检索结果-内蒙古大学图书馆

Density Based Clustering Approach Combined with Fuzzy Logic for Elimination of Random Valued Impulse Noise

Journal of The Institution of Engineers (India): Series B 2025年 1-14页

作者： Basu, Sulagna Bandyopadhyay, Aritra Department of Computer Science and Engineering Supreme Knowledge Foundation Group of Institutions 1 Khan Road Mankundu West Bengal Chandannagar712139 India

The reduction of impulse noise is crucial in processing pictures since it directly impacts the patterns of noise present. This paper proposes a two-step technique, known as DCIFF (DBSCAN clustering identified fuzzy filter), to effectively eliminate impulsive noise from digital images. The suggested DCIFF methodology employs the DBSCAN clustering algorithm to identify and classify noise. Subsequently, a noise reduction technique is presented, which relies on the principles of fuzzy reasoning. The density-based clustering approach DBSCAN is utilized to identify commonalities throughout all 5 × 5 sized windows that are created by centering each of the pixels in the picture. Next, to properly reduce noise, a sized 7 × 7 window is formed with the centre of each identified disturbed pixel. The non-noisy pixel intensities are multiplied by their triangle fuzzy membership values, and then the products are added together. The total result is then divided by the sum of the fuzzy membership of all the non-noisy pixels’ intensities. The outcome is utilized to eliminate the noise from the central pixel that is affected by noise. The DCIFF is assessed using standard image evaluation criteria for various pictures. On the Lena image modified by random valued impulsive noise at 80% noise density, DCIFF provided peak-signal-to-noise ratios (PSNR) of 25.86 dB and structural similarity indexes (SSIM) of 0.8429. In contrast to prior research on the same topic, the current study findings consistently demonstrate striking outcomes. © The Institution of Engineers (India) 2025.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Enhancing reliability in coronary artery disease prediction using ensemble learning for key attribute identification

引用

Life Cycle Reliability and Safety engineering 2025年 1-14页

作者： Upadhyay, Sachin Sagar, Anil Kumar Roy, Nihar Ranjan Department of Computer Science and Engineering School of Engineering and Technology Sharda University Knowledge Park III Greater Noida India Department of Computer Science and Engineering School of Engineering and Technology VIPS-TC Delhi Pitampura India

Cardiovascular disease (CAD) is a significant public health concern, affecting a large population worldwide. Early diagnosis and management of CAD can minimize the risk of acute myocardial infarction and improve patient outcomes. Assessment tools like SBP, cholesterol, pulse rate, and ST segment depression can help identify causes early and manage them effectively. Management includes medication therapy, healthy dietary habits, and exercise. Several machine learning (ML) methodologies have been researched to enhance CAD predictions, including AdaBoost, ANNs, J48, Decision Tree, K Nearest Neighbor (KNN), Naïve Bayes, and Random Forest. However, single models still lack sufficient capacity to address the complexity and flexibility of CAD. Ensemble learning, which uses multiple classifiers to boost predictability, has been employed to address these issues. The system was developed after benchmarking it with multiple classifiers on a Cleveland cardiac disease dataset. The ensemble method showed a 92.11% accuracy rate, far better than the highest performing classifier operating individually. This suggests the possibility of practical solutions for CAD prediction using ensemble methods, enabling precise early diagnosis and efficient targeted treatment. Comparing ensemble learning for CAD predictors reveals how these approaches can revolutionize medicine by enabling early diagnosis and personalized treatment plans. There is a need to further develop these methods for clinical application, such as creating practical tools for easier application by healthcare workers and integrating sophisticated techniques. In conclusion, ensemble learning methods represent significant advancements in CAD prediction, with superior performance in identifying critical attributes and enhancing predictive accuracy. As healthcare evolves with the integration of intelligent technologies, the adoption of ensemble learning methods holds great promise for enhancing patient outcomes and reducing the

关键词： ANN CAD Decision Trees Ensemble KNN Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

LSTM-XGBoost: An Ensemble Model for Blood Demand Distribution Forecasting – A Case Study in Zakho City, Kurdistan Region, Iraq

引用

Operations Research Forum 2025年第1期6卷 1-22页

作者： Zebari, Rizgar R. Zebari, Gheyath M. Al-zebari, Adel Mohammed, Marwan Aziz Department of Computer Science College of Science Knowledge University Erbil 44001 Iraq Department of Information Technology Technical College of Informatics Akre University for Applied Sciences Kurdistan Akre Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq

