检索结果-内蒙古大学图书馆

Enhancing Medical Image Security: A Deep Learning Approach with Cloud-based Color Space Scrambling

International Journal of Information technology (Singapore) 2024年第8期16卷 5041-5054页

作者： Cherian, Aswathy K. Simpson, Serin V. Vaidhehi, M. Marimuthu, Ramaprabha Shankar, M. Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chennai India School of Computer Science and Engineering Presidency University Bangalore India Veltech Dr. Rangarajan Dr. Sagunthala Research Institute of Science and Technology Avadi Chennai India Department of Computer Science and Technology Madanapalle Institute of Technology and Science Angallu Andhra Pradesh Madanapalle India

Progress in wisdom medicine has been driven by advancements in big data, cloud computing, and artificial intelligence, enabling the accumulation of valuable information and insights. However, the increasing reliance on cloud-based storage and transmission of medical images has raised significant concerns regarding information security. The risk of unauthorized access to patients' private data poses a considerable obstacle to medical research advancement. Thus, safeguarding patient data in cloud environments is imperative. Color space-based scrambling algorithms (CSSA) are gaining traction for multimedia data encryption due to their compatibility with JPEG and reduced processing requirements. However, traditional CSSA methods rely on colorful images to optimize security, limiting their applicability in fields like medical image processing where color images may be scarce. This study seeks to integrate CSSA image encryption with Multilayer Perceptron (MLP)-based techniques for securing medical images. Additionally, a noise-based data augmentation method is developed to address data scarcity in medical image analysis. Security analysis and temporal complexity assessments are employed to evaluate the effectiveness of the proposed MLP-CSSA deep learning model in encrypting medical images. Results demonstrate robust security in encrypting both grayscale and color medical images, with the proposed MLP-CSSA method outperforming existing encryption techniques. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Colour space-based scrambling algorithms (CSSA) Deep learning Encryption techniques JPEG standard Medical images Multilayer Perceptron’s (MLP)

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Model of Time Segment Power Usage Behavior Using Unsupervised Learning

引用

Journal of Internet technology 2024年第3期25卷 455-463页

作者： Ho, Wen-Jen Hsieh, Hsin-Yuan Tsai, Chia-Wei Software Technology Institute Institute for Information Industry Taiwan Department of Computer Science and Information Engineering National Taitung University Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taiwan

In Taiwan, the current electricity prices for residential users remain relatively low. This results in a diminished incentive for these users to invest in energy-saving improvements. Consequently, devising strategies to encourage residential users to adopt energy-saving measures becomes a vital research area. Grounded in behavioral science, this study introduces a feasible approach where an energy management system provides alerts and corresponding energy-saving recommendations to residential users upon detecting abnormal electricity consumption behavior. To pinpoint anomalous electricity usage within specific time segments, this research employs an unsupervised machine learning method, developing an anomaly detection model for the overall electricity consumption behavior of residential users. The model focuses on analyzing 2-hour intervals of electricity consumption, enabling more effective detection of abnormal usage patterns. It is trained using power consumption data collected from five actual residential users as part of an experimental study. The results indicate that the proposed anomaly detection model achieves performance metrics such as Precision, Recall, and F1-score of 0.90 or above, showcasing its potential for practical implementation. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Two Counterexamples to Tokenization and the Noiseless Channel 30

Two Counterexamples to Tokenization and the Noiseless Channe...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Cognetta, Marco Zouhar, Vilém Moon, Sangwhan Okazaki, Naoaki Tokyo Institute of Technology School of Computing Japan ETH Zurich Department of Computer Science Switzerland

ISBN: (纸本)9782493814104

In Tokenization and the Noiseless Channel (Zouhar et al., 2023a), Rényi efficiency is suggested as an intrinsic mechanism for evaluating a tokenizer: for NLP tasks, the tokenizer which leads to the highest Rényi efficiency of the unigram distribution should be chosen. The Rényi efficiency is thus treated as a predictor of downstream performance (e.g., predicting BLEU for a machine translation task), without the expensive step of training multiple models with different tokenizers. Although useful, the predictive power of this metric is not perfect, and the authors note there are additional qualities of a good tokenization scheme that Rényi efficiency alone cannot capture. We describe two variants of BPE tokenization which can arbitrarily increase Rényi efficiency while decreasing the downstream model performance. These counterexamples expose cases where Rényi efficiency fails as an intrinsic tokenization metric and thus give insight for building more accurate predictors. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Task Offloading using Deep Learning for Vehicular Edge computing Networks: A Survey

