检索结果-内蒙古大学图书馆

Non-Destructive Detection of Fillet Fish Quality Using MQ135 Gas Sensor and Neutrosophic Logic-Enhanced System

Neutrosophic Sets and Systems 2025年 80卷 540-563页

作者： Shams, M.Y. Darwesh, M.R. Bhatnagar, Roheet Al-Sattary, N.S.A. Salama, A.A. Ghoname, M.S. Deptartment of Machine Learning Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheihk33516 Egypt Department of Agriculture Engineering Faculty of Agriculture Tanta University Tanta31527 Egypt Department of Food Processing Faculty of Industry and Energy Samannoud Technological University Egypt Department of Computer Science and Engineering Manipal University Rajasthan Jaipur India Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt

This paper demonstrates the feasibility of using an electronic nose to assess fish quality by analyzing air quality and examining volatile organic compounds (VOCs) alongside physical variables, with pH, protein content, and VOCs serving as chemical reference points. Artificial intelligence algorithms were employed to predict quality and calculate regression coefficients. Using the reference neural network algorithm based on chemical and physical compounds, regression coefficients (R values) achieved were 0.99, 0.98, and 0.97, respectively. Additionally, ANFIS (Adaptive Neuro-Fuzzy Inference System) produced R values of 0.99, 0.85, and 0.98. Both fuzzy logic and ANFIS proved effective for predicting fish quality. Image processing techniques, including histogram analysis, color mapping, and edge detection, were also applied to assess fish quality. To enhance the inference process, Neutrosophic Logic-Enhanced Fuzzy Logic Systems were utilized, addressing uncertainty and imprecision in fish quality assessment. Neutrosophic logic combines fuzzy logic's partial truth with indeterminacy, represented by three membership functions: truth, indeterminacy, and falsity. Neutrosophic fuzzy inference integrates steps like neutrosophication, rule evaluation, aggregation, and defuzzification, ensuring improved expressiveness and fidelity. For instance, neutrosophic fuzzy rules evaluated fish freshness and appearance to determine quality ratings such as poor, good, or excellent. This integration enhances decision-making by accurately modeling complex real-world uncertainties. These methods, combining electronic nose technology, artificial intelligence, and neutrosophic inference, provide a robust, non-destructive, and cost-effective approach to detecting spoilage in fillet fish. © 2025, University of New Mexico. All rights reserved.

关键词： Volatile organic compounds

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Multiplex Graph Neural Networks for Recommendation

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3327-3341页

作者： Li, Xiang Fu, Chaofan Zhao, Zhongying Zheng, Guangjie Huang, Chao Yu, Yanwei Dong, Junyu Ocean University of China Faculty of Information Science and Engineering Qingdao266005 China Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266590 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China The University of Hong Kong Department of Computer Science Hong Kong

Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10 respectively. The source code of our paper is available at https://***/lx970414/TKDE-DCMGNN. © 1989-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Fixed Point Theorems in Neutrosophic Fuzzy Metric Space and a Characterization to its Completeness

引用

Neutrosophic Sets and Systems 2025年 81卷 575-602页

作者： Ghosh, Samriddhi Bhardwaj, Ramakant Narayan, Satyendra Sonam, Sonam Department of Mathematics Amity University Kolkata India School of Computer Science and Technology Algoma University Canada

The present research work aims to establish some basic conventional fixed point theorems such as the Banach fixed point theorem, Edelstein fixed point theorem and Kannan fixed point theorem, for a recently introduced topological space, known as the neutrosophic fuzzy metric space. The Kannan fixed point theorem has also further been classified into two categories namely, (1/2)−Kannan and (1)−Kannan fixed point theorems. Also the concept of semi-metric in the said space has been introduced, and along with it the results hence obtained are used to characterize the completeness of the mentioned space. To the best of known literatures, this type of work in the said space has not yet been found. © 2025, University of New Mexico. All rights reserved.

