检索结果-内蒙古大学图书馆

ICGNN: Graph Neural Network Enabled Scalable Beamforming for MISO Interference Channels

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Changpeng Lu, Yang Ai, Bo Dobre, Octavia A. Ding, Zhiguo Niyato, Dusit School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Faculty of Engineering and Applied Science Memorial University St. John’sNLA1C 5S7 Canada Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi127788 United Arab Emirates College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

This paper investigates the graph neural network (GNN)-enabled beamforming design for interference channels. We propose a model termed interference channel GNN (ICGNN) to solve a quality-of-service constrained energy efficiency maximization problem. The ICGNN is two-stage, where the direction and power parts of beamforming vectors are learned separately but trained jointly via unsupervised learning. By formulating the dimensionality of features independent of the transceiver pairs, the ICGNN is scalable with the number of transceiver pairs. Besides, to improve the performance of the ICGNN, the hybrid maximum ratio transmission and zero-forcing scheme reduces the output ports, the feature enhancement module unifies the two types of links into one type, the subgraph representation enhances the message passing efficiency, and the multi-head attention and residual connection facilitate the feature extracting. Furthermore, we present the over-the-air distributed implementation of the ICGNN. Ablation studies validate the effectiveness of key components in the ICGNN. Numerical results also demonstrate the capability of ICGNN in achieving near-optimal performance with an average inference time less than 0.1 ms. The scalability of ICGNN for unseen problem sizes is evaluated and enhanced by transfer learning with limited fine-tuning cost. The results of the centralized and distributed implementations of ICGNN are illustrated. © 2025, CC BY.

关键词： Graph neural networks

Bayesian optimization of one-dimensional convolutional neural networks (1D CNN) for early diagnosis of Autistic Spectrum Disorder

学校读者我要写书评

暂无评论

Journal of Computational Mathematics and Data science 2024年 13卷

作者： Omotehinwa, Temidayo Oluwatosin Lawrence, Morolake Oladayo Oyewola, David Opeoluwa Dada, Emmanuel Gbenga Department of Mathematics and Computer Science Federal University of Health Sciences Otukpo P.M.B. 145 Nigeria Department of Computer Science Faculty of Computing & Applied Sciences Baze University Abuja Nigeria Department of Mathematics and Statistics Federal University Kashere Gombe P.M.B. 0182 Nigeria Department of Mathematical Sciences University of Maiduguri Maiduguri P.M.B. 1069 Nigeria

Autistic Spectrum Disorder (ASD) is a challenging neurological development disorder, which involves poor social interaction, communication, and repetitive behaviours. If autism is identified early enough it can be treated with better outcomes but present diagnostic tests are dependent on subjective opinion, consume a lot of time, and are vague. This study is aimed at optimizing one-dimensional convolutional neural networks (1D CNN) to improve the precision and speed of early ASD diagnosis. Four ASD datasets representing different age groups — toddlers, children, adolescents, and adults were modelled using one-dimensional convolutional neural networks (1D CNN). These datasets are accessible to the public on the UCI Machine Learning Repository and Kaggle, they consist of behavioural features relevant to ASD diagnosis. Each dataset underwent feature selection, categorical encoding, and missing value handling. Then, baseline 1D CNN with predefined hyperparameters was modelled on each of the datasets. Subsequently, the baseline models were optimized using the Tree-structured Parzen Estimator (TPE). An interactive web-based ASD diagnostic tool was developed, where user inputs are processed through age-specific pre-trained optimized models to determine ASD probability. The optimized 1D CNN models significantly outperformed the baseline models across all age groups and achieved scores of 100% in accuracy, precision, recall, F1-score, MCC, and AUC ROC. This implies that the optimized models can reliably identify people in various age groups who have and do not have ASD. The development of an interactive web-based diagnostic tool extends the practical utility of the models, making them accessible for clinical and at-home use. © 2024 The Author(s)

关键词： 1D CNN Autistic Spectrum Disorder Machine learning One-dimension convolution neural networks Tree-structured parzen estimator

Forex exchange using big data analytics 1

学校读者我要写书评

暂无评论

Forex exchange using big data analytics

1st International Conference on Advances in Computational science and Engineering, ICACSE 2020

作者： Sadhasivam, Jayakumar Arun, M. Deepa, R. Muthukumaran, V. Lokesh Kumar, R. Prasanna Kumar, R.B. Vellore Institute of Technology Vellore India School of Computing Kalasalingam Academy of Research and Education Tamilnadu 626128 India Telangana Hyderabad India Department of Mathematics School of Applied Science REVA University Bengaluru64 India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Vellore632 014 India Department of Computer Science REVA University Bengaluru64 India