引用

IEIE Transactions on Smart Processing and computing 2024年第1期13卷 1-11页

作者： Abuthahir, S. Syed Peter, J. Selvin Paul Department of Computing Technologies SRM Institute of Science & Technology KTR Campus Tamil Nadu Chennai India

Vehicular networks must support connection ubiquity and high levels of services for a large number of vehicles. In vehicular networks, mobile edge computing (MEC) is considered a viable technique, utilizing computing resources at the edge of wireless access networks. This survey examines effectual task offloading systems forvehicular edge computing (VEC) networks. Several deep learning methods have been suggested to enable task offloading schemes. Therefore, task offloading optimality is a main research topic in fog computing. The main aim of this work is to offer readers an overview of the journey from the task offloading concept to its mathematic problem formulation. This survey introduces fog computing and the process of task offloading that emulates numerous aspects of optimization. Subsequently, a number of machine learning and deep learning methodologies are employed in task offloading,and the challenge of fog computing is discussed. This paper provides a detailed statistical analysis from papers published between 2019 and 2022. Copyrights © 2024 The institute of Electronics and Information Engineers.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Stage Classification Using Image Empirical Mode Decomposition (IEMD) and Deep Learning from Fundus Images 4th

Glaucoma Stage Classification Using Image Empirical Mode Dec...

引用

4th EAI International Conference on Cognitive computing and Cyber Physical Systems, IC4S 2023

作者： Shankar, D. Harsha, I. Sri Madhuri, P. Shyamala Naidu, J. N. S. S. Janardhana Madhuri, P. Krishna Cherukuvada, Srikanth Department of Computer Science and Engineering Vishnu Institute of Technology Kovvada India Department of Networking and Communications School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9783031488870

Glaucoma is an ocular pathology characterized by the gradual deterioration of neural cells in the eye, which is attributed to elevated intra ocular pressure within the retina. Glaucoma takes the second spot in terms of its prevalence as a neurodegenerative eye disease, failure to diagnose glaucoma at an early stage can lead to complete blindness. This underlying issue requires a streamlined system that uses experienced medical experts, little equipment, and less time. To categories the stages of glaucoma, a computer-Aided Diagnosis (CAD) method is used called Image Empirical Mode Decomposition (IEMD). Segmentation-based algorithms utilizing features like cup-to-disc ratio (CDR) and textural characteristics close to the optic disc region can distinguish glaucoma. To capture pixel variations for this investigation, the pre-processed fundus images are separated and transformed into a diverse range of intrinsic mode function (IMFs). The study employs deep learning-based framework for finding the optic nerve head from coloured fundus photographs, to transform the fundus images into a delimited region of interest (ROI) and utilizes multiple deep networks like RFCN and RCNN classifiers identified glaucoma stages separately. The CAD system serves as an automated tool for retinal image processing and demonstrates superior performance over the RFCN classifier, achieving an impressive accuracy of 96% with the RCNN classifier in classifying glaucoma stages. © 2024, ICST institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Updated deep long short-term memory with Namib beetle Henry optimisation for sentiment-based stock market prediction

引用

International Journal of Intelligent Information and Database Systems 2024年第3期16卷 316-344页

作者： Adikane, Nital Nirmalrani, V. Department of School of Computing Sathyabama Institute of Science and Technology Semmancheri Tamil Nadu Chennai600119 India

