检索结果-内蒙古大学图书馆

An implementation of personalized therapy in Clinical Decision Support System using adaptive transformer and hybrid deep learning network

引用

Australian Journal of Electrical and Electronics engineering 2025年第1期22卷 105-120页

作者： Praveena Rachel Kamala, S. T, Saraswathi. Kaliraj, V. Nithya, A. Hema, R. Ramyadevi, R. Department of Information Technology Easwari Engineering college Tamil Nadu Chennai India Department of CSE S.A Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering St.Joseph’s College of Engineering Tamil Nadu Chennai India Department of Electronics and Communication Engineering Easwari Engineering College Tamil Nadu Chennai India Department of Computer Science and Applications SRM Institute of Science and Technology Tamil Nadu Chennai India

This paper suggests a new mechanism from deep learning concept for personalised therapy in Clinical Decision Support Systems (CDSS). Basically, the texts used for the observation are acquired from the standard data sources and then forwarded to the text preprocessing task. In the pre-processing phase, the punctuation and special character removal, stop word removal, and stemming process are applied to remove noise and help to eliminate the redundant information in order to improve the data quality. Further, the pre-processed text is applied to the Adaptive Transformer Net (ATN) for the feature extraction purpose, where the attributes in this task are optimally determined with the aid of the Adaptive Walrus Optimization Algorithm (AWOA). Finally, the resultant text is subjected to the Hybrid Deep Learning Network (HDLNet). The HDLNet model is implemented by integrating the ‘Residual Long Short-Term Memory (Residual LSTM) with Dilated Recurrent Neural Network (Dilated RNN)’. From the results, the sensitivity analysis performed in the implemented technique secured 3.7% more efficient than LSTM, 7.76% improved than MobileNet, 6.7% superior to residual LSTM, and 0.90% effective than dilated RNN in dataset 1. Throughout the validation, the conventional techniques are evaluated with the suggested personalised therapy in CDSS to prove its efficacy. ©, Engineers Australia.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Blockchain assisted fog computing framework for secure data sharing mechanism in smart home 1

A Blockchain assisted fog computing framework for secure dat...

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Apat, Hemant K. Sahoo, Bibhudatta Mohanty, Sagarika Mukul, Manas Barik, Rabindra K. National Institute of Technology Computer Science and Engineering Rourkela India Kalinga Institute of Industrial Technology School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350335774

The demand and popularity of Internet of Things (IoT) has been growing with exponential rate due to the rapid growth of various smart devices in the IoT ecosystem. The request generated through various smart devices is generally stochastic and unscheduled. The existing IoT-Cloud paradigm does not provide the security services efficiently and effectively. In order to provide better security services to different IoT applications domain particularly in smart home domain, it introduces the blockchain technology. So, in the present article, it proposes BlockCFS framework, which is an innovative blockchain assisted fog computing framework, as a safe datasharing mechanism for smart homes. It also illustrates the methodical sequence diagram for the BlockCFS, for registering and transmitting data from a variety of smart devices that are connected in a smart home. © 2023 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

HGP-NLP at BioLaySumm: Leveraging LoRA for Lay Summarization of Biomedical Research Articles using Seq2Seq Transformers 23

HGP-NLP at BioLaySumm: Leveraging LoRA for Lay Summarization...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Malik, Hemang Pradeep, Gaurav Seth, Pratinav Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Data Science & Computer Applications India Dept. of Computer Science & Engineering India

