检索结果-内蒙古大学图书馆

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Neeraj Nandal, Poonam Department of Computer Science & Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad India

ISBN: (纸本)9798331530389

A key aspect of artificial intelligence is continual learning. The capacity of a model to incrementally learn from a new task and adapt to it without losing the previous knowledge. A fundamental challenge that comes to successful continual learning is catastrophic forgetting;while learning a new task the model forgets the previously learned tasks. Various approaches to mitigate forgetting and enhance continual learning have been discussed across benchmark datasets such as MNIST, CIFAR-10, and Permuted MNIST. we focus mainly on replay, regularization, and modular architecture-based methods to prevent forgetting. Regularization methods penalize the significant change in parameters during the learning of new tasks while maintaining crucial parameters of previously completed tasks. Replay-based methods store samples of earlier tasks in explicit memory or generate pseudo-samples with the help of generative models. Modular architecture-based methods partition the neural architecture into task-specific modules to prevent interference between tasks, to effectively address catastrophic forgetting. This paper presents a comparative study of the key continual learning methods that reduce catastrophic forgetting. The findings demonstrate the trade-offs between different methods. We examine the efficiency and effectiveness of each method and propose a hybrid technique to prevent catastrophic forgetting. Our comparative analysis emphasizes the significance of choosing the best method depending on the specific requirement of the learning environment, the task complexity, and resource constraints. © 2025 IEEE.

关键词： artificial intelligence catastrophic forgetting continual learning

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Depression Detection System: Integrating Multimodal Analysis for Early Diagnosis

AI-Enhanced Depression Detection System: Integrating Multimo...

引用

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

作者： Patidar, Aditya Gore, Dhruv Inje, Bhushan Alhat, Apurva Department of Computer Science SVKM's Narsee Monjee Institute of Management Studies Maharashtra Shirpur India

ISBN: (纸本)9798331512965

Depression is a prevalent mental health condition affecting millions globally, often going undiagnosed due to social stigma and limited accessibility to healthcare. This study presents an innovative AI-enhanced system for early depression detection, utilizing multimodal analysis integrating natural language processing (NLP) and patient health metrics. Two machine learning models form the system's core: a text classification model leveraging logistic regression to analyze user inputs and predict emotional tone and a health-data-based model that incorporates factors such as BMI, blood features, and comorbid conditions for comprehensive evaluation. The models were integrated into a web application offering a dual advantage of accurate screening and accessible mental health recommendations. Results demonstrated high efficacy with classification accuracy exceeding 91% across models, underscoring its potential to transform early-stage mental health interventions. Future enhancements include adopting advanced deep learning frameworks and expanding multilingual capabilities to broaden accessibility. © 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

Securing Drug Traceability: Blockchain-Enhanced Privacy Protection and Anti-Counterfeit Measures in Pharmaceutical Supply Chains

引用

Journal of Pharmaceutical Innovation 2025年第3期20卷 1-21页

作者： Kalpana, R. Sridevi, S. Department of Computer Science and Engineering VELS Institute of Science Technology and Advanced Studies (VISTAS) Chennai India

The pharmaceutical sector is under severe threat in ensuring the genuineness of drugs and securing sensitive information throughout the supply chain. Conventional security measures tend to be ineffective in addressing these issues comprehensively, resulting in weaknesses like counterfeit medicines and illegitimate access to data. This research suggests an integrated, state-of-the-art security system to provide improved data protection, encryption effectiveness, and supply chain integrity in the pharmaceutical industry. The suggested framework utilizes Attribute-Based Encryption (ABE) in conjunction with QR code technology for secure, fine-grained data encryption. For the optimization of encryption key selection, a hybrid optimization method combining Red Panda Optimization (RPO) Algorithm and Group Teaching Optimization Algorithm (GTOA) is proposed. Additionally, Multi-Party Computation (MPC) protocols and Shamir’s Secret Sharing scheme are used to guarantee that only legitimate parties can reconstruct and view important data, maintaining confidentiality and integrity. Performance testing shows that the framework proposed performs better than traditional cryptos. Encryption time registered was at 0.21234 seconds, which was quicker than RSA (0.308372) and 3DES (0.36462). Decryption took 0.22112 seconds, which was faster than RSA’s 0.312773. Total turnaround time was cut to 0.431231 seconds, which was far superior to Blowfish at 0.52356 seconds. The system also attained a restoration efficiency level of 0.987453, ahead of RSA at 0.92133 and Blowfish at 0.94109. The security model offers a secure and feasible solution for end-to-end data protection and prevention of tampering and unauthorized access in the pharma supply chain.

