检索结果-内蒙古大学图书馆

PPGCN: Phase-Aligned Periodic Graph Convolutional Network for Dual-Task-Based Cognitive Impairment detection

IEEE ACCESS 2024年 12卷 37679-37691页

作者： Godo, Akos Wu, Shuqiong Okura, Fumio Makihara, Yasushi Ikeda, Manabu Sato, Shunsuke Suzuki, Maki Satake, Yuto Taomoto, Daiki Yagi, Yasushi Osaka Univ SANKEN Osaka Ibaraki 5650871 Japan Osaka Univ Grad Sch Informat Sci & Technol Osaka Suita 5650871 Japan Osaka Univ Grad Sch Med Dept Psychiat Osaka Suita 5650871 Japan Esaka Hosp Dept Psychiat Osaka Suita 5650871 Japan Osaka Univ United Grad Sch Child Dev Dept Behav Neurol & Neuropsychiat Osaka Suita 5650871 Japan

Early detection methods for cognitive impairment are crucial for its effective treatment. Dual-task-based pipelines that rely on skeleton sequences can detect cognitive impairment reliably. Although such pipelines achieve state-of-the-art results by analyzing skeleton sequences of periodic stepping motion, we propose that their performance can be improved by decomposing the skeleton sequence into representative phase-aligned periods and focusing on them instead of the entire sequence. We present the phase-aligned periodic graph convolutional network, which is capable of processing phase-aligned periodic skeleton sequences. We trained it with a cross-modality feature fusion loss using a representative dataset of 392 samples annotated by medical professionals. As part of a dual-task cognitive impairment detection pipeline that relies on two-dimensional skeleton sequences extracted from RGB images to improve its general usability, our proposed method outperformed existing approaches and achieved a mean sensitivity of 0.9231 and specificity of 0.9398 in a four-fold cross-validation setup.

关键词： Task analysis Feature extraction Convolutional neural networks Motors Dementia Cognition detection algorithms convolutional neural networks dementia task analysis

来源：评论

学校读者我要写书评

暂无评论

Privacy-Centric Multi-Class detection of COVID 19 Through Breathing Sounds and Chest X-Ray Images: Blockchain and Optimized Neural Networks

引用

IEEE ACCESS 2024年 12卷 89968-89985页

作者： Thandu, Asha Latha Gera, Pradeepini Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vijayawada 520002 India

The CoronaVirus Disease of 2019 (COVID19) pandemic poses a significant global challenge, with millions affected and millions of lives lost. This study presents a privacy-conscious technique to early identification of COVID19 using breathing sounds and chest X-ray images. Using Blockchain and optimized neural networks, the suggested solution provides data confidentiality and accuracy. Chest X-ray pictures are preprocessed, segmented, and feature extracted using modern algorithms. Breathing sounds are treated simultaneously using tri-gaussian filters and mel frequency cepstral coefficient features. A progressive split deformable field fusion module combines audio and visual characteristics. The proposed Dual Sampling dilated Pre-activation residual Attention convolution Neural Network (DSPANN) improves classification accuracy while decreasing computational complexity using augmented snake optimization. Furthermore, a privacy-focused blockchain-based encrypted crypto hash federated method is used for safe global model training. This complete method overcomes COVID-19 detection issues while simultaneously prioritizing data privacy in healthcare applications. The proposed framework exhibited recognition accuracy rates of 98%, specificity of 97.02%, and sensitivity of 98%.

关键词： COVID-19 X-ray imaging Blockchains Accuracy Feature extraction Filters Diseases detection algorithms Lung Respiratory system Coronaviruses Early detection COVID 19 multimodal fusion deep learning breathing sounds chest X-ray images

来源：评论

学校读者我要写书评

暂无评论

Financial Fraud detection Using Value-at-Risk With Machine Learning in Skewed Data