ISBN: (纸本)9798891761308

Lay summarization aims to generate summaries of technical articles for non-experts, enabling easy comprehension for a general audience. The technical language used in research often hinders effective communication of scientific knowledge, making it difficult for non-experts to understand. Automatic lay summarization can enhance access to scientific literature, promoting interdisciplinary knowledge sharing and public understanding. This has become especially important for biomedical articles, given the current global need for clear medical information. Large Language Models (LLMs) (Yao et al., 2024), with their remarkable language understanding capabilities, are ideal for abstractive summarization, helping to make complex information accessible to the public. This paper details our submissions to the BioLaySumm 2024 Shared Task: Lay Summarization of Biomedical Research Articles (Goldsack et al., 2024). We fine-tune and evaluate sequence-to-sequence models like T5 across various training dataset settings and optimization methods such as LoRA (Hu et al., 2021b) for lay summarization. Our submission achieved the 53rd position overall.. ©2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Improved UNET Architecture for Effective COVID-19 Severity Prediction from Pulmonary CT Images 1

Improved UNET Architecture for Effective COVID-19 Severity P...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Ramla, M. Jasmine, R. Anita Ramesh, M. Bai, Femilda Josephin Joseph Shobana SRM Institute of Science and Technology Department of Computer Applications Chennai India SRM Institute of Science and Technology Department of Data Science and Business Systems Chennai India SRM Institute of Science and Technology Department of Computer Science Chennai India Istinye University Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350376517

COVID-19, is one of the deadliest pandemic hit globally crises in the recent years, continues to persist with emerging variants of concern. Due to the virus's high transmissibility, rapid and precise detection of COVID-19 is crucial for timely medical intervention. This research presents an advanced deep transfer learning approach for quantifying the severity of COVID-19 infection from CT lung images. Using computer vision techniques, lung regions were extracted from CT scans through semantic segmentation using SegNet. An enhanced U-Net architecture, integrated with the Atrous Spatial Pyramid Pooling (ASPP) technique, was employed to semantically segment the infected regions of the lungs. Based on the segmented infection areas, the severity of the infection was classified into mild, moderate, and severe. The proposed framework, which incorporates lung extraction followed by Ground-Glass Opacity (GGO) segmentation, achieves the segmentation accuracy of 96% and a prediction accuracy of 98.9%. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in the Internet of Things: A Trust-Based Protocol for Resilient Communication

引用

SN computer science 2024年第1期5卷 4页

作者： Althaf Ali, A. Hussain, Mohammed Muzaffar Subramaneswara Rao, A. Lavanya, S. Feroz Khan, A.B. Department of Computer Applications Madanapalle Institute of Technology & Science (MITS) Andhra Pradesh Madanapalle India Department of Computer Science and Engineering C. Abdul Hakeem College of Engineering and Technology Tamil Nadu Melvisharam India Department of Software Applications Thiruthangal Nadar College Tamil Nadu Chennai India Department of Computer Science Syed Hameedha Arts and Science College Tamil Nadu Kilakarai India

The quick increasing in the Internet of Things (IoT) devices has raised significant security concerns, particularly in the face of reactive jamming attacks. This paper proposes a trust-based protocol named Trust-Based Protocol for Resilient Communication (TBRC) that incorporates a robust key management technique to improve the security of IoT systems and mitigate the impact of reactive jamming attacks. To assess the effectiveness of our protocol, the work is compared with existing schemes such as CKMT, EDDK, and CEMT. Through extensive simulations under realistic conditions, we analyze key performance metrics, including energy consumption, packet loss, computational time, and throughput. The comparative analysis demonstrates that our proposed protocol outperforms CKMT, EDDK, and CEMT in terms of computational efficiency, throughput, and delay, making it a more effective solution for secure IoT communication. By leveraging a robust key management technique, our protocol provides a secure and resilient communication framework for IoT environments, effectively countering reactive jamming attacks. The integration of this technique strengthens the overall security posture of IoT networks, ensuring reliable and secure communication between devices. This work contributes to advancing IoT security by introducing a trust-based protocol with a robust key management technique that effectively mitigates the impact of reactive jamming attacks. The comparative evaluation against existing schemes validates the superiority of our proposed approach in terms of security, efficiency, and reliability. The results of our evaluation highlight the improved performance of our protocol, positioning it as a promising solution for real-world IoT deployments. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DDoS IoT Security Trusted metrics

