检索结果-内蒙古大学图书馆

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Sharma, Sushil Das, Arindam Sistu, Ganesh Halton, Mark Eising, Ciarán Department of Electronic & Computer Engineering University of Limerick Ireland SFI CRT Foundations in Data Science University of Limerick Ireland

ISBN: (纸本)9781837242672

Predicting ego vehicle trajectories remains a critical challenge, especially in urban and dense areas due to the unpredictable behaviours of other vehicles and pedestrians. Multimodal trajectory prediction enhances decision-making by considering multiple possible future trajectories based on diverse sources of environmental data. In this approach, we leverage ResNet-50 to extract image features from high-definition map data and use IMU sensor data to calculate speed, acceleration, and yaw rate. A temporal probabilistic network is employed to compute potential trajectories, selecting the most accurate and highly probable trajectory paths. This method integrates HD map data to improve the robustness and reliability of trajectory predictions for autonomous vehicles. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Autonomous Vehicles HDMap Images MultiModel Trajectory Prediction Probabilistic Network

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Autoencoder-Based Detection of False data Injection Attacks Against data Poisoning in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1287-1301页

作者： Takiddin, Abdulrahman Ismail, Muhammad Atat, Rachad Davis, Katherine R. Serpedin, Erchin Department of Electrical and Computer Engineering Texas A and M University College StationTX77843 United States Department of Computer Science Tennessee Tech University CookevilleTN38505 United States Department of Electrical and Computer Engineering Program Texas A and M University Qatar Doha23874 Qatar

Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Robust Sign Language Recognition Leveraging Bi-LSTM with CNN 2

Robust Sign Language Recognition Leveraging Bi-LSTM with CNN

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Jansirani, S. Savitha, N. Kiruba Priyadharshini, V. Sruthi Sree, S.G. Jansons Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore India Jansons Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

People who are partially or completely deaf are considered hearing impaired or silent. Communication is the primary obstacle they encounter. Sign Language Recognition (SLR) model provides a mechanism to improve accessibility and inclusion by facilitating smooth communication, which is used to address this issue. Traditional SLR systems frequently use alternative designs, such as CNNs alone or regular Recurrent Neural Networks (RNNs). However, that may not be able to handle long-term dependencies in video data or interpret sequence data. This paper uses a model which improves sequential pattern recognition and outperforms conventional RNNs in continuous recognition by combining CNN for visual feature extraction from ISL video frames with BiLSTM to capture temporal relationships. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing IT Job Candidates Through Interpretable Machine Learning Model

Assessing IT Job Candidates Through Interpretable Machine Le...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Andrew Sukardi Jayagatha Saputra Sebastian Hariman Alexander Agung Santoso Gunawan Karli Eka Setiawan Computer Science Department Data Science Program School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

The escalating demand for skilled IT professionals underscores the increasing significance of the recruitment process. Traditional methods often fall short in identifying individuals poised for success in the dynamic technology industry. This paper aims to address the challenges in recruiting proficient applicants by proposing an interpretable machine learning model for assessing IT job candidates. The study conducts experiments comparing various machine learning algorithms, including Logistic Regression, Random Forest, and Decision Tree, using data from the ‘IT job applicant’ public dataset. Evaluation methods such as the confusion matrix, accuracy, recall, and precision are employed to assess the model's performance. The findings reveal that the decision tree exhibits an accuracy exceeding 99.8%, establishing it as the top-performing model. The key contributing factor to this accuracy is identified as the 'computerSkills' feature. Additionally, within the decision tree, *** and Microsoft SQL Server are highlighted as influential factors positively impacting individual decision interpretation.

关键词： Industries Measurement Accuracy Systematics Computational modeling Decision making Servers Random forests Regression tree analysis Recruitment

来源：评论

学校读者我要写书评

暂无评论

Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes 38

Provably Optimal Memory Capacity for Modern Hopfield Models:...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jerry Yao-Chieh Wu, Dennis Liu, Han Center for Foundation Models and Generative AI United States Department of Computer Science United States Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States

We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories. We present a tight analysis by establishing a connection between the memory configuration of KHMs and spherical codes from information theory. Specifically, we treat the stored memory set as a specialized spherical code. This enables us to cast the memorization problem in KHMs into a point arrangement problem on a hypersphere. We show that the optimal capacity of KHMs occurs when the feature space allows memories to form an optimal spherical code. This unique perspective leads to: (i) An analysis of how KHMs achieve optimal memory capacity, and identify corresponding necessary conditions. Importantly, we establish an upper capacity bound that matches the well-known exponential lower bound in the literature. This provides the first tight and optimal asymptotic memory capacity for modern Hopfield models. (ii) A sub-linear time algorithm U-Hop+ to reach KHMs' optimal capacity. (iii) An analysis of the scaling behavior of the required feature dimension relative to the number of stored memories. These efforts improve both the retrieval capability of KHMs and the representation learning of corresponding transformers. Experimentally, we provide thorough numerical results to back up theoretical findings. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Defending Against IoT Threats: A Comprehensive Framework with Advanced Models and Real-Time Threat Intelligence for DDoS Detection 2