引用

IEEE ACCESS 2024年 12卷 64285-64299页

作者： Usman, Abdullahi Ubale Abdullahi, Sunusi Bala Yu, Liping Alghofaily, Bayan Almasoud, Ahmed S. Rehman, Amjad Zhejiang Gongshang Univ Sch Stat & Math Hangzhou 310018 Peoples R China King Mongkuts Univ Technol Thonburi Fac Engn Dept Elect & Telecommun Engn Bang ModThrung Khru Bangkok 10140 Thailand Kano Univ Sci & Technol Dept Stat Wudil 713281 Nigeria Prince Sultan Univ Coll Comp & Informat Sci Riyadh 11586 Saudi Arabia

The significant losses that banks and other financial organizations suffered due to new bank account (NBA) fraud are alarming as the number of online banking service users increases. The inherent skewness and rarity of NBA fraud instances have been a major challenge to the machine learning (ML) models and happen when non-fraud instances outweigh the fraud instances, which leads the ML models to overlook and erroneously consider fraud as non-fraud instances. Such errors can erode the confidence and trust of customers. Existing studies consider fraud patterns instead of potential losses of NBA fraud risk features while addressing the skewness of fraud datasets. The detection of NBA fraud is proposed in this research within the context of value-at-risk as a risk measure that considers fraud instances as a worst-case scenario. Value-at-risk uses historical simulation to estimate potential losses of risk features and model them as a skewed tail distribution. The risk-return features obtained from value-at-risk were classified using ML on the bank account fraud (BAF) Dataset. The value-at-risk handles the fraud skewness using an adjustable threshold probability range to attach weight to the skewed NBA fraud instances. A novel detection rate (DT) metric that considers risk fraud features was used to measure the performance of the fraud detection model. An improved fraud detection model is achieved using a K-nearest neighbor with a true positive (TP) rate of 0.95 and a DT rate of 0.9406. Under an acceptable loss tolerance in the banking sector, value-at-risk presents an intelligent approach for establishing data-driven criteria for fraud risk management.

关键词： Fraud Machine learning Finance Biological system modeling Risk management Data models Mathematical models detection algorithms Nearest neighbor methods detection rate fraud detection K-nearest neighbor skewed instances value-at-risk

来源：评论

学校读者我要写书评

暂无评论

General Recursive Least Square Algorithm for Distributed detection in Massive MIMO

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第8期73卷 12137-12142页

作者： Chen, Qiqiang Wang, Zheng Ma, Cong Dai, Xiaoming Ng, Derrick Wing Kwan Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China ZTE Corp Shenzhen 518057 Peoples R China Univ Sci & Technol Beijing Beijing 100083 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

In this paper, a general recursive least square (GRLS) detection algorithm is proposed for the uplink of distributed massive multiple-input multiple-output (MIMO) to alleviate the bottlenecks in both computational complexity and data bandwidth for interconnection. Different from the existing recursive least square (RLS) detection algorithm which only supports a single antenna in each distributed unit (DU), the proposed GRLS allows for multiple antennas in each DU, rendering it adaptable to a variety of practical scenarios. Moreover, among the total C DUs and with an integer parameter C-0, the computational complexity of C-C-0 DUs in GRLS can be significantly reduced by leveraging the channel hardening property. Through analysis, we demonstrate that the convergence of the GRLS algorithm is guaranteed if C-0 >= [ ( root B / 2 + root K )(2) / B ] holds, where K and B denote the numbers of antennas at the user side and each DU, respectively. Furthermore, based on the daisy-chain architecture, the proposed GRLS algorithm also enjoys excellent scalability, which can be easily extended with extra DUs for further improvement. Finally, the detection complexity and data bandwidth analysis are also provided to unveil the superiority of GRLS compared to other distributed detection schemes for massive MIMO.

关键词： Complexity theory Massive MIMO detection algorithms Computer architecture Bandwidth Antennas Antenna arrays Daisy-chain decentralized signal detection distributed MIMO detection RLS

来源：评论

学校读者我要写书评

暂无评论

detection and Defense: Student-Teacher Network for Adversarial Robustness

引用

IEEE ACCESS 2024年 12卷 82742-82752页

作者： Park, Kyoungchan Kang, Pilsung Korea Univ Sch Ind Management Engn Seoul 02841 South Korea

