检索结果-内蒙古大学图书馆

Enhancing CNN-based network intrusion detection through hyperparameter optimization

Intelligent Systems with Applications 2025年 26卷

作者： Kaissar, Antanios Nassif, Ali Bou Soudan, Bassel Injadat, MohammadNoor College of Engineering University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science & AI Faculty of Information Technology Zarqa University Zarqa Jordan

This research investigates the optimization of hyperparameters in Convolutional Neural Networks (CNNs) to enhance the performance of Network Intrusion Detection Systems (NIDS). Four distinct optimization techniques, including Grid Search (GS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO), are rigorously examined. Comprehensive experiments employ the UNSW-NB15 and CSE-CIC-IDS2018 datasets to determine the optimal hyperparameter configurations for each technique. Subsequently, detailed experiments evaluate the efficiency of the optimized models in detecting network attacks. The findings consistently reveal that optimized CNN models outperform their non-optimized counterparts across all optimization techniques. Notably, GWO emerges as the top-performing technique, achieving remarkable detection performance on both datasets, with 97.08 % accuracy, 96.95 % precision, 97.21 % recall, and 97.08 % F1 score on the UNSW-NB15 dataset, and 96.37 % accuracy, 96.13 % precision, 96.59 % recall, and 96.36 % F1 score on the CSE-CIC-IDS2018 dataset. Furthermore, hyperparameter optimization significantly reduces training and testing times. The GWO-optimized model achieved a reduction of >11 % in training time and 6.14 % in testing time on the UNSW-NB15 dataset. On the CSE-CIC-IDS2018 dataset, the GA-optimized model provided the best improvements, reducing training and testing times by 9.63 % and 8.61 %, respectively. In comparison to existing CNN models trained on the same datasets, the GWO-optimized CNN model consistently excels in all performance metrics, without the need for complex hybrid Deep Learning models. These results underscore the value of systematic hyperparameter optimization in enhancing CNN-based NIDS, with GWO standing out as a compelling technique for achieving optimal model configurations. © 2025 The Author(s)

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Foundation Models in Computational Pathology: A Review of Challenges, Opportunities, and Impact

arXiv

引用

arXiv 2025年

作者： Bilal, Mohsin Aadam Raza, Manahil Altherwy, Youssef Alsuhaibani, Anas Abduljabbar, Abdulrahman Almarshad, Fahdah Golding, Paul Rajpoot, Nasir Information Systems Department College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia Luddy School of Informatics Computing and Engineering Indiana University Indianapolis United States Tissue Image Analytics Centre Department of Computer Science University of Warwick Coventry United Kingdom Frontier AI San Francisco Bay Area United States

From self-supervised, vision-only models to contrastive visual-language frameworks, computational pathology has rapidly evolved in recent years. Generative AI "co-pilots" now demonstrate the ability to mine subtle, sub-visual tissue cues across the cellular-to-pathology spectrum, generate comprehensive reports, and respond to complex user queries. The scale of data has surged dramatically, growing from tens to millions of multi-gigapixel tissue images, while the number of trainable parameters in these models has risen to several billion. The critical question remains: how will this new wave of generative and multi-purpose AI transform clinical diagnostics? In this article, we explore the true potential of these innovations and their integration into clinical practice. We review the rapid progress of foundation models in pathology, clarify their applications and significance. More precisely, we examine the very definition of foundational models, identifying what makes them foundational, general, or multipurpose, and assess their impact on computational pathology. Additionally, we address the unique challenges associated with their development and evaluation. These models have demonstrated exceptional predictive and generative capabilities, but establishing global benchmarks is crucial to enhancing evaluation standards and fostering their widespread clinical adoption. In computational pathology, the broader impact of frontier AI ultimately depends on widespread adoption and societal acceptance. While direct public exposure is not strictly necessary, it remains a powerful tool for dispelling misconceptions, building trust, and securing regulatory support. © 2025, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Exploiting Circular Shifts for Efficient Chaotic Image Encryption

引用

IEEE Access 2025年 13卷 92997-93016页

作者： Lazaros Moysis Marcin Lawnik Wassim Alexan Sotirios K. Goudos Murilo S. Baptista George F. Fragulis Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Department of Mechanical Engineering University of Western Macedonia Kozani Greece Department of Mathematical Methods in Technics and Informatics Faculty of Applied Mathematics Silesian University of Technology Gliwice Poland Communications Department Faculty of Information Engineering and Technology German University in Cairo Cairo Egypt ELEDIA@AUTH School of Physics Aristotle University of Thessaloniki Thessaloniki Greece Department of Physics Institute for Complex Systems and Mathematical Biology SUPA The University of Aberdeen Aberdeen U.K.

