检索结果-内蒙古大学图书馆

computer Networks 2024年 253卷

作者： Tu, Yi-Hao Lin, En-Cheng Ke, Chih-Heng Ma, Yi-Wei Department of Electrical Engineering National Taiwan University of Science and Technology Taipei106335 Taiwan Master Program of Information Technology and Applications National Quemoy University Kinmen892009 Taiwan Department of Computer Science of Information Engineering National Quemoy University Kinmen892009 Taiwan

In this paper, we introduce the Enhanced Smart Exponential-Threshold-Linear (Enhanced-SETL) algorithm, a new approach that uses the multi-variable Deep Reinforcement Learning (DRL) framework to simultaneously optimize multiple settings of the Contention Window (CW) in IEEE 802.11 wireless networks. Unlike traditional DRL methods that adjust only a single CW parameter, our innovative approach simultaneously optimizes both the CW minimum (CWmin) and CW Threshold (CWThreshold), significantly improving network traffic control. We utilize a Double Deep Q-learning Network (DDQN) for dynamic updates of these CW settings, broadcasted across the dense Wi-Fi networks. This dual adjustment method, coupled with dynamic, data-driven updates, not only enhances throughput, but also reduces collision rates, and ensures fairness access across both static and dynamic wireless environments. Enhanced-SETL achieves a throughput improvement ranging from 3.55% up to 43.73% and from 3.98% up to 30.15% in static and dynamic scenarios over standard protocols and state-of-the-art DRL models, while maintaining a fairness index near 99% across diverse stations, showcasing its effectiveness and adaptability in various network conditions. © 2024

关键词： Wireless local area networks (WLAN)

AI-Powered Precision: Revolutionizing Skin Cancer Detection with Advanced Machine Learning

学校读者我要写书评

暂无评论

AI-Powered Precision: Revolutionizing Skin Cancer Detection ...

Novel Intelligent and Leading Emerging sciences Conference (NILES)

作者： Mariam M. Abd-elaziz Basma M. Elshafie Hagar Abdullah Karen Y. Gerges Ingy A. Ghanem Khaled M. Fouad Amir El-Ghamry Ibrahim F. Moawad Sara El-Metwally Faculty of computer science and engineering New Mansoura university Dakahlia Egypt Faculty of Engineering Computer and Communication program Faculty of Computer Science and Engineering Mansoura University New Mansoura University Information Systems Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer and Information Sciences Faculty of Computer Science and Engineering Mansoura University New Mansoura University Egypt School of Engineering and Computer Science University of Hertfordshire GAF Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Department of Artificial Intelligence College of Computer Science and Engineering Taibah University Medina Saudi Arabia

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

Skin cancer's increasing incidence rates necessitate advanced diagnostic tools. This research uses MobileNet architecture to develop an enhanced system for skin cancer detection. MobileNet's efficient CNN architecture, combined with Keras for model lifecycle management and TensorFlow for real-time inference, forms the foundation of this study. Using 10,015 dermatoscopic pictures from seven different classifications of skin cancer in the HAM10000 dataset, the methodology includes several key stages: image preprocessing to correct illumination and adjust resolution, data augmentation to balance the dataset, and model training using Transfer Learning. The MobileNet model was trained over 50 epochs with a comprehensive architecture incorporating multiple specialized layers. By combining large-scale data analysis and adaptive learning, this methodology demonstrates The revolutionary possibilities of AI and ML in improving skin cancer diagnostics and public health outcomes. Keywords Skin Cancer Detection, Dermatoscopic Images, Machine Learning, Deep Learning

关键词： Training Deep learning Adaptation models Image resolution Transfer learning Lighting Real-time systems Image preprocessing Public healthcare Skin cancer

The Robustness of Structural Features in Species Interaction Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Fard, Sanaz Hasanzadeh Dolson, Emily Department of Computer Science and Engineering Michigan State University United States Program in Ecology Evolution and Behavior Michigan State University United States