Defense against adversarial attacks is critical for the reliability and safety of deep neural networks (DNNs). Current state-of-the-art defense methods achieve significant robustness against adversarial attacks. However, such defense methods cannot distinguish between adversarial examples (AEs) and normal examples (NEs). Thus, they apply the same defense process for both examples to perform classification, resulting in performance degradation for NEs. In this paper, we propose a novel defense method based on the student-teacher framework that can minimize the classification performance degradation for NEs by detecting AEs and then applying the defense process only to AEs. Focusing on the fact that distortion in the hidden layer features is inevitable for the success of adversarial attacks, we train the student network to predict the undistorted hidden layer features of the teacher network (target DNN). Therefore, our method can detect AEs through the difference in the hidden layer features between the student and teacher network, and then recover the classification result of AEs using the penultimate layer features predicted by the student network. Through extensive experiments on representative image classification benchmark datasets, i.e., CIFAR-10, CIFAR-100, and TinyImagenet, we demonstrate the superiority of our method in both detection and defense compared with state-of-the-art methods. Furthermore, we show that our method achieves robust detection and defense performance for a fully white-box attack that assumes an attacker knows the information of our entire detection and defense mechanism.

关键词： Training Feature extraction Distortion Task analysis Robustness Perturbation methods Adversarial machine learning detection algorithms Education Artificial neural networks Adversarial attack adversarial detection adversarial defense student-teacher network

来源：评论

学校读者我要写书评

暂无评论

Toward Long Range detection of Elephants Using Seismic Signals: A Geophone-Sensor Interface for Embedded Systems

引用

IEEE ACCESS 2024年 12卷 72210-72223页

作者： Wijayaraja, Jaliya L. Wijekoon, Janaka L. Wijesundara, Malitha Mendis Wickramasinghe, L. J. Sri Lanka Inst Informat Technol Malabe 10115 Sri Lanka Victorian Inst Technol Adelaide SA 5000 Australia Keio Univ Dept Syst Design Engn Yokohama 1080073 Japan Herpetol Fdn Sri Lanka HFS Wattala 11300 Sri Lanka

The long-distance detection of the presence of elephants is pivotal to addressing the human-elephant conflict. IoT-based solutions utilizing seismic signals originating from the movement of elephants are a novel approach to solving this problem. This study introduces an instrumentation system comprising a specially designed geophone-sensor interface for non-invasive, long-range elephant detection using seismic waves while minimizing the vulnerability of seismic signals to noise. The geophone-sensor interface involves a cascade array of an instrumentation amplifier, a second-order Butterworth filter for signal filtering, and a signal amplifier. The introduced geophone-sensor interface was tested under laboratory conditions, and then real-world experiments were carried out for tamed, partly tamed, and untamed elephants. The experimental results reveal that the system remains stable within the tested frequency range from 1 Hz to 1 kHz and the temperature range of 10 degrees C to 40 degrees C. The system successfully captured the seismic signals generated by the footfalls of elephants within a maximum detection range of 155.6 m, with an overall detection accuracy of 99.5%.

关键词： Embedded systems Noise measurement Seismic waves Gain Electric fences Testing Instruments detection algorithms Animals Human factors Embedded system Sri Lankan elephant seismic wave geophone HEC elephant detection elephant locomotion sensor interfacing

来源：评论

学校读者我要写书评

暂无评论

Oil Palm Loose Fruit detection Using YOLOv4 for an Autonomous Mobile Robot Collector

引用

IEEE ACCESS 2024年 12卷 138582-138593页

作者： Japar, Ahmed Fareed Ramli, Hafiz Rashidi Norsahperi, Nor Mohd Haziq Hasan, Wan Zuha Wan Univ Putra Malaysia Dept Elect & Elect Engn Serdang 43400 Selangor Malaysia

