检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ravaut, Mathieu Zhang, Hao Xu, Lu Sun, Aixin Liu, Yong School of Computer Science and Engineering Nanyang Technological University Singapore Singapore University of Technology and Design Singapore

Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation. Prior work often utilizes external knowledge graphs for items’ semantic information, a language model for dialogue generation, and a recommendation module for ranking relevant items. This combination of multiple components suffers from a cumbersome training process, and leads to semantic misalignment issues between dialogue generation and item recommendation. In this paper, we represent items in natural language and formulate CRS as a natural language processing task. Accordingly, we leverage the power of pre-trained language models to encode items, understand user intent via conversation, perform item recommendation through semantic matching, and generate dialogues. As a unified model, our PECRS (Parameter-Efficient CRS), can be optimized in a single stage, without relying on non-textual metadata such as a knowledge graph. Experiments on two benchmark CRS datasets, ReDial and INSPIRED, demonstrate the effectiveness of PECRS on recommendation and conversation. Our code is available at: https://***/Ravoxsg/efficient_unified_crs. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Establishing a Secure Mobile Online Banking System using AES

Establishing a Secure Mobile Online Banking System using AES

引用

Delhi Section Conference (DELCON), IEEE

作者： R. C. Karpagalakshmi J. Lenin Robin Rohit V. K. Saravanan Rajesh Sharma R. Sumit Kumar Banshal Department of Computer Science and Information Technology Alliance College of Engineering and Design Alliance University Bangalore India School of Computer Science & Engineering and Information Science Presidency University Bangalore India Department of Information Science Engineering New Horizon College of Engineering Bangalore India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Using a mobile phone or other portable device to conduct financial transactions online is known as “mobile banking.” Activities such as verifying one's account balance, transferring funds to another account, making bill payments, and finding a local automated teller machine (ATM) are included under this classification. Due to the significant expenses associated with implementing this technology, Authentication of users, data privacy, non-repudiation, data integrity, and obtainability of services are all areas where people have voiced concerns. The analysis described in this paper introduces a more advantageous and convenient framework for addressing these issues. The proposed approach effectively accomplishes its intended goals via the use of a widely adopted technique known as salting, which involves the application of the Secure Hash Algorithm (SHA512) to obfuscate sensitive information such as user IDs and passwords. The encoding and decoding procedures used the Advanced Encoding Standard (AES) technique while implementing one-time passwords (OTPs) was implemented to enhance user authentication. The design approach used PHP, JScript, CSS, and a MySQL database. The password recovery technique was used to assess the model's credibility and reliability and acquire the outcomes. This program enhances the process of recovering passwords across various scenarios. It intercepts network traffic using dictionary attacks, brute-force assaults, and cryptanalytics attacks to decrypt encrypted passwords. Additionally, it uncovers password bins, retrieves secreted passwords and analyses routing protocols. The gathered findings support the idea's feasibility since the encrypted and hashed data demonstrates resistance to unauthorized access.

关键词： Online banking Automated teller machine Authentication Passwords Telecommunication traffic Mobile handsets Encoding Routing protocols Internet Standards

来源：评论

学校读者我要写书评

暂无评论

Advancing Alzheimer's Diagnosis: Performance Analysis of Deep Learning Ensembles in Medical Imaging

Advancing Alzheimer's Diagnosis: Performance Analysis of Dee...

引用

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Sonali Deshpande Nilima Kulkarni Computer Science & Engineering Department MIT SoC MIT Art Design and Technology University Pune India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

Neuroimaging and deep learning have become the focus of much research for diagnosing Alzheimer's disease (AD) in recent years. Nevertheless, the limited availability of neuroimaging training data has resulted in significant overfitting issues for several deep learning models. However, the dataset was very imbalanced. To address this issue, we employed several augmentation techniques such as flipping, rotating, and zooming to balance the dataset. The ADNI dataset consisted of four classes: mild demented, moderate demented, very mild demented, and non-demented. In this work, we have proposed an ensemble of EfficientNetB2, DenseNet121, VGG16, and Xception for the diagnosis of Alzheimer at early stage. Experiment results shows that EfficientNetB2 ensemble with Xception and VGG16 performed extremely well with 99.1% and 99.4% respectively.

关键词： Deep learning Neuroimaging Industries Accuracy Training data Medical services Performance analysis Ensemble learning Alzheimer's disease Overfitting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Digital Twin for Human Activity Recognition 29

Deep Learning-based Digital Twin for Human Activity Recognit...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Su, Jian Liao, Zhenlong Mao, Qiankun Sheng, Zhengguo Liu, Alex X. Nanjing University of Information Science and Technology The School of Software Nanjing China Zhejiang Wanli University The Hwamei College of Life and Health Sciences Ningbo China Nanjing University of Information Science and Technology The School of Computer Nanjing China University of Sussex The Department of Engineering and Design Brighton United Kingdom Michigan State University The Department of Computer Science and Engineering East Lansing United States

