检索结果-内蒙古大学图书馆

Adaptive Flowing Traffic Prediction in Contention Random Access for Optimizing Virtual/Physical Resource in B5G/5G New Radio and Core Network

引用

IEEE Transactions on Network science and engineering 2024年第2期11卷 1934-1946页

作者： Chang, Ben-Jye Lin, Yu-Ting National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu City64002 Taiwan

For differentiating and customizing different classes of traffic and virtualizing physical resources of networks and machines, B5G/5G specifies several novel mechanisms, including VNF, SDN, Service Function Chaining, Network Slicing, MEC, etc. In B5G/5G, the out-of-band contention based random access using PHY subframe preambles is specified before data transmissions. However, B5G/5G requires dynamically efficient approaches for realizing real 5G, including randomly contending limited sharing channel preambles, dynamically determining flow slicing of SFC, dynamically determining PM/VNFi/VNFc resources, while minimizing carrying cost and energy consumption via multi-link/multi-path 5G network. This paper thus proposes the efficient Adaptive Slice Flowing Prediction in Contention Random Access for Optimizing Virtual/Physical Resource in 5G (APROR) consisting of two phases: Dynamic Flow Random Contention of 5G (dFRC) and Adaptive Real-time Predictive Flow Data Rate of diverse types of slicing (aRPF). Numerical results show APROR outperforms all approaches in performance metrics: contention collision probability, access delay, E2E delay, loss, throughput, etc. Consequently, several contributions are definitely achieved: 1) to dynamically determine the preamble configuration modes and dynamic flow backoff, 2) to adaptively differentiate collision domains for different types of flows and minimize collision probability, and 3) to determine the optimal Virtual/Physical Resource achieving optimal SFC corresponding to network slices. © 2013 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Concise Concepts with Probabilistic Modeling for Interpretable Visual Recognition

引用

IEEE Transactions on Multimedia 2025年 27卷 3117-3131页

作者： Zhang, Yixuan Liu, Chuanbin Liu, Yizhi Gao, Yifan Lu, Zhiying Xie, Hongtao Zhang, Yongdong University of Science and Technology of China School of Information Science and Technology China Hunan University of Science and Technology Department of Computer Science and Engineering China

Interpretable visual recognition is essential for decision-making in high-stakes situations. Recent advancements have automated the construction of interpretable models by leveraging Visual Language Models (VLMs) and Large Language Models (LLMs) with Concept Bottleneck Models (CBMs), which process a bottleneck layer associated with human-understandable concepts. However, existing methods suffer from two main problems: a) the collected concepts from LLMs could be redundant with task-irrelevant descriptions, resulting in an inferior concept space with potential mismatch. b) VLMs directly map the global deterministic image embeddings with fine-grained concepts results in an ambiguous process with imprecise mapping results. To address the above two issues, we propose a novel solution for CBMs with Concise Concept and Probabilistic Modeling (CCPM) that can achieve superior classification performance via high-quality concepts and precise mapping strategy. Fisrt, we leverage in-context examples as category-related clues to guide LLM concept generation process. To mitigate redundancy in the concept space, we propose a Relation-Aware Selection (RAS) module to obtain a concise concept set that is discriminative and relevant based on image-concept and inter-concept relationships. Second, for precise mapping, we employ a Probabilistic Distribution Adapter (PDA) that estimates the inherent ambiguity of the image embeddings of pre-trained VLMs to capture the complex relationships with concepts. Extensive experiments indicate that our model achieves state-of-the-art results with a 5.48% improvement in classification accuracy on eight mainstream recognition benchmarks as well as reliable explainability through interpretable analysis. © 1999-2012 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Novel Framework for an Intrusion Detection System Using Multiple Feature Selection Methods Based on Deep Learning

引用

Tsinghua science and Technology 2024年第4期29卷 948-958页

作者： A.E.M.Eljialy Mohammed Yousuf Uddin Sultan Ahmad Department of Information Systems College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharjSaudi Arabia Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharjSaudi Arabiaand also with University Center for Research and Development(UCRD)Department of Computer Science and EngineeringChandigarh UniversityPunjabIndia

Intrusion detection systems (IDSs) are deployed to detect anomalies in real time. They classify a network’s incoming traffic as benign or anomalous (attack). An efficient and robust IDS in software-defined networks is an inevitable component of network security. The main challenges of such an IDS are achieving zero or extremely low false positive rates and high detection rates. Internet of Things (IoT) networks run by using devices with minimal resources. This situation makes deploying traditional IDSs in IoT networks unfeasible. Machine learning (ML) techniques are extensively applied to build robust IDSs. Many researchers have utilized different ML methods and techniques to address the above challenges. The development of an efficient IDS starts with a good feature selection process to avoid overfitting the ML model. This work proposes a multiple feature selection process followed by classification. In this study, the Software-defined networking (SDN) dataset is used to train and test the proposed model. This model applies multiple feature selection techniques to select high-scoring features from a set of features. Highly relevant features for anomaly detection are selected on the basis of their scores to generate the candidate dataset. Multiple classification algorithms are applied to the candidate dataset to build models. The proposed model exhibits considerable improvement in the detection of attacks with high accuracy and low false positive rates, even with a few features selected.

