检索结果-内蒙古大学图书馆

IEEE Networking Letters 2024年第4期6卷 232-236页

作者： Zhou, Changshi Liu, Weiqi Han, Tao Ansari, Nirwan New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States Auburn University at Montgomery Department of Computer Science and Computer Information Systems MontgomeryAL36117 United States

From AI-assisted art creation to large language model (LLM)-powered ChatGPT, AI-generated contents and services are becoming a transforming force. It calls for the telecom industry to embrace the prospects of AIGC services and face the unique challenges posed by incorporating generative model services into the AI-native 6G wireless network paradigm. We propose enabling AIGC inference services on mobile devices by optimizing MEC-device computing offloading, through which AIGC task latency is minimized by reinforcement learning based policy agent in a computing resource constrained and bandwidth limited wireless environment. Simulation results are presented to demonstrate the performance advantage. © 2019 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Firefly with Dynamic Multi-swarm Particle Swarm Optimization for WSN Deployment

引用

Journal of Internet technology 2023年第4期24卷 825-836页

作者： Chang, Wei-Yan Soma, Prathibha Chen, Huan Chang, Hsuan Tsai, Chun-Wei Department of Computer Science and Engineering National Chung Hsing University Taiwan Department of Information Technology Sri Sai Ram Engineering College India Department of Computer Science and Engineering National Sun Yat-Sen University Taiwan

Enhancing the coverage area of the sensing range with the limiting resource is a critical problem in the wireless sensor network (WSN). Mobile sensors are patched coverage holes and they also have limited energy to move in large distances. Several recent studies indicated the metaheuristic algorithms can find an acceptable deployed solution in a reasonable time, especially the PSO-based algorithm. However, the speeds of convergence of most PSO-based algorithms are too fast which will lead to the premature problem to degrade the quality of deployed performance in WSN. A hybrid metaheuristic combined with dynamic multi-swarm particle swarm optimization and firefly algorithm will be presented in this paper to find an acceptable deployed solution with the maximum coverage rate and minimum energy consumption via static and mobile sensors. Moreover, a novel switch search mechanism between sub-swarms will also be presented for the proposed algorithm to avoid fall into local optimal in early convergence process. The simulation results show that the proposed method can obtain better solutions than other PSO-based deployment algorithms compared in this paper in terms of coverage rate and energy consumption. © 2023 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

IVIDNet: Intelligent iris vitality detection via weighted prediction score level fusion

引用

Multimedia Tools and Applications 2023年第29期82卷 45959-45981页

作者： Verma, Palak Selwal, Arvind Sharma, Deepika Department of Computer Science and Engineering Indian Institute of Technology Jammu PO-Nagrota Jammu181221 India Department of Computer Science and Information Technology Central University of Jammu Samba181143 India

Iris recognition is one of the most widely used human authentication mechanism that has gained huge popularity due to its security and efficiency. However, recently attackers have breached the security of these systems via synthetically generated fake iris traits using a variety of artefacts such as paper printouts, video attacks, and cosmetic lenses. To countermeasure these attacks, an anti-deception sub-system is instilled between sensor and feature extractor modules of the system. These sub-systems intelligently measure the vitality of the presented iris traits and are popularly known as iris vitality detection (IVID) or iris anti-spoofing techniques. Recently, the deep learning-based models are widely deployed for iris anti-spoofing approaches, but these methods result in additional training overhead as well as require larger training dataset. In this paper, we expound a novel iris vitality detection network (IVIDNet) that employs the robust features of two pre-trained deep convolutional neural networks (DCNN). The extracted features are then integrated via a new weighted score-level fusion technique. To demonstrates the efficacy of the proposed technique, experimental analysis is carried out on benchmark iris liveness detection Notre Dame 2017 and Notre Dame cosmetic lenses dataset (NDCLD) 2015. The proposed IVIDNet exhibits excellent performance in the known attack scenario with an average classification error rate (ACER) of 0.60%. Moreover, IVIDNet shows superior performance in the unseen attacks scenario (i.e. cross-database) with an ACER of 9.72%. In overall, the proposed model outperforms other similar iris anti-spoofing approaches and efficient in terms of computational overhead. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Extracting Facial Features to Detect Deepfake Videos Using Machine Learning

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 834-842页

作者： Aslam, Ayesha Mir, Jamaluddin Zaman, Gohar Rahman, Atta Salam, Asiya Abdus Ali, Farhan Alhiyafi, Jamal Bakry, Aghiad Gul, Mustafa Jamal Gollapalli, Mohammed Mahmud, Maqsood Department of Computer Science Abbottabad University of Science and Technology Havelian Pakistan Department of Computer Science College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam31441 Saudi Arabia Department of Computer Information Systems College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam31441 Saudi Arabia College of Electronics and Information Engineering Shenzhen University Shenzhen China Department of Computer Science Kettering University FlintMI United States Department of Business Administration University of York York YO10 5DD Heslington United Kingdom Department of Information Technology & Engineering Sydney Met SydneyNSW2000 Australia School of Computing Ulster University Northern Ireland Belfast United Kingdom