Species interaction networks are a powerful tool for describing ecological communities;they typically contain nodes representing species, and edges representing interactions between those species. For the purposes of drawing abstract inferences about groups of similar networks, ecologists often use graph topology metrics to summarize structural features. However, gathering the data that underlies these networks is challenging, which can lead to some interactions being missed. Thus, it is important to understand how much different structural metrics are affected by missing data. To address this question, we analyzed a database of 148 real-world bipartite networks representing four different types of species interactions (pollination, host-parasite, plant-ant, and seed-dispersal). For each network, we measured six different topological properties: number of connected components, variance in node betweenness, variance in node PageRank, largest Eigenvalue, the number of non-zero Eigenvalues, and community detection as determined by four different algorithms. We then tested how these properties change as additional edges – representing data that may have been missed – are added to the networks. We found substantial variation in how robust different properties were to the missing data. For example, the Clauset-Newman-Moore and Louvain community detection algorithms showed much more gradual change as edges were added than the label propagation and Girvan-Newman algorithms did, suggesting that the former are more robust. Robustness also varied for some metrics based on interaction type. These results provide a foundation for selecting network properties to use when analyzing messy ecological network data. © 2025, CC BY.

关键词： Anthropogenic

Untapped Potential in Self-Optimization of Hopfield Networks: The Creativity of Unsupervised Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Weber, Natalya Guckelsberger, Christian Froese, Tom Embodied Cognitive Science Unit Okinawa Institute of Science and Technology Graduate University Okinawa904-0412 Japan Department of Computer Science Aalto University Espoo02150 Finland School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

The Self-Optimization (SO) model can be considered as the third operational mode of the classical Hopfield Network, leveraging the power of associative memory to enhance optimization performance. Moreover, it has been argued to express characteristics of minimal agency, which renders it useful for the study of artificial life. In this article, we draw attention to another facet of the SO model: its capacity for creativity. Drawing on creativity studies, we argue that the model satisfies the necessary and sufficient conditions of a creative process. Moreover, we show that learning is needed to find creative outcomes above chance probability. Furthermore, we demonstrate that modifying the learning parameters in the SO model gives rise to four different regimes that can account for both creative products and inconclusive outcomes, thus providing a framework for studying and understanding the emergence of creative behaviors in artificial systems that learn. Copyright © 2024, The Authors. All rights reserved.

关键词： Unsupervised learning

RSCNet: Dynamic CSI Compression for Cloud-based WiFi Sensing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Barahimi, Borna Singh, Hakam Tabassum, Hina Waqar, Omer Omer, Mohammad Electrical Engineering and Computer Science Department York University Canada School of Computing University of the Fraser Valley BC Canada Cognitive Systems Corp. Waterloo Canada

WiFi-enabled Internet-of-Things (IoT) devices are evolving from mere communication devices to sensing instruments, leveraging Channel State Information (CSI) extraction capabilities. Nevertheless, resource-constrained IoT devices and the intricacies of deep neural networks necessitate transmitting CSI to cloud servers for sensing. Although feasible, this leads to considerable communication overhead. In this context, this paper develops a novel Real-time Sensing and Compression Network (RSCNet) which enables sensing with compressed CSI;thereby reducing the communication overheads. RSCNet facilitates optimization across CSI windows composed of a few CSI frames. Once transmitted to cloud servers, it employs Long Short-Term Memory (LSTM) units to harness data from prior windows, thus bolstering both the sensing accuracy and CSI reconstruction. RSCNet adeptly balances the trade-off between CSI compression and sensing precision, thus streamlining real-time cloud-based WiFi sensing with reduced communication costs. Numerical findings demonstrate the gains of RSCNet over the existing benchmarks like SenseFi, showcasing a sensing accuracy of 97.4% with minimal CSI reconstruction error. Numerical results also show a computational analysis of the proposed RSCNet as a function of the number of CSI frames. © 2024, CC BY.

