The actual operating environment of rotating mechanical device contains a large number of noisy interference sources, leading to complex components, strong coupling, and low signal to noise ratio for vibration. It becomes a big challenge for intelligent fault diagnosis from high-noise vibration signals. Thus, this paper proposes a new deep learning approach, namely decomposition-enhance Fourier residual network (DEFR-net), to achieve high noise immunity for vibration signal and learn effective features to discriminate between different types of rotational machine faults. In the proposed DEFR-net, a novel algorithm is proposed to explicitly model high-noise signals for noisy data filtering and effective feature enhancement based on a hard threshold decomposition function and muti-channel self-attention mechanism. Furthermore, it deeply integrates complementary analysis based on fast Fourier transform in the time-frequency domain and extends the breadth of network. The performance of the proposed model is verified by comparison with five state-of-the-art algorithms on two public datasets. Moreover, the noise experimental results show that the fault diagnosis accuracy is still 85.91% when the signal-to-noise-ratio reaches extreme noise of –8 dB. The results demonstrate that the proposed method is a valuable study for intelligent fault diagnosis of rotating machines in high-noise environments.
旋转机械设备的实际运行环境中存在大量噪声干扰源，导致部件复杂、耦合性强、振动信噪比低。如何从高噪声振动信号中进行智能故障诊断成为一大挑战。因此，本文提出了一种新的深度学习方法，即分解增强傅立叶残差网络（DEFR-net），以实现振动信号的高抗噪能力，并学习有效特征来区分不同类型的旋转机械故障。在所提出的 DEFR-net 中，基于硬阈值分解函数和多通道自注意机制，提出了一种新的算法，对高噪声信号进行显式建模，以实现噪声数据过滤和有效的特征增强。此外，它还深度整合了基于时频域快速傅立叶变换的补充分析，并扩展了网络的广度。通过在两个公共数据集上与五种最先进算法的比较，验证了所提模型的性能。此外，噪声实验结果表明，当信噪比达到极端噪声 -8 dB 时，故障诊断准确率仍为 85.91%。这些结果表明，所提出的方法对高噪声环境下旋转机械的智能故障诊断具有重要的研究价值。
{"title":"DEFR-net: A decompose-enhance fourier residual network for fault diagnosis of rotating machine with high noise immunity","authors":"B. Du, Fujiang Zhang, Jun Guo, Xiang Sun","doi":"10.3233/jifs-233190","DOIUrl":"https://doi.org/10.3233/jifs-233190","url":null,"abstract":"The actual operating environment of rotating mechanical device contains a large number of noisy interference sources, leading to complex components, strong coupling, and low signal to noise ratio for vibration. It becomes a big challenge for intelligent fault diagnosis from high-noise vibration signals. Thus, this paper proposes a new deep learning approach, namely decomposition-enhance Fourier residual network (DEFR-net), to achieve high noise immunity for vibration signal and learn effective features to discriminate between different types of rotational machine faults. In the proposed DEFR-net, a novel algorithm is proposed to explicitly model high-noise signals for noisy data filtering and effective feature enhancement based on a hard threshold decomposition function and muti-channel self-attention mechanism. Furthermore, it deeply integrates complementary analysis based on fast Fourier transform in the time-frequency domain and extends the breadth of network. The performance of the proposed model is verified by comparison with five state-of-the-art algorithms on two public datasets. Moreover, the noise experimental results show that the fault diagnosis accuracy is still 85.91% when the signal-to-noise-ratio reaches extreme noise of –8 dB. The results demonstrate that the proposed method is a valuable study for intelligent fault diagnosis of rotating machines in high-noise environments.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140225577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nowadays, automatic human activity recognition from video images is necessary for monitoring applications and caring for disabled people. The use of surveillance cameras and the processing of the obtained images leads to the achievement of a smart, accurate system for the recognition of human behavior. Since human detection in different scenes is associated with many challenges, several approaches have been implemented to detect human activity from video image processing. Due to the complexity of human activities, background noises and other factors affect the detection. For the solution of these problems, two deep learning-based algorithms have been described in the current article. According to the convolutional neural networks, the LSTM + CNN method and the 3D CNN method have been used to recognize the human activities in the images of the video. Each algorithm is explained and analyzed in detail. The experiments designed in this paper are performed by two datasets: the HMDB-51 dataset and the UCF101 dataset. In the HMDB-51 dataset, the highest obtained accuracy for CNN + LSTM method was equal to 70.2 and for method 3D CNN equal to 54.4. In the UCF101 dataset, the highest obtained accuracy for CNN + LSTM method was equal to 95.1 and for method 3D CNN equal to 90.8.