关键词： Fixed point arithmetic

来源：评论

学校读者我要写书评

暂无评论

***: employment of advanced deep learning and human–robot interaction for virtual coaching

引用

Intelligent Service Robotics 2025年 1-17页

作者： Cauli, Nino Reforgiato Recupero, Diego Department of Mathematics and Computer Science University of Cagliari Via Ospedale 72 Sardinia Cagliari09124 Italy

Ensuring healthy aging and physical fitness is crucial for leading a happy, independent, and fulfilling life. Daily gentle gymnastic training at home can significantly contribute to maintaining physical health among older adults. Virtual and robotic coaches serve as valuable tools to assist elders during their daily exercise routines. In this paper, we introduce the design of a comprehensive robotic coach capable of guiding patients throughout their training sessions. Additionally, we propose an innovative synthetic dataset generator to train the video action recognition module of the robot effectively. To evaluate the efficacy of our robotic coach, we conducted tests with nine patients aged over 50, who were asked to complete a system usability scale (SUS) survey. © The Author(s) 2025.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

ALTEM: A New Lightweight Trust Evaluation Mechanism for Wireless Sensor Networks

ALTEM: A New Lightweight Trust Evaluation Mechanism for Wire...

引用

International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2024

作者： Saidi, Ahmed Department of Mathematics and Computer Science Faculty of Exact Sciences University of Ghardaia Ghardaia Algeria

ISBN: (纸本)9783031803000

Recently, wireless sensor networks (WSN) have played an important role in various Internet of Things applications such as smart homes, smart grids, smart cities, and intelligent agriculture. Security is a fundamental aspect of WSN. Trust management is a promising security technique used to secure the network for different operations such as routing, localization, and data aggregation. However, most trust schemes fail to consider both direct and indirect trust, leaving the network exposed and susceptible to attacks specifically designed for trust systems. Moreover, these trust models are complicated systems that impact the allocation of resources in sensor nodes. This research presents a novel and efficient trust method that simultaneously assesses both direct and indirect trust. Furthermore, the measurement of indirect trust involves the use of both one-hop and multi-hop trust evaluations. The suggested model obtains high detection rates by employing overstimulation and surpasses other competitor models in performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Automating skin cancer screening: a deep learning

引用

Journal of Engineering and Applied science 2025年第1期72卷 1-18页

作者： Rashad, Nada M. Abdelnapi, Noha MM. Seddik, Ahmed F. Sayedelahl, M.A. Department of Computer Science Faculty of Computers and Information Suez University Suez43221 Egypt Biomedical Engineering Department Faculty of Engineering Helwan University Cairo11795 Egypt Department of Computer Science Faculty of Computers and Information Damanhour University Damanhour22511 Egypt

Skin cancer presents in various forms, including squamous cell carcinoma (SCC), basal cell carcinoma (BCC), and melanoma. Established risk factors include ultraviolet (UV) radiation exposure from solar or artificial sources, lighter skin pigmentation, a history of sunburns, and a family history of the disease. Early detection and prompt intervention are crucial for achieving a favorable prognosis. Traditionally, treatment modalities include surgery, radiation therapy, and chemotherapy. Recent advancements in immunotherapy have revolutionized skin cancer diagnosis, but manual identification remains time-consuming. Artificial intelligence (AI) has shown potential in skin cancer classification, leading to automated screening methods. To support dermatologists, we improved the model for classifying images. This model is able to recognize seven different kinds of skin lesions. On the ISIC dataset, an analysis has been done. This study offers a novel approach to early skin cancer diagnosis based on image processing. Our approach leverages the high accuracy of a specific convolutional neural network architecture, utilizing transfer learning with pre-trained data to further enhance detection performance. Our findings demonstrate that the employed ResNet-50 transfer learning model achieves a remarkable accuracy of 97%, while ResNet50 without augmentation gives an accuracy of 81.57% and an F1-score of 75.75%. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

L1-predictor–corrector method for ψ-Caputo type fractional differential equations

引用

Computational and Applied mathematics 2025年第5期44卷 1-26页

作者： Sivalingam, S.M. Govindaraj, V. Sousa, J. Vanterler da C. Hendy, A.S. Department of Mathematics National Institute of Technology Puducherry Karaikal609609 India Department of Mathematics Aerospace Engineering PPGEA-UEMA DEMATI-UEMA MA São Luís65054 Brazil Department of Computational Mathematics and Computer Science Institute of Natural Sciences and Mathematics Ural Federal University 19 Mira St. Yekaterinburg620002 Russia Department of Mechanics and Mathematics Western Caspian University Baku1001 Azerbaijan Department of Mathematics and Computer Science Faculty of Science Benha University Benha13511 Egypt