关键词： Internet of things

Comprehensive Study and Analysis for StarGAN and StarGAN-v2 in the Task of Image Generation

学校读者我要写书评

暂无评论

Comprehensive Study and Analysis for StarGAN and StarGAN-v2 ...

作者： Yuanan Cai Yepeng Li Zhenyu Zhang Department of Computer Engineering Baskin School of EngineeringUniversity of California-Santa Cruz Department of Cognitive Science University of California–San Diego Department of information technology Monash University

With the continuous development of deep learning and artificial intelligence industry,more and more neural networks have been *** them,one typical network widely used is *** solves the problem of requiring multiple generators and discriminators for multiple domains and style *** this article,we will analyze and explore StarGAN v1 and StarGAN *** StarGAN's development history,advantages and disadvantages in the application,*** the same time,we will compare StarGAN with other neural networks such as CycleGAN and MSGAN through some discrimination criteria,and clearly demonstrate the influence of different networks on the generation of image data sets through quantitative and qualitative *** addition,we also found a representative code on some of the actual uses of StarGAN for hair replacement through online *** this code may be used to confuse the use of StarGAN v1 and v2,we will also improve this code in the article and put forward suggestions for *** this paper,we carried out the specific analysis of StarGAN's loss function based on the existing data and put forward some relevant *** taking the data we searched for StarGAN,it can be found that StarGAN could use as few resources as possible to achieve clearer and more varied results during the image generation task.

关键词： GAN StarGAN Machine learning Deep Learning Image Generation

Updating Clinical Risk Stratification Models Using Rank-Based Compatibility: Approaches for Evaluating and Optimizing Clinician-Model Team Performance 8

学校读者我要写书评

暂无评论

Updating Clinical Risk Stratification Models Using Rank-Base...

8th Machine Learning for Healthcare Conference, MLHC 2023

作者： Ötles, Erkin Denton, Brian T. Wiens, Jenna Medical Scientist Training Program University of Michigan Ann ArborMI United States Department of Industrial and Operations Engineering University of Michigan Ann ArborMI United States Division of Computer Science and Engineering University of Michigan Ann ArborMI United States

As data shift or new data become available, updating clinical machine learning models may be necessary to maintain or improve performance over time. However, updating a model can introduce compatibility issues when the behavior of the updated model does not align with user expectations, resulting in poor user-model team performance. Existing compatibility measures depend on model decision thresholds, limiting their applicability in settings where models are used to generate rankings based on estimated risk. To address this limitation, we propose a novel rank-based compatibility measure, CR, and a new loss function that aims to optimize discriminative performance while encouraging good compatibility. Applied to a case study in mortality risk stratification leveraging data from MIMIC, our approach yields more compatible models while maintaining discriminative performance compared to existing model selection techniques, with an increase in CR of 0.019 (95% confidence interval: 0.005, 0.035). This work provides new tools to analyze and update risk stratification models used in clinical care. © 2023 E. Ötles., B.T. Denton & J. Wiens.

关键词： Risk assessment

GLaPE: Gold Label-agnostic Prompt Evaluation for Large Language Models

学校读者我要写书评

暂无评论

GLaPE: Gold Label-agnostic Prompt Evaluation for Large Langu...

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Xuanchang Zhang, Zhuosheng Zhao, Hai College of Zhiyuan Shanghai Jiao Tong University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761643

Despite the rapid progress of large language models (LLMs), their task performance remains sensitive to prompt design. Recent studies have explored leveraging the LLM itself as an optimizer to identify optimal prompts that maximize task accuracy. However, when evaluating prompts, such approaches heavily rely on elusive manually annotated gold labels to calculate task accuracy for each candidate prompt, which hinders its generality. To overcome the limitation, this work proposes GLaPE, a gold label-agnostic prompt evaluation method to alleviate dependence on gold labels. GLaPE is composed of two critical aspects: self-consistency evaluation of a single prompt and mutual-consistency refinement across multiple prompts. Experimental results on 8 widely-recognized reasoning tasks demonstrate that GLaPE can produce more effective prompts, achieving performance comparable to those derived from manually annotated gold labels. Analysis shows that GLaPE provides reliable evaluations aligned with accuracy, even in the absence of gold labels. Code is publicly available at https://***/thunderous77/GLaPE. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