Defending Against IoT Threats: A Comprehensive Framework wit...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Jyothsna, B. Jyothsna, V. Mohan Babu University Department of Computer Science and Engineering Sree Sainath Nagar Tirupati India Mohan Babu University Department of Data Science Sree Sainath Nagar Tirupati India

ISBN: (纸本)9798350365269

The incorporation of Software Defined Networking (SDN) with IoT emerges as an auspicious strategy for enhancing security and access control mechanisms. Nevertheless, substantial threats from DDoS attacks persist in IoT networks, with the potential for execution over botnet or zombie attack, incorporating a machine learning-based detection scheme enables establishing it a framework have been introduced to analyze the performance of IoT devices. Profiles that inform decision-making processes are amassed by these frameworks, ultimately protecting the security of the IoT devices. This work presents a machine learning-based approach for detecting DDoS attacks in an SDN-WISE IoT controller. The incorporation of a machine learning-based detection scheme enables the establishment of a testbed environment for simulating the traffic of DDoS attacks. A logging mechanism within the SDN-WISE controller detects the traffic, generating network logs that are pre-processed and transformed into a dataset. The machine learning DDoS detection module entrenched in the SDN-WISE controller uses Naive Bayes (NB), Decision Tree (DT), and Support Vector Machine (SVM) algorithms to categorize SDN-IoT data. The proposed framework's performance is assessed across various traffic simulation scenarios, and the results from the machine learning DDoS detection module are analyzed. The proposed framework exhibits an accuracy rate of 98.2%, 97.1%, and 97.18% for NB, SVM, and DT, respectively. The attack detection module consumes up to 36% of memory and CPU usage, saving approximately 64% of memory while maintaining up to 71% CPU availability to analyze SD-IoT network traffic. The proposed framework achieves an accuracy of 98.2% which proves the efficiency of the work over state of the work models. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

E-Government Interoperability: Provincial-Level Architecture Model to Enable Fast Healthcare Interoperability Resources (FHIR) 9

E-Government Interoperability: Provincial-Level Architecture...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Wijayanti, Diana Urbaya, Satriawansyah Sitompul, Taufiq Adrian, Verry BINUS Graduate Program Bina Nusantara University Department of Information Systems Jakarta11480 Indonesia Program USAID Indonesia Jakarta12930 Indonesia University of Oslo Department of Informatics Oslo0316 Norway Binus Graduate Program - Doctor Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Jakarta Provincial Health Office Center of Data and Information Technology Jakarta10160 Indonesia

ISBN: (纸本)9798350390025

The process of using ICT to provide services to the public is known as the Indonesian e-Government system, or Sistem Pemerintahan Berbasis Elektronik (SPBE). The e-Government initiative in Jakarta Provincial Health Office involves enhancing collaboration among public health entities for efficient data exchange and streamlined processes, especially between the Provincial and District Health Offices, public hospitals, government clinics, and primary health care centers (Puskesmas). Achieving interoperability requires standardized protocols and a well-defined architectural model to integrate data seamlessly. This study presents a provincial-level architectural model focused on improving electronic health records interoperability, aiming to promote the adoption of the national Fast Healthcare Interoperability Resources (FHIR) health information exchange platform and enhance the integrity of health data in Jakarta. The study methodology involves conducting literature reviews, observations, and discussions with representatives from healthcare facilities to develop the e-Government architecture model and prototype of the infrastructure layer aiming to facilitate the interoperability of Electronic Health Records (EHRs) across 93 healthcare facilities, all of which are part of the SPBE users. © 2024 IEEE.

关键词： e-government

来源：评论

学校读者我要写书评

暂无评论

Adaptive Learning in Multiagent Systems Using Brain-computer Interfaces 2

Adaptive Learning in Multiagent Systems Using Brain-Computer...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Dhatterwal, Jagjit Singh Kaswan, Kuldeep Singh Thapliyal, Nitin Malik, Kiran Koneru Lakshmaiah Education Foundation Artificial Intelligence and Data Science AP Guntur India Galgotias University Department of Computer Science and Engineering UP Greater Noida India Graphic Era Hills University Department of Computer Science and Engineering Uttarakhand Dehradun India Matu Ram Institute of Engineering and Management Department of Computer Science and Engineering Haryana Rohtak India

ISBN: (纸本)9798350371055

Adaptive learning in multiagent systems has emerged as a promising approach to enhance agents' capabilities to adapt to dynamic environments and optimize their performance. In this research paper, we investigate the integration of brain-computer interfaces (BCIs) as a novel means to facilitate adaptive learning in multiagent systems. BCIs establish direct communication channels between the human brain and external devices, enabling real-time monitoring and interpretation of neural activity. By leveraging BCIs, agents can capture valuable cognitive signals from human operators and use this information to adapt their decision-making processes and behaviors. We present a theoretical framework that outlines the incorporation of BCIs into multiagent systems and the mechanisms for adaptive learning. Additionally, we propose a comprehensive methodology for evaluating the effectiveness of this approach. The results of our experiments demonstrate the potential of adaptive learningin multiagent systems using BCIs, paving the way for new applications in various domains, including human-machine col-laboration, assistive technologies, and interactive gaming systems. © 2024 IEEE.