This work presents a chaotic image encryption algorithm that acts on the binary level of the image for effective permutation, and on the byte level for substitution. The permutation step combines actions of bit level rearranging, and bit shuffling. Circular shift operations are used for bit shuffling, to reduce the execution time. Circular shifts are also applied to shuffle the permutation and substitution rules, effectively increasing security at a very low execution cost. The encryption keys are plaintext dependent, and a key mixing step in included, so that each part of the key affects all the subsequent encryption operations. For the encryption, a new Soboleva hyperbolic tangent based map is first designed. The dynamical behavior of the map is studied and shows robust chaos, and an absence of equilibria, meaning that it can generate hidden attractors. This map is used as an entropy source, along with a chaotic pseudo random number generator (PRNG). The encryption process shows a good performance under a collection of tests, and has also a low execution time, 0.0134 sec for a $256\times 256$ image, 0.0530 sec for a $512\times 512$ image, and 0.2050 sec for a $1024\times 1024$ image. So the proposed algorithm is a viable option for fast, efficient, and secure data encryption.

关键词： Encryption Security Chaotic communication Generators Robustness Matrices Costs Standards Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Exploring Grounding Abilities in Vision-Language Models through Contextual Perception

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Xu, Wei Zhou, Tianfei Zhang, Taoyuan Li, Jie Chen, Peiyin Pan, Jia Liu, Xiaofeng Hohai University College of Artificial Intelligence and Automation Changzhou213022 China Beijing Institute of Technology Department of Computer Science China De Anza College CA United States Nanjing Medical University Engineering Research Center of Intelligent Theranostics Technology and Instruments Ministry of Education Nanjing211166 China Nanjing Medical University School of Biomedical Engineering and Informatics Nanjing211166 China University of Hong Kong Department of Computer Science Hong Kong

Vision language models (VLMs) have demonstrated strong general capabilities and achieved great success in areas such as image understanding and reasoning. Visual prompts enhance the focus of VLMs on designated areas, but their fine-grained grounding has not been fully developed. Recent research has used Set-of-Mark (SoM) approach to unleash the grounding capabilities of Generative Pre-trained Transformer-4 with Vision (GPT-4V), achieving significant benchmark performance. However, SoM still has problems with label offset and hallucination of vision language models, and the grounding ability of VLMs remains limited, making it challenging to handle complex scenarios in human-robot interaction. To address these limitations and provide more accurate and less hallucinatory results, we propose Contextual Set-of-Mark (ConSoM), a new SoM-based prompting mechanism that leverages dual-image inputs and contextual semantic information of images. Experiments demonstrate that ConSoM has distinct advantages in visual grounding, improving by 11% compared to the baseline on the dataset Refcocog. Furthermore, we evaluated ConSoM’s grounding abilities in five indoor scenarios, where it exhibited strong robustness in complex environments and under occlusion conditions. We also introduced a scalable annotation method for pixel-level question-answering dataset. The accuracy, scalability, and depth of world knowledge make ConSoM a highly effective approach for future human-robot interactions. © 2016 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Container Scheduling Strategy Based on Image Layer Reuse and Sequential Arrangement in Mobile Edge Computing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wu, Haijie Lin, Weiwei Zhang, Haotong Shi, Fang Shen, Wangbo Li, Keqin Zomaya, Albert Y. South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Shenzhen518066 China South China University of Technology School of Software Engineering Guangzhou510006 China South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China State University of New York Department of Computer Science New PaltzNY12561 United States University of Sydney School of Computer Science SydneyNSW2006 Australia