{"title":"Human activities recognition from video images by using convolutional neural network","authors":"Dan Wang, Jingfa Yao, Yanmin Zhang","doi":"10.3233/jifs-236068","DOIUrl":"https://doi.org/10.3233/jifs-236068","url":null,"abstract":"Nowadays, automatic human activity recognition from video images is necessary for monitoring applications and caring for disabled people. The use of surveillance cameras and the processing of the obtained images leads to the achievement of a smart, accurate system for the recognition of human behavior. Since human detection in different scenes is associated with many challenges, several approaches have been implemented to detect human activity from video image processing. Due to the complexity of human activities, background noises and other factors affect the detection. For the solution of these problems, two deep learning-based algorithms have been described in the current article. According to the convolutional neural networks, the LSTM + CNN method and the 3D CNN method have been used to recognize the human activities in the images of the video. Each algorithm is explained and analyzed in detail. The experiments designed in this paper are performed by two datasets: the HMDB-51 dataset and the UCF101 dataset. In the HMDB-51 dataset, the highest obtained accuracy for CNN + LSTM method was equal to 70.2 and for method 3D CNN equal to 54.4. In the UCF101 dataset, the highest obtained accuracy for CNN + LSTM method was equal to 95.1 and for method 3D CNN equal to 90.8.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140226149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The interaction of several workers with intelligent construction machinery can lead to serious collisions. Typically, the safety distance is used as an indicator of the safety of worker–machine interactions (WMI). However, the degree of risk does not increase linearly with decreasing worker–machine distances. To further reveal the essence of WMI safety, this study proposes a new method for assessing the safety state of WMIs, namely, the construction safety potential field. It is used to describe the factors and patterns associated with the spatial overlap and decay of hazardous energy in WMI operations. The proposed method was tested in an earthworks construction WMI operation and the results were valid. A preliminary discussion of the relevant parameters constituting the construction safety potential field model is presented. The contributions of the research is proposing a generic energy-based model, which provides a novel idea for the interpretation of safety issues in construction WMI operations and opens up a new foundation for the development of active safety control.
{"title":"Potential functions of construction worker–machine interaction safety assessment","authors":"Yu Bai, Q. Hu, Zhenxiang Zhou, Q. Cai, Leping He","doi":"10.3233/jifs-236423","DOIUrl":"https://doi.org/10.3233/jifs-236423","url":null,"abstract":"The interaction of several workers with intelligent construction machinery can lead to serious collisions. Typically, the safety distance is used as an indicator of the safety of worker–machine interactions (WMI). However, the degree of risk does not increase linearly with decreasing worker–machine distances. To further reveal the essence of WMI safety, this study proposes a new method for assessing the safety state of WMIs, namely, the construction safety potential field. It is used to describe the factors and patterns associated with the spatial overlap and decay of hazardous energy in WMI operations. The proposed method was tested in an earthworks construction WMI operation and the results were valid. A preliminary discussion of the relevant parameters constituting the construction safety potential field model is presented. The contributions of the research is proposing a generic energy-based model, which provides a novel idea for the interpretation of safety issues in construction WMI operations and opens up a new foundation for the development of active safety control.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140227615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
There is scope to enhance agricultural measurement and control systems user interactivity, which typically necessitates training for users to perform specific operations successfully. With the continuous development of natural language semantic processing technology, it has become essential to augment the user-friendliness of multifaceted control and query operations in the agricultural measurement and control sector, ultimately leading to reduced operation costs for users. The study aims to focus on command parsing. The proposed AMR-OPO semantic parsing framework is based on the natural language understanding method of Abstract Meaning Representation of Rooted Markup Graphs (AMR). It transforms the user’s natural language inputs into structured ternary (OPO) statements (operation-place-object) and converts the corresponding parameters of the user’s input commands. The framework subsequently sends the transformed commands to the relevant devices via the IoT gateway. To tackle the intricate task of parsing instructions, we developed a BERT-BiLSTM-ATT-CRF-OPO entity recognition model. This model can detect and extract entities from agricultural instructions, and precisely populate them into OPO statements. Our model shows exceptional accuracy in instruction parsing, with precision, recall, and F-value all measuring at 92.13%, 93.12%, and 92.76%, correspondingly. The findings from our experiment reveal outstanding and precise performance of our approach. It is anticipated that our algorithm will enhance the user experience offered by agricultural measurement and control systems, while also making them more user-friendly.