来源：评论

学校读者我要写书评

暂无评论

Integrative Remote Sensing Approaches Using Generative Adversarial Networks for Urban Heat Island Analysis and Mitigation

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 681-698页

作者： Sundar, Ganapathy Patchaiammal, Pitchaimuthu Venkateshwarulu, Balaji Vijayan Kumar, Thangavel Pradeesh Rajamannar, Kesavamoorthy Tripathi, Rajesh Kumar Department of Computer Applications Sindhi College Chennai India Department of Information Science and Engineering HKBK College of Engineering VTU Belagum Bengaluru Nagawara India VIT School of Agricultural Innovations and Advanced Learning (VAIAL) VIT Vellore India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Computer Engineering and Applications GLA University Uttar Pradesh Mathura India

The phenomenon of urban heat islands (UHI) presents a critical challenge for urban sustainability, exacerbating local temperatures, increasing energy demands, and impairing public health. Traditional methods for addressing UHI are often resource-intensive and slow. This study introduces a novel approach, utilizing a Hybrid CycleGAN-SVM (HCGS) model that leverages the synergy of Generative Adversarial Networks (GANs) and Support Vector Machines (SVMs) to efficiently analyze and mitigate UHI effects through high-resolution satellite imagery and temperature data. The model incorporates Enhanced Vision Transformers (EViTs) for superior feature extraction, adept at capturing intricate spatial and spectral urban patterns. The CycleGAN component of the model generates high-quality synthetic imagery, enhancing the dataset and addressing class imbalances, thereby bolstering the SVM classifier’s ability to precisely pinpoint heat-prone urban areas. Implemented in Google Colab, the HCGS model demonstrated exceptional performance, achieving a classification accuracy of 0.98. This indicates its potential as an effective tool for urban heat mitigation, offering actionable insights for urban planning and policy-making. By integrating advanced machine learning techniques with remote sensing data, the HCGS model paves the way for innovative climate adaptation strategies, fostering more sustainable and resilient urban environments. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Enhanced Vision Transformers EViTs GANs Generative Adversarial Networks HCGS model Hybrid CycleGAN-SVM Satellite imagery Support Vector Machines SVM UHI effect Urban heat island

来源：评论

学校读者我要写书评

暂无评论

Bubble Prediction in Stock Markets: Leveraging SVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations based on Support Vector Machine (SVM) and through important technical indicators. Among these are momentum indicators, such as the Relative Strength Index (RSI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from Bollinger Bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out based on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Impact of nutrients in food quality and safety by machine learning classifier using internet of things

引用

International Journal of Information Technology (Singapore) 2024年第5期16卷 2803-2812页

作者： Balamurugan, S. Gurumoorthi, E. Devi, P.P. Maruthamuthu, R. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & amp Department of IT CMR College of Engineering and Technology Telangana Hyderabad India Department of Computer Applications Madanapalle Institute of Technology and Science AP Madanapalle India

The traditional Food Supply Chain (FSC) is challenged by a number of issues, including uncertainty, security, expense, complexity, and quality worries. A precise supply chain is required to address these problems. Managing the supply chain to distribute high-quality goods is a difficult task in the modern food sector. The efficient Tree Augmented Naive Bayes linked with FSC utilizing Internet of Things (IoT) is proposed in this paper to enable tracking, tracing, and managing the full food supply chain process, including supplier, exporter, and consumers. This paper's goals are to evaluate the food safety and create the best possible chronological data for the analysis of potential future assumptions. It also intends to connect the producer and the buyer by delivering high-quality food goods while using IoT technology to transport food from the producers to the customers. IoT-based food supply chain traceability is used to successfully transact data with ambiguous, unreliable, and inadequate data. In order to provide secure backdrop and food safety for FSC process utilizing IoT technology, the suggested effective Tree Augmented Naive Bayes algorithm would be able to overcome the challenges of conventional supply chain. © Bharati Vidyapeeth's institute of computer applications and Management 2024.