In Mobile Edge Computing (MEC) scenarios, computational tasks are popularly deployed using containerization to isolate the runtime environment. To complete the execution of the task, the edge server first pulls the image, then instantiates and runs the container. Since it takes a lot of time for the edge server to download the image from the cloud, image reuse reduces the pulling latency significantly. However, the limited storage capacity of edge servers hinders image reuse. Recent works have enhanced reuse efficiency by leveraging the hierarchical structure of images and caching high-value layers. However, their efficiency remains limited due to the lack of multi-container collaboration. This paper proposes a novel container scheduling strategy based on image layer reuse and sequence arrangement (ILR-SA) for MEC scenarios, which achieves efficient scheduling by collaborating multiple containers. First, containers are greedily deployed into the edge cluster. Then, the execution sequence of containers is modeled as an optimal Hamiltonian path problem, efficiently solved by our proposed decomposition algorithm. Finally, an efficient image layer update strategy is used to achieve layer reuse. We conduct rigorous experiments to demonstrate that our proposed container scheduling strategy reduces the computational task completion time by up to 91.3% compared to existing approaches. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A Practical Distortion Simulator for Screen-Shooting Resilient Image Watermarking in Consumer Electronic Applications

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Yulin Ni, Jiangqun Malwi, Wajdan Al Asiri, Fatima Ahmad, Jawad Jiang, Donghua Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Cyber Science and Technology Shenzhen518107 China Peng Cheng Laboratory Department of New Networks Shenzhen518055 China King Khalid University College of Computer Science Department of Informatics and Computer Systems Abha61421 Saudi Arabia Prince Mohammad Bin Fahd University Cybersecurity Center Alkhobar Saudi Arabia

Nowadays screen-shooting resilient watermarking still remains as a predictive and challenging area of research for proactive data protection in consumer electronic applications. Present deep learning-based methodologies embrace end-to-end frameworks and devise specialized noise layer to simulate the distortions introduced in cross-media transmission between consumer electronics. Typically, the noise layer is designed as a deterministic image-to-image network to simulate the transformation from the clean images to the screen-captured ones, overlooking the randomness of real-world distortions, which makes it challenging to satisfy the demands of various consumer electronics and application scenarios. To address this issue, we conceptualize the screen-shooting channel as an image degradation model and accordingly develop the Resolver-Simulator framework (ReSim). The involved screen-shooting simulator is designed as a conditional image-to-image network to learn the exact degradation function. By taking advantage of the pre-trained parameter resolver, the noise components can be disentangled to compose the instance sets. Then the set sampling strategy is adopted to obtain the noise instances for realistic screen-shooting simulation for unseen images. Experimental results demonstrate that the proposed scheme outperforms the previous arts in terms of real-world robustness as well as exhibits high computational efficiency to enable real-time security solutions in consumer devices. © 1975-2011 IEEE.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

A House Divided: How U.S. Politics Could Shape Contact-Tracing Adoption in Future Pandemics 25

A House Divided: How U.S. Politics Could Shape Contact-Traci...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Garrett Smith Kirsten Chapman Tzu-Yu Weng Haijing Hao Mainack Mondal Staci Smith Yunan Chen Xinru Page Brigham Young University Provo Utah USA Computer Science Brigham Young University Provo Utah USA Bentley University Waltham Massachusetts USA Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur West Bengal India Informatics University of California Irvine Irvine California USA Department of Computer Science Brigham Young University Provo Utah USA

来源：评论

学校读者我要写书评

暂无评论

An Effective Deep Learning Technique for Analyzing COVID - 19 Using X-Ray Images 15th

An Effective Deep Learning Technique for Analyzing COVID - 1...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Uma Maheswari, V. Aluvalu, Rajanikanth Guduri, Manisha Kantipudi, M. V. V. Prasad Department of Computer Science and Engineering Chaitanya Bharati Institute of Technology Telangana Hyderabad India Pune India School of Computing and Informatics University of Louisiana at Lafayette LafayetteLA70503 United States University Pune412115 India