Spiking representation learning for associative memories

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ravichandran, Naresh Lansner, Anders Herman, Pawel Computational Cognitive Brain Science Group Department of Computational Science and Technology School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Mathematics Stockholm University Stockholm Sweden Digital Futures KTH Royal Institute of Technology Stockholm Sweden

Networks of interconnected neurons communicating through spiking signals offer the bedrock of neural computations. Our brain’s spiking neural networks have the computational capacity to achieve complex pattern recognition and cognitive functions effortlessly. However, solving real-world problems with artificial spiking neural networks (SNNs) has proved to be difficult for a variety of reasons. Crucially, scaling SNNs to large networks and processing large-scale real-world datasets have been challenging, especially when compared to their non-spiking deep learning counterparts. The critical operation that is needed of SNNs is the ability to learn distributed representations from data and use these representations for perceptual, cognitive and memory operations. In this work, we introduce a novel SNN that performs unsupervised representation learning and associative memory operations leveraging Hebbian synaptic and activity-dependent structural plasticity coupled with neuron-units modelled as Poisson spike generators with sparse firing (~1 Hz mean and ~100 Hz maximum firing rate). Crucially, the architecture of our model derives from the neocortical columnar organization and combines feedforward projections for learning hidden representations and recurrent projections for forming associative memories. We evaluated the model on properties relevant for attractor-based associative memories such as pattern completion, perceptual rivalry, distortion resistance, and prototype extraction. © 2024, CC BY-SA.

关键词： Unsupervised learning

Convolutional Neural Network Approach for Sentiment Analysis of GoFood Services

学校读者我要写书评

暂无评论

Convolutional Neural Network Approach for Sentiment Analysis...

computer sciences, engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Zaenal Abidin Adzqi Aulia Ryan Randy Suryono Permata Akmal Junaidi Wamiliana Wamiliana Doctoral Program of Mathematics and Natural Sciences Universitas Lampung Bandarlampung Indonesia Faculty of Engineering and Computer Science Universitas Teknokrat Indonesia Bandarlampung Indonesia Department of Computer Science Universitas Lampung Bandarlampung Indonesia Department of Mathematics Universitas Lampung Bandarlampung Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

In the age of swift digital advancement, social media has emerged as a vital and readily available information source for users. Individuals utilize social media to communicate, articulate thoughts, and disseminate their viewpoints, both textually and visually. Twitter is a social media platform that people extensively utilize to disseminate both favorable and unfavorable information regarding GoFood services. This study intends to apply the Convolutional Neural Network (CNN) algorithm within the GoFood service on Twitter. This research also seeks to assess the accuracy of the CNN algorithm in relation to GoFood services. Employing deep learning techniques, particularly the convolutional neural network algorithm, to analyze Twitter user sentiment can enhance the efficiency, accuracy, and simplicity of classifying answers to GoFood services. The findings indicated that the Convolutional Neural Network technique was effectively employed to classify positive, negative, and neutral feelings. The optimal accuracy rate was attained through preprocessing with Stemming, yielding 51% accuracy for multiclass classification and 72% for binary class classification. The accuracy percentage for classification without stemming was 49% for multiclass classification and 70% for binary classification. This research holds possible consequences for Gojek firms and can serve as evaluative and assessment material for GoFood services, enabling them to implement necessary corrective measures.

关键词： Sentiment analysis Accuracy Social networking (online) Convolution Blogs Text categorization Feature extraction Classification algorithms Convolutional neural networks Testing