检索结果-内蒙古大学图书馆

Streamlining plant disease diagnosis with convolutional neural networks and edge devices

Neural Computing and Applications 2024年第29期36卷 18445-18477页

作者： Ahamed, Md. Faysal Salam, Abdus Nahiduzzaman, Md. Abdullah-Al-Wadud, M. Islam, S. M. Riazul Department of Computer Science and Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical and Computer Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical Engineering Qatar University Doha Qatar Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Natural and Computing Sciences University of Aberdeen AberdeenAB24 3FX United Kingdom

In addressing labor-intensive process of manual plant disease detection, this article introduces an innovative solution—the lightweight parallel depthwise separable convolutional neural network (PDSCNN) coupled with a hybrid ridge regression extreme learning machine classifier. This combined approach automates plant disease classification, significantly expediting the learning process and reducing computational complexity. The PDSCNN model excels in feature capture, boasting a mere 9 layers and 0.053 million parameters, resulting in exceptional computational efficiency. On top of that, the classification performances of traditional ELM increased by introducing a hybrid ridge ELM model. Its accelerated operations, reduced memory usage, and optimized parallel processing render it lightweight and ideal for edge devices. The proposed framework exhibits remarkable efficacy, showcasing a precision of 95.76%, a recall of 89.29%, an F1-score of 91.25%, an accuracy of 94.22%, and an AUC of 99.72%. Moreover, training and testing times clock in at just 0.2314 and 0.0259 s, respectively. A comparative analysis against state-of-the-art transfer learning methods underscores its real-time analytical prowess. To demonstrate real-world applicability, we successfully validated our model on the Jetson Nano hardware, making it suitable for resource-constrained settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

TOST: School Bus Monitoring and Management System for Schools and Parents

TOST: School Bus Monitoring and Management System for School...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Thakur, Fahad Aqeel Hafiz, Muhammad Alani, Maath Saadoon, Muntadher Kian Chiew, Chiew Thiam University of Malaya Faculty of Computer Science & Information Technology Kuala Lumpur Malaysia Hillool Software Engineering Department Queensland Australia Universiti Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur50603 Malaysia

ISBN: (纸本)9798350302684

School bus contributes positively to reducing the number of cars on the road, thereby reducing the environmental impact of cars. It also dramatically relieves working parents, who do not have to pick up and drop off their children separately in their private vehicles. However, the irregularity of the bus arrival times often leads to an extended waiting time for students at the bus stops, potentially compromising the students' safety. The communication barrier between schools, parents and bus drivers is also a significant challenge, mainly when a delay occurs during the transit of the students. This paper presents TOST (to-school-together), a school bus monitoring and management system for schools and parents. The school administrators, parents, and bus drivers are connected in one comprehensive school bus system. The proposed system provides realtime updates on the bus status, allowing peace of mind and easing the burden of parents, school administrators, and bus drivers. The design of TOST is based on feedback from the system stakeholders collected via a survey. We draw a complete understanding of the existing issues by analyzing the feedback. Finally, we have implemented the system using state-of-the-art technologies to address the identified issues and fulfil the system requirements. © 2023 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Decentralized Ransomware Recovery Network: Enhancing Resilience and Security Through Secret Sharing Schemes 9

Decentralized Ransomware Recovery Network: Enhancing Resilie...

引用

9th International Conference on Internet of Things, Big Data and Security, IoTBDS 2024

作者： Ali, Sijjad Wang, Jia Leung, Victor Chung Ming Ali, Asad College of Computer Science and Software Engineering Shenzhen University Yuehai Campus Guangdong China College of Electronics and information Engineering Shenzhen University Yuehai Campus Guangdong China

ISBN: (纸本)9789897586996

Ransomware attacks present multiple threats to individuals such as businesses and organizations, causing data loss, financial stress, and operational interruptions. Traditional measures to mitigate ransomware threats usually include backups and secure applications. However, these countermeasures may not protect against sophisticated attacks. The purpose of this article is to explore a decentralized approach for recovering from multiple ransomware attacks. A decentralized secure approach is employed by the decentralized ransomware recovery network (DRRN) as a platform for sharing data privacy. Backup and restoration of encryption keys on shared domains are performed in the event of a ransomware attack. By paying for ransomware, users can encrypt their files. Additionally, the technical design of the DRRN and its management, as well as ransomware attacks are explored in our studies. A hybrid approach is utilized to evaluate its effectiveness and implications for cybersecurity and data protection. Finally, we assert that our proposed scheme is more secure and effective in the DRRN environment. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Ensemble based unsupervised anomaly detection with concept drift adaptation for time series data 10

Ensemble based unsupervised anomaly detection with concept d...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Li, Danlei Nair, Nirmal Wang, Kevin I-Kai Sakurai, Kouichi University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Kyushu University Department of Informatics Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798331520861

Anomaly detection is the identification of instances that substantially deviate from the majority of the data and do not conform to a well-defined normal behavior. Investigating time series anomalies has become increasingly popular in recent years due to widely deployed IoT devices and sensors. Although most existing methods apply image anomaly detection algorithms directly on time series and commonly assume the data is IID (independent and identically distributed). However, in most realworld applications, the underlying data distribution alters over time. Changes in data over time are referred to as concept drift and can significantly degrade the efficacy of an anomaly detection model. Existing research also indicates that the majority of anomaly detection frameworks ignored concept drift, resulting in poor long-term model performance. This paper presents an ensemble-based, unsupervised anomaly detection framework that is adaptive to the concept drift in time series data. Both distribution and performance-based techniques are used to detect concept drift and update the model to ensure the framework's longterm performance reliability. The proposed method is evaluated using a real-world univariate time series data that captures sea surface temperature data over a 2 -year period. By comparing our proposed framework to other state-of-the-art algorithms, we demonstrate our proposed method has obvious benefits in accuracy and long-term stability. © 2024 IEEE.