关键词： Bayes classifier algorithm Food safety and IoT FSC Traceability Tree augmented Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Prediction of Efficient Driving Mode for Vehicle using Machine Learning 3

Prediction of Efficient Driving Mode for Vehicle using Machi...

引用

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Hegde, Ramakrishna Kripa Das, Sujan D Sriraksha, M.S. Siri, R. Siri Gowri, H. Soumyasri, S.M. Vidyavardhaka College of Engg. Computer Science Engineering Mysuru India PES University Computer Science Engineering Bengaluru India The National Institute of Engineering Master of Computer Applications Mysuru India

ISBN: (纸本)9798350340358

The field of autonomous driving cars is a rapidly growing area of research, machine learning and image recognition technology plays a pivotal role in ensuring their safe navigation on the roads. Different driving modes are offered by modern cars to accommodate various road conditions and driver preferences. However, manually selecting these modes can be cumbersome. Addressing the dynamic nature of mode switching in autonomous driving systems presents a multifaceted challenge. The system must continuously assess a multitude of variables such as traffic patterns, road conditions, weather conditions, and the wear and tear of vehicle components. Traffic conditions can change rapidly, requiring real-time analysis of traffic flow and congestion. Road conditions, including the presence of obstacles, construction zones, or slippery surfaces, demand instant adaptation for safe navigation. Weather conditions further complicate the scenario, as rain, snow, fog, or even intense sunlight can impact visibility and road grip. Addressing these challenges requires sophisticated algorithms capable of processing vast amounts of data from various sensors in real time. Machine learning models must be trained to recognize patterns in diverse conditions, enabling the system to make informed decisions swiftly and accurately. Moreover, the system must possess the ability to prioritize these factors based on their immediate impact on driving safety and efficiency. This can be a future enhancement of the paper. By leveraging machine learning algorithms, the mode selection process can be automated. The system constantly monitors driving conditions, learns from real-time camera sensor data and selects the most optimal mode to adapt to current situation. Different models such as Convolutional Neural Network (CNN), CNN with MobileNetV2 as base and decision trees are analyzed. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Novel Anchor Generation Based Residual Network for Object Tracking in Video-Surveillance applications

引用

SN computer science 2025年第2期6卷 1-12页

作者： Mohanapriya, D. Rajalakshmi, K. Helen Josephine, V.L. Panneerselvam, Karthick Department of Computer Science (SF) Sourasthra College Tamil Nadu Madurai India Department of Computer Applications CMR Institute of Technology Karnataka Bangalore India Business Analytics School of Business and Management Christ University Karnataka Bangalore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamilnadu Uthupalayam 641407 India

The activity of the object in question is alerted directly upon completion of an effective object tracking. Dependent on hardware support or not, a strong object tracking protocol is required for a precise object tracking application. According to these methods, tracking an object accurately within a predetermined processing time window required a significant amount of computer complexity. In contrast, a variety of quality-degrading elements, including occlusion, shifting lighting, shadows, and so on, have an adverse effect on tracking. All of these tracking shortcomings will be fixed by a revolutionary residual network based on loss operator and anchor creation. Detection of object has concerns that rely on the process of feature extraction to afford efficient quality. For this purpose a model called ResNet has been used that comprises thirty layers and hence named as Resnet-thirty. These networks are a type of Convolutional Neural Network (CNN) that contain residual connections among various layers. The various merits of these connections is the network has the capability to learn the features of global, local and intermediate in parallel. As such, the system is robust against changes in lighting. These variations in light were understood in terms of tracking objects within a changing background. The proposed work uses MOT datasets. This dataset comprises of MOT 15, MOT16, MOT17 and MOT20. The results have been found by using these datasets. Hence, it evidently outperforms in terms of precision, recall, MOTA, IDF, MOTP, SAIDF and F1 measure to track the objects. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： computer vision Loss operator Object tracking Residual network

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：