This paper proposes a three-point L1-based predictor–corrector scheme for the ψ-Caputo derivative. The L1-based rule and linear spline-based interpolation are utilized to perform the discretization of the derivative. The Daftardar-Gejji Jafari scheme (DGJ) is used to frame the iterative scheme. The error in the discretization procedure and the proposed approach is theoretically verified. The stability of the proposed approach is given in detail. Several numerical examples are solved to prove the numerical efficacy of the approach. An example is given by using the properties of the ψ-Caputo derivative to compare the proposed approach. Further, the computer virus model and the Chen system are simulated to demonstrate the method’s accuracy for a system of equations. © The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional 2025.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

The influence of fear effect and phase of chaos control of discrete predator–prey system with mixed Holling types

引用

Alexandria Engineering Journal 2025年 127卷 296-308页

作者： Madian, A.M. Zheng, Rong El-sheikh, M.M.A. Elettreby, M.F. El-Gaber, A.A. Mathematics and Computer Science Department Faculty of Science Menofia University Menofia Egypt New Engineering Industry College Putian University Fujian Putian351100 China School of Information Engineering Sanming University Fujian Sanming365004 China Mathematics Department Faculty of Science Mansoura University Mansoura35516 Egypt

In this paper, a discrete-time predator–prey system with mixed Holling types I and III functional responses and fear effect is discussed. Three fixed points are determined and their stability is established. Analytical criteria for Neimark Sacker bifurcation (NSB) and flip bifurcation (FB) are proposed. Applying the technique of state feedback control, we introduce the corresponding controlled system. At an unstable fixed point the chaotic orbits can be stabilized. We show that the fear effect of prey species has a negative effect on the density of predator species in our model. Furthermore, fear effect may increase the possibility that prey species will go extinct, which implies that Allee effect may occur in this case. These analytical studies are illustrated with some numerical simulations. © 2025 The Authors

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Enhanced model for abstractive Arabic text summarization using natural language generation and named entity recognition

引用

Neural Computing and Applications 2025年第10期37卷 7279-7301页

作者： Essa, Nada El-Gayar, M.M. El-Daydamony, Eman M. Department of Information Technology Faculty of Computer and Information Science Mansoura University Mansoura35516 Egypt

With the rise of Arabic digital content, effective summarization methods are essential. Current Arabic text summarization systems face challenges such as language complexity and vocabulary limitations. We introduce an innovative framework using Arabic Named Entity Recognition to enhance abstractive summarization, crucial for NLP applications like question answering and knowledge graph construction. Our model, based on natural language generation techniques, adapts to diverse datasets. It identifies key information, synthesizes it into coherent summaries, and ensures grammatical accuracy through deep learning. Evaluated on the EASC dataset, our model achieved a 74% ROUGE1 score and a 97.6% accuracy in semantic coherence, with high readability and relevance scores. This sets a new standard for Arabic text summarization, greatly improving NLP information processing. © The Author(s) 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

EAFL: Edge-Assisted Federated Learning for real-time disease prediction using privacy-preserving AI

引用

Iran Journal of computer science 2025年 1-11页

作者： Rawas, Soha Samala, Agariadne Dwinggo Faculty of Science Department of Mathematics and Computer Science Beirut Arab University Beirut Lebanon Faculty of Engineering Universitas Negeri Padang West Sumatra Padang Indonesia

The growing demand for real-time disease prediction in healthcare necessitates advanced AI frameworks capable of ensuring both computational efficiency and patient privacy. This study introduces an Edge-Assisted Federated Learning (EAFL) system designed for real-time disease prediction while preserving sensitive data using privacy-preserving AI techniques. Leveraging lightweight convolutional neural networks and federated learning, the framework decentralizes model training across simulated edge nodes, reducing reliance on centralized data storage. Differential privacy mechanisms are integrated to secure inter-node communications, enhancing data protection. The proposed framework was evaluated on publicly available datasets, including CheXpert and COVID-19 radiography, achieving an accuracy of 94.2% and 97.5%, respectively, with minimal latency (0.85 s per prediction). Comparative analysis reveals that the EAFL system matches the performance of centralized AI models while significantly reducing privacy risks. To demonstrate scalability, additional evaluation was conducted across different dataset distributions, revealing consistent performance across varying data characteristics and medical scenarios. This research offers a scalable, privacy-focused solution that bridges the gap between real-time disease prediction and secure data handling, paving the way for its adoption in modern healthcare applications. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Disease prediction Edge AI Federated learning GDPR compliance in AI Healthcare data security

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：