Analysis and Prediction of forex has gained immense value in today's economy. The stock price prediction is a difficult process owing to the irregularities in stock prices. Every trader wants to know if the pattern has been repeated in past to know what the possible output of the current situation will be. The primary objective is to propose a methodology that will use a historical dataset and provide a more accurate prediction on stock price. In this paper, we will be using machine learning pattern recognition algorithm on forex tick dataset. The learned model then will produce pattern from the given dataset and on the pattern of increasing or decreasing, the buyer will initiate a buy or sell the stock respectively. We will use python coding to execute the algorithm in jupyter notebook. Matplot library will help us to perform graphing in the process and Numpy will be helpful in doing statistical analysis of data. © Published under licence by IOP Publishing Ltd.

关键词： Python

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks

学校读者我要写书评

暂无评论

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicu...

IEEE Conference on Wireless Communications and Networking

作者： Sarah Al–Shareeda Fusun Ozguner Keith Redmill Trung Q. Duong Berk Canberk Electrical and Computer Engineering Department Center for Automotive Research (CAR) The Ohio State University USA BTS Group Turkey Department of AI and Data Engineering Istanbul Technical University Turkey School of Electronics Electrical Engineering and Computer Science Queen's University Belfast UK Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John's NL Canada School of Computing Engineering and The Built Environment Edinburgh Napier University UK

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50 % due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1].

关键词： 6G mobile communication Performance evaluation Identity-based encryption Authentication Deep reinforcement learning Reproducibility of results Resource management Cryptography Optimization Software development management

Wind speed prediction and insight for generalized predictive modeling framework: a comparative study for different artificial intelligence models

学校读者我要写书评

暂无评论

Neural computing and Applications 2024年第23期36卷 14119-14150页

作者： Bhagat, Suraj Kumar Tiyasha, Tiyasha Shather, A.H. Jamei, Mehdi Kumar, Adarsh Al-Khafaji, Zainab Goliatt, Leonardo Shafik, Shafik S. Alawi, Omer A. Yaseen, Zaher Mundher Faculty of Civil Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Department of Computer Engineering Technology Al Kitab University Altun Kopru Kirkuk00964 Iraq Faculty of Civil Engineering and Architecture Shahid Chamran University of Ahvaz Ahvaz Iran Canadian Centre for Climate Change and Adaptation University of Prince Edward Island St PetersPE Canada Building and Construction Techniques Engineering Department College of Engineering and Engineering Techniques Al-Mustaqbal University Hillah Babylon51001 Iraq Department of Computational and Applied Mechanics Federal University of Juiz de Fora Juiz de Fora Brazil Experimental Nuclear Radiation Research Group Scientific Research Center Al-Ayen University Thi-Qar64001 Iraq Johor Bahru Skudai81310 Malaysia Civil and Environmental Engineering Department King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Department of Civil Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Dehradun India Dept of Environmental Science Gitam School of Science GITAM University Visakhapatnam India

Wind speed (WS) has played a vital role in local urban and sub-urban weather, agriculture, and ecosystem. Several meteorological parameters are influencing WS such as relative humidity (at 2 m, %), surface pressure (kPa), maximum temperature (at 2 m, °C), minimum temperature (at 2 m, °C), average temperature (at 2 m, °C), and all sky insolation incident on a horizontal surface (kW-h/m2/day). The current research was conducted to predict WS at different locations at Vietnam using the feasibility of computer aid models (i.e., multivariate adaptive regression splines (MARS), extreme gradient boosting (XGBoost) and random forest generator (Ranger)). Pearson correlation (PC) was investigated to select the high significant predictors to predict the WS at 10 m high. All inputs (maximum number, 6) are chosen by the PC approach for PhuongNinh, DaNang, and HaNoi;and for minimum number of inputs i.e four, are selected for PhuongHung, CanTho, and SaPa city;that exhibit the relationship with WS, citywise. The sequence selection of input parameters differed in each station as per the PC analysis. Based on the statistical evaluation and graphical presentation, MARS model attained the best prediction results, followed by XGBoost and Ranger. MARS predictive model remains at the top performance among others based on 95% confidence interval. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Forecasting

What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environments

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gopinathan, Muraleekrishna Abu-Khalaf, Jumana Suter, David Paheding, Sidike Rawashdeh, Nathir A. School of Science Edith Cowan University JoondalupWA6027 Australia Department of Computer Science Fairfield University 1073 N Benson Rd FairfieldCT06824 United States Department of Applied Computing Michigan Technological University 1400 Townsend Drive HoughtonMI49931-1295 United States

