检索结果-内蒙古大学图书馆

A novel deep learning model for early diabetes risk prediction using attention-enhanced deep belief networks with highly imbalanced data

引用

International Journal of Information Technology (Singapore) 2025年第4期17.0卷 1933-1955页

作者： Olabanjo, Olusola Wusu, Ashiribo Olabanjo, Olufemi Asokere, Mauton Afisi, Oseni Akinnuwesi, Boluwaji Center for Equitable AI and Machine Learning Systems (CEAMLS) Morgan State University Baltimore 21251 MD United States Department of Mathematics Morgan State University Baltimore MD United States Department of Computer Science Lagos State University Lagos Nigeria Department of Mathematics Lagos State University Lagos Nigeria Department of Cybersecurity University of Derby Derby United Kingdom Department of Philosophy Lagos State University Lagos Nigeria Department of Computer Science Faculty of Science and Engineering University of Eswatini Kwaluseni Swaziland

Diabetes mellitus is a prevalent chronic illness with severe complications that demand timely diagnosis. This study introduces an attention-enhanced Deep Belief Network (DBN) for early diabetes risk prediction, designed to address challenges associated with highly imbalanced datasets. Using a dataset from Sylhet Diabetes Hospital, which includes symptom and demographic information from patients, we applied an ensemble feature selection approach to identify critical predictors. To address the class imbalance, Generative Adversarial Networks (GANs) were used to generate synthetic data, ensuring the model’s robustness in identifying underrepresented cases. Additionally, a hybrid loss function combining cross-entropy and focal loss was implemented to improve classification, especially for hard-to-detect instances. Our results show that the attention-based DBN model, augmented with synthetic data from GANs and optimized with a hybrid loss function, achieves an AUC of 1.00, F1-score of 0.97, precision of 0.98, and recall of 0.95, outperforming several baseline models. This research offers a novel and effective approach for early diabetes detection, demonstrating potential for use as a clinical tool in preventive healthcare settings. © The Author(s) 2025.

关键词： Attention mechanism Deep belief networks (DBN) Diabetes risk Generative adversarial networks (GANs) Hybrid loss function Imbalanced data

来源：评论

学校读者我要写书评

暂无评论

Oral Cancer Classification Using a Hybrid Attention-Aided Deep Learning Model 5th

Oral Cancer Classification Using a Hybrid Attention-Aided D...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Dutta, Srinjan Roy, Jibesh Mandal, Diptarka Kaplun, Dmitrii Shpakovskaya, Irina Sarkar, Ram Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri India School of Computer Engineering and Mathematical Sciences Defence Institute of Advanced Technology Pune India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Process Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India I.P. Pavlov Saint Petersburg First State Medical University St. Petersburg Russia

ISBN: (纸本)9789819638628

Oral cancer remains a critical global health challenge, characterized by high morbidity and mortality due to late-stage diagnosis. This paper addresses the need for improved diagnostic accuracy by introducing a novel hybrid-attention aided deep learning model for oral cancer classification. Our approach integrates the EfficientNetB0 model for feature extraction with a customized hybrid attention module, combining self, spatial, and soft attention mechanisms to emphasize crucial features. The model has been trained and evaluated on both microscopic and macroscopic oral cancer datasets, demonstrating its generalizability. Our proposed model achieves an accuracy of 96.97% on a macroscopic dataset and 92% on a microscopic dataset, with respective F1-scores of 0.97 and 0.89, outperforming baseline models. This hybrid attention-aided deep learning model shows significant potential in improving early detection and treatment planning of oral cancer. Source code and additional results of this work can be found at the GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM

Hybrid Approach for Electricity Price Forecasting using Alex...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Bosubabu Sambana Kotamsetty Geethika Devi Bandi Rajeswara Reddy Galeti Mohammad Hussain Gownivalla Siddartha Department of Computer Science and Engineering (Data Science) School of Computing Mohan Babu University Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and price which leads to insufficient analysis of data. To address this issue, using the hybrid approach, which focuses on external variables that also effect the predicted prices. Nevertheless, due to AlexNet's excellent feature extraction and LSTM's learning sequential patterns, the prediction accuracy is vastly increased. The model is built on the past data, which has been supplied with the most significant elements like demand, temperature, sunlight, and rain. For example, the model applies methods, such as minimum-maximum scaling and a time window, to predict the electricity prices of the future. The results show that this hybrid model is good than the standalone ones in terms of accuracy. Although we got our accuracy rating of 97.08, it shows higher accompaniments than remaining models RNN and ANN with accuracies of 96.64 and 96.63 respectively.

