检索结果-内蒙古大学图书馆

Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Annesi, Brandon L. Malatesta, Enrico M. Zamponi, Francesco Department of Computing Sciences Bocconi University Milano20136 Italy Institute for Data Science and Analytics Bocconi University Milano20136 Italy Dipartimento di Fisica Sapienza Università di Roma RomeI-00185 Italy

We analyze the problem of storing random pattern-label associations using two classes of continuous non-convex weights models, namely the perceptron with negative margin and an infinite-width two-layer neural network with non-overlapping receptive fields and generic activation function. Using a full-RSB ansatz we compute the exact value of the SAT/UNSAT transition. Furthermore, in the case of the negative perceptron we show that the overlap distribution of typical states displays an overlap gap (a disconnected support) in certain regions of the phase diagram defined by the value of the margin and the density of patterns to be stored. This implies that some recent theorems that ensure convergence of Approximate Message Passing (AMP) based algorithms to capacity are not applicable. Finally, we show that Gradient Descent is not able to reach the maximal capacity, irrespectively of the presence of an overlap gap for typical states. This finding, similarly to what occurs in binary weight models, suggests that gradient-based algorithms are biased towards highly atypical states, whose inaccessibility determines the algorithmic threshold. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

Park4U: A Blockchain-Based Parking Reservation and Management for Smart Cities

学校读者我要写书评

暂无评论

Park4U: A Blockchain-Based Parking Reservation and Managemen...

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Amjad Aldweesh Mohammad Alauthman Ahmad Al-Qerem Mohammad Al Khaldy Saad Alateef Someah Alangari College of computing and IT Shaqra University Shaqra Saudi Arabia Faculty of Information Technology University of Petra Amman Jordan Faculty of Information Technology Zarqa University Zarqa Jordan Department of Business Intelligence and Data Analytics University of Petra Amman Jordan School of Computing Science Newcastle University Newcastle UK College of Computing and IT Shaqra University Aldawadmi Saudi Arabia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Urbanization and increasing vehicles in smart cities have created challenges in managing parking efficiently. Traditional systems face issues like lack of transparency, security vulnerabilities, and poor stakeholder coordination. This paper introduces Park4U, a blockchain-based parking reservation and management system for smart cities. It takes advantage of blockchain's decentralized, secure, and transparent nature to improve efficiency, accessibility, and reliability of parking services. Park4U integrates IoT sensors, smart contracts, and a mobile application facilitating seamless reservation, payment, and management. The system aims to enhance resource utilization, reduce congestion, and provide a secure and transparent platform for stakeholders: drivers, operators, and authorities. An evaluation of performance and comparison with traditional systems are presented, showcasing blockchain-based approach's benefits. It also explores potential challenges and future research directions.

关键词： Smart cities Smart contracts Blockchains Mobile applications Stakeholders Security Reliability Intelligent sensors Faces Vehicles

Advanced Techniques in Network Traffic Analysis: Utilizing Wireshark For In-Depth Live data Packet Inspection And Information Capture

学校读者我要写书评

暂无评论

Advanced Techniques in Network Traffic Analysis: Utilizing W...

Communication, Security and Artificial Intelligence (ICCSAI), International Conference on

作者： Santhosh Chowhan Abhilash Kumar Saxena Department of Data Analytics and Mathematical Sciences Jain (deemed to be) University Bangalore Karnataka India College Of Computing Science and Information Technology Teerthanker Mahaveer University Moradabad Uttar Pradesh India

The escalating frequency and sophistication of cyber-attacks have placed a spotlight on the importance of Quality of Service (QoS) and robust network security mechanisms. Effective traffic analysis and distribution are critical for maintaining the integrity of network applications and safeguarding data. Our research focuses on the development and assessment of a network intrusion detection system (NIDS) that utilizes the advanced packet analysis capabilities of Wireshark, a renowned network protocol analyzer. The system is designed to enhance network security by enabling more efficient and accurate data collection through network monitoring tools. This serves as the foundation for detecting and thwarting a wide range of malicious activities, including malware and spyware incursions, within network traffic. The innovation of our approach lies in its integration of packet sniffing technology with AI-driven analysis techniques. By applying Machine Learning algorithms to the data captured by Wireshark, our NIDS is capable of identifying patterns indicative of intrusive behavior, which might elude traditional detection methods. We present a comprehensive evaluation of our system, showcasing its efficacy in real-time intrusion detection and its potential for integration into existing network infrastructures. This study contributes to the ongoing discourse in cybersecurity, offering a sophisticated tool in the battle against digital threats and reinforcing the role of intelligent systems in protecting network environments

关键词：

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimizing Radiotherapy Treatment Plans in Oropharyngeal Cancer

学校读者我要写书评

暂无评论

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimi...