A safe and adequate blood supply is essential for healthcare systems to function effectively. Accurately forecasting blood demand plays a key role in efficient inventory management and resource allocation. Traditional forecasting methods, like moving averages and ARIMA models, often fall short due to the complexity of factors influencing blood demand. This study introduces an innovative hybrid ensemble model that combines Long Short-Term Memory (LSTM) networks with XGBoost, harnessing their combined strengths to enhance forecasting accuracy. By analyzing blood donation data from the Zakho Blood Bank (January 1, 2015—July 22, 2022), the model outperforms individual LSTM and XGBoost models, excelling in metrics such as Mean Square Error (MSE) and Mean Absolute Error (MAE). These findings underscore the potential of advanced machine learning techniques to improve healthcare supply chain management and ensure the timely availability of critical blood supplies. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Blood banking Blood demand forecasting Healthcare supply chain LSTM network Machine learning XGBoost

来源：评论

学校读者我要写书评

暂无评论

The superalignment of superhuman intelligence with large language models

引用

science China(Information sciences) 2025年第06期 101-111页

作者： Minlie HUANG Yingkang WANG Shiyao CUI Pei KE Jie TANG The CoAI Group Department of Computer Science and Technology Tsinghua University Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China Knowledge Engineering Group Department of Computer Science and Technology Tsinghua University

We have witnessed the emergence of superhuman intelligence thanks to the fast development of large language models(LLMs) and multimodal language models. As the application of such superhuman models becomes increasingly popular, a critical question arises: how can we ensure they still remain safe, reliable, and aligned well with human values encompassing moral values, Schwartz's Values, ethics, and many more? In this position paper, we discuss the concept of superalignment from a learning perspective to answer this question by outlining the learning paradigm shift from large-scale pretraining and supervised fine-tuning, to alignment training. We define superalignment as designing effective and efficient alignment algorithms to learn from noisy-labeled data(point-wise samples or pair-wise preference data) in a scalable way when the task is very complex for human experts to annotate and when the model is stronger than human experts. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We then present a conceptual framework for superalignment, which comprises three modules: an attacker which generates the adversary queries trying to expose the weaknesses of a learner model, a learner which refines itself by learning from scalable feedbacks generated by a critic model with minimal human experts, and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing. We discuss some important research problems in each component of this framework and highlight some interesting research ideas that are closely related to our proposed framework, for instance, self-alignment, self-play, self-refinement, and more. Last, we highlight some future research directions for superalignment, including the identification of new emergent risks and multi-dimensional alignment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in NSL-KDD Dataset Using Hybrid Self-Organizing Map Model

引用

computer Modeling in engineering & sciences 2025年第4期143卷 639-671页

作者： Noveela Iftikhar Mujeeb Ur Rehman Mumtaz Ali Shah Mohammed J.F.Alenazi Jehad Ali Knowledge Unit of Systems and Technology University of Management and TechnologySialkot51310Pakistan Department of Computer Science University ofWahWah Cantt47010Pakistan Department of Computer Engineering College of Computer and Information Sciences(CCIS)King Saud UniversityRiyadh11451Saudi Arabia Department of AI Convergence Network Ajou UniversitySuwon16499Republic of Korea

Intrusion attempts against Internet of Things(IoT)devices have significantly increased in the last few *** devices are now easy targets for hackers because of their built-in security *** a Self-Organizing Map(SOM)hybrid anomaly detection system for dimensionality reduction with the inherited nature of clustering and Extreme Gradient Boosting(XGBoost)for multi-class classification can improve network traffic intrusion *** proposed model is evaluated on the NSL-KDD *** hybrid approach outperforms the baseline line models,Multilayer perceptron model,and SOM-KNN(k-nearest neighbors)model in precision,recall,and F1-score,highlighting the proposed approach’s scalability,potential,adaptability,and real-world ***,this paper proposes a highly efficient deployment strategy for resource-constrained network *** results reveal that Precision,Recall,and F1-scores rise 10%-30% for the benign,probing,and Denial of Service(DoS)*** particular,the DoS,probe,and benign classes improved their F1-scores by 7.91%,32.62%,and 12.45%,respectively.