关键词： Blockchain Counterfeit drugs Drug traceability Key generation Optimization Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Hybrid Ensemble Gradient Boosting Algorithm to Predict Diabetes Health Care Analytics 3rd

Hybrid Ensemble Gradient Boosting Algorithm to Predict Diabe...

引用

3rd International Conference on Advancements in Smart Computing and Information Security, ASCIS 2024

作者： Deepa, S. Booba, B. Department of Computer Science Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai 600117 India Department of Information Technology Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai 600117 India

ISBN: (纸本)9783031862984

Diabetes is a chronic illness characterized by high blood sugar that can cause major damage to the kidney, heart, eyes, brain system, and kidneys, among other organs. Healthcare analytics improves patient care by utilizing a variety of data analysis techniques. A machine learning model was built utilizing several machine learning approaches to predict the sickness as soon as feasible in order to prevent it. The Andaman and Nicobar Islands’ 770 diabetic individuals are the subject of the research project. In this research, the collected dataset have been splits into training and testing sets using exploratory data analysis techniques for data pre-processing. Subsequently, the study employed feature engineering methodologies to ascertain the significance of every attribute and make an accurate prediction of diabetes mellitus based on the risk factor identified by the Indian Diabetes Risk Score (IDRS). The current research work′s model employs nine machine learning algorithms, including the Gaussian Naïve Bayes algorithms, Ada Boosting classifier, XG Boosting classifier, Random Forest classifier, Bagging classifier, Logistic Regression, Linear SVC Algorithm, KNN classifier, and decision trees algorithm and produces accuracy, precision, recall, and f1 score. Depend upon the findings, it was concluded that the Bagging classifier, Ada Boosting, XG Boosting, KNN, and Random Forest classifiers provided the highest accuracy of 88%, followed by the Gaussian Naïve Bayes method, Decision Trees, and Logistic Regression. Subsequently, the research effort created a hybrid ensemble gradient boosting method and applied it to the proposed system, yielding the greatest results in terms of accuracy (99%), precision (79%), recall (84%), AUC (87%), and ROC curve (87%). This leads to the conclusion that the proposed hybrid ensemble gradient boosting classifier not only produces superior results and beats the other machine learning methods, but it also correctly predicts patients’ likeliho

关键词： Accuracy AUC Cross Validation Score Diabetes Mellitus F1 Score Hybrid Gradient Boosting Algorithm Precision Recall and ROC Curve

来源：评论

学校读者我要写书评

暂无评论

Improvised Spectral Efficiency and Channel Estimation Parameters in Visible Light Vehicular Communication by Integrating Simulation of Urban Mobility Data

引用

IEEE Access 2025年 13卷 70828-70848页

作者： Wheeb, Ali H. Maurya, Sudhanshu Karimullah, Shaik Shaik, Fahimuddin Chowdhury, Subrata Siva Prasad, B.V.V. Sinha, Anurag Sood, Adamya Hussain, Syed Abid University of Baghdad College of Engineering Department of Aeronautical Engineering Baghdad10071 Iraq Department of Computer Science and Engineering Pune412115 India Annamacharya University Department of ECE Rajampet516126 India Sreenivasa Institute of Technology and Management Studies Department of Computer Science and Engineering Chittoor517127 India Anurag University School of Engineering Department of Computer Science and Engineering Hyderabad500088 India ICFAI University Tech School Computer Science Department Ranchi835222 India Amity University Amity School of Engineering and Technology Computer Science Department Noida201313 India Bakhtar University Department of Computer Science and Engineering Karta-e-Chahar Kabul1001 Afghanistan Lovely Professional University Division of Research and Development Phagwara144001 India Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Rajpura140401 India