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Bhuvanashree Murugadoss J Amudha Vijayan Sugumaran Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Bengaluru Karnataka India Center for Data Science and Big Data Analytics Oakland University Rochester MI USA Department of Decision and Information Sciences Oakland University Rochester MI USA

Automated radiotherapy treatment planning aims to improve treatment accuracy and efficiency. However, the prevalent Knowledge-Based Planning (KBP) method faces issues like lengthy manual problem formulation and challenges in accurately modeling human anatomy and processing high-dimensional data. This work focuses on treatment plan optimization and considers deep learning as a potential solution. Deep learning algorithms, by virtue of their ability to learn from large quantities of data and model complex relationships, can automate the formulation of the optimization problem in KBP, saving significant time and effort. However, despite these compelling advantages, it should be noted that the current convolution-based encoder-decoder models used for radiotherapy treatment plan optimization have a limited capability in capturing long-range dependencies between distant voxels. This work aims to introduce ‘DE-ConvGraph 3D UNet’, a novel deep learning model, to address these limitations and optimize radiotherapy treatment plans for oropharyngeal cancer. The proposed ‘DE-ConvGraph 3D UNet’ model includes a Graph Convolutional Network (GCN) component to capture long-range dependencies between distant voxels. Furthermore, the dual-encoder structure of the model combines the strengths of GCN and 3D Convolutional U-Net, enabling global relationships and local pattern capturing in a 3D patient volume. Experiments were conducted using the benchmark dataset - OpenKBP-Opt. The proposed model shows improvements in performance in comparison to state-of-the-art U-Net variants in terms of mean squared voxel-wise error, dose volume histogram points and clinical criteria satisfaction.

关键词：

End-To-End Emotion Recognition using Peripheral Physiological Signals 35

学校读者我要写书评

暂无评论

End-To-End Emotion Recognition using Peripheral Physiologica...

35th British HCI Conference Towards a Human-Centred Digital Society, HCI 2022

作者： Pidgeon, M. Kanwal, N. Murray, N. Asghar, M. Software Research Institute Technological University of the Shannon Athlone Ireland School of Computing and Mathematics Keele University Newcastle United Kingdom Department of Electronics and Informatics Technological University of the Shannon Athlone Ireland Insight Centre for Data Analytics National University of Ireland Galway Galway Ireland

The study of emotion recognition from physiological signals has seen a huge growth in recent decades. Studies initially used traditional machine learning classification to estimate either discrete emotions or combinations of arousal and valence. However, different feature engineering techniques such as Ensemble Empirical Mode Decomposition (EEMD) Analysis for electroencephalography (EEG) signals and statistical calculations for peripheral signals are used prior to machine learning. Also, several sensors needed to be worn by participants to predict the emotions. This study aims to investigate whether arousal and valence can be predicted from a single peripheral signal using deep learning. The Galvanic Skin Response(GSR), Respiration (RSP), Blood Volume Pulse (BVP) and Temperature (Temp) signals from the DEAP dataset are used. The signals are downsampled to approximately three hertz (Hz) and input to a convolutional network (CNN) to predict arousal and valence. GSR, RSP and BVP had similar F1 and accuracy results. BVP had an F1 result of 0.673 and 0.632 and accuracies of 63.5% and 61.1% respectively for arousal and valence. RSP's F1 results were 0.677 and 0.669 and accuracies were 61.3% and 64.2% for arousal and valence respectively. GSR had F1 results of 0.699 and 0.663 and accuracies of 62.5% and 60.2% respectively for arousal and valence. Using raw signals and examining the peripheral signals individually, we were able to identify which sensors showed the best potential for further research to bring emotion classification into a real-world scenario using non-invasive sensors. © 2022 *** Rights Reserved.

关键词： Emotion Recognition

Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yan, Sen Fang, Hongyuan Li, Ji Ward, Tomas O’Connor, Noel Liu, Mingming The School of Electronic Engineering SFI Insight Centre for Data Analytics Dublin City University Dublin 9 Ireland The School of Computing SFI Insight Centre for Data Analytics Dublin City University Dublin 9 Ireland The Department of Mechanical Engineering University of Birmingham BirminghamB15 2TT United Kingdom

Battery Electric Vehicles (BEVs) are increasingly significant in modern cities due to their potential to reduce air pollution. Precise and real-time estimation of energy consumption for them is imperative for effective itinerary planning and optimizing vehicle systems, which can reduce driving range anxiety and decrease energy costs. As public awareness of data privacy increases, adopting approaches that safeguard data privacy in the context of BEV energy consumption modeling is crucial. Federated Learning (FL) is a promising solution mitigating the risk of exposing sensitive information to third parties by allowing local data to remain on devices and only sharing model updates with a central server. Our work investigates the potential of using FL methods, such as FedAvg, and FedPer, to improve BEV energy consumption prediction while maintaining user privacy. We conducted experiments using data from 10 BEVs under simulated real-world driving conditions. Our results demonstrate that the FedAvg-LSTM model achieved a reduction of up to 67.84% in the MAE value of the prediction results. Furthermore, we explored various real-world scenarios and discussed how FL methods can be employed in those cases. Our findings show that FL methods can effectively improve the performance of BEV energy consumption prediction while maintaining user privacy. © 2023, CC BY.

