检索结果-内蒙古大学图书馆

International Conference on Electrical and Electronics engineering, ICEEE 2023

作者： Shaik, Nazeer Gupta, Ankur Bhati, Sunita Kumar, Jaideep Singh, Jagendra Budhiraja, Ishan Department of Computer Science and Engineering Srinivasa Ramanujan Institute of Technology Andhra Pradesh Anantapur India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Applications JECRC University Jaipur India Raj Kumar Goel Institute of Technology AKTU University Lucknow India

ISBN: (纸本)9789819986606

Segregation of images is a critical step in processing images, computer vision, and a variety of other disciplines. The technique involves decomposing an illustration into numerous components or components, every single one that consists of an ensemble of elements with identical features for example African descent, frequency, or consistency. The most important objective of appearance, the intention of fragmentation seems to reduce complexity or customize the mathematical representation of an illustration in a way that is more readily reasonable and more straightforward for assessment. It is widely employed to locate boundaries and features in photos, and this is favorable in an assortment of industries including clinical imaging, object detection, recognition, and autonomous vehicles. Several image segmentation techniques are available, and in incorporating thresholding, zone is an area-based differentiation and corner-based recognition. A threshold segment is a simple and commonly used technique that involves setting a threshold value and dividing the pixels into two classes based on their intensity values. Region-based segmentation involves grouping pixels based on their spatial proximity and similarity in characteristics, while edge-based segmentation involves detecting edges or boundaries in an image and using them to separate different regions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

pFedCal: Lightweight Personalized Federated Learning with Adaptive Calibration Strategy

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1627-1640页

作者： Deng, Dongshang Wu, Xuangou Zhang, Tao Xiang, Chaocan Zhao, Wei Xu, Minrui Kang, Jiawen Han, Zhu Niyato, Dusit Anhui University of Technology School of Computer Science and Technology Anhui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243002 China Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Anhui Provincial Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui243002 China Chongqing University College of Computer Science Chongqing400044 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Guangdong University of Technology School of Automation Guangzhou510062 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Federated learning (FL) is a promising artificial intelligence framework that enables clients to collectively train models with data privacy. However, in real-world scenarios, to construct practical FL frameworks, several challenges have to be addressed, including statistical heterogeneity, constrained resources, and fairness. Therefore, we first investigate an aggregation gap caused by statistical heterogeneity during local model initialization, which not only causes additional computational overhead for clients but also leads to the degradation of fairness. To bridge this gap, we propose pFedCal, a novel personalized federated learning with lightweight adaptive calibration strategy that performs calibration compensation through the prior knowledge of clients. Specifically, we introduce compensation for each client at the model initialization, with the compensation derived from the global gradient and the latest gradient bias. To enhance the calibration effect, we introduce a smoothing-based calibration strategy, and we design an adaptive calibration strategy. A representative example demonstrates that the proposed calibration and smoothing strategies improve fairness for clients. The theoretical analysis indicates that with an appropriate learning rate, pFedCal converges to a first-order stationary point for non-convex loss functions. Comprehensive experimental results show that pFedCal achieves faster convergence, higher accuracy, and improved fairness than the state-of-the-art methods. © 2008-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Precision Medicine: Advancing Personalized Treatment Plans in Oncology

Deep Learning for Precision Medicine: Advancing Personalized...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Shrivastava, Anurag Kotiyal, Arnav Jain, Alok Devi, V.S Anusuya Rao, Bolleddu Devananda Bansal, Saloni Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Phagwara India New Horizon College of Engineering Department of Applied Sciences Bangalore India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798331512965

