MyMedR

Displaying publications 21 - 40 of 419 in total

Abstract:

Sort:

Fulltext Sign language recognition using the fusion of image and hand landmarks through multi-headed convolutional neural network

Pathan RK, Biswas M, Yasmin S, Khandaker MU, Salman M, Youssef AAF

Sci Rep, 2023 Oct 09;13(1):16975.
PMID: 37813932 DOI: 10.1038/s41598-023-43852-x

Sign Language Recognition is a breakthrough for communication among deaf-mute society and has been a critical research topic for years. Although some of the previous studies have successfully recognized sign language, it requires many costly instruments including sensors, devices, and high-end processing power. However, such drawbacks can be easily overcome by employing artificial intelligence-based techniques. Since, in this modern era of advanced mobile technology, using a camera to take video or images is much easier, this study demonstrates a cost-effective technique to detect American Sign Language (ASL) using an image dataset. Here, "Finger Spelling, A" dataset has been used, with 24 letters (except j and z as they contain motion). The main reason for using this dataset is that these images have a complex background with different environments and scene colors. Two layers of image processing have been used: in the first layer, images are processed as a whole for training, and in the second layer, the hand landmarks are extracted. A multi-headed convolutional neural network (CNN) model has been proposed and tested with 30% of the dataset to train these two layers. To avoid the overfitting problem, data augmentation and dynamic learning rate reduction have been used. With the proposed model, 98.981% test accuracy has been achieved. It is expected that this study may help to develop an efficient human-machine communication system for a deaf-mute society.
Load forecasting using combination model of multiple linear regression with neural network for Malaysian city

Nur Arina Bazilah Kamisan, Muhammad Hisyam Lee, Suhartono Suhartono, Abdul Ghapor Hussin, Yong Zulina Zubairi

Sains Malaysiana, 2018;47:419-426.

Forecasting a multiple seasonal data is differ from a usual seasonal data since it contains more than one cycle in a
data. Multiple linear regression (MLR) models have been used widely in load forecasting because of its usefulness in the
forecast a linear relationship with other factors but MLR has a disadvantage of having difficulties in modelling a nonlinear
relationship between the variables and influencing factors. Neural network (NN) model, on the other hand, is a good
model for modelling a nonlinear data. Therefore, in this study, a combination of MLR and NN models has proposed this
combination to overcome the problem. This hybrid model is then compared with MLR and NN models to see the performance
of the hybrid model. RMSE is used as a performance indicator and a proposed graphical error plot is introduce to see the
error graphically. From the result obtained this model gives a better forecast compare to the other two models.
Fulltext Automated classification of tropical shrub species: a hybrid of leaf shape and machine learning approach

Murat M, Chang SW, Abu A, Yap HJ, Yong KT

PeerJ, 2017;5:e3792.
PMID: 28924506 DOI: 10.7717/peerj.3792

Plants play a crucial role in foodstuff, medicine, industry, and environmental protection. The skill of recognising plants is very important in some applications, including conservation of endangered species and rehabilitation of lands after mining activities. However, it is a difficult task to identify plant species because it requires specialized knowledge. Developing an automated classification system for plant species is necessary and valuable since it can help specialists as well as the public in identifying plant species easily. Shape descriptors were applied on the myDAUN dataset that contains 45 tropical shrub species collected from the University of Malaya (UM), Malaysia. Based on literature review, this is the first study in the development of tropical shrub species image dataset and classification using a hybrid of leaf shape and machine learning approach. Four types of shape descriptors were used in this study namely morphological shape descriptors (MSD), Histogram of Oriented Gradients (HOG), Hu invariant moments (Hu) and Zernike moments (ZM). Single descriptor, as well as the combination of hybrid descriptors were tested and compared. The tropical shrub species are classified using six different classifiers, which are artificial neural network (ANN), random forest (RF), support vector machine (SVM), k-nearest neighbour (k-NN), linear discriminant analysis (LDA) and directed acyclic graph multiclass least squares twin support vector machine (DAG MLSTSVM). In addition, three types of feature selection methods were tested in the myDAUN dataset, Relief, Correlation-based feature selection (CFS) and Pearson's coefficient correlation (PCC). The well-known Flavia dataset and Swedish Leaf dataset were used as the validation dataset on the proposed methods. The results showed that the hybrid of all descriptors of ANN outperformed the other classifiers with an average classification accuracy of 98.23% for the myDAUN dataset, 95.25% for the Flavia dataset and 99.89% for the Swedish Leaf dataset. In addition, the Relief feature selection method achieved the highest classification accuracy of 98.13% after 80 (or 60%) of the original features were reduced, from 133 to 53 descriptors in the myDAUN dataset with the reduction in computational time. Subsequently, the hybridisation of four descriptors gave the best results compared to others. It is proven that the combination MSD and HOG were good enough for tropical shrubs species classification. Hu and ZM descriptors also improved the accuracy in tropical shrubs species classification in terms of invariant to translation, rotation and scale. ANN outperformed the others for tropical shrub species classification in this study. Feature selection methods can be used in the classification of tropical shrub species, as the comparable results could be obtained with the reduced descriptors and reduced in computational time and cost.
MSTCN: A multiscale temporal convolutional network for user independent human activity recognition