关键词： random forest feature selection decision tree software-defined network logistic regression intrusion detection system XGB classifier AdaBoost

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年 13卷 90316-90332页

作者： Huang, Huang Asemi, Adeleh Universiti Malaya Faculty of Computer Science Information Technology Department of Software Engineering Kuala Lumpur Malaysia

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domainspecific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting," arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains—Laptops, Restaurants, Tweets, and Finance—this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CrowdDC: Ranking From Crowdsourced Paired Comparison With Divide-and-Conquer

引用

IEEE Transactions on Computational Social Systems 2024年第2期11卷 3015-3021页

作者： Wang, Ming-Hung Zhang, Chia-Yuan Song, Jia-Ru National Chung Cheng University Department of Computer Science and Information Engineering Chiayi621301 Taiwan

This article introduces a novel algorithm, named 'CrowdDC,' that aims to solve the issue of ranking large datasets based on subjective factors using crowdsourced paired comparisons. In traditional paired comparison analysis, dealing with a sizeable dataset can become impractical as the number of comparisons required increases quadratically. To address this problem, CrowdDC is designed as a divide-and-conquer algorithm that partitions the dataset into smaller subsets and compares them independently. The results of these comparisons are then combined to generate an overall ranking. Simulation results showed that, when ranking more than 100 items, CrowdDC succeeded in reducing the number of requisite tasks by 45%-75%, while concurrently maintaining an accuracy range of 90%-95% relative to the baseline approach. © 2014 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Conditional-GAN-Based Face Inpainting Approaches With Symmetry and View-Degree Utilization

引用

IEEE Access 2024年 12卷 87467-87478页

作者： Hong, Tzung-Pei Wu, Jin-Hang Su, Ja-Hwung Yin, Tang-Kai National University of Kaohsiung Department of Computer Science and Information Engineering Kaohsiung811726 Taiwan National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804201 Taiwan

Recently, image inpainting has been proposed as a solution for restoring the polluted image in the field of computer vision. Further, face inpainting is a subfield of image inpainting, which refers to a set of image editing algorithms re-conducting the missing regions in face smoothly. Actually, face inpainting is more challenging than general image inpainting because it needs more face structure information. Although a number of past studies were proposed for face inpainting by using face segmentation, face edge and face topology, there is some important information ignored, such as geometric and symmetric properties. Based on such concepts, in this paper, we propose a two-stage face inpainting method called CGAN (Conditional Generative Adversarial Network) which integrates face landmarks and Generative Adversarial Network (called GAN). In the first stage, the face landmark is predicted as the condition, providing GAN with important information of geometry and symmetry. The main idea in this stage is to dynamically adjust the loss by the proposed view degree. Accordingly, the masked face image and the corresponding face landmark are used as conditions input to the GAN in the second stage. Finally, the missing-regions are inpainted by the proposed CGAN. To reveal the effectiveness of proposed method, a number of evaluations were conducted on real datasets. The experimental results show that, the proposed method predicts a better face landmark by information of geometric structures and symmetric outlooks, and thereupon the proposed CGAN reconstructs the missing regions superior to the compared methods. © 2013 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Exploring Nonuniform Structure of NSRTDs for Characterizing MACA Rules in the Null-Boundary Condition

引用

Complex Systems 2025年第1期34卷 91-127页

作者： Hazra, Suvadip Banerjee, Som Dalui, Mamata Chakraborty, Bidesh Department of Computer Science and Engineering Indian Institute of Information Technology Karnataka Dharwad58009 India Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur713209 India Department of Computer Science and Engineering Haldia Institute of Technology West Bengal Haldia721657 India

The cellular automaton (CA), a discrete model, is gaining popularity in simulations and scientific exploration across various domains, including cryptography, error-correcting codes, VLSI design and test pattern generation. This paper examines a two-state three-neighborhood nonuniform finite CA with a specified number of fixed points. We utilize a graph-based tool known as the next state rule minterm transition diagram (NSRTD) to analyze the spatiotemporal behavior of these cellular automata (CAs) across all lengths. We devise methods for synthesizing nonuniform single length cycle multi-attractor CAs (MACAs), a specialized class of irreversible CA with a predefined number of fixed points for any arbitrary length. Despite the method’s exponential worstcase time complexity, it offers the advantage of selecting rules for each CA cell from a set of candidate rules, ensuring the desired number of fixed points. © 2025, Complex Systems Publications, Inc. All rights reserved.