A new approach to cancer care, precision medicine tailors treatments to each patient's specific genetic, molecular, and clinical characteristics. In order to analyze complicated, high-dimensional data and create individualized treatment plans, deep learning - a potent subfield of AI - has arisen as a game-changing tool in this area. Discover how deep learning methods are being used in precision oncology to improve cancer diagnosis, prognosis, and treatment planning in this groundbreaking article. A few examples of notable developments are the use of CNNs to medical image tumor identification and segmentation, RNNs to treatment outcome prediction, and LSTM models to patient survival. More effective and less harmful treatments are possible because too deep learning models that integrate multimodal data, such as genetic sequences, histopathological pictures, and electronic health records. These models can detect new biomarkers and forecast how different medications will affect individual patients. The clinical translation of deep learning models is hindered by a number of obstacles, despite these encouraging improvements. Problems including data scarcity, unequal distribution of classes, and unintelligibility are major roadblocks. Also, to make sure these models are accurate and reliable, they need to be standardized and validated thoroughly before they can be used in clinical processes. Fostering trust and acceptance in therapeutic contexts also requires addressing ethical problems, such as data security, possible biases in algorithmic predictions, and patient privacy. This work offers a thorough analysis of existing approaches, delves into the difficulties and moral concerns, and suggests avenues for further study to improve the use of deep learning in precision oncology. Personalized treatment regimens, made possible by deep learning, have the potential to revolutionize cancer care by vastly increasing patient outcomes. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Consumption in Smart Buildings through Reinforcement Learning-Based Demand Response Strategies

Optimizing Energy Consumption in Smart Buildings through Rei...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Kansal, Vipashi Al-Attabi, Kassem Kumar, Rakesh Boob, Nandini Shirish Anand, Sami Gupta, Priyanka Graphic Era Deemed To Be University Department Of Computer Science & Engineering Dehradun India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Gla University Department Of Computer Engineering & Applications Mathura India Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Tamilnadu Chennai India Lovely Professional University Phagwara India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India

ISBN: (纸本)9798350366846

This research studies the feasibility of RL-based response strategies that can maximize energy consumption in a smart building. By the inclusion of recreational pondering and observational investigation, RL operators automatically calibrated HVAC setpoints lighting levels level machine usage to reduce energy costs without compromising human comfort. It is thus evident from the results that significant value energy used on savings, RL-based algorithms achieved an average cost reduction of 16% compared to pattern based techniques. And the reasonable limits of tenant consolation hold standard fluctuation in temperature at 0.4 °C and variances from normal lighting level up to ten percent are also allowed. The occurrence of imperative violation is also reduced as RL-based approaches exhibit a lower number in comparison to rule based control and passive planning methods. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Virtualization Security with a Z-Score Based Conjugate Self-Organizing Migration ML Model 15

Enhancing Cloud Virtualization Security with a Z-Score Based...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sidana, Sagar Thakur, Sujata Negi Sinha, Anurag Indhumathi, N. Raj, Petheru Al-Khayyat, Ahmed Modi, Vyom Mishra, Aditya Kumari, Anita Maharshi Dayanand University Department of computer science and engineering Haryana Rohtak India Graphic Era Hill University Department of computer science and engineering India Ignou School of Computing and information Science New Delhi India Kongu Engineering College Department of Electronics and Communication Engineering Erode Perundurai638060 India Reliance Jio Platforms Ltd Bangalore India Islamic University Department of computer science and engineering Iraq Marwari Education Foundations Group Of Institutions Rajkot India Gla University Department of computer science and engineering Applications Mathura India Rkdf University Department f English Literature India

ISBN: (纸本)9798350370249

This study presents a new machine learning model for detecting malware in cloud computing settings called Conjugate Self-Organizing Migration (CSOM), which is based on Z-score. Feature vectors are standardized by the model through the use of Z-score normalization, which improves its flexibility with changing data distributions. By merging self-organizing migratory processes with statistical analysis, the CSOM model effectively reduces the threat of growing malware. Using Z-score normalization to guarantee correct representation of changing data, the imaging approach depicts the cloud environment as a dynamic, self-organizing landscape. Through conjugate migration techniques, the CSOM model dynamically modifies synaptic weights to minimize false positives and enable the identification of tiny fluctuations in harmful actions. The Z-score-based CSOM model is effective in detecting malware at high accuracy rates in a variety of dynamic cloud environments, as demonstrated by the experimental results. The model demonstrates its flexibility in responding to changing cyberthreats with its strong performance in real-world settings. Finally, with its better accuracy and adaptability, the suggested Z-score-based CSOM model offers a potential approach for cloud computing virus detection. In order to handle the constantly shifting environment of cloud-based cyber threats, further research may examine scalability and more refinement. © 2024 IEEE.