Raja Sekaran S, Pang YH, Ling GF, Yin OS

F1000Res, 2021;10:1261.
PMID: 36896393 DOI: 10.12688/f1000research.73175.1

Background: In recent years, human activity recognition (HAR) has been an active research topic due to its widespread application in various fields such as healthcare, sports, patient monitoring, etc. HAR approaches can be categorised as handcrafted feature methods (HCF) and deep learning methods (DL). HCF involves complex data pre-processing and manual feature extraction in which the models may be exposed to high bias and crucial implicit pattern loss. Hence, DL approaches are introduced due to their exceptional recognition performance. Convolutional Neural Network (CNN) extracts spatial features while preserving localisation. However, it hardly captures temporal features. Recurrent Neural Network (RNN) learns temporal features, but it is susceptible to gradient vanishing and suffers from short-term memory problems. Unlike RNN, Long-Short Term Memory network has a relatively longer-term dependency. However, it consumes higher computation and memory because it computes and stores partial results at each level. Methods: This work proposes a novel multiscale temporal convolutional network (MSTCN) based on the Inception model with a temporal convolutional architecture. Unlike HCF methods, MSTCN requires minimal pre-processing and no manual feature engineering. Further, multiple separable convolutions with different-sized kernels are used in MSTCN for multiscale feature extraction. Dilations are applied to each separable convolution to enlarge the receptive fields without increasing the model parameters. Moreover, residual connections are utilised to prevent information loss and gradient vanishing. These features enable MSTCN to possess a longer effective history while maintaining a relatively low in-network computation. Results: The performance of MSTCN is evaluated on UCI and WISDM datasets using a subject independent protocol with no overlapping subjects between the training and testing sets. MSTCN achieves accuracies of 97.42 on UCI and 96.09 on WISDM. Conclusion: The proposed MSTCN dominates the other state-of-the-art methods by acquiring high recognition accuracies without requiring any manual feature engineering.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Research on the Communication Strategy of History and Culture in Shaanxi Based on BP Neural Network Model

Xie D, Yin C

Comput Intell Neurosci, 2022;2022:8965622.
PMID: 35111216 DOI: 10.1155/2022/8965622

Shaanxi is one of China's most important cradles of civilization. The main vein of Chinese culture is rich history and culture, and brilliant red culture embodies the essence of socialist core values. It is still relatively weak to deeply analyze the related research of Shaanxi Province's cultural province construction on the basis of studying the achievements of cultural development in foreign countries and China and combining with the reality of Shaanxi Province. In this paper, a BPNN (BP neural network) model is selected to study the comprehensive evaluation of tourism competitiveness of smart tourism cities, and the software is used to realize the simulation of the comprehensive evaluation system of tourism competitiveness of smart tourism cities, which more comprehensively and objectively reflects the level of comprehensive competitiveness of each city. It is believed that there are some problems in Shaanxi regional cultural communication, such as insufficient exploration of content resources, insufficient communication channels, and low audience awareness, hoping to provide ideas and reference for further exploring the promotion of cultural communication power.

Matched MeSH terms: Neural Networks (Computer)*
Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features

Acharya UR, Raghavendra U, Koh JEW, Meiburger KM, Ciaccio EJ, Hagiwara Y, et al.