This study researches the usage of YOLOv4 for real-time loose fruit detection in oil palm plantations as the first step in implementing automation in the collection of loose fruits. Our system leverages high-resolution video data (4K and 1080p) from various plantation settings. To address the challenges of detecting small and numerous loose fruits, we introduced an image preprocessing technique called "image tiling" into the vision system workflow. We studied the effects this has on the performance of the detection model. This involves slicing the image into smaller sections (i.e., tiles) for individual processing by YOLOv4 and YOLOv4-tiny models, enhancing detection accuracy. Refined models (YOLOv4-tiling and YOLOv4-tiny-tiling) are then evaluated. YOLOv4 achieved the highest precision (97%) and F1-score (86.3%), while YOLOv4-tiling offered a slight improvement in recall (80.8%). Notably, YOLOv4-tiny, initially underperforming (precision: 37.2%, recall: 20.9%, F1-score: 25%), showed significant improvement with tiling (precision: 90.5%, recall: 67.1%, F1-score: 73.8%). Also, replacing the SPP layer in YOLOv4 with SPP-Fast resulted in increased precision (92.6%) and a significantly improved F1 score of 91.4%. This vision system was then integrated with a custom-designed Loose Fruit Collector Robot through the Robot Operating System (ROS).

关键词： YOLO Training Accuracy Robots Plantations Data models Crops Plants (biology) detection algorithms Mobile robots Operating systems Object detection oil palm automation loose fruit (LF)

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Spam detection Using Natural Language Processing With AMALS Models

引用

IEEE ACCESS 2024年 12卷 124298-124313页

作者： Agarwal, Ruchi Dhoot, Anshita Kant, Surya Singh Bisht, Vimal Malik, Hasmat Ansari, Md. Fahim Afthanorhan, Asyraf Hossaini, Mohammad Asef JIMS Engn Management Tech Campus Dept Comp Sci Greater Noida 201303 India Moscow Inst Phys & Technol Sch Radio Engn & Comp Technol Dept Phystech Moscow 141701 Russia Graph Era Hill Univ Dept Elect & Commun Engn Bhimtal 263136 India Univ Teknol Malaysia UTM Fac Elect Engn Dept Elect Power Engn Skudai 81310 Johor Bahru Malaysia Graph Era Dept Elect Engn Dehra Dun India Univ Sultan Zainal Abidin UniSZA Artificial Intelligence Islamic Civilizat & Sustai Kuala Nerus 21300 Terengganu Malaysia Univ Sultan Zainal Abidin UniSZA Operat Res & Management Sci Kuala Nerus 21300 Terengganu Malaysia Badghis Univ Dept Phys Badghis 3351 Afghanistan

To enhance their company operations, organizations within the industry leverage the ecosystem of big data to manage vast volumes of information effectively. To achieve this objective, it is imperative to analyze textual data while prioritizing the safeguarding of data integrity and implementing robust measures for organizing and validating data through the utilization of spam filters. Various methodologies can be employed, including Word2Vec, bag-of-words, BERT, as well as term frequency & reciprocal document frequency (TF-IDF). Nevertheless, none of these solutions effectively address the problem of data scarcity, which might lead to the existence of missing information in the collected documents. To properly address this problem, it is necessary to employ a strategy that categorizes each document based on the topic matter and uses statistical approaches for approximation. This research paper presents a novel approach for spam detection using natural language processing. The proposed strategy utilizes a least-squares model to modify themes and incorporates gradient descent and altering least-squares (i.e., AMALS) models for estimating missing data. TF-IDF and uniform-distribution methods perform the estimation. The performance evaluation reveals that the suggested technique exhibits a superior performance of 98% compared to the existing industry TF-IDF model in accurately predicting spam within big data ecosystems. By this model, the environment of an organization or a company can be saved from spamming or other attacks, which can lead to extracting their data for unauthorized users to protect the details.

关键词： Unsolicited e-mail Natural language processing Machine learning Internet of Things Biological system modeling Big Data Security Artificial intelligence detection algorithms big data machine learning spam detection

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Lightweight Machine Learning Techniques for Cyber-Attacks detection in Blockchain-Enabled Industrial Supply Chain

引用

IEEE ACCESS 2024年 12卷 102481-102491页

作者： Ismail, Shereen Dandan, Salah Dawoud, Diana W. Reza, Hassan Univ Michigan Merit Network Inc Ann Arbor MI 48108 USA Univ North Dakota Sch Elect Engn & Comp Sci Grand Forks ND 58202 USA Univ Dubai Coll Engn & Informat Technol Dubai U Arab Emirates