{"title":"Natural language command parsing for agricultural measurement and control based on AMR and entity recognition","authors":"Weihao Yuan, Mengdao Yang, Hexu Gu, Gaojian Xu","doi":"10.3233/jifs-237280","DOIUrl":"https://doi.org/10.3233/jifs-237280","url":null,"abstract":"There is scope to enhance agricultural measurement and control systems user interactivity, which typically necessitates training for users to perform specific operations successfully. With the continuous development of natural language semantic processing technology, it has become essential to augment the user-friendliness of multifaceted control and query operations in the agricultural measurement and control sector, ultimately leading to reduced operation costs for users. The study aims to focus on command parsing. The proposed AMR-OPO semantic parsing framework is based on the natural language understanding method of Abstract Meaning Representation of Rooted Markup Graphs (AMR). It transforms the user’s natural language inputs into structured ternary (OPO) statements (operation-place-object) and converts the corresponding parameters of the user’s input commands. The framework subsequently sends the transformed commands to the relevant devices via the IoT gateway. To tackle the intricate task of parsing instructions, we developed a BERT-BiLSTM-ATT-CRF-OPO entity recognition model. This model can detect and extract entities from agricultural instructions, and precisely populate them into OPO statements. Our model shows exceptional accuracy in instruction parsing, with precision, recall, and F-value all measuring at 92.13%, 93.12%, and 92.76%, correspondingly. The findings from our experiment reveal outstanding and precise performance of our approach. It is anticipated that our algorithm will enhance the user experience offered by agricultural measurement and control systems, while also making them more user-friendly.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140226700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Garden landscape is the combination of nature and humanity, with high aesthetic value, ecological value and cultural value, has become an important part of people’s life. Modern people have a higher pursuit for the spiritual food such as garden landscape after the material life is satisfied, which brings new challenges to the construction of urban garden landscape. As an advanced type of machine learning, deep learning applied to landscape image recognition can solve the problem of low quality and low efficiency of manual recognition. Based on this, this paper proposes a garden landscape image recognition algorithm based on SSD (Single Shot Multibox Detector), which realizes accurate extraction and recognition of image features by positioning the target, and can effectively improve the quality and efficiency of landscape image recognition. In order to test the feasibility of the algorithm proposed in this paper, experimental analysis was carried out in the CVPR 2023 landscape data set. The experimental results show that the algorithm has a high recognition accuracy for landscape images, and has excellent performance compared with traditional image recognition algorithms.
{"title":"Landscape image recognition and analysis based on deep learning algorithm","authors":"Nong Limei, Dongfan Wu, Zhang Bo","doi":"10.3233/jifs-239654","DOIUrl":"https://doi.org/10.3233/jifs-239654","url":null,"abstract":"Garden landscape is the combination of nature and humanity, with high aesthetic value, ecological value and cultural value, has become an important part of people’s life. Modern people have a higher pursuit for the spiritual food such as garden landscape after the material life is satisfied, which brings new challenges to the construction of urban garden landscape. As an advanced type of machine learning, deep learning applied to landscape image recognition can solve the problem of low quality and low efficiency of manual recognition. Based on this, this paper proposes a garden landscape image recognition algorithm based on SSD (Single Shot Multibox Detector), which realizes accurate extraction and recognition of image features by positioning the target, and can effectively improve the quality and efficiency of landscape image recognition. In order to test the feasibility of the algorithm proposed in this paper, experimental analysis was carried out in the CVPR 2023 landscape data set. The experimental results show that the algorithm has a high recognition accuracy for landscape images, and has excellent performance compared with traditional image recognition algorithms.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140226763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Folk dance is an important intangible cultural heritage in China. In the environment where movement recognition technology is widely used, there is still no research field on the protection and inheritance of folk dance culture. In order to better protect and inherit the minority dance, screening the typical movements of 5 types of minority dance, through the dance video frame processing, obtain the key movements of 19 class dance sequence, build the national dance typical action data set, put forward a 3D CNN fusion Transformer national dance recognition network model (FCTNet), the recognition rate of 96.7% in the experiment. The results show that the construction method of the folk dance data set is reasonable, the identification model has good performance for the classification of folk dance, and can effectively identify and record the folk dance movements, which also makes new contributions to the digital protection of folk dance.