ISBN: (纸本)9783031810794

The COVID - 19 disease is a extremely contagious viral infection with significant global health insinuations. COVID has a negative impact on the world economy. If positive patients are identified early, the proliferation of this pandemic infection can be slackened. COVID-19 disease prophecy is useful for finding the people with health issues who are at risk of COVID. The Deep Learning and machine learning approaches for COVID prediction using X-ray images have the possibility to be tremendously helpful in addressing the shortage of clinicians and doctors in rural areas. This research presents a deep layered Convolutional Neural Network (CNN) for recognizing the COVID-19 patients by training the system with the datasets of around 6000 chest X-ray images collected from various sources. We are categorized them as normal or COVID - impacted. Our model trained the X-ray images of chest to find these patients. And it also predicted well with the help of image analysis and deep learning by showcasing the better results comparing with the state-of-the-art methods in terms of the average accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Wheelchair Wheel Design with Transformable “Wheel-Leg” Configuration for Climbing Stairs and Various Surfaces

Wheelchair Wheel Design with Transformable “Wheel-Leg” Con...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Islam Magomedov Timur Aygumov Anzor A. Kanametov Bissnes informatics Kadyrov Chechen state university Grozny Russia Department of software engineering computer technology and automated systems Dagestan State Technical University Dagestan Russia Department of Electronics and Digital Information Technologies Kabardino-Balkarian State University Nalchik Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The dynamic and uneven terrain of our environment introduces complexity for locomotion vehicles to navigate easily across different settings. Wheelchairs belong to the category of vehicles that require locomotion across various uneven terrains, such as stairs and other partitions. Therefore, the aim of this work is to design a wheel that can travel through various environments without using complex mechanisms. This aim was achieved by creating a novel transformable wheel. This wheel can turn into a legged wheel without using a complex mechanism and, when unnecessary, transform back into a normal wheel. Several simulations were carried out to understand the design's capability to overcome obstacles. In this case, the stair was the obstacle, and the results illustrated that the wheel is capable of climbing stairs without serious issues. Different parameters, such as speed and force, were examined with various values. The results showed that the weight on the wheelchair plays a significant role in climbing. For instance, with lighter weight, the structure moves without major slipping. The roughness of the surface is also related to the wheelchair's ability to reach the top of the stairs. A finer depth of cuts on the surface of the stairs increases the chance of the legged wheel firmly gripping and moving up the stairs.

关键词： Shape Navigation Wheelchairs Wheels Rotors Transforms Stairs Surface roughness Rough surfaces Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

SACR: Self-training with Saliency-Augmented Consistency Regularization for Few-Shot Learners

SACR: Self-training with Saliency-Augmented Consistency Regu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yanyan Feng Yue Zhou Yun Xue Fenghuan Li Zehong Lin School of Electronics and Information Engineering South China Normal University Foshan China Department of Artiffcial Intelligence School of Informatics Xiamen University Xiamen China School of Computer Science and Technology Guangdong University of Technology Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Pre-trained language models have made significant strides in natural language processing tasks, enabling flexible fine-tuning for downstream applications. However, in few-shot learning scenarios, pre-trained models face challenges related to overfitting due to limited training samples, which hinders their ability to capture data diversity and robustly handle input variations. To overcome these limitations, we propose the Saliency-Augmented Consistency Regularization (SACR) framework, a novel self-training strategy designed to improve few-shot learning performance and robustness. SACR consists of three key components: (1) Saliency-guided Data Perturbation, which uses saliency analysis to identify and perturb words that significantly influence model predictions, generating semantically consistent pseudo-samples; (2) Semantic-equivalent Sample Mining, which employs K-means clustering to select semantically similar samples and prevent semantic shift; and (3) Consistency Training, where regularization ensures consistency between the semantics and prediction distributions of the original and perturbed samples. We conducted extensive experiments on 15 public datasets to evaluate our approach. SACR significantly outperforms strong baseline models and demonstrates superior generalization capabilities compared to state-of-the-art methods, achieving an average 1.0% improvement in classification accuracy.

关键词： Training Adaptation models Sensitivity Perturbation methods Semantics Signal processing Data models Natural language processing Few shot learning Speech processing

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：