关键词： Learning systems

Acquiring Better Load Estimates by Combining Anomaly and Change Point Detection in Power Grid Time Series Measurements

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bouman, Roel Schmeitz, Linda Buise, Luco Heres, Jacco Shapovalova, Yuliya Heskes, Tom Institute for Computing and Information Sciences department of Data Science Radboud University Toernooiveld 212 Nijmegen6525EC Netherlands Advanced Analytics Alliander N.V. Utrechtseweg 68 Arnhem6812AH Netherlands

In this paper we present novel methodology for automatic anomaly and switch event filtering to improve load estimation in power grid systems. By leveraging unsupervised methods with supervised optimization, our approach prioritizes interpretability while ensuring robust and generalizable performance on unseen data. Through experimentation, a combination of binary segmentation for change point detection and statistical process control for anomaly detection emerges as the most effective strategy, specifically when ensembled in a novel sequential manner. Results indicate the clear wasted potential when filtering is not applied. The automatic load estimation is also fairly accurate, with approximately 90% of estimates falling within a 10% error margin, with only a single significant failure in both the minimum and maximum load estimates across 60 measurements in the test set. Our methodology’s interpretability makes it particularly suitable for critical infrastructure planning, thereby enhancing decision-making processes. © 2024, CC BY.

关键词： Change detection

Sparse Index Tracking via Topological Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Goel, Anubha Pasricha, Puneet Kanniainen, Juho Computing Science/Financial Computing and Data Analytics Group Tampere University Finland Ecole Polytechnique Fédérale de Lausanne LausanneCH 1015 Switzerland Department of Mathematics Indian Institute of Technology Punjab Ropar140001 India

In this research, we introduce a novel methodology for the index tracking problem with sparse portfolios by leveraging topological data analysis (TDA). Utilizing persistence homology to measure the riskiness of assets, we introduce a topological method for data-driven learning of the parameters for regularization terms. Specifically, the Vietoris-Rips filtration method is utilized to capture the intricate topological features of asset movements, providing a robust framework for portfolio tracking. Our approach has the advantage of accommodating both 1 and 2 penalty terms without the requirement for expensive estimation procedures. We empirically validate the performance of our methodology against state-of-the-art sparse index tracking techniques, such as Elastic-Net and SLOPE, using a dataset that covers 23 years of S&P 500 index and its constituent data. Our out-of-sample results show that this computationally efficient technique surpasses conventional methods across risk metrics, risk-adjusted performance, and trading expenses in varied market conditions. Furthermore, in turbulent markets, it not only maintains but also enhances tracking performance. © 2023, CC BY.

关键词： Commerce

Evolutionary Transfer Neural Architecture Search Across Spaces via Representation Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2025年

作者： Hou, Boyu Feng, Liang Chen, Xuefeng Tang, Jing Tan, Kay Chen Liao, Xiaofeng Chongqing University College of Computer Science China Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing Chongqing400044 China The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong999077 Hong Kong Data Science and Analytics Thrust Guangzhou511453 China

Neural Architecture Search (NAS) has emerged as a crucial method for automating the design of deep learning models. Despite its potential, NAS frequently requires substantial computational and hardware resources. To mitigate these challenges, transferable NAS (TNAS) has been introduced, leveraging prior NAS results to enhance performance on new tasks. However, existing methods largely focus on knowledge transfer within identical neural search spaces, overlooking the potential for cross-domain transferability. Motivated by this gap, we explore evolutionary TNAS across heterogeneous search spaces by learning common neural representations. In particular, we introduce a novel approach that encodes both operational and topological information of neural architectures into a unified sequence using a simple tokenizer. This sequence is then processed by a variational auto-encoder, with a Transformer-based encoder to capture rich neural representations and a decoder that reconstructs the original sequence. By utilizing these latent representations, we further establish an inter-domain mapping that acts as a bridge, enabling effective explicit solution transfer among diverse search spaces to enhance the evolutionary NAS process. To harness this capability, we develop an evolutionary sequential transfer optimization approach that transfers knowledge during population initialization, providing both flexibility and adaptability. To the best of our knowledge, this work serves as the first attempt in the literature exploring evolutionary TNAS across diverse spaces. Moreover, we demonstrate the utility of our method through comprehensive empirical studies using different architecture spaces, including NAS-Bench-101, NAS-Bench-201, and the DARTS search space. Our results show that the proposed method significantly enhances the adaptability and performance of NAS across varied domains. © 1997-2012 IEEE.

关键词： Transfer learning