关键词： Adaptive Learning Brain-computer Interfaces Human-Agent Interaction Human-Machine Collaboration Multiagent Systems

来源：评论

学校读者我要写书评

暂无评论

Enhanced Weld Defect Categorization via Nature-Inspired Optimization-Driven Neural Networks

引用

SN computer science 2024年第8期5卷 1035页

作者： Antony Vigil, M.S. Maheswari, K. Minu, M.S. Kulkarni, Gururaj L. Chandra Sekhar Reddy, L. Satishkumar, P. Haldar, Barun Department of Computer Science and Engineering SRM Institute of Science and Technology Tamilnadu Ramapuram Chennai India Department of Computer Science and Engineering CMR Technical Campus Telangana Kandlakoya Hyderabad India Computer Science and Engineering Vardhaman College of Engineering Hyderabad Shamshabad India Department of Computer Science and Engineering (Data Science) CMR College of Engineering & amp Technology Kandlakoya(V) Hyderabad Medchal India Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India Mechanical and Industrial Engineering Department College of Engineering Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia

In many different sectors, the safety and dependability of welded structures are crucially dependent on the accurate identification of weld defects. To address this, we present a novel method for categorizing weld defects named as Pelican Optimization-based convolutional Bi-Long Short-Term Memory Networks (POCBi-LSTM). With this integrated strategy, weld defect categorization is intended to be more accurate and effective. To train and assess a suggested classification algorithm, a collection of 220 samples with 5various types of weld faults is utilized. The study's technique comprised denoising with a Modified Median Filter (MMF) for noise reduction and binary histogram equalization (BHE) for image enhancement. The Scale Invariant Feature Transform (SIFT) was used to extract features. The outcomes demonstrate that the proposed strategy performs greater than conventional methods and delivers superior recognition accuracy, precision, recall, and F1 scores of 92.9%, 94.5%, 89.5%, and 92.8%, respectively. Experiment findings demonstrate the effectiveness and advantage of the recommended approach in classifying weld faults. Through the use of an integrated strategy, it is hoped to increase the dependability and effectiveness of weld defect categorization by handling local pattern recognition and long-term interdependence efficiently. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Modified median filter Pelican Optimization-Based convolutional Bi-Long Short Term Memory Networks (POCBi-LSTM) Weld defects Weld structures

来源：评论

学校读者我要写书评

暂无评论

Enhancing Tourism Industry Insights: LeveragingLDA and KMeans for Topic Extraction in Indonesian OTAs' Reviews

Enhancing Tourism Industry Insights: LeveragingLDA and KMean...

引用

International Conference of Information and Communication Technology (ICoICT)

作者： Laurentia Alyssa Castilani Natasha Hartanti Winata Nathania Christy Nugraha Alexander Agung Santoso Gunawan Karli Eka Setiawan Lili Ayu Wulandari Computer Science Department Data Science Program School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350363432

ISBN: (纸本)9798350363449

Indonesia's tourism sector, boosted by its captivating landscapes, has seen a rise in the popularity of Online Travel Agencies (OTAs) like Traveloka, ***, and Agoda. To effectively assist tourists, OTAs are anticipated to comprehend tourists' needs and interests, with insights gathered through scraping data from the Google Play Store. Through topic extraction from customers' reviews, this research aims to optimize the tourist experience and offer actionable insights for the tourism industry's marketing strategies. Furthermore, it endeavors to eliminate the reliance on brute force approaches in determining the candidate number of topics. To achieve the research goal, this research employs topic modeling, specifically Latent Dirichlet Allocation (LDA) enhanced through the K- means elbow method. The evaluation of the optimal topic number utilizes a coherence score, while human judgement serves as a quantitative metric for overall performance, with a remarkable validity rate across three platforms: Agoda (91%), *** (88%), and Traveloka (94%). This highlights the approach's effectiveness in accurately identifying and categorizing topics. In conclusion, the model accurately discerned essential topics, revealing that the majority of the reviews on these OTAs focus on the transaction and refund systems on each platform. Furthermore, this model offers promising recommendations to enhance the understanding and response to customers' reviews, facilitating faster and more effective responses. These insights are invaluable for continuous development and improvement strategies within the dynamic changes in the tourism industry across these influential platforms.

关键词： Measurement Adaptation models Analytical models Technological innovation Sentiment analysis Reviews Tourism industry Market research Real-time systems Resource management

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：