{"title":"FCTNet: Fusion of 3D CNN and transformer dance action recognition network","authors":"Tao Ning, Tingting Zhang, Guowei Huang","doi":"10.3233/jifs-235302","DOIUrl":"https://doi.org/10.3233/jifs-235302","url":null,"abstract":"Folk dance is an important intangible cultural heritage in China. In the environment where movement recognition technology is widely used, there is still no research field on the protection and inheritance of folk dance culture. In order to better protect and inherit the minority dance, screening the typical movements of 5 types of minority dance, through the dance video frame processing, obtain the key movements of 19 class dance sequence, build the national dance typical action data set, put forward a 3D CNN fusion Transformer national dance recognition network model (FCTNet), the recognition rate of 96.7% in the experiment. The results show that the construction method of the folk dance data set is reasonable, the identification model has good performance for the classification of folk dance, and can effectively identify and record the folk dance movements, which also makes new contributions to the digital protection of folk dance.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140227607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Karthikeyan, Ilhami Colak, S. Sagar Imambi, J. Joselin Jeya Sheela, Sruthi Nair, B. Umarani, Andril Alagusabai, K. Suriyakrishnaan, A. Rajaram
This research paper introduces a cutting-edge approach to electric demand forecasting by incorporating the Temporal Fusion Transformer (TFT). As the landscape of demand forecasting becomes increasingly intricate, precise predictions are vital for effective energy management. To tackle this challenge, we leverage the sequential and temporal patterns in an extensive electric demand dataset spanning from 2003 to 2014. Our proposed Temporal Fusion Transformer model combines attention mechanisms with the transformer architecture, enabling it to adeptly capture intricate temporal dependencies. Thorough data preprocessing, including temporal embedding and external features, enhances prediction accuracy. Through rigorous evaluation, the TFT model surpasses existing forecasting techniques, showcasing its capacity for accurate, resilient, and adaptive predictions. This research contributes to the advancement of electric demand forecasting, harnessing the TFT’s capabilities to excel in capturing diverse temporal patterns. The findings hold the potential to enhance energy management and support decision-making in the energy sector, bridging the gap between innovation and practical utility.
{"title":"Advancing electric demand forecasting through the temporal fusion transformer model","authors":"M. Karthikeyan, Ilhami Colak, S. Sagar Imambi, J. Joselin Jeya Sheela, Sruthi Nair, B. Umarani, Andril Alagusabai, K. Suriyakrishnaan, A. Rajaram","doi":"10.3233/jifs-236036","DOIUrl":"https://doi.org/10.3233/jifs-236036","url":null,"abstract":"This research paper introduces a cutting-edge approach to electric demand forecasting by incorporating the Temporal Fusion Transformer (TFT). As the landscape of demand forecasting becomes increasingly intricate, precise predictions are vital for effective energy management. To tackle this challenge, we leverage the sequential and temporal patterns in an extensive electric demand dataset spanning from 2003 to 2014. Our proposed Temporal Fusion Transformer model combines attention mechanisms with the transformer architecture, enabling it to adeptly capture intricate temporal dependencies. Thorough data preprocessing, including temporal embedding and external features, enhances prediction accuracy. Through rigorous evaluation, the TFT model surpasses existing forecasting techniques, showcasing its capacity for accurate, resilient, and adaptive predictions. This research contributes to the advancement of electric demand forecasting, harnessing the TFT’s capabilities to excel in capturing diverse temporal patterns. The findings hold the potential to enhance energy management and support decision-making in the energy sector, bridging the gap between innovation and practical utility.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140226867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The traditional multi-task Takagi-Sugeno-Kang (TSK) fuzzy system modeling methods pay more attention to utilizing the inter-task correlation to learn the consequent parameters but ignore the importance of the antecedent parameters of the model. To this end, we propose a novel multi-task TSK fuzzy system modeling method based on multi-task fuzzy clustering. This method first proposes a novel multi-task fuzzy c-means clustering method that learns multiple specific clustering centers for each task and some common clustering centers for all tasks. Secondly, for the consequent parameters of the fuzzy system, the novel low-rank and row-sparse constraints are proposed to better implement multi-task learning. The experimental results demonstrate that the proposed model shows better performance compared with other existing methods.
