检索结果-内蒙古大学图书馆

International Conference on Innovations in Information technology

作者： Ahmed Abdelhadi Ahmed Munkhjargal Gochoo Mohamad Taghizadeh Munkh-Erdene Otgonbold Ganzorig Batnasan Department of Computer Science & Software Engineering College of Information Technology (CIT) United Arab Emirates University Al Ain UAE Department of Electrical Engineering Iran University of Science and Technology Iran

As stated by the United Arab Emirates’s (UAE) Community Development Authority (CDA), there are around 3,065 individuals with hearing disabilities in the country. These individuals often struggle to communicate with broader society and rely on scarce sign language (SL) interpreters. Moreover, Arabic’s dialects diversity compounds the issue by causing dialects in the Arabic Sign Language (ArSL). Hence, the call for a standardized reference for ArSL in the region is a priority. To address these challenges, we’ve developed an Emirate Sign Language (ESL) electronic dictionary (e-dictionary) with a dataset of 127 signs and 50 sentences, recorded by hearing-impaired individuals in the UAE with various degrees of deafness. Supervised by certified interpreters and validated by ESL’s department head at CDA in Dubai, the recordings were made using Azure Kinect DK, resulting in 708 recordings. The dataset is then processed to 10fps. The e-dictionary offers features such as webcam-based sign recognition using YOLOv8 technology, voice-based signing via Arabic Automatic Speech Recognition, text-based signing, and words spelling in ArSL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An LWE-Based Multi-Key Privacy-Preserving Distributed Deep Learning∗ 23

An LWE-Based Multi-Key Privacy-Preserving Distributed Deep L...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Antwi-Boasiako, Emmanuel Zhou, Shijie Liao, Yongjian Danso, Ebenezer Kwaku School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Ghana Institute of Management and Public Administration Computer Science Department Accra Ghana China University for Development Studies Ghana

ISBN: (纸本)9781665494571

Privacy preservation in distributed deep learning (DDL) has received a lot of attention recently. One key approach to preserving privacy for DDL is the use of Homomorphic Encryption (HE), which allows computation on ciphertexts without decryption. Although current applications of HE provide some level of privacy to DDL, they are not post-quantum resistant and multi-key compliant. The use of same key by all participants could lead to collusion attacks and possible leakage of sensitive information from a participant's local dataset in the distributed deep learning setting. Furthermore, most of the privacy solutions provided for the DDL assume that all learning participants must be present before the start of the protocol. Hence, such solutions do not allow a new participant to benefit from the utility of the joint learning of other participants, for which it was not present. To address the above problems, we propose a new privacy preserving solution for DDL that uses an LWE-based Multi-key approach. Our proposed privacy preserving DDL solution is multi-key compliant, post-quantum resistant and has an additional property of allowing a new participant to benefit from the utility of an already trained collaborative deep learning system. We prove that our privacy-preserving distributed deep learning system is secured. We note that our proposed solution generally provides a robust privacy-preserving solution for the DDL and at the same time has great potential to reduce communication and computation costs associated with similar systems. © 2021 IEEE.

关键词： Deep learning Resistance Privacy Protocols Costs Collaboration Cryptography

来源：评论

学校读者我要写书评

暂无评论

EEG-based epileptic seizure pattern decoding using vision transformer

EEG-based epileptic seizure pattern decoding using vision tr...

引用

International Conference on Innovations in Information technology

作者： Abdelhadi Hireche Rafat Damseh Parikshat Sirpal Abdelkader Nasreddine Belkacem Department of Computer and Network Engineering College of Information Technology United Arab Emirates University United Arab Emirates Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates School of Electrical and Computer Engineering Gallogly College of Engineering University of Oklahoma United States of America

Epilepsy is a prevalent neurological disorder and has been studied through the analysis of Electroencephalogram (EEG) signals. However, the identification and classification of epileptic seizure patterns remains challenging due to the non-stationary nature of EEG signals and the presence of artifacts. In this paper, we investigate the applicability of a transformer-based deep learning model to classify seizure patterns observed in epileptic patients. We employed the self-attention mechanism inherent in transformers to capture complex temporal relationships in the EEG recordings. By prepossessing the EEG signals into suitable input sequences and adapting the transformer architecture, we achieved 78.11% in distinguishing between different epileptic seizure patterns. Our findings indicate that the transformer model, with its ability to manage long-range dependencies, offers a robust approach to EEG-based seizure pattern classification. This work is important for building advanced automated diagnostic tools for epilepsy and related neurological disorders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diagnosis Of Cassava Leaf Diseases and Classification Using Deep Learning Techniques

Diagnosis Of Cassava Leaf Diseases and Classification Using ...