关键词： Cloud Computing Conjugate Self-Organizing Migration Machine Learning Model Malware Detection Z-score

来源：评论

学校读者我要写书评

暂无评论

Integrating Embedded Systems with Natural Language Processing: Innovations and applications in Intelligent Systems 4

Integrating Embedded Systems with Natural Language Processin...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Shrivastava, Anurag Rawat, Ruchira Al-Fatlawy, Ramy Riad Bansal, Saloni Sehgal, Archana Gupta, Priyanka Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Gla University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798331518981

The amalgamation of Natural Language Processing (NLP) with Embedded Systems signifies a revolutionary progression in the creation of intelligent systems, permitting them to participate in interactions that are akin to those of humans. This study looks into the creative ways that NLP and embedded technology can be used in a variety of industries, such as healthcare, automotive, and smart homes. The paper illustrates how NLP enables embedded devices to comprehend, interpret, and react to human commands, improving user experience and operational efficiency, by looking at the underlying principles. The main obstacles to this integration are thoroughly examined, including resource shortages, the need for real-time processing, and environmental restrictions. The study emphasises how important it is to use low-power, compact NLP models that enable real-time language processing without sacrificing system efficiency. Additionally, the research discusses the fundamental approaches for improving these models' using methods like transfer learning, quantisation, and model reduction. In the end, this work seeks to shed light on the enormous potential of voice-enabled intelligence in embedded systems, opening the door to more interactive, intuitive, and adaptable technologies that can easily adjust to changing human needs. This study advances the continuous development of smart gadgets by bridging the linguistic and technological divide, increasing their usability and accessibility in daily life. © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligence-Based Clustering Algorithms for Wireless Sensor Networks

Swarm Intelligence-Based Clustering Algorithms for Wireless ...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Nainwal, Ankita Shnain, Ammar Hameed Kumar, Rakesh Boob, Nandini Shirish Verma, Vikas Sangeeta, K. Graphic Era Deemed To Be University Department Of Computer Science & Engineering Dehradun India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Gla University Department Of Computer Engineering & Applications Mathura India Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Tamilnadu Chennai India Lovely Professional University Phagwara India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India

ISBN: (纸本)9798350366846

This work studies the use of swarm intelligence-based clustering algorithms such as Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO) Bee Algorithm (BA), and Firefly Algorithm (FA), to optimize Wireless Sensor Networks. (WSNs). It evaluated their performance by strict simulations on energy consumption level, network lifetime, and clustering quality. It is observed that ACO and PSO consistently showed better results with moderate energy consumption by achieving long network lifetimes as well as precise clustering. However, BA and FA have been competitive but had lower efficiency when looking at certain metrics. The comparative analysis highlights the need for algorithmic selection according to specific demands in WSN deployments. The study complements related research on the application of swarm intelligence in WSN by focusing on routing challenges, energy-aware protocols, and centralized clustering solutions. The results give useful information to practitioners who are looking for the best algorithms, especially in real WSN situations. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

AI for Smart Farming: Machine Learning Models for Precision Crop Yield Prediction

AI for Smart Farming: Machine Learning Models for Precision ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Praveen, R.V.S. Maindola, Meenakshi Bhavana, Munugapati Nijhawan, Ginni Raju, Hemanth Bansal, Saloni LTIMindtree Limited Digital Engineering and Assurance Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Lovely Professional University Dept. of Comp. Sc. & Engg. Phagwara India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798331512965