Visible Light Communication (VLC) has emerged as a promising technology for vehicular communication due to its high data rates, low latency, and immunity to electromagnetic interference. However, optimizing spectral efficiency and channel estimation in dynamic vehicular environments remains a key challenge. This paper proposes an OFDM-QAM-based VLC system to enhance spectral efficiency and improve channel estimation accuracy in vehicular networks. To achieve this, we leverage Simulation of Urban Mobility (SUMO) data, which provides detailed insights into vehicular movement and traffic patterns. By integrating SUMO with VLC system simulations, we optimize modulation schemes, multiple access techniques, and spatial reuse strategies to adapt to varying traffic conditions. Additionally, a mathematical framework is developed to evaluate the impact of vehicular mobility on spectral efficiency and bit error rate (BER) performance across different QAM modulation schemes. Simulation results demonstrate that the proposed VLC system significantly improves spectral efficiency, achieving values up to 1.4 bits/s/Hz, while maintaining low BER across varying Signal to Noise Ratio (SNR) levels. These findings confirm the effectiveness of the proposed methodology in enhancing Visible Light Communication (VLC) performance for vehicular applications, making it a viable solution for next-generation intelligent transportation systems. © 2013 IEEE.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-task Oriented Efficient Computational Offloading Orchestrator for IoT Applications in Mobile Edge Computing

引用

IEEE Internet of Things Journal 2025年第10期12卷 14096-14108页

作者： Wang, Leilei Deng, Xiaoheng Zhang, Honggang Wan, Shaohua Min, Geyong Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Central South University School of Computer Science and Engineering Changsha410075 China Central South University Shenzhen Research Institute China Umass Boston Engineering Department BostonMA02125 United States University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Mobile Edge Computing (MEC) can accelerate computation-intensive applications and emerge as a promising technology for enabling Internet of Things (IoT). MEC improves the processing performance of tasks by assigning them to the edge nodes. However, with massive terminals contending for computation and communication resources simultaneously, how to develop a flexible computational offloading mechanism becomes the fundamental issue of MEC-enabled IoT systems. This paper aims to develop an effective computational offloading decision scheme by jointly considering the computational resource and diverse user demands with two goals, i.e., minimizing both the latency and the energy consumption. Specifically, we develop a two-stage computational offloading mechanism, where the computational resources and offloading decisions can be allocated and coordinated with the variation of computation requirements. To achieve the two goals, this work introduces an edge node recommendation model within the cloud-edge-end architecture to reduce the offloading optimization search space. Furthermore, we propose a new computational offloading (CROCA) algorithm based on Chemical Reaction Optimization (CRO) for optimizing offloading utility, which thoroughly considers the competition between mobile device requests and computational resources. Extensive evaluation results demonstrate that the proposed CROCA scheme can effectively improve the computational offloading performance. © 2014 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Constructing Rectilinear Steiner Minimum Tree with Conditional Generative Adversarial Network 38

Constructing Rectilinear Steiner Minimum Tree with Condition...

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Saha, Kritanta Banerjee, Pritha Sur-Kolay, Susmita Indian Statistical Institute Advanced Computing and Microelectronics Unit Kolkata India Sister Nivedita University Department of Computer Science and Engineering Kolkata India University of Calcutta Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331522445

Given n points in the 2D plane which are the pins of a net, a Rectilinear Steiner Minimum Tree (RSMT) which consists only of vertical and horizontal line segments is the shortest network to interconnect the pins along with a few extra (Steiner) points. An RSMT for a net has a minimum total wirelength in Manhattan distance and acts as a backbone to many state-of-the-art global routers. However, finding an RSMT is NPcomplete. In this work, we propose a method for constructing an RSMT with an image-to-image translation using a conditional generative adversarial network (cGAN) based model. Images of RSMTs with optimal wirelength for randomly generated nets form our training dataset. Experimental results show that, after training, our model generates RSMTs with = 0.348% wirelength error on average compared with the optimal solution for nets with degrees up to 50. This is the first successful attempt to solve the RSMT construction problem as an image-to-image translation problem using a cGAN based model. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hard Sample Meta-Learning for CIR NLOS Identification in UWB Positioning

引用

IEEE Internet of Things Journal 2025年第10期12卷 14136-14149页

作者： Liu, Yinong Si, Haonan Boateng, Gordon Owusu Guo, Xiansheng Cao, Yu Qian, Bocheng Ansari, Nirwan University of Electronic Science and Technology of China Department of Electronic Engineering Chengdu611731 China New Jersey Institute of Technology Advanced Networking Lab Department of Electrical and Computer Engineering NewarkNJ07102 United States