ISBN: (纸本)9798350330717

With the rapid development of the Internet of Things (IoT) related technologies, the application of digital twins (DT) in industry and healthcare becomes possible. Human activity recognition (HAR) is emerging as a hot research area with great potential in healthcare. Activity recognition systems combined with DT will make it easier to monitor human health conditions to improve the quality of life and happiness with individualized healthcare. In this paper, we design an effective HAR system, called HAR-Net, which uses WiFi time series data collected by sensors to train a deep learning network. Deep learning's great learning ability is utilized to extract features of various human activities for activity recognition. We built the DT system with Unity, which is combined with the HAR system. In the DT system, real-world physical activities are mapped onto human models. The results of activity prediction can be evaluated in real-time in DT, and warnings can be issued quickly when dangerous activities occur. To make our human activity recognition system more adaptive, we propose a one-shot recognition method based on meta-learning. Specifically, we design a Bi-path basic network that extracts features in the time-domain and frequency-domain, and a meta-learning framework with a classification module and a WiFi metric module. Using datasets from different environments, we conducted various experiments on HAR-Net, and the results proved that our presented method was superior to the baseline network. © 2023 IEEE.

关键词： Digital Twin Healthcare Human Activity Recognition Meta-Learning WiFi

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-user Offloading of Personalized Diffusion Models: A DRL-Convex Hybrid Solution

引用

IEEE Transactions on Mobile Computing 2025年

作者： Yang, Wanting Xiong, Zehui Guo, Song Mao, Shiwen Kim, Dong In Debbah, Merouane Singapore University of Technology and Design Pillar of Engineering Systems and Design Singapore Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Hong Kong Auburn University Department of Electrical and Computer Engineering Auburn36830 United States Sungkyunkwan University Department of Electrical and Computer Engineering Suwon16419 Korea Republic of Khalifa University KU 6G Research Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates University Paris-Saclay CentraleSupelec Gif-sur-Yvette91192 France

Generative diffusion models like Stable Diffusion are at the forefront of the thriving field of generative models today, celebrated for their robust training methodologies and high-quality photorealistic generation capabilities. These models excel in producing rich content, establishing them as essential tools in the industry. Building on this foundation, the field has seen the rise of personalized content synthesis as a particularly exciting application. However, the large model sizes and iterative nature of inference make it difficult to deploy personalized diffusion models broadly on local devices with heterogeneous computational power. To address this, we propose a novel framework for efficient multi-user offloading of personalized diffusion models. This framework accommodates a variable number of users, each with different computational capabilities, and adapts to the fluctuating computational resources available on edge servers. To enhance computational efficiency and alleviate the storage burden on edge servers, we propose a tailored multi-user hybrid inference approach. This method splits the inference process for each user into two phases, with an optimizable split point. Initially, a cluster-wide model processes low-level semantic information for each user's prompt using batching techniques. Subsequently, users employ their personalized models to refine these details during the later phase of inference. Given the constraints on edge server computational resources and users' preferences for low latency and high accuracy, we model the joint optimization of each user's offloading request handling and split point as an extension of the Generalized Quadratic Assignment Problem (GQAP). Our objective is to maximize a comprehensive metric that balances both latency and accuracy across all users. To solve this NP-hard problem, we transform the GQAP into an adaptive decision sequence, model it as a Markov decision process, and develop a hybrid solution combining dee

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Towards BIM-based robot localization: A real-world case study 39

Towards BIM-based robot localization: A real-world case stud...

引用

39th International Symposium on Automation and Robotics in Construction, ISARC 2022

作者： Yin, H. Liew, J.M. Lee, W.L. Ang, M.H. Yeoh, J.K.W. College of Design and Engineering National University of Singapore Singapore Singapore Department of Electronic and Computer Engineering Hong Kong University of Science and Technology HKSAR Hong Kong

ISBN: (纸本)9789526952420

Conventional mobile robots rely on pre-built point cloud maps for online localization. These map points are generally built using specialized mapping techniques, which involve high labor and computational costs. While in the architectural, engineering and construction (AEC) industry, asplanned building information modelings (BIM) are available for management and operation. In this paper, we consider the use of the digital representations of BIM for robot localization in built environments. First, we convert BIM data into localization-oriented point clouds, which is easy to implement and operate compared to relatively complex SLAM systems. Then, we perform iterative closest point (ICP)-based localization on the metric map using a laser scanner. The experiments are tested using collected laser data and BIM in the real world. The results show that ICP-based localization can track the robot pose with low errors ( © 2022 International Association on Automation and Robotics in Construction.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Model for Hardware Trojan Detection in Integrated Circuit design

SSRN

引用

SSRN 2024年

作者： Rathor, Vijaypal Singh Podder, Soykot Department of Computer Science and Engineering PDPM Indian Institute of Information TechnologyDesign and Manufacturing Jabalpur India