Comput Methods Programs Biomed, 2018 Nov;166:91-98.
PMID: 30415722 DOI: 10.1016/j.cmpb.2018.10.006

BACKGROUND AND OBJECTIVE: Liver fibrosis is a type of chronic liver injury that is characterized by an excessive deposition of extracellular matrix protein. Early detection of liver fibrosis may prevent further growth toward liver cirrhosis and hepatocellular carcinoma. In the past, the only method to assess liver fibrosis was through biopsy, but this examination is invasive, expensive, prone to sampling errors, and may cause complications such as bleeding. Ultrasound-based elastography is a promising tool to measure tissue elasticity in real time; however, this technology requires an upgrade of the ultrasound system and software. In this study, a novel computer-aided diagnosis tool is proposed to automatically detect and classify the various stages of liver fibrosis based upon conventional B-mode ultrasound images.
METHODS: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis.
RESULTS: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis.
CONCLUSIONS: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.
A model-based bone milling state identification method via force sensing for a robotic surgical system

Al-Abdullah KI, Lim CP, Najdovski Z, Yassin W

Int J Med Robot, 2019 Jun;15(3):e1989.
PMID: 30721570 DOI: 10.1002/rcs.1989

BACKGROUND: This paper presents a model-based bone milling state identification method that provides intraoperative bone quality information during robotic bone milling. The method helps surgeons identify bone layer transitions during bone milling.
METHODS: On the basis of a series of bone milling experiments with commercial artificial bones, an artificial neural network force model is developed to estimate the milling force of different bone densities as a function of the milling feed rate and spindle speed. The model estimations are used to identify the bone density at the cutting zone by comparing the actual milling force with the estimated one.
RESULTS: The verification experiments indicate the ability of the proposed method to distinguish between one cortical and two cancellous bone densities.
CONCLUSIONS: The significance of the proposed method is that it can be used to discriminate a set of different bone density layers for a range of the milling feed rate and spindle speed.
Fulltext In-vitro diagnosis of single and poly microbial species targeted for diabetic foot infection using e-nose technology

Yusuf N, Zakaria A, Omar MI, Shakaff AY, Masnan MJ, Kamarudin LM, et al.

BMC Bioinformatics, 2015;16:158.
PMID: 25971258 DOI: 10.1186/s12859-015-0601-5

Effective management of patients with diabetic foot infection is a crucial concern. A delay in prescribing appropriate antimicrobial agent can lead to amputation or life threatening complications. Thus, this electronic nose (e-nose) technique will provide a diagnostic tool that will allow for rapid and accurate identification of a pathogen.
Prediction of sediment heavy metal at the Australian Bays using newly developed hybrid artificial intelligence models

Bhagat SK, Tiyasha T, Awadh SM, Tung TM, Jawad AH, Yaseen ZM

Environ Pollut, 2021 Jan 01;268(Pt B):115663.
PMID: 33120144 DOI: 10.1016/j.envpol.2020.115663

Hybrid artificial intelligence (AI) models are developed for sediment lead (Pb) prediction in two Bays (i.e., Bramble (BB) and Deception (DB)) stations, Australia. A feature selection (FS) algorithm called extreme gradient boosting (XGBoost) is proposed to abstract the correlated input parameters for the Pb prediction and validated against principal component of analysis (PCA), recursive feature elimination (RFE), and the genetic algorithm (GA). XGBoost model is applied using a grid search strategy (Grid-XGBoost) for predicting Pb and validated against the commonly used AI models, artificial neural network (ANN) and support vector machine (SVM). The input parameter selection approaches redimensioned the 21 parameters into 9-5 parameters without losing their learned information over the models' training phase. At the BB station, the mean absolute percentage error (MAPE) values (0.06, 0.32, 0.34, and 0.33) were achieved for the XGBoost-SVM, XGBoost-ANN, XGBoost-Grid-XGBoost, and Grid-XGBoost models, respectively. At the DB station, the lowest MAPE values, 0.25 and 0.24, were attained for the XGBoost-Grid-XGBoost and Grid-XGBoost models, respectively. Overall, the proposed hybrid AI models provided a reliable and robust computer aid technology for sediment Pb prediction that contribute to the best knowledge of environmental pollution monitoring and assessment.
Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications

Kasabov N, Scott NM, Tu E, Marks S, Sengupta N, Capecci E, et al.