关键词： Temperature distribution Accuracy Recurrent neural networks Rain Electricity Predictive models Prediction algorithms Data models Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Decoupling While Coupling: Towards More Accurate Stereo Image Sand Removal Beyond Certainty

Decoupling While Coupling: Towards More Accurate Stereo Imag...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

On the Possibility of Creating Energy-Efficient Mesh Network to Prevent Forest Fires and Provide Video Surveillance of Hard-to-Reach Areas

On the Possibility of Creating Energy-Efficient Mesh Network...

引用

International Youth Conference on Radio Electronics, Electrical and Power engineering (REEPE)

作者： Artem D. Penkin Denis I. Kochetkov Nikita D. Nashchekin Danila P. Posevin Igor P. Ivanov Department of Computer Science and Control Systems Bauman Moscow State Technical University Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

The paper considers the possibility of creating an energy-efficient mesh network for video monitoring of hard-to-reach areas, such as forests, tunnels and mountainous areas, in order to prevent forest fires. The main focus is on the use of decentralized MANET networks, which do not require infrastructure and have a low deployment cost. The paper proposes a prototype of a hardware and software system based on ESP8266 microcontrollers, using the painlessMesh library to transmit images between end nodes. Tests were carried out to determine the network throughput and optimal data transmission parameters depending on the required image quality and acceptable losses.

关键词： Mesh networks Forests Microcontrollers Prototypes Throughput Hardware Energy efficiency Data communication Monitoring Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach to Decision Support in Ensuring Software Code Security

Hybrid Approach to Decision Support in Ensuring Software Cod...

引用

International Youth Conference on Radio Electronics, Electrical and Power engineering (REEPE)

作者： Zuev I. A. Sakulin S. A. Shmakova A. V. Department of Computer Science and Control Systems Bauman Moscow State Technical University Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

In the context of the growing use of software, code security is of particular importance for preventing data leakages, financial losses and threats to national security. This paper proposes a hybrid approach to decision support for ensuring code security based on a combination of the results of static and dynamic code analysis. Static and dynamic analysis together allow identifying and eliminating vulnerabilities at various stages of the software development life cycle. The proposed approach is implemented as a decision support system for ensuring the software code security. During the experiment conducted on the implemented system, it was found that the use of the decision support module allows more efficient analysis of data on identified vulnerabilities. The system visualizes the results in graphical form, which facilitates the decision-making process for the user. In the presence of large data volumes and complex calculations, the human factor can lead to errors, which makes automation of the analysis process especially important. The results of the experiment confirm that the proposed approach not only improves the analysis quality, but also contributes to a more reliable software development process, given the constantly changing threat landscape.

关键词： Decision support systems Power engineering Codes Static analysis Reliability engineering Software Software reliability Security Risk management Software development management

来源：评论

学校读者我要写书评

暂无评论

Integration of Large Language Models for Autonomous Navigation of a Mobile Robot

Integration of Large Language Models for Autonomous Navigati...

引用

International Youth Conference on Radio Electronics, Electrical and Power engineering (REEPE)

作者： Andrew N. Kravtsov Boris S. Goryachkin Department of Computer Science and Control Systems Bauman Moscow State Technical University Moscow Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

The paper considers the integration of large language models (LLMs) to improve autonomous navigation of mobile robots. Traditional navigation methods are often limited by rigid algorithms that cannot adapt to dynamic environments. In contrast, LLMs enable robots to interpret complex spatial scenarios and make more informed decisions. The study demonstrates a new approach to robot control using the ROS with Gazebo simulator, where LLMs transform visual and sensory data into navigation commands. Experimental results demonstrate the feasibility of using LLMs to navigate in a pre-undefined environment improving the adaptability and autonomy of robots. The most successful model was the GPT -4o, and the best camera field of view was $90^{\circ}$ . The paper highlights the potential of LLMs in creating more intelligent and intuitive robot control systems.