{"title":"A novel multi-task TSK fuzzy system modeling method based on multi-task fuzzy clustering","authors":"Ziyang Yao","doi":"10.3233/jifs-232312","DOIUrl":"https://doi.org/10.3233/jifs-232312","url":null,"abstract":"The traditional multi-task Takagi-Sugeno-Kang (TSK) fuzzy system modeling methods pay more attention to utilizing the inter-task correlation to learn the consequent parameters but ignore the importance of the antecedent parameters of the model. To this end, we propose a novel multi-task TSK fuzzy system modeling method based on multi-task fuzzy clustering. This method first proposes a novel multi-task fuzzy c-means clustering method that learns multiple specific clustering centers for each task and some common clustering centers for all tasks. Secondly, for the consequent parameters of the fuzzy system, the novel low-rank and row-sparse constraints are proposed to better implement multi-task learning. The experimental results demonstrate that the proposed model shows better performance compared with other existing methods.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140227042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Obsessive-compulsive disorder (OCD) is a chronic disease and psychosocial disorder that significantly reduces the quality of life of patients and affects their personal and social relationships. Therefore, early diagnosis of this disorder is of particular importance and has attracted the attention of researchers. In this research, new statistical differential features are used, which are suitable for EEG signals and have little computational load. Hilbert-Huang transform was applied to EEGs recorded from 26 OCD patients and 30 healthy subjects to extract instant amplitude and phase. Then, modified mean, variance, median, kurtosis and skewness were calculated from amplitude and phase data. Next, the difference of these statistical features between various pairs of EEG channels was calculated. Finally, different scenarios of feature classification were examined using the sparse nonnegative least squares classifier. The results showed that the modified mean feature calculated from the amplitude and phase of the interhemispheric channel pairs produces a high accuracy of 95.37%. The frontal lobe of the brain also created the most distinction between the two groups among other brain lobes by producing 90.52% accuracy. In addition, the features extracted from the frontal-parietal network produced the best classification accuracy (93.42%) compared to the other brain networks examined. The method proposed in this paper dramatically improves the accuracy of EEG classification of OCD patients from healthy individuals and produces much better results compared to previous machine learning techniques.
{"title":"Automatic detection of obsessive-compulsive disorder from EEG signals based on Hilbert-Huang transform and sparse coding classification","authors":"Yuntao Hong","doi":"10.3233/jifs-237946","DOIUrl":"https://doi.org/10.3233/jifs-237946","url":null,"abstract":"Obsessive-compulsive disorder (OCD) is a chronic disease and psychosocial disorder that significantly reduces the quality of life of patients and affects their personal and social relationships. Therefore, early diagnosis of this disorder is of particular importance and has attracted the attention of researchers. In this research, new statistical differential features are used, which are suitable for EEG signals and have little computational load. Hilbert-Huang transform was applied to EEGs recorded from 26 OCD patients and 30 healthy subjects to extract instant amplitude and phase. Then, modified mean, variance, median, kurtosis and skewness were calculated from amplitude and phase data. Next, the difference of these statistical features between various pairs of EEG channels was calculated. Finally, different scenarios of feature classification were examined using the sparse nonnegative least squares classifier. The results showed that the modified mean feature calculated from the amplitude and phase of the interhemispheric channel pairs produces a high accuracy of 95.37%. The frontal lobe of the brain also created the most distinction between the two groups among other brain lobes by producing 90.52% accuracy. In addition, the features extracted from the frontal-parietal network produced the best classification accuracy (93.42%) compared to the other brain networks examined. The method proposed in this paper dramatically improves the accuracy of EEG classification of OCD patients from healthy individuals and produces much better results compared to previous machine learning techniques.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intrusion Detection (ID) in cloud environments is vital to maintain the safety and integrity of data and resources. However, the presence of class imbalance, where normal samples significantly outweigh intrusive instances, poses a challenge in constructing a potential ID system. Deep Learning (DL) methods, with their capability to automatically study complex patterns and features, present a promising solution in various ID tasks. Such methods can automatically learn intricate features and patterns from the input dataset, making them suitable for detecting anomalies and finding intrusions in cloud environments. Therefore, this study proposes a Class Imbalance Data Handling with an Optimal Deep Learning-Based Intrusion Detection System (CIDH-ODLIDS) in a cloud computing atmosphere. The CIDH-ODLIDS technique leverages optimal DL-based classification and addresses class imbalance. Primarily, the CIDH-ODLIDS technique preprocesses the input data using a Z-score normalization approach to ensure data quality and consistency. To handle class imbalance, the CIDH-ODLIDS technique employs oversampling techniques, particularly focused on synthetic minority oversampling techniques such as Adaptive Synthetic (ADASYN) sampling. ADASYN generates synthetic instances for the minority class depending on the available data instances, effectively balancing the class distribution and mitigating the impact of class imbalance. For the ID process, the CIDH-ODLIDS technique utilizes a Fuzzy Deep Neural Network (FDNN) model, and its tuning procedure is performed using the Chaotic Tunicate Swarm Algorithm (CTSA). CTSA is employed to choose the learning rate of the FDNN methods optimally. The experimental assessment of the CIDH-ODLIDS method is extensively conducted on three IDS datasets. The comprehensive comparison results confirm the superiority of the CIDH-ODLIDS algorithm over existing techniques.
