more accurate results for the classification of Parkinson’s disease patients with excellent accuracy of 94.87%. We have also compared the results with other existing approaches like linear discriminant analysis, support vector machine, K-nearest neighbor, decision tree, classification and regression trees, random forest, linear regression, logistic regression, multi-layer perceptron, and Naive Bayes.

A Semi-supervised Deep Learning Method for Cervical Cell Classification.

Currently, the Thinprep cytologic test (TCT) is the most popular cervical cancer cytology test technique. It can detect precancerous conditions and microbial infections. However, this technique entirely relies on manual operation and doctors' naked eye observation, resulting in a heavy workload and low accuracy rate. Recently, automatic pathological diagnosis has been developed to solve this problem. Cervical cell classification is a key technology in the intelligent cervical cancer diagnosis system. Training a deep neural network-based classification model requires a large amount of data. However, cervical cell labeling requires specialized physicians and the cost of labeling is high, resulting in a lack of sufficient labeling data in this field. To address this problem, we propose a method to ensure high accuracy in cervical cell classification with a small amount of labeled data by introducing manual features and a voting mechanism to achieve data expansion in semi-supervised learning. The method consists of three main steps, using a clarity function to filter out high-quality cervical cell images, annotating a small amount of them, and balancing the training data using a voting mechanism. With a small amount of labeled data, the accuracy of the proposed method in this paper can reach to 91.94%.

Highly imbalanced fault diagnosis of mechanical systems based on wavelet packet distortion and convolutional neural networks

The healthy operations of mechanical systems are crucially important for ensuring human safety and economic benefits, so that there is a high demand on the automatic fault diagnosis techniques. However, the number of available faulty samples of mechanical systems is often far less than healthy samples, and thereby the traditional data-driven methods often suffer a high rate of misdiagnosis. In this paper, a new fault diagnosis method is developed on the basis of wavelet packet distortion and convolutional neural networks. First, wavelet packet distortion means that wavelet packet coefficients are distorted to augment fault samples, in order to achieve the equilibrium between healthy and faulty classes. Second, a convolutional neural network-based classification model is trained using the balanced training dataset. Third, the trained model is applied to classify the testing samples. Finally, the efficacy of this developed method in imbalanced fault diagnosis of mechanical systems is demonstrated through a number of experiments.

Deep Learning-Based Detection of Epileptiform Discharges for Self-Limited Epilepsy With Centrotemporal Spikes.

Centrotemporal spike-waves (CTSWs) are typical interictal epileptiform discharges (IEDs) observed in centrotemporal regions in self-limited epilepsy with centrotemporal spikes (SLECTS). This study aims to develop a deep learning-based approach for automated detection of CTSWs in scalp electroencephalography (EEG) recordings of patients with SLECTS. To lower the substantial burden of IED annotation on clinicians, we simplified it by limiting IEDs to CTSWs because electroencephalographic patterns of CTSWs are known to be highly consistent. Two neurologists annotated 1672 CTSWs of 20 patients with SLECTS. Thereafter, we performed a two-level CTSW detection procedure: epoch-level and EEG-level. In the epoch-level detection, we constructed convolutional neural network-based classification models for CTSW and non-CTSW binary classification using the recordings of 20 patients and 20 controls. We then set the thresholds of the classification models for 100% specificity. In the EEG-level detection, we applied the threshold-adjusted classification models to the recordings of 50 patients and 50 controls that were not used in the epoch-level detection to distinguish between CTSW-positive (with one or more CTSWs) and CTSW-negative (with no CTSW) recordings based on the detection of CTSW presence. We obtained an average sensitivity, specificity, and accuracy of 99.8%, 98.4%, and 99.1%, respectively, with an average false detection rate of 0.19/hr for the controls. Our approach showed high detectability for CTSWs despite the simplified annotation process. We expect that the proposed CTSW detectors have potential clinical usefulness for efficiently reading EEGs and diagnosing SLECTS, and can significantly reduce the burden of IED annotation on clinicians.

Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network.

Recently, the estimation of bone maturation using deep learning has been actively conducted. However, many studies have considered hand–wrist radiographs, while a few studies have focused on estimating cervical vertebral maturation (CVM) using lateral cephalograms. This study proposes the use of deep learning models for estimating CVM from lateral cephalograms. As the second, third, and fourth cervical vertebral regions (denoted as C2, C3, and C4, respectively) are considerably smaller than the whole image, we propose a stepwise segmentation-based model that focuses on the C2–C4 regions. We propose three convolutional neural network-based classification models: a one-step model with only CVM classification, a two-step model with region of interest (ROI) detection and CVM classification, and a three-step model with ROI detection, cervical segmentation, and CVM classification. Our dataset contains 600 lateral cephalogram images, comprising six classes with 100 images each. The three-step segmentation-based model produced the best accuracy (62.5%) compared to the models that were not segmentation-based.