Non-line-of-sight (NLOS) identification is the key technique to improve the accuracy of the channel impulse response (CIR) based ultrawideband (UWB) positioning system. However, most existing NLOS identification approaches are tailored to static environments and often encounter difficulties in dynamic settings with both temporal and spatial variations, particularly when dealing with limited and hard samples. This paper introduces a hard sample meta-learning (HSML) approach to address the issues of NLOS identification across different scenarios and domains. HSML includes two phases: a hard sample meta-training phase and a fine-grained meta-testing phase. During the meta-training phase, we train a two-loop learning network using CIR from multiple scenarios (tasks). The inner loop focuses on learning task-specific features, while the outer loop captures cross-task generalization properties using a cross-entropy loss. Hard samples are identified based on estimated residuals for each task, and a new dataset is created, consisting of both hard samples and samples with small residuals. To improve the robustness against hard samples, we implement a residual-corrected focal loss, which is used to retrain the network on this new dataset. In the fine-grained meta-testing phase, we apply a filtering mechanism based on the tendency of estimated residuals during fine-tuning. This mitigates the risk of poor performance caused by anomalous samples. We validate the effectiveness and robustness of the proposed HSML method using two datasets containing multiple real-world scenarios. Our experimental results demonstrate that HSML outperforms existing models in terms of identification accuracy, robustness and generalization performance. © 2014 IEEE.

关键词： Impulse response

来源：评论

学校读者我要写书评

暂无评论

Provable Data Possession with Outsourced Tag Generation for AI-Driven E-Commerce

引用

computers, Materials & Continua 2025年第5期83卷 2719-2734页

作者： Yi Li Wenying Zheng Yu-Sheng Su Meiqin Tang School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science and Technology(School of Artificial Intelligence) Zhejiang Sci-Tech UniversityHangzhou310018China Department of Computer Science and Information Engineering National Chung Cheng UniversityChiayi621301TaiwanChina Advanced Institute of Manufacturing with High-tech Innovations National Chung Cheng UniversityChiayi621301TaiwanChina Department of Computer Science and Engineering National Taiwan Ocean UniversityKeelung202301TaiwanChina School of Integrated Circuits Wuxi Vocational College of Science and TechnologyWuxi214028China

AI applications have become ubiquitous,bringing significant convenience to various *** e-commerce,AI can enhance product recommendations for individuals and provide businesses with more accurate predictions for market strategy ***,if the data used for AI applications is damaged or lost,it will inevitably affect the effectiveness of these AI ***,it is essential to verify the integrity of e-commerce *** existing Provable Data Possession(PDP)protocols can verify the integrity of cloud data,they are not suitable for e-commerce scenarios due to the limited computational capabilities of edge servers,which cannot handle the high computational overhead of generating homomorphic verification tags in *** address this issue,we propose PDP with Outsourced Tag Generation for AI-driven e-commerce,which outsources the computation of homomorphic verification tags to cloud servers while introducing a lightweight verification method to ensure that the tags match the uploaded ***,the proposed scheme supports dynamic operations such as adding,deleting,and modifying data,enhancing its ***,experiments show that the additional computational overhead introduced by outsourcing homomorphic verification tags is acceptable compared to the original PDP.

关键词： Provable data possession data auditing cloud computing e-commerce bloom filter

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based FOD Detection For Runway Health Monitoring 1

Deep Learning Based FOD Detection For Runway Health Monitori...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Kumar, Amarjeet Mittal, Aanya Dixit, Abhishek Agrawal, Pooja School of Robotics Defence Institute of Advanced Technology Pune India Manipal University Jaipur Department of Computer Science Rajasthan India Defence Institute of Advanced Technology Department of Aerospace Pune India

ISBN: (纸本)9798350355611

This paper focuses on the safety of airport runways, which is crucial for aviation industries. Foreign Object Debris (FOD) i.e. objects like nails or bolts can cause significant harm to aircraft and potentially lead to catastrophic incidents and fatalities. This study delves into detecting objects on runways by using versions of the YOLO (You Only Look Once) model. Further, it also presents the differences in detecting objects and comparing the accuracy across a range of objects, paying attention to their ability to identify even the smallest things that have a potential danger. In order to identify the model variation and enable real-time runway surveillance, the proposed methodology considers the trade-off between detection speed and precision. The results illustrate the effectiveness of the latest YOLO model in object recognition over existing models, this can support the improvement of runway safety and the development of automated systems that monitor runway conditions. © 2025 IEEE.

关键词： Aircraft accidents

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：