关键词： Visualization Large language models Heuristic algorithms Robot control Semantics Robot vision systems Radio navigation Transforms Mobile robots Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Integrated Non-Terrestrial and Terrestrial Quantum Anonymous Networks

引用

IEEE Network 2025年第3期39卷 196-206页

作者： Khan, Awais Bui, Tinh Thanh Rehman, Junaid Ur Chatzinotas, Symeon Cotton, Simon L. Dobre, Octavia A. Duong, Trung Q. Shin, Hyundong Kyung Hee University Department of Electronics and Information Convergence Engineering Gyeonggi-do Yongin-si17104 Korea Republic of King Fahd University of Petroleum and Minerals Department of Electrical Engineering Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia University of Luxembourg Luxembourg City1855 Luxembourg Memorial University Department of Electrical and Computer Engineering St. John'sNLA1B 3X5 Canada Queen's University Belfast Department of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom

Due to optical fiber limitations for quantum communication, global-scale quantum networks are possible only by integrating non-terrestrial components in the overall network architecture. Quantum networks are expected to support distributed tasks for quantum information processing, such as quantum sensing, control, communication, and computing. These networks enable emerging applications that are uniquely quantum or augmented by quantum mechanics. Leveraging quantum resources, anonymous networking can be enhanced to such an extent that even an adversary with control over all network resources cannot trace the message source, achieving perfect untraceability. To provide this untraceable global connectivity, we demonstrate the integration of non-terrestrial networks (NTNs) and terrestrial networks (TNs) for quantum anonymous communication (QAC), highlighting possible architectures and key challenges in these integrated NTN-TN quantum anonymous networks (QANs). To illustrate and benchmark the design of QAC protocols within integrated networks, we present essential quantum protocols such as anonymous conference key agreement (CKA) and anonymous broadcast. In the first case study, we propose a satellite-to-ground quantum anonymous CKA (QA-CKA) protocol and assess the anonymous key exchange rate. This QA-CKA protocol utilizes low Earth orbit satellites to generate anonymous keys among two distinct TN nodes. In the second case study, we develop an air-to-ground quantum anonymous broadcast (QAB) protocol and examine the anonymous broadcast announcement rate. This QAB protocol exploits unmanned aerial vehicles to enable a broadcasting party to transmit classical information anonymously across two distinct TNs. These QAC protocols are simulated with realistic integrated network parameters to provide practical estimates of achievable performance. Furthermore, we discuss future research directions for enabling integrated NTN-TN QANs. © 1986-2012 IEEE.

关键词： Broadcasting antennas

来源：评论

学校读者我要写书评

暂无评论

Chatbot and its Impact on the Retail Industry 3

Chatbot and its Impact on the Retail Industry

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Tatikonda, Reshmi Kempanna, M. Thatikonda, Ramya Bhuvanesh, A. Thota, Ragupathi Keerthanadevi, R. Department of Computer Information Systems University of the Central Missouri Warrensburg United States Department of AI and ML Bangalore Institute of Technology Bengaluru India Department of Information Technology University of the Cumberlands Williamsburg United States Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli India Department of Information Technology Jawaharlal Technological University Hyderbad India Department of Computer Science and Engineering PSN College of Engineering and Technology Tirunelveli India

ISBN: (纸本)9798331527549

This study explores the transformative potential of chatbots in the retail industry, highlighting their role in enhancing customer engagement, optimizing business processes, and revolutionizing the nature of retail interactions. Through a comprehensive review of existing literature and case studies, the paper delves into the cognitive processes underlying human-chatbot interactions and examines their impact on customer experience, satisfaction, and loyalty. Chatbots serve a wide array of operational functions, including inventory management, automated order processing, data-driven analytics, and employee training. These functionalities streamline workflows, improve efficiency, and maximize resource utilization. The paper further explores the innovative applications of chatbots, including AI-driven personalization, conversational commerce, and seamless integration with emerging technologies. By analyzing both the current applications and challenges of chatbot technology in retail, the study uncovers the exciting opportunities they present for shaping the future of retail by fostering more personalized, efficient, and interactive customer experiences. © 2025 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Potential of Self-Supervised Monocular Depth Estimation via Patch-Based Self-Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 18042-18055页

作者： Yu, Ting Pan, Shan Chen, Wei Tian, Zijian Wang, Zehua Yu, F. Richard Leung, Victor C. M. Postdoctoral Research Station China RongTong Academy of Sciences Group Corporation Limited Beijing100022 China China RongTong Artificial Intelligence Research Center Beijing100022 China China University of Mining and Technology School of Artificial Intelligence Beijing100083 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China School of Artificial Intelligence Beijing100083 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

Perceiving scene depth and 3D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a Patch-based Self-Distillation Learning Framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentati

关键词： Image enhancement

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：