The security of Industrial Supply Chain (ISC) has emerged through the integration of Industrial Internet of Things (IIoT) and Blockchain (BC) technology. This new era involves effectively protecting IIoT systems from various threats and ensuring their smooth operation and resilience against potential cyber-attacks. Within the ISC ecosystem, combining machine learning (ML)-based security models for cyber-attack detection can play a crucial role in enhancing the ISC security and proactively identifying potential threats. This paper presents a BC-enabled ISC that embed ML security model integrated within a multi-layered approach. We conducted a comparative study and performance analysis of several ML classification techniques, with a focus on supervised methods to identify the lightweight model for cyber-attack detection suitable for deployment in resource-constrained IIoT environment. We investigate the performance of Gaussian Naive Bayes (NB), K-Nearest Neighbors (KNN), Random Forest (RF), Decision Tree (DT), and three ensemble techniques, namely Bagging, Stacking, and Boosting. The study employs the WUSTL-IIOT-2021 imbalanced dataset, which contains samples representing four types of attacks, including denial of service (DoS), SQL injection, reconnaissance, and backdoor. The paper addresses the imbalance in class representation by customizing the dataset for training and testing the ML models. Both Mutual Information (MI) and Extra-trees (ET) are applied as a one-stage ensemble feature selection. The performance of the ML models are investigated using classification accuracy (Acc), precision, recall, F1 score, Matthews correlation coefficient (MCC), model size (Mem), training time (TT) and prediction time (PT).

关键词： Industrial Internet of Things Security Cyberattack Biological system modeling Nearest neighbor methods Radio frequency Monitoring Supply chains detection algorithms Blockchains Industrial supply chain industrial Internet of Things security cyber-attacks detection machine learning blockchain lightweight

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning and Machine Learning Approaches for Brain Hemorrhage detection

引用

IEEE ACCESS 2024年 12卷 45060-45093页

作者： Ahmed, Samia Esha, Jannatul Ferdous Rahman, Md. Sazzadur Kaiser, M. Shamim Hosen, A. S. M. Sanwar Ghimire, Deepak Park, Mi Jin Bangladesh Univ Profess Dept Informat & Commun Technol ICT Dhaka 1216 Bangladesh Jahangirnagar Univ Inst Informat Technol Dhaka 1342 Bangladesh Woosong Univ Dept Artificial Intelligence & Big Data Daejeon 34606 South Korea Soongsil Univ Coll Informat Technol Sch AI Convergence Seoul 06978 South Korea Catholic Univ Korea Coll Med Seoul St Marys Hosp Dept Psychiat Seoul 03083 South Korea

Brain hemorrhage refers to a potentially fatal medical disorder that affects millions of individuals. The percentage of patients who survive can be significantly raised with the prompt identification of brain hemorrhages, due to image-guided radiography, which has emerged as the predominant treatment modality in clinical practice. A Computed Tomography Image has frequently been employed for the purpose of identifying and diagnosing neurological disorders. The manual identification of anomalies in the brain region from the Computed Tomography Image demands the radiologist to devote a greater amount of time and dedication. In the most recent studies, a variety of techniques rooted in Deep learning and traditional Machine Learning have been introduced with the purpose of promptly and reliably detecting and classifying brain hemorrhage. This overview provides a comprehensive analysis of the surveys that have been conducted by utilizing Machine Learning and Deep Learning. This research focuses on the main stages of brain hemorrhage, which involve preprocessing, feature extraction, and classification, as well as their findings and limitations. Moreover, this in-depth analysis provides a description of the existing benchmark datasets that are utilized for the analysis of the detection process. A detailed comparison of performances is analyzed. Moreover, this paper addresses some aspects of the above-mentioned technique and provides insights into prospective possibilities for future research.

关键词： Deep learning Machine learning Brain injuries Hemorrhaging Medical treatment Computed tomography Neurological diseases Feature extraction Diagnostic radiography Benchmark testing Classification algorithms Image preprocessing detection algorithms Artificial intelligence brain hemorrhage convolutional neural network deep learning intracranial hemorrhage human health machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：