Neural Netw, 2016 Jun;78:1-14.
PMID: 26576468 DOI: 10.1016/j.neunet.2015.09.011

The paper describes a new type of evolving connectionist systems (ECOS) called evolving spatio-temporal data machines based on neuromorphic, brain-like information processing principles (eSTDM). These are multi-modular computer systems designed to deal with large and fast spatio/spectro temporal data using spiking neural networks (SNN) as major processing modules. ECOS and eSTDM in particular can learn incrementally from data streams, can include 'on the fly' new input variables, new output class labels or regression outputs, can continuously adapt their structure and functionality, can be visualised and interpreted for new knowledge discovery and for a better understanding of the data and the processes that generated it. eSTDM can be used for early event prediction due to the ability of the SNN to spike early, before whole input vectors (they were trained on) are presented. A framework for building eSTDM called NeuCube along with a design methodology for building eSTDM using this is presented. The implementation of this framework in MATLAB, Java, and PyNN (Python) is presented. The latter facilitates the use of neuromorphic hardware platforms to run the eSTDM. Selected examples are given of eSTDM for pattern recognition and early event prediction on EEG data, fMRI data, multisensory seismic data, ecological data, climate data, audio-visual data. Future directions are discussed, including extension of the NeuCube framework for building neurogenetic eSTDM and also new applications of eSTDM.

Matched MeSH terms: Neural Networks (Computer)*
A Novel Classification Model Using Optimal Long Short-Term Memory for Classification of COVID-19 from CT Images

Vinothini R, Niranjana G, Yakub F

J Digit Imaging, 2023 Dec;36(6):2480-2493.
PMID: 37491543 DOI: 10.1007/s10278-023-00852-7

The human respiratory system is affected when an individual is infected with COVID-19, which became a global pandemic in 2020 and affected millions of people worldwide. However, accurate diagnosis of COVID-19 can be challenging due to small variations in typical and COVID-19 pneumonia, as well as the complexities involved in classifying infection regions. Currently, various deep learning (DL)-based methods are being introduced for the automatic detection of COVID-19 using computerized tomography (CT) scan images. In this paper, we propose the pelican optimization algorithm-based long short-term memory (POA-LSTM) method for classifying coronavirus using CT scan images. The data preprocessing technique is used to convert raw image data into a suitable format for subsequent steps. Here, we develop a general framework called no new U-Net (nnU-Net) for region of interest (ROI) segmentation in medical images. We apply a set of heuristic guidelines derived from the domain to systematically optimize the ROI segmentation task, which represents the dataset's key properties. Furthermore, high-resolution net (HRNet) is a standard neural network design developed for feature extraction. HRNet chooses the top-down strategy over the bottom-up method after considering the two options. It first detects the subject, generates a bounding box around the object and then estimates the relevant feature. The POA is used to minimize the subjective influence of manually selected parameters and enhance the LSTM's parameters. Thus, the POA-LSTM is used for the classification process, achieving higher performance for each performance metric such as accuracy, sensitivity, F1-score, precision, and specificity of 99%, 98.67%, 98.88%, 98.72%, and 98.43%, respectively.
Optimal selection of mother wavelet for accurate infant cry classification

Saraswathy J, Hariharan M, Nadarajaw T, Khairunizam W, Yaacob S

Australas Phys Eng Sci Med, 2014 Jun;37(2):439-56.
PMID: 24691930 DOI: 10.1007/s13246-014-0264-y

Wavelet theory is emerging as one of the prevalent tool in signal and image processing applications. However, the most suitable mother wavelet for these applications is still a relative question mark amongst researchers. Selection of best mother wavelet through parameterization leads to better findings for the analysis in comparison to random selection. The objective of this article is to compare the performance of the existing members of mother wavelets and to select the most suitable mother wavelet for accurate infant cry classification. Optimal wavelet is found using three different criteria namely the degree of similarity of mother wavelets, regularity of mother wavelets and accuracy of correct recognition during classification processes. Recorded normal and pathological infant cry signals are decomposed into five levels using wavelet packet transform. Energy and entropy features are extracted at different sub bands of cry signals and their effectiveness are tested with four supervised neural network architectures. Findings of this study expound that, the Finite impulse response based approximation of Meyer is the best wavelet candidate for accurate infant cry classification analysis.