Humans use their knowledge of common house layouts obtained from previous experiences to predict nearby rooms while navigating in new environments. This greatly helps them navigate previously unseen environments and locate their target room. To provide layout prior knowledge to navigational agents based on common human living spaces, we propose WIN (What Is Near), a commonsense learning model for Vision Language Navigation (VLN) tasks. VLN requires an agent to traverse indoor environments based on descriptive navigational instructions. Unlike existing layout learning works, WIN predicts the local neighborhood map based on prior knowledge of living spaces and current observation, operating on an imagined global map of the entire environment. The model infers neighborhood regions based on visual cues of current observations, navigational history, and layout common sense. We show that local-global planning based on locality knowledge and predicting the indoor layout allows the agent to efficiently select the appropriate action. Specifically, we devised a cross-modal transformer that utilizes this locality prior for decision-making in addition to visual inputs and instructions. Experimental results show that locality learning using WIN provides better generalizability compared to classical VLN agents in unseen environments. Our model performs favorably on standard VLN metrics, with Success Rate 68% and Success weighted by Path Length 63% in unseen environments. Embodied Agents, Mapping, Vision-Language Navigation © 2023, CC BY-SA.

关键词： Navigation

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code

学校读者我要写书评

暂无评论

arXiv 2024年

作者： McCully, Gary A. Hastings, John D. Xu, Shengjie Fortier, Adam The Beacom College of Computer and Cyber Sciences Dakota State University MadisonSD United States Department of Cyber Intelligence and Information Operations College of Applied Science & Technology University of Arizona TucsonAZ United States College of Computing Georgia Institute of Technology AtlantaGA United States

Ransomware and other forms of malware cause significant financial and operational damage to organizations by exploiting long-standing and often difficult-to-detect software vulnerabilities. To detect vulnerabilities such as buffer overflows in compiled code, this research investigates the application of unidirectional transformer-based embeddings, specifically GPT-2. Using a dataset of LLVM functions, we trained a GPT-2 model to generate embeddings, which were subsequently used to build LSTM neural networks to differentiate between vulnerable and non-vulnerable code. Our study reveals that embeddings from the GPT-2 model significantly outperform those from bidirectional models of BERT and RoBERTa, achieving an accuracy of 92.5% and an F1-score of 89.7%. LSTM neural networks were developed with both frozen and unfrozen embedding model layers. The model with the highest performance was achieved when the embedding layers were unfrozen. Further, the research finds that, in exploring the impact of different optimizers within this domain, the SGD optimizer demonstrates superior performance over Adam. Overall, these findings reveal important insights into the potential of unidirectional transformer-based approaches in enhancing cybersecurity defenses. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

Bi-Directional Transformers vs. word2vec: Discovering Vulnerabilities in Lifted Compiled Code

学校读者我要写书评

暂无评论

arXiv 2024年

Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM IR) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 48k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformers (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. Word2vec Skip-Gram models achieved 92% validation accuracy in detecting vulnerabilities, outperforming word2vec Continuous Bag of Words (CBOW), BERT, and RoBERTa. This suggests that complex contextual embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 48K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Generating and Analyzing Program Call Graphs using Ontology

学校读者我要写书评

暂无评论

Generating and Analyzing Program Call Graphs using Ontology

IEEE/ACM International Workshop on Programming and Performance Visualization Tools (ProTools)

作者： Ethan Dorta Yonghong Yan Chunhua Liao Department of Computer Science University of North Carolina at Charlotte Charlotte North Carolina USA Lawrence Livermore National Laboratory Center for Applied Scientific Computing Livermore California USA

ISBN: (纸本)9781665475655

Call graph or caller-callee relationships have been used for various kinds of static program analysis, performance analysis and profiling, and for program safety or security analysis such as detecting anomalies of program execution or code injection attacks. However, different tools generate call graphs in different formats, which prevents efficient reuse of call graph results. In this paper, we present an approach of using ontology and resource description framework (RDF) to create knowledge graphs for specifying call graphs to facilitate the construction of full-fledged and complex call graphs of computer programs, realizing more interoperable and scalable program analyses than conventional approaches. We create a formal ontology-based specification of call graph information to capture concepts and properties of both static and dynamic call graphs so different tools can collaboratively contribute to more comprehensive analysis results. Our experiments show that ontology enables merging of call graphs generated from different tools and flexible queries using a standard query interface.

关键词： Visualization Natural languages Merging Ontologies Resource description framework Performance analysis Safety