Ensuring the security of integrated circuits (ICs) is crucial due to the threat posed by malicious inclusion called hardware Trojan (HT). The hardware Trojan installed during the design or manufacturing process can compromise the security of a system by changing the IC functionality, leaking sensitive information, and reducing the system’s reliability. To address this issue, researchers have focused on the detection of Trojans during the pre-silicon and post-silicon phases of the ICs. Recently machine learning (ML) has gained significant attention for detecting hardware Trojans. However, the previously proposed ML-based HT detection methods are often evaluated only on detection Accuracy or F1-score;they need a comprehensive evaluation of different metrics. Further, the existing techniques are only tested on a single data set and perform poorly on other data sets. Therefore, an effective method is required to accurately detect hardware Trojans, perform well on different evaluation metrics (Accuracy, precision, recall, F1-score, AUC), and be effective across diverse data sets. This work proposes an Ensemble Learning (EL) model that addresses the limitations of existing methods and effectively detects the hardware Trojans in the design. The proposed EL model combines multiple weak learners, i.e., Support Vector Machines (SVM), K-Nearest Neighbors (KNN), XGBoost (XGB), Logistic regression, and Random Forest, to achieve robust detection capabilities. The implementation and evaluation of the proposed EL model on three different Trust-hub benchmark data sets show an accuracy of 100% and F1-scores of 98%, 100%, and 100%. The best-known previous Ml-based methods provide a maximum accuracy of 99.98% and an F1-score of 86.74%. Besides, the cross-validation of the proposed EL model obtains the accuracy ranging from 99.06% to 99.92% and F1-score and F1-score 98.38%. This demonstrates the consistency and effectiveness of our EL model across different types of hardware Trojan dete

关键词： Hardware security

来源：评论

学校读者我要写书评

暂无评论

Addressing Challenges and Opportunities in Precision Medicine Using Deep Learning and Personalized Cancer Treatment

Addressing Challenges and Opportunities in Precision Medicin...

引用

Delhi Section Conference (DELCON), IEEE

作者： G S Pradeep Ghantasala Nalli Vinaya Kumari R Rajesh Sharma Pellakuri Vidyullatha Akey Sungheetha Saliha Bathool Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Department of Computer Science and Engineering Malla Reddy Engineering College for Women JNTUH Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Andhra Pradesh India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

The primary aim of personalized cancer treatment is to increase effectiveness and reduce side effects by tailoring therapies based on a patient's unique genetic and molecular characteristics. This research investigates how deep learning is transforming personalized cancer care through its ability to process and analyze complex, high-dimensional data. The study explores the use of deep learning techniques in predicting tumor classifications, genetic mutations, and treatment responses by integrating clinical data, genomic profiles, and medical imaging. It reviews recent advancements in deep learning applications for cancer, such as targeted therapy through genetic profiling, tumor identification from histopathology images, and optimization of treatment protocols. Additionally, the paper discusses challenges including model transparency, clinical integration, and data security. The study demonstrates how deep learning can enhance patient outcomes and outlines future opportunities for this evolving area of cancer care.

关键词： Deep learning Privacy Accuracy Cancer treatment Genomics Real-time systems Bioinformatics Medical diagnostic imaging Cancer Tumors

来源：评论

学校读者我要写书评

暂无评论

Bridging the Modality Gap: Generative Adversarial Networks for T1-T2 MRI Image Translation

Bridging the Modality Gap: Generative Adversarial Networks f...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Mayank Pandey Naga Sai Shreya Kunda Pranave Kc Tripty Singh Rekha R Nair Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Dept. of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

CycleGAN, a significant deep learning model, has transformed medical imaging by providing a remedy for translating MRI images between different modalities. Its ability to transform T1-weighted to T2-weighted images is crucial in healthcare environments where obtaining multiple scans can be time-consuming and burdensome for patients. This can be achieved by utilizing CycleGAN, which generates images that contains vital information that will help the healthcare professionals to diagnose the patient without exposing them to further radiations. This unleashes an effective and safer way of diagnosing patients. The adaptability of CycleGAN also allows scalability and the ability to customize it for different types of medical images, where scanning can be achieved with less exposure to radiation, without loosing or compromising any important information.

关键词： Deep learning Magnetic resonance imaging Scalability Magnetic resonance Medical services Transforms Generative adversarial networks Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Maximization of Profit and Throughput of EV-Charging Station Integrated with PV and ESS

Maximization of Profit and Throughput of EV-Charging Station...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Ram Mohan Chowdary Kota Jaishree Mayank Sanjeet Kumar Nayak Department of Computer Science and Engineering Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai India

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

Electric vehicles (EVs) provide a promising solution to global pollution by replacing conventional vehicles. Enough public charging stations must be built to encourage the broad adoption of electric vehicles (EVs). Additionally, efficient scheduling and planning of EV arrivals at charging stations with a variety of power sources is essential for improving overall operating efficiency. This paper presents a framework for optimizing both the profit and throughput of a charging station that incorporates a solar photovoltaic system and an energy storage system. We present an Integer Linear Programming model to find the optimal solution. We propose a heuristic strategy to efficiently find near-optimal solutions. Our experimental results demonstrate that the proposed approach can provide a reasonably good solution and for small inputs, the performance deviation is less than 5%. For larger inputs, a comparison of the heuristic and baseline is presented. In certain scenarios, the heuristic performs well, while the baseline exhibits better performance in others. We can use both approaches and select the one that yields better results.

关键词： Photovoltaic systems Vehicular and wireless technologies Costs Pollution Charging stations Throughput Electric vehicles

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：