Generative adversarial networks (GANs) have gained popularity for their ability to synthesize images from random inputs in deep learning models. One of the notable applications of this technology is the creation of realistic videos known as deepfakes, which have been misused on social media platforms. The difficulty lies in distinguishing these fake videos from real ones with the naked eye, leading to significant concerns. This study proposes a supervised machine learning approach to effectively differentiate between real and counterfeit videos by detecting visual artifacts. To achieve this, two facial features are extracted: eye blinking and nose position, utilizing landmark detection techniques. Both features were trained on supervised machine learning classifiers and evaluated using the publicly available UADFV and Celeb-DF deepfake datasets. The experiments successfully demonstrate that the proposed method achieves a promising and superior performance, with an area under the curve (AUC) of 97% for deepfake detection in contrast to state-of-the-art methods investigating the same datasets. © (2025), (Science and information Organization). All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Salp Swarm Incorporated Adaptive Dwarf Mongoose Optimizer with Lévy Flight and Gbest-Guided Strategy

引用

Journal of Bionic engineering 2024年第4期21卷 2110-2144页

作者： Gang Hu Yuxuan Guo Guanglei Sheng Department of Applied Mathematics Xi’an University of TechnologyXi’an710054People’s Republic of China School of Computer Science and Engineering Xi’an University of TechnologyXi’an710048People’s Republic of China Department of Electronics and Information Engineering Bozhou UniversityBozhou236800People’s Republic of China

In response to the shortcomings of Dwarf Mongoose Optimization(DMO)algorithm,such as insufficient exploitation capability and slow convergence speed,this paper proposes a multi-strategy enhanced DMO,referred to as ***,we propose an improved solution search equation that utilizes the Gbest-guided strategy with different parameters to achieve a trade-off between exploration and exploitation(EE).Secondly,the Lévy flight is introduced to increase the diversity of population distribution and avoid the algorithm getting stuck in a local *** addition,in order to address the problem of low convergence efficiency of DMO,this study uses the strong nonlinear convergence factor Sigmaid function as the moving step size parameter of the mongoose during collective activities,and combines the strategy of the salp swarm leader with the mongoose for cooperative optimization,which enhances the search efficiency of agents and accelerating the convergence of the algorithm to the global optimal solution(Gbest).Subsequently,the superiority of GLSDMO is verified on CEC2017 and CEC2019,and the optimization effect of GLSDMO is analyzed in *** results show that GLSDMO is significantly superior to the compared algorithms in solution quality,robustness and global convergence rate on most test ***,the optimization performance of GLSDMO is verified on three classic engineering examples and one truss topology optimization *** simulation results show that GLSDMO achieves optimal costs on these real-world engineering problems.

关键词： Dwarf mongoose optimization algorithm Gbest-guided Lévy flight Adaptive parameter Salp swarm algorithm engineering optimization Truss topological optimization

来源：评论

学校读者我要写书评

暂无评论

Detection of Hardware Trojan in Nanocrossbar-Based Cryptographic Circuit 6th

Detection of Hardware Trojan in Nanocrossbar-Based Cryptogra...

引用

6th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Basu, Subhashree Ghoshal, Ranjit Kule, Malay Department of Information Technology St. Thomas’ College of Engineering and Technology Kolkata India Department of Computer Technology Indian Institute of Engineering Science and Technology Howrah Shibpur India

ISBN: (纸本)9789819780891

Many electronic components can be combined into a single chip using VLSI technology. However, as Moore predicted, this technology will soon reach a limit, making it impossible to reduce the size of VLSI circuits further. Scientists are focusing on developing nanotechnology as a result of the impending technological roadblock. Memristor technology presents itself as a viable substitute for transistor-based technology with the advantages of significantly higher speed, reduced dimensions, and low power consumption. This chapter studies the possibility of insertion of Hardware Trojan in a cryptography circuit developed from symmetric functions. Active and passive Trojans are inserted, and their effects on the actual result are analyzed to propose methods for detecting them. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classifiers for Social Media Bots Detection on Twitter using Explainable AI 2

Machine Learning Classifiers for Social Media Bots Detection...

引用

2nd International Conference on Informatics, ICI 2023

作者： Gupta, Sarishty Sinha, Adwitiya Jaypee Institute of Information Technology Department of Computer Science and Engineering and Information Technology Noida India

ISBN: (纸本)9798350343830

Social networks have shaped modern society by revolutionizing how people connect and communicate with others around the world. Social media bots have become more prevalent as a result of social networks' phenomenal development and influence, nevertheless. These automated systems that are guided by algorithms or malicious actors can mimic human behavior and provide the impression that actual people are there. Growing concerns about the integrity of online debate, the dissemination of false information, and potential public opinion manipulation have been sparked by the use of social media bots. It is now necessary to create efficient procedures for identifying and thwarting social media threats in order to tackle this expanding danger. Such efforts use a variety of methods, including as examining profile metadata, observing behavioral patterns, and utilizing the strength of machine learning algorithms. In this paper, we propose an approach which uses multiple features of a user entity on Twitter to train a model for social media bot detection. We employed Twibot-22 dataset to conduct the experiment and compared the performance of our approach with established benchmark models in order to assess its efficacy. Remarkably, our Random Forest model outperformed the benchmarks, achieving an accuracy rate of 0.96. We utilized explainable AI technique to enhance the interpretability of random forest model. This study provides insights that are of immense value in refining the model and delving deeper into the distinguishing features of social bots and human users within the Twitter environment. © 2023 IEEE.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

StressMLIoT: IoT Sensor Features Reduction and Machine Learning driven Stress Identification System 2

StressMLIoT: IoT Sensor Features Reduction and Machine Learn...