Stock price prediction is a challenging and promising area of research due to the volatile nature of stock markets influenced by factors like investor sentiment and market rumours. Developing accurate prediction models is difficult, given the complexity of stock data. Long short-term memory (LSTM) models have proven effective in uncovering hidden patterns, enabling precise predictions. Therefore, in this research work, an innovative approach called updated deep LSTM (UDLSTM) combined with Namib beetle Henry optimisation (BH-UDLSTM) is proposed and applied to historical stock market and sentiment analysis data. The UDLSTM model enhances prediction performance, offering stability during training and increased data accuracy. By incorporating Namib beetle and Henry gas algorithms, BH-UDLSTM further improves prediction accuracy by striking a balance between exploration and exploitation. The evaluation against existing methods demonstrates that the proposed approach achieves a higher accuracy rate (92.45%) in stock price prediction compared to state-of-the-art techniques. © 2024 Inderscience Enterprises Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning of Bigdata Set Using Randomized Measurements 7

Quantum Machine Learning of Bigdata Set Using Randomized Mea...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Minu, R.I. Nagarajan, G. Jabez, J. Yamini, G. SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Veltech Institute of Science and Technology Department of English Tamil Nadu India

ISBN: (纸本)9798350372816

Utilizing discriminative deep belief networks (DDBNs) within the framework of semi-supervised learning, this technique leverages a combination of a limited set of labeled samples to enhance intrusion prevention efficacy while reducing recognition errors. By integrating both non-local and local regularization techniques, the method effectively tackles the inherent challenge of high error rates in cyber prevention models. Additionally, this approach is designed for implementation on Quantum computing platforms, harnessing advanced machine learning algorithms to significantly improve cybersecurity measures. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Object Detection Using Deep Learning for Blind People with Voice Feedback

Object Detection Using Deep Learning for Blind People with V...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Pongiannan, R.K. Franklin, J. Richard Pravin, A. Maria, Marissa Mishra, Sarvottam Kumar Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur India Computer Science Engineering Srm Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331510022

BlindSpace is an innovative application aimed at improving the lives of visually challenged individuals. Leveraging cutting-edge image captioning and object detection technologies, the app allows users to capture images using their smartphone's camera, providing detailed scene descriptions and audibly identifying objects within those images. This not only enhances users' understanding of their environment but also fosters independence and confidence. With voice commands and text-to-speech technology, the application offers a user-friendly experience and can be customized to individual preferences. Operating efficiently offline, BlindSpace stands as a significant leap in accessibility technology, bridging the gap between the visual and non-visual worlds for visually challenged individuals and promoting inclusivity and autonomy. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Advancing mental health detection in texts via multi-task learning with soft-parameter sharing transformers

引用

Neural computing and Applications 2025年第5期37卷 3077-3110页

作者： Kodati, Dheeraj Tene, Ramakrishnudu Department of Computer Science and Engineering National Institute of Technology Warangal India Department of Computer Science and Engineering Mahindra University Hyderabad India

In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, facing challenges like task interference, limited adaptability, and difficulty in capturing nuanced linguistic expressions indicative of various conditions. In response to these challenges, our research presents three novel models employing multi-task learning (MTL) to understand mental health behaviors comprehensively. These models encompass soft-parameter sharing-based long short-term memory with attention mechanism (SPS-LSTM-AM), SPS-based bidirectional gated neural networks with self-head attention mechanism (SPS-BiGRU-SAM), and SPS-based bidirectional neural network with multi-head attention mechanism (SPS-BNN-MHAM). Our models address diverse tasks, including detecting disorders such as bipolar disorder, insomnia, obsessive-compulsive disorder, and panic in psychiatric texts, alongside classifying suicide or non-suicide-related texts on social media as auxiliary tasks. Emotion detection in suicide notes, covering emotions of abuse, blame, and sorrow, serves as the main task. We observe significant performance enhancement in the primary task by incorporating auxiliary tasks. Advanced encoder-building techniques, including auto-regressive-based permutation and enhanced permutation language modeling, are recommended for effectively capturing mental health contexts’ subtleties, semantic nuances, and syntactic structures. We present the shared feature extractor called shared auto-regressive for language modeling (S-ARLM) to capture high-level representations that are useful across tasks. Additionally, we recommend soft-parameter sharing (SPS) subtypes-fully sharing, partial sharing, and independent layer-to minimize tight coupling and enhance adaptability. Our models exhibit outstanding performance across various datasets, achieving accuracies of 96.9%, 97.

关键词： Multi-task 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

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：