AI and other advanced technologies are gradually beginning to invade the agriculture sector to serve the increasing demand of the consumers for better methods of food production. A key component of precision agriculture, this work focuses on how to use machine learning models to predict crop yields with high accuracy. Specifically, the nature and volatility of the environmental context - such as the nature and quality of soils, as well as the climatic and water conditions - present a major challenge to the application of the conventional modeling approaches aimed at forecasting productive capacity in agriculture. Still, when comparing, the AI-driven models will allow sorting through much information gathered from different sources, including sensors, satellite imagery, and yield history. This work examines the differences of several machine learning models. Such models are the Random Forests, SVMs, and CNNs and other Deep Learning methodologies respectively. A quality model is evaluated based on scalability, computational performance, and prediction accuracy. Also in scope of the study, there is an opportunity to employ IoT together with data collected with remote sensing to make and provide realtime forecasts and evaluations. By the utilization of the results attained, it is established that the yields expected by the machine learning models are much more precise, which aids in enhancing agricultural decision-making concerning resource utilizing, crop handling, and risk minimization. The purpose of this study is focused on the promotion of the agricultural sustainability and production through the development of the innovative data driven farming practices. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A novel soft computing based efficient feature selection approach for timely identification of COVID-19 infection using chest computed tomography images: a human centered intelligent clinical decision support system

引用

Multimedia Tools and applications 2025年第14期84卷 13717-13785页

作者： Singh, Law Kumar Khanna, Munish Garg, Hitendra Singh, Rekha Department of Computer Engineering and Applications GLA University Mathura281406 India School of Computing Science and Engineering Galgotias University Plot No.2 Sector 17-A Yamuna Expressway Gautam Buddh Nagar Greater Noida203201 India Department of Physics Uttar Pradesh Rajarshi Tandon Open University Uttar Pradesh Prayagraj India

The SARS-CoV-2 coronavirus strain’s introduction in December 2019 resulted in the development of the new coronavirus disease, COVID-19. Following its first appearance, the virus quickly spread throughout the world and is now considered to be a pandemic. There were 6,885,962 recorded deaths and 689,853,908 confirmed cases as of April 4, 2023. It is essential to put in place a thorough testing strategy in order to stop the disease from spreading. Nonetheless, a number of testing approaches are presently under consideration due to a restricted inventory and a limited supply of testing equipment. Recent expert analysis suggests that images from chest computed tomography (CT) scans could reveal important information about COVID-19, which is why we are using this modality as a focus of our investigation. Moreover, numerous recent studies have demonstrated that selecting the most informative features from the subject images improves the classification models’ efficiency and shortens the time needed for training and testing. All of this encourages us to present a study that suggests a novel, efficient, and fast feature selection system as the core of the proposed highly competent clinical decision support system for COVID-19 infection prediction. Using a publicly accessible CT image dataset, this four-phase system divides the images into two categories: "COVID-19-infected human" and "healthy human". Pre-processing is the first step in the study, after which features from different categories in the images are extracted in the next phase. In the third phase, the most influential features are then selected using three algorithms: the Teaching Learning-Based Optimization Algorithm (TLBO), the Cuckoo Search Optimization Algorithm (CSO), and a proposed hybrid of these two. To the best of the authors’ knowledge, these algorithms have rarely been applied to feature selection for COVID-19 infection prediction, which highlights the originality and inventiveness of the work. Followin

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Multilingual and Cross Lingual Audio Emotion Analysis Using RNN 1

引用

International Conference on Advances in IoT, Security with AI, ICAISA 2023

作者： Bhattacharya, Sudipta Mishra, Brojo Kishore Borah, Samarjeet Department of Computer Science and Engineering GIET University Gunupur India Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim Gangtok India

ISBN: (数字)9789819950881

ISBN: (纸本)9789819950874

Speech and language are necessary for a person’s development of their emotional and social skills. Reading, writing, and verbal apprehensions are vital components of the overall learning process, and hence, instruction or some linguistic representation is necessary for academic achievement. This study has been highlighted using several audio files based on various linguistic methodologies, and it has been compared using multilingual and cross-lingual methods. For our experiments with the English, German, Italian, and Canadian-English emotion datasets, we have decided to use CNN and LSTM as our models of choice. We obtained the most outstanding results in Canadian English during the trial with a single language. Here, we obtained CNN at 99.12% and LSTM at 98.96%. During the experiment with several languages, only English test data was found to be secure at 98.19% in CNN and 93.41% in LSTM. Lastly, in the cross-lingual domain of Canadian English, namely 93.25%, we found 98.19% using the CNN and LSTM models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Emotion Recognition

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：