引用

2nd International Conference on Informatics, ICI 2023

作者： Vinayaka, Samarth Dhariwal, Harsh Aggarwal, Kirti Arora, Anuja Jaypee Institute of Information Technology Department of Computer Science and Engineering and Information Technology Noida India

ISBN: (纸本)9798350343830

Disruption and disturbance in activities in the work environment are the causes of stress in employees. A variety of IoT sensors, Kinect 3D sensors, health data sensors, log files, etc. assist in fetching human activity and interruption details. Sensors captured data is usually high volume and inputting it into the learning model is a challenging task. The research work aims to build an optimal stress identification system due to interruptions while doing office work. In order to build an optimal system, the dimensions of sensor data are reduced with a negotiable reduction in stress identification accuracy. Principal Component Analysis has been applied for feature reduction and three machine learning algorithms- K Nearest Neighbour, Random Forest, and Support vector machine are used to validate the outcome of reduced dimension and not reduced dimensions stress identification system. Random forest algorithm outperformed and achieved accuracy and F-measures are 99.9% and 99.9% respectively in 25 seconds with all dimensions and 92% and 92.4% with reduced dimensions in approximately one-fourth less time i.e. 6.9 seconds. Overall, After dimension reduction the execution time was brought down to 75% - 50% with a slight reduction in achieved accuracy in the 5%-7% range. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Secure Multi-factor Authentication Protocol for Healthcare Services Using Cloud-based SDN

引用

computers, Materials & Continua 2023年第2期74卷 3711-3726页

作者： Sugandhi Midha Sahil Verma Kavita Mohit Mittal Nz Jhanjhi Mehedi Masud Mohammed A.AlZain Department of Computer Science and Engineering Chandigarh UniversityMohali140413India Chandigarh Engineering College Jhanjeri Mohali140307India School of Computer Science and Engineering SCETaylor’s UniversitySubang Jaya47500Malaysia FITTaylor’s UniversitySubang Jaya47500Malaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Cloud-based SDN(Software Defined Network)integration offers new kinds of agility,flexibility,automation,and speed in the *** and Cloud providers both leverage the benefits as networks can be configured and optimized based on the application *** integration of cloud and SDN paradigms has played an indispensable role in improving ubiquitous health care *** has improved the real-time monitoring of patients by medical ***’data get stored at the central server on the cloud from where it is available to medical practitioners in no *** centralisation of data on the server makes it more vulnerable to malicious attacks and causes a major threat to patients’*** recent days,several schemes have been proposed to ensure the safety of patients’*** most of the techniques still lack the practical implementation and safety of *** this paper,a secure multi-factor authentication protocol using a hash function has been ***(Body Area Network)logic has been used to formally analyse the proposed scheme and ensure that no unauthenticated user can steal sensitivepatient *** Protocol Animator(SPAN)–Automated Validation of Internet Security Protocols and Applications(AVISPA)tool has been used for *** results prove that the proposed scheme ensures secure access to the database in terms of spoofing and *** comparisons of the proposed scheme with other related historical schemes regarding time complexity,computation cost which accounts to only 423 ms in proposed,and security parameters such as identification and spoofing prove its efficiency.

关键词： Multi-factor authentication hash function BAN logic SPANAVISPA

来源：评论

学校读者我要写书评

暂无评论

Escape Routing Using Deep Reinforcement Learning

Escape Routing Using Deep Reinforcement Learning

引用

2025 International Workshop on Advanced Imaging technology, IWAIT 2025

作者： Cheng, Hsu Fu Cheng, Dun Wei Department of Computer Science and Information Engineering National Yunlin University of Science & Technology Yunlin Taiwan

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

Escape routing is a critical task in the design of printed circuit boards (PCB) and integrated circuits (IC), aiming to establish effective connections among multiple pin points while avoiding path overlaps and interference from *** paper proposes a Deep Reinforcement Learning (DRL)-based solution utilizing a Deep Q-Network (DQN) to address the escape routing *** problem is modeled as a Markov Decision Process (MDP), and the agent learns effective routing strategies through interactions with the *** were conducted in a 25×26 simulated grid environment, testing scenarios with 30, 60, and 90 pin *** study highlights the potential of Deep Reinforcement Learning in solving escape routing problems, offering a novel approach to addressing routing challenges in PCB design. © 2024 SPIE.

关键词： Deep reinforcement learning

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：