关键词： Intrusion detection self-organizing map Internet of Things dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Assessment of ingestion dose from 226Ra, 228Ra, and 40K in vegetables consumed in Koya district, Iraq

引用

Environmental science and Pollution Research 2025年第19期32卷 11972-11980页

作者： Saleh, Dedawan Salam Salh, Hemn Smail, Jahfer Majeed Ahmad, Saddon Taha Department of Physics Faculty of Science and Health Koya University Kurdistan Region KoyaKOY45 Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil44001 Iraq Faculty of Medicine Koya University KoyaKOY45 Iraq

The present work comprises the measurement of activity concentrations of three radionuclides, 22⁶Ra, 228Ra, and 4⁰K in 33 species of vegetables commonly used in Koya district, the Iraqi Kurdistan region. The analysis of the samples was performed with high purity germanium (HPGe) gamma spectrometry. Among the analyzed samples, mushrooms presented the highest activity concentrations of 22⁶Ra (3.34 ± 1.18 Bq·kg⁻1), 228Ra (1.24 ± 0.5 Bq·kg⁻1), and 4⁰K (1481.93 ± 14.46 Bq·kg⁻1) while legumes had the lowest levels of these radionuclides. The estimated annual effective dose from the consumption of these vegetables was computed to be 97.216 µSv·y⁻1 and this is much lower than the United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) global reference level of 290 µSv·y⁻1. Therefore, it can be concluded that the radiological risk from the consumption of vegetables in this area is very low thus giving a reassurance to the people on the safety implication on the radiological health hazards. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Radiation effects

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Allocation in Edge Computing via Deep Deterministic Policy Gradient Reinforcement Learning 3

Dynamic Resource Allocation in Edge Computing via Deep Deter...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Gopal, Vidhya Surendar, U. Bajulunisha, A. Tamilselvi, M. Sathiyapriya, V. Saranya, N. Sona College of Technology Department of Computer Science and Engineering Salem India Srm institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Kundrathur India Roever Engineering College Department of Computer Science and Engineering Perambalur India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India Karpagam College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798331508456

The difficulty with dynamic and heterogeneous natured edge computing environments is resource provisioning. Reinforcement Learning (RL) can be promising to solve the problems of resource allocation under conditions of dynamics and complexity. This research work presents a novel DDPG-based (Deep Deterministic Policy Gradient) approach for optimizing the dynamics of resource allocation in edge computing environments by exploiting the CRAWDAD KAIST-WIBRO dataset for the proposed model. This approach implements a neural network that learns the optimal policies of allocations with dynamism towards new changes in workloads and resource availabilities. In order to test the performance of this method, conducted several simulations over real-world workload and resource data, mapping the parameters like rewards and variation in episodes. The simulation results indicate that proposed approach performs superior compared to traditional heuristic-based approaches as well as other RL algorithms for resource usage, response time, and energy efficiency. This proposed approach permits optimized resource utilization along with quality of service, of paramount importance in executing complex and demanding applications at the edge computing environment. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing mechanical strength and thermal stability of sisal fiber-plastic composites by high-temperature treatment

引用

Interactions 2025年第1期246卷 1-15页

作者： Mungle, Nischal P. Jadhav, Varsha D. Kulkarni, Sumant Khanderao D.S.Vijayan Saminathan, Rajasekaran Satishkumar, P. Department of Mechanical Engineering Yeshawantrao Chavan College of Engineering Maharashtra Wanadongari Nagpur India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Maharashtra Pune India School of Civil Engineering REVA University Rukmini Knowledge Park Karnataka Kattigenahalli Bengaluru India Tamilnadu Chennai India Department of Mechanical Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India