云环境中的入侵检测（ID）对于维护数据和资源的安全性和完整性至关重要。然而，由于存在类不平衡（正常样本明显多于入侵实例），这给构建潜在的 ID 系统带来了挑战。深度学习（DL）方法具有自动研究复杂模式和特征的能力，为各种 ID 任务提供了一种前景广阔的解决方案。这些方法可以自动学习输入数据集中的复杂特征和模式，因此适合在云环境中检测异常和查找入侵。因此，本研究提出了一种在云计算环境下基于优化深度学习的类失衡数据处理入侵检测系统（CIDH-ODLIDS）。CIDH-ODLIDS 技术利用基于深度学习的最优分类来解决类不平衡问题。首先，CIDH-ODLIDS 技术使用 Z 分数归一化方法对输入数据进行预处理，以确保数据质量和一致性。为了处理类不平衡问题，CIDH-ODLIDS 技术采用了超采样技术，尤其侧重于合成少数群体超采样技术，例如自适应合成（ADASYN）采样。ADASYN 会根据可用的数据实例生成少数群体的合成实例，从而有效平衡类别分布，减轻类别失衡的影响。在 ID 过程中，CIDH-ODLIDS 技术使用了模糊深度神经网络（FDNN）模型，其调整过程使用混沌调谐群算法（CTSA）进行。CTSA 用于优化选择 FDNN 方法的学习率。CIDH-ODLIDS 方法在三个 IDS 数据集上进行了广泛的实验评估。综合比较结果证实了 CIDH-ODLIDS 算法优于现有技术。
{"title":"Optimizing deep learning-based intrusion detection in cloud computing environment with chaotic tunicate swarm algorithm","authors":"C. Jansi Sophia Mary, K. Mahalakshmi","doi":"10.3233/jifs-237900","DOIUrl":"https://doi.org/10.3233/jifs-237900","url":null,"abstract":"Intrusion Detection (ID) in cloud environments is vital to maintain the safety and integrity of data and resources. However, the presence of class imbalance, where normal samples significantly outweigh intrusive instances, poses a challenge in constructing a potential ID system. Deep Learning (DL) methods, with their capability to automatically study complex patterns and features, present a promising solution in various ID tasks. Such methods can automatically learn intricate features and patterns from the input dataset, making them suitable for detecting anomalies and finding intrusions in cloud environments. Therefore, this study proposes a Class Imbalance Data Handling with an Optimal Deep Learning-Based Intrusion Detection System (CIDH-ODLIDS) in a cloud computing atmosphere. The CIDH-ODLIDS technique leverages optimal DL-based classification and addresses class imbalance. Primarily, the CIDH-ODLIDS technique preprocesses the input data using a Z-score normalization approach to ensure data quality and consistency. To handle class imbalance, the CIDH-ODLIDS technique employs oversampling techniques, particularly focused on synthetic minority oversampling techniques such as Adaptive Synthetic (ADASYN) sampling. ADASYN generates synthetic instances for the minority class depending on the available data instances, effectively balancing the class distribution and mitigating the impact of class imbalance. For the ID process, the CIDH-ODLIDS technique utilizes a Fuzzy Deep Neural Network (FDNN) model, and its tuning procedure is performed using the Chaotic Tunicate Swarm Algorithm (CTSA). CTSA is employed to choose the learning rate of the FDNN methods optimally. The experimental assessment of the CIDH-ODLIDS method is extensively conducted on three IDS datasets. The comprehensive comparison results confirm the superiority of the CIDH-ODLIDS algorithm over existing techniques.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：