关键词： Anomaly detection Concept drift adaptation Ensemble method Time series Unsupervised method

来源：评论

学校读者我要写书评

暂无评论

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for the fusion of EEG and EMG

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for th...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： He, ZhengXiao Cai, Minghong Li, Letian Tian, Siyuan Dai, Ren-Jie Tongji University College of Electronic and Information Engineering Shanghai China Tongji University School of Software Engineering Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering China

ISBN: (纸本)9798350386226

Motor pattern recognition paradigms are the main forms of Brain-computer Interfaces(BCI) aimed at motor function rehabilitation and are the most easily promoted applications. In recent years, many researchers have suggested encouraging patients to perform real motor control execution simultaneously in MI-based BCI rehabilitation training systems. Electromyography (EMG) signals are the most direct physiological signals that can assess the execution of movements. Multimodal signal fusion is practically significant for decoding motor patterns. Therefore, we introduce a multimodal motion pattern recognition algorithm for EEG and EMG signals: EEG-EMG FAConformer, a method with several attention modules correlated with temporal and frequency information for motor pattern recognition. We especially devise a frequency band attention module to encode EEG information accurately and efficiently. What's more, modules like Multi-Scale Fusion Module, Independent ChannelSpecific Convolution Module(ICSCM), and Fuse Module which can effectively eliminate irrelevant information in EEG and EMG signals and fully exploit hidden dynamics are developed and show great effects. Extensive experiments show that EEGEMG FAConformer surpasses existing methods on Jeong2020 dataset, showcasing outstanding performance, high robustness and impressive stability. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Deep Learning Technologies to Assist Educational Inclusion for Children with Down Syndrome 5

Effectiveness of Deep Learning Technologies to Assist Educat...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Silva, Shehan Jayasinghe, Anjula Dilshan, Rishitha Dissanayake, Chandur Vidhanaarachchi, Samitha De Silva, Dilshan Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Down Syndrome (DS) is a genetic disorder causing intellectual disability and developmental delays. Despite instances of discrimination, several individuals with DS have achieved success through proper education and community support. This research addresses the challenges faced by children with DS in terms of motor skill development, cognitive impairments, and speech difficulties with the use of Deep Learning Technologies such as LSTM, CNN machine learning models. To bridge the educational gap and improve speech intelligibility, this study focuses on oral motor exercises that enhance articulation skills. Cognitive development in individuals with DS is also a concern, prompting the proposal of a self-learning system to foster cognitive growth. Fine motor skills improvement is explored through yoga exercises, and interventions like interactive technologies are considered to enhance learning experiences. This paper discusses the development of a user-friendly mobile application for early intervention in DS, integrating interactive activities using advanced technologies and a parent therapy dashboard. The system's potential for improving developmental skills and future expansion is emphasized. © 2023 IEEE.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling for Early Identification of Disease Severity in Acute Respiratory Infections: A Case Study with COVID-19 5

Predictive Modeling for Early Identification of Disease Seve...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Kalapuge, Vindhya Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Department of Computer Science & Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

The COVID-19 pandemic, declared a global emergency by WHO in March 2020, has had a profound impact on global health. With millions affected, the pandemic's magnitude became evident. Even advanced healthcare systems grappled with resource shortages, from protective gear to ventilators. Late diagnosis and the inability to adapt to new SARS-CoV-2 variants led to misdiagnoses and high casualties. Overburdened healthcare facilities and the absence of a centralized patient data system hindered swift decision-making. The lack of real-time monitoring meant many didn't receive timely, personalized care, underscoring the need for an integrated healthcare response during global emergencies. To tackle these challenges and improve hospital resource management during pandemics, this study presents a web approach harnessing big data analytics to develop a machine learning predictive model. This model has been developed to enable hospitals to assess patients' severity in real-time, taking into account a wide range of factors such as symptoms, medical history, and demographics. To acquire data regularly, a streaming data pipeline was established using Apache Kafka and Apache Streaming. In predicting the severity levels of patients, both Multinomial Logistic Regression and Multilayer Perceptron (MLP) models were employed. One noteworthy finding was that using datasets with balanced classes yielded significantly higher accuracy for the MLP model compared to unbalanced datasets. Specifically, MLP achieved the highest accuracy of 60.4% when trained on balanced classes. This model's real-time severity insights have the potential to revolutionize decision-making and resource allocation in healthcare. It represents a significant step towards a more effective response to future pandemics and the strengthening of the global healthcare system. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

DIG: Improved DINO for Graffiti Detection

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3557-3569页

作者： Wang, Bingshu Mao, Qianchen Liu, Aifei Chen, Long Chen, C. L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China University of Macao Department of Computer and Information Science China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL);2) Denoising Task with binary contrastive denoising (BCDN);and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an AP50 of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios. © 2013 IEEE.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

Earthworm Optimization with Improved SqueezeNet Enabled Facial Expression Recognition Model

引用

computer Systems science & engineering 2023年第8期46卷 2247-2262页

作者： N.Sharmili Saud Yonbawi Sultan Alahmari E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Computer Science and Engineering Department Gayatri Vidya Parishad College of Engineering for WomenVisakhapatnamAndhra PradeshIndia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11564Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass *** techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or *** execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image ***,many studies presented an endwise structure for facial expression recognition by utilizing DL ***,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)*** presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing *** addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)***,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE ***-ranging experimental analysis is carried out to examine the performance of the proposed *** experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.

关键词： Facial expression recognition deep learning computer vision earthworm optimization hyperparameter optimization

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：