In this experiment, high-temperature polyethylene terephthalate (PT) was mixed with epoxy resin (ER) that had been thinned with acetone. Sisal fibers were coated with the resulting product. Composites of Coated treated sisal fibre-reinforced PT (CTSF-PT) were made using a constant fiber loading of 10 wt% and processing temperatures of 230, 250, and 270ºC. The fibers were treated with NaOH. These composites were then characterized for thermal, mechanical and morphological performances. When comparing findings obtained at 250 and 270ºC, the optimal processing temperature was found to be 230ºC. This temperature resulted in the best thermal and mechanical properties, and excellent interfacial adhesion among the coated fibers and the PT. In comparison to the uncoated SF, the coated composites showed a 9.5% reduction in degradation onset temperature and a 13% improvement in decomposition temperature following resin coating, according to thermogravimetric analysis. The CSF-PT composites surpassed the uncoated composites by 2.18% and 2.8% in terms of glass transition (Tg) and melting temperature (Tm) measured by differential scanning calorimetry (DSC), with peak values at 122.2 °C and 265.1 °C, respectively. Coated Sisal-reinforced PT (CSF-PT) and coated-treated PT (CTSF-PT) composites outperformed raw Sisal (SF-PT) composites in terms of overall qualities and morphological properties, regardless of processing temperature. Applying resin to natural fibers enhances their heat resistance and the bond between the coated fibers and the plastic matrix, making them better suited for engineering plastic composites. Applications involving high temperatures, such as construction and automotive industries are well-suited to the resulting composites. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

BiCSA-PUL: binary crow search algorithm for enhancing positive and unlabeled learning

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1729-1743页

作者： Azizi, Nabil Ben Othmane, Mohamed Hamouma, Moumen Siam, Abderrahim Haouassi, Hichem Ledmi, Makhlouf Hamdi-Cherif, Aboubekeur Department of Computer Science Mostefa Ben Boulaid University Batna 2 Batna 05001 Algeria Department of Computer Science Abbes Laghrour University Khenchela 40004 Algeria Knowledge Engineering and IT Security Laboratory (ICOSI) Abbes Laghrour University Khenchela 40004 Algeria Department of Computer Science Ferhat Abbas University of Setif 1 Setif 19137 Algeria

This paper presents a novel metaheuristic binary crow search algorithm (CSA) designed for positive-unlabeled (PU) learning, a paradigm where only positive and unlabeled data are available, with applications in many diversified fields, such as medical diagnosis and fraud detection. The algorithm represent a useful adaptation of CSA, itself inspired by the food-hiding behavior of crows. The proposed BiCSA-PUL (binary crow search algorithm for positive-unlabeled learning) selects reliable negative samples from unlabeled data using binary vectors, and updates positions employing Hamming distance, guided by a modified F1-score, as fitness function. The algorithm was tested on 30 samples from 10 diverse datasets, outperforming seven state-of-the-art PU learning methods. The results reveal that BiCSA-PUL provides a robust and efficient approach for PU learning, significantly improving fitness and reliability. This work opens new avenues for applying metaheuristic optimization methods to challenging classification problems with limited labeled data. The main limitations are the potentially time-intensive process of parameters tuning and reliance on initial sampling. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Classification Machine learning Metaheuristic optimization Positive and unlabeled learning Raw search algorithm Two-step algorithms

来源：评论

学校读者我要写书评

暂无评论

Dual AAV Cluster-Assisted Maritime Physical-Layer Secure Communications via Collaborative Beamforming

引用

IEEE Internet of Things Journal 2025年第9期12卷 12589-12607页

作者： Huang, Jiawei Wang, Aimin Sun, Geng Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Autonomous aerial vehicles (AAVs) can be utilized as relay platforms to assist maritime wireless communications. However, complex channels and multipath effects at sea can adversely affect the quality of AAV transmitted signals. Collaborative beamforming (CB) can enhance the signal strength and range to assist the AAV relay for remote maritime communications. However, due to the open nature of AAV channels, security issue requires special consideration. This article proposes a dual AAV cluster-assisted system via CB to achieve physical-layer security in maritime wireless communications. Specifically, one AAV cluster forms a maritime AAV-enabled virtual antenna array (MUVAA) relay to forward data signals to the remote legitimate vessel, and the other AAV cluster forms an MUVAA jammer to send jamming signals to the remote eavesdropper. In this system, we formulate a secure and energy-efficient maritime communication multiobjective optimization problem (SEMCMOP) to maximize the signal-to-interference-plus-noise ratio (SINR) of the legitimate vessel, minimize the SINR of the eavesdropping vessel and minimize the total flight energy consumption of AAVs. Since the SEMCMOP is an NP-hard and large-scale optimization problem, we propose an improved swarm intelligence optimization algorithm with chaotic solution initialization and hybrid solution update strategies to solve the problem. Simulation results indicate that the proposed algorithm outperforms other comparison algorithms, and it can achieve more efficient signal transmission by using the CB-based method. © 2014 IEEE.

关键词： Multiobjective optimization

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：