Matched MeSH terms: Neural Networks (Computer)*
Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network

Hariharan M, Sindhu R, Yaacob S

Comput Methods Programs Biomed, 2012 Nov;108(2):559-69.
PMID: 21824676 DOI: 10.1016/j.cmpb.2011.07.010

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.

Matched MeSH terms: Neural Networks (Computer)*
Analysis of infant cry through weighted linear prediction cepstral coefficients and Probabilistic Neural Network

Hariharan M, Chee LS, Yaacob S

J Med Syst, 2012 Jun;36(3):1309-15.
PMID: 20844933 DOI: 10.1007/s10916-010-9591-z

Acoustic analysis of infant cry signals has been proven to be an excellent tool in the area of automatic detection of pathological status of an infant. This paper investigates the application of parameter weighting for linear prediction cepstral coefficients (LPCCs) to provide the robust representation of infant cry signals. Three classes of infant cry signals were considered such as normal cry signals, cry signals from deaf babies and babies with asphyxia. A Probabilistic Neural Network (PNN) is suggested to classify the infant cry signals into normal and pathological cries. PNN is trained with different spread factor or smoothing parameter to obtain better classification accuracy. The experimental results demonstrate that the suggested features and classification algorithms give very promising classification accuracy of above 98% and it expounds that the suggested method can be used to help medical professionals for diagnosing pathological status of an infant from cry signals.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Common institutional investors and the quality of management earnings forecasts-Empirical and machine learning evidences

Yang S, Li X, Jiang Z, Xiao M

PLoS One, 2023;18(10):e0290126.
PMID: 37844110 DOI: 10.1371/journal.pone.0290126

Based on the data of the Chinese A-share listed firms in China Shanghai and Shenzhen Stock Exchange from 2014 to 2021, this article explores the relationship between common institutional investors and the quality of management earnings forecasts. The study used the multiple linear regression model and empirically found that common institutional investors positively impact the precision of earnings forecasts. This article also uses graph neural networks to predict the precision of earnings forecasts. Our findings have shown that common institutional investors form external supervision over restricting management to release a wide width of earnings forecasts, which helps to improve the risk warning function of earnings forecasts and promote the sustainable development of information disclosure from management in the Chinese capital market. One of the marginal contributions of this paper is that it enriches the literature related to the economic consequences of common institutional shareholding. Then, the neural network method used to predict the quality of management forecasts enhances the research method of institutional investors and the behavior of management earnings forecasts. Thirdly, this paper calls for strengthening information sharing and circulation among institutional investors to reduce information asymmetry between investors and management.
An interactively recurrent functional neural fuzzy network with fuzzy differential evolution and its applications

Lin CJ, Lin HY, Yu CY, Wu CF

Sains Malaysiana, 2015;44:1721-1728.

In this paper, an interactively recurrent functional neural fuzzy network (IRFNFN) with fuzzy differential evolution (FDE)
learning method was proposed for solving the control and the prediction problems. The traditional differential evolution
(DE) method easily gets trapped in a local optimum during the learning process, but the proposed fuzzy differential
evolution algorithm can overcome this shortcoming. Through the information sharing of nodes in the interactive layer,
the proposed IRFNFN can effectively reduce the number of required rule nodes and improve the overall performance of
the network. Finally, the IRFNFN model and associated FDE learning algorithm were applied to the control system of the
water bath temperature and the forecast of the sunspot number. The experimental results demonstrate the effectiveness
of the proposed method.
Municipal solid waste management for low-carbon transition: A systematic review of artificial neural network applications for trend prediction

Hoy ZX, Phuang ZX, Farooque AA, Fan YV, Woon KS

Environ Pollut, 2024 Mar 01;344:123386.
PMID: 38242306 DOI: 10.1016/j.envpol.2024.123386