引用

International Conference on Open Source Systems and Technologies (ICOSST)

作者： Syed Mursleen Riaz Muhammad Ahsan Muhammad Usman Akram Department of Computer & Software Engineering National University of Sciences and Technology (NUST) Islamabad Pakistan

ISBN: (纸本)9781665464789

The plants disease diagnosis is very challenging research in the field of agriculture. Cassava is a second most provider of carbohydrates in Africa. It is a key food for people of Africa in very harsh conditions. According to United Nations (FAO) almost eighty percent farmers of sub Saharan Africa are growing cassava roots, but due to a variety of viral diseases the production of cassava is very low from last two years. With the help of data science, it is possible to diagnose and classify these types of viral diseases. Existing methods of disease detection require farmers to solicit the help of government-funded agricultural experts to visually inspect and diagnose the plants. Moreover, this process is labor-intensive, time taken, costly and impacting the production and supply cycle. As an added challenge, effective solutions for farmers must perform well under significant constraints since African farmers may only have access to mobile-quality cameras with low-bandwidth. The dataset which we use in this research is taken from Kaggle competition 2020. Dataset contains 21397 images of cassava plants which belongs to five different classes i.e., Cassava Bacterial Blight, Cassava Brown Streak Disease, Cassava Green Mottle, Cassava Mosaic Disease and Healthy leaves. In this work we have used augmentation technique to increase the samples for classification and balancing the uneven distribution of data for all classes and used deep learning model efficiennetB3 for identification classification of diseases and got 83.03% overall accuracy on test dataset with more than 90% individual accuracy of each class. We have developed a graphical user interface for using the model in more efficient way with the aim to help the industry for prediction of diseases during its initial stages.

关键词： Deep learning Microorganisms Plants (biology) Africa Production Predictive models Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Improved Kernel Fuzzy C-Means Clustering Method Based on Smart Grid

Improved Kernel Fuzzy C-Means Clustering Method Based on Sma...

引用

World Conference on Mechanical engineering and Intelligent Manufacturing (WCMEIM)

作者： Shuqi Niu Zhao Zhang Xintong Tian Xueyan Zhao School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781665473705

The improved kernel fuzzy clustering method is used to classify the load data of the smart grid accurately. It lays a good foundation for the subsequent work of power load forecasting and provides a more efficient, safe, and reliable direction for the operation of the power system. Firstly, the collected power load data is preprocessed to reduce data redundancy and improve data quality. Secondly, the kernel fuzzy C-means clustering algorithm based on particle swarm optimization is used to cluster the load data with the same power consumption characteristics. Finally, the improved kernel fuzzy clustering method is compared with the fuzzy C-means clustering method through a simulation example to verify the effectiveness of this method.

关键词： Clustering methods Data integrity Redundancy Clustering algorithms Smart grids Power system reliability Reliability

来源：评论

学校读者我要写书评

暂无评论

Blocking Flow Shop Scheduling Based on a Multi-Group Collaborative Sparrow Search Algorithm

Blocking Flow Shop Scheduling Based on a Multi-Group Collabo...

引用

第34届中国控制与决策会议

作者： Kai Ma Yafei Geng Kan Xu Shiliang Guo Jie Yang School of Electrical Engineering Yanshan University Shanghai Development Center of Computer Software Technology

The blocking flow shop scheduling problem(BFSP) prevails widely in the process manufacturing *** this paper,a multi-group collaborative sparrow search algorithm(MGCSSA) is proposed for minimizing the makespan for ***,a collaborative initialization strategy is designed to generate initialized populations with certain ***,an elite solution set and a multi-group collaboration mechanism are introduced to improve the adequacy of the global search,and the producer and scrounger position update formulas are improved to increase the population ***,three neighborhood heuristics are used to locally strengthen individuals in the elite solution set that enhance the ability of the algorithm to jump out of the local ***,the proposed algorithm is evaluated experimentally in test *** experimental data and comparative results show that the proposed MGCSSA has superior performance and is highly competitive in solving BFSP.

关键词： Blocking Flow Shop Scheduling Hybrid Modified Global Optimal Sparrow Search Algorithm Neighborhood Heuristics

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition System via Facial Expressions and Speech Using Machine Learning and Deep Learning Techniques

引用

SN computer Science 2023年第4期4卷 363页

作者： Chaudhari, Aayushi Bhatt, Chintan Nguyen, Thanh Thi Patel, Nisarg Chavda, Kirtan Sarda, Kalind U & P U. Patel Department of Computer Engineering Chandubhai S. Patel Institute of Technology Charotar University of Science And Technology (CHARUSAT) Gujarat Changa 388421 India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Knowledge Corridor Gujarat Gandhinagar 382007 India School of Information Technology Faculty of Science Engineering and Built Environment Deakin University Victoria 3216 Australia Bishop University 2600 College St Sherbrooke J1M 1Z7 QC Canada Crest Data Systems Private Limited Gandhinagar Highway Makarba Gujarat Ahmedabad 380051 India Programmer Analyst Meditab Software Pvt Ltd Kalasagar Mall Ghatlodiya Gujarat Ahmedabad 380061 India