关键词： cellular automata fixed-point attractor length cycle multi-attractor cellular automata MACA next state rule minterm transition diagram NSRTD

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning (RL)-based semantic segmentation and attention based backpropagation convolutional neural network (ABB-CNN) for breast cancer identification and classification using mammogram images

引用

Neural Computing and Applications 2024年第24期36卷 14797-14823页

作者： Thakur, Neha Kumar, Pardeep Kumar, Amit Department of Computer Science & amp Engineering Jaypee University of Information Technology HP Solan India

Breast cancer poses a threat to women’s health and contributes to an increase in mortality rates. Mammography has proven to be an effective tool for the early detection of breast cancer. However, it faces many challenges in early breast cancer detection due to poor image quality, traditional segmentation, and feature extraction. Therefore, this work addresses these issues and proposes an attention-based backpropagation convolutional neural network (ABB-CNN) to detect breast cancer from mammogram images more accurately. The proposed work includes image enhancement, reinforcement learning-based semantic segmentation (RLSS), and multiview feature extraction and classification. The image enhancement is performed by removing noise and artefacts through a hybrid filter (HF), image scaling through a pixel-based bilinear interpolation (PBI), and contrast enhancement through an election-based optimization (EO) algorithm. In addition, the RLSS introduces intelligent segmentation by utilizing a deep Q network (DQN) to segment the region of interest (ROI) strategically. Moreover, the proposed ABB-CNN facilitates multiview feature extraction from the segmented region to classify the mammograms into normal, malignant, and benign classes. The proposed framework is evaluated on the collected and the digital database for screening mammography (DDSM) datasets. The proposed framework provides better outcomes in terms of accuracy, sensitivity, specificity, precision, f-measure, false-negative rate (FNR) and area under the curve (AUC). This work achieved (99.20%, 99.35%), (99.56%, 99.66%), (98.96%, 98.99%), (99.05%, 99.12%), (0.44%, 0.34%), (99.31%, 99.39%) and (99.27%, 99.32%) of accuracy, sensitivity, specificity, precision, FNR, f-measure and AUC on (collected, DDSM datasets), respectively. This research addresses the prevalent challenges in breast cancer identification and offers a robust and highly accurate solution by integrating advanced deep-learning techniques. The evaluated re

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Optimizing photo-to-anime translation with prestyled paired datasets

引用

Multimedia Tools and Applications 2024年第41期83卷 89393-89414页

作者： Chang, Chuan-Wang Dharmawan, Pratamagusta Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung Taiwan

Animation is a widespread artistic expression that holds a special place in people's hearts. Traditionally, animation creation has relied heavily on manual techniques, demanding skilled drawing abilities and a significant amount of time. For instance, many Japanese anime films draw inspiration from real-world settings, requiring access to relevant references and artists capable of translating them into anime visuals. Consequently, the development of technology that automatically converts images into anime holds great significance. Numerous methods for style transfer have been developed using unsupervised learning and have achieved impressive results. However, unsupervised learning methods suffer when the image contains multiple styles within itself because they learn the style of the image globally. To solve this problem, we propose splitting these styles within the image into multiple classes: sky, buildings, greenery, water, and other objects. Then, we style these separated classes using existing image-to-image translation models. Finally, we train a pix2pix model to learn image style transfer in a paired manner. The experimental results show that the images are effectively styled into the resulting anime-styled image domain with comparable results to existing unsupervised learning GAN-based methods. The proposed method can effectively transfer the style from real-world photos into the anime-styled image domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Drought Modeling in South Asia: Machine Learning Approaches, Challenges and Opportunities

引用

IEEE Access 2025年 13卷 87654-87671页

作者： Reshan, Mana Saleh Al Raza, Muhammad Owais Mahoto, Naeem Ahmed Rajab, Adel Shaikh, Asadullah Elmagzoub, M.A. Rajab, Khairan Najran University College of Computer Science and Information Systems Department of Information Systems Najran61441 Saudi Arabia College of Computer Science and Information Systems Najran61441 Saudi Arabia Istanbul Sabahattin Zaim University Department of Computer Engineering Istanbul34303 Turkey Mehran University of Engineering and Technology Department of Software Engineering Sindh Jamshoro76062 Pakistan Najran University College of Computer Science and Information Systems Department of Computer Science Najran61441 Saudi Arabia Najran University College of Computer Science and Information Systems Department of Network and Communication Engineering Najran Saudi Arabia

Drought is an environmental and economic problem. Sustainable ecosystems, water resources, food security, and all are severely affected by drought. Due to the increasing frequency and severity of droughts caused by climate change. Effective drought modeling is crucial for early warning systems and risk mitigation. Recent advances in machine learning (ML) and deep learning (DL) techniques have been developed as potential drought modeling tools that offer accurate drought modeling, providing policymakers and decision-makers with insightful information. The geographical scope of this study is the region of South Asia. This region is selected because of its heavy reliance on agriculture and vulnerability to droughts. The review offers a thorough grasp of how drought conditions are evaluated by gathering and analyzing the most important drought indicators and metrics specific to South Asia. The paper explores the current state- of-the-art in ML and DL (Complex Machine learning and deep learning models) for drought modeling, highlighting current challenges such as incomplete and inconsistent datasets, Lack of explainability and interpretability in complex ML/DL models, unavailability of benchmarks. Based on these challenges, this review suggests the following techniques to address these challenges: Data integration (Data fusion), distributed machine learning (Federated Learning) and explainable AI (XAI, SHAP, LIME, etc.). © 2013 IEEE.

关键词： Federated 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：