Improper municipal solid waste (MSW) management contributes to greenhouse gas emissions, necessitating emissions reduction strategies such as waste reduction, recycling, and composting to move towards a more sustainable, low-carbon future. Machine learning models are applied for MSW-related trend prediction to provide insights on future waste generation or carbon emissions trends and assist the formulation of effective low-carbon policies. Yet, the existing machine learning models are diverse and scattered. This inconsistency poses challenges for researchers in the MSW domain who seek to identify and optimize the machine learning techniques and configurations for their applications. This systematic review focuses on MSW-related trend prediction using the most frequently applied machine learning model, artificial neural network (ANN), while addressing potential methodological improvements for reducing prediction uncertainty. Thirty-two papers published from 2013 to 2023 are included in this review, all applying ANN for MSW-related trend prediction. Observing a decrease in the size of data samples used in studies from daily to annual timescales, the summarized statistics suggest that well-performing ANN models can still be developed with approximately 33 annual data samples. This indicates promising opportunities for modeling macroscale greenhouse gas emissions in future works. Existing literature commonly used the grid search (manual) technique for hyperparameter (e.g., learning rate, number of neurons) optimization and should explore more time-efficient automated optimization techniques. Since there are no one-size-fits-all performance indicators, it is crucial to report the model's predictive performance based on more than one performance indicator and examine its uncertainty. The predictive performance of newly-developed integrated models should also be benchmarked to show performance improvement clearly and promote similar applications in future works. The review analyzed the shortcomings, best practices, and prospects of ANNs for MSW-related trend predictions, supporting the realization of practical applications of ANNs to enhance waste management practices and reduce carbon emissions.
A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure

Masuyama N, Loo CK, Wermter S

Int J Neural Syst, 2019 Jun;29(5):1850052.
PMID: 30764724 DOI: 10.1142/S0129065718500521

This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by integrating Kernel Bayes Rule (KBR) and Correntropy-Induced Metric (CIM) into Adaptive Resonance Theory (ART) framework. KBR performs a covariance-free Bayesian computation which is able to maintain a fast and stable computation. CIM is a generalized similarity measurement which can maintain a high-noise reduction ability even in a high-dimensional space. In addition, a Growing Neural Gas (GNG)-based topology construction process is integrated into the ART framework to enhance its self-organizing ability. The simulation experiments with synthetic and real-world datasets show that the proposed model has an outstanding stable self-organizing ability for various test environments.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext On the combination of adaptive neuro-fuzzy inference system and deep residual network for improving detection rates on intrusion detection

Liu J, Yinchai W, Siong TC, Li X, Zhao L, Wei F

PLoS One, 2022;17(12):e0278819.
PMID: 36508410 DOI: 10.1371/journal.pone.0278819

Deep Residual Networks (ResNets) are prone to overfitting in problems with uncertainty, such as intrusion detection problems. To alleviate this problem, we proposed a method that combines the Adaptive Neuro-fuzzy Inference System (ANFIS) and the ResNet algorithm. This method can make use of the advantages of both the ANFIS and ResNet, and alleviate the overfitting problem of ResNet. Compared with the original ResNet algorithm, the proposed method provides overlapped intervals of continuous attributes and fuzzy rules to ResNet, improving the fuzziness of ResNet. To evaluate the performance of the proposed method, the proposed method is realized and evaluated on the benchmark NSL-KDD dataset. Also, the performance of the proposed method is compared with the original ResNet algorithm and other deep learning-based and ANFIS-based methods. The experimental results demonstrate that the proposed method is better than that of the original ResNet and other existing methods on various metrics, reaching a 98.88% detection rate and 1.11% false alarm rate on the KDDTrain+ dataset.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Time-sequential graph adversarial learning for brain modularity community detection

Gong C, Xue B, Jing C, He CH, Wu GC, Lei B, et al.

Math Biosci Eng, 2022 Sep 13;19(12):13276-13293.
PMID: 36654046 DOI: 10.3934/mbe.2022621

Brain community detection is an efficient method to represent the communities of brain networks. However, time-variable functions of the brain and the intricate brain community structure impose a great challenge on it. In this paper, a time-sequential graph adversarial learning (TGAL) framework is proposed to detect brain communities and characterize the structure of communities from brain networks. In the framework, a novel time-sequential graph neural network is designed as an encoder to extract efficient graph representations by spatio-temporal attention mechanism. Since it is difficult to capture the community structure, the measurable modularity loss is used to optimize by maximizing the modularity of the community. In addition, the framework employs an adversarial scheme to guide the learning of representation. The effectiveness of our model is shown through experiments on the real-world brain network datasets, and the great performance of brain community detection demonstrates the advantage of the proposed framework.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links