Patients in hospitals frequently exhibit psychological issues such as sadness, pessimism, eccentricity, and anxiety. However, hospitals normally lack tools and facilities to continuously monitor the psychological health of patients. It is desirable to identify depression in patients so that it can be managed by instantly providing better therapy. This can be possible by advances in machine learning for image processing with notable applications in the domain of emotion recognition using facial expressions. In this paper, we have proposed two different methods, i.e. facial expression detection and voice analysis, to predict emotions. For facial expression recognition, we have used two approaches, one is the use of Gabor filters for feature extraction with support vector machine for classification and another is using convolutional neural network (CNN). For voice analysis, we extracted mel-frequency cepstral coefficients from speech data and, based on those features, predicted the emotions of the speech using a CNN model. Experimental results show that our proposed emotion recognition methods obtained high accuracy and thus could be potentially deployed to real-world applications. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CNN Deep learning Expressions Facial emotion Machine learning Speech SVM

来源：评论

学校读者我要写书评

暂无评论

Data-Driven DLT3 Federated Deep Reinforcement Learning for Secure and Efficient Autonomous Driving

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Fei, Rong Li, Qianxi Wang, Kan Khan, Fazlullah Alturki, Ryan Lan, Dapeng Xi’an University of Technology School of Computer and Engineering Xi’an710000 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Ningbo315104 China Umm Al-Qura University College of Computing Department of Software Engineering Makkah21955 Saudi Arabia Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110003 China

As autonomous vehicles (AVs) become increasingly widespread, the intelligent driving control and safety concerns have emerged. Recent advents in Internet of Things (IoTs) and 6G technologies have vastly boosted AVs’ sensing and communication capabilities, thereby enabling the high-speed and real-time data exchange. However, efficiently utilizing data while safeguarding the privacy remains challenges. Thus, we propose a federated learning (FL) framework with the privacy protection to facilitate the deep reinforcement learning (DRL) for longitudinal vehicle safety tracking control. First, the proposed framework enables the efficient information sharing and policy updates via encrypted policy gradient transmission. Then, the twin delayed deep deterministic policy gradient (TD3) method makes the velocity decision in the local model, while the dual long short-term memory (LSTM) network captures the temporal trajectory information. Finally, stacked denoising autoencoders (SDAE) is used to extract high-level environmental features, and the dual-LSTM-TD3 (DLT3)-SDAE model is introduced to enhance the policy decision efficiency and accuracy. Experimental results demonstrate that within the FL framework supported by homomorphic encryption, the DLT3-SDAE-based AV agent surpasses other DRL methods in terms of collision avoidance and average rewards, in the LAF environment. The safety, efficiency and comfort of the DLT3-SDAE AV agent are also evaluated and demonstrated. © 1975-2011 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Automatic Reflective Clothing Detection Algorithm Based on YOLOv5 for Work Type Recognition 11

An Automatic Reflective Clothing Detection Algorithm Based o...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： He, Xinyi Ma, Ping Chen, Yiyang Liu, Yuan School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Key Laboratory of Media Design and Software Technology Wuxi214122 China School of Mechanical and Electrical Engineering Soochow University Suzhou215137 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

At present, traditional manual methods are still utilized for the inspection of reflective clothing on a wide range of construction sites. Using this manual inspection methods wastes much human resource. In this paper, the YOLOv5 model is used as the network framework to automatically detects whether the workers wear reflective clothing, and determines types of work by examining reflective clothing of different colors. By identifying the color difference of the reflective clothing, the network is capable of distinguish whether the target work type can enter relevant construction areas with different danger levels. In this paper, by constructing the labeled data set and training on the basis of YOLOv5 model framework, a target model is obtained. Its detection speed can adapt to real-time monitoring. The accuracy and recall rates can meet the requirements on the training set and verification set. It has a desired effect on the testing set of real website captured images, and can realize the intelligent recognition of reflective clothing on construction sites. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fed-AugMix: Balancing Privacy and Utility via Data Augmentation

arXiv

引用

arXiv 2024年

作者： Li, Haoyang Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate this issue, they often lead to notable performance degradation. Existing methods struggle to preserve model performance while ensuring privacy. To address this challenge, we propose a novel data augmentation-based framework designed to achieve a favorable privacy-utility trade-off, with the potential to enhance model performance in certain cases. Our framework incorporates the AugMix algorithm at the client level, enabling data augmentation with controllable severity. By integrating the Jensen-Shannon divergence into the loss function, we embed the distortion introduced by AugMix into the model gradients, effectively safeguarding privacy against deep leakage attacks. Moreover, the JS divergence promotes model consistency across different augmentations of the same image, enhancing both robustness and performance. Extensive experiments on benchmark datasets demonstrate the effectiveness and stability of our method in protecting privacy. Furthermore, our approach maintains, and in some cases improves, model performance, showcasing its ability to achieve a robust privacy-utility trade-off. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

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：