检索结果-内蒙古大学图书馆

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Reddy, Balaram Raj, Jebarson Aroulanandam, Vijay Vasanth School of Computing SRM IST Faculty of Engineering and Technology Department of Networking and Communications Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798331530013

There have been a lot of traffic issues in cities due to parking anomalies and unavailability of parking. That is why SmartPark was created. It is a smart parking system that uses computer vision and sensors to improve parking efficiency and make it easier for drivers. This parking system uses computer vision to see if parking spaces are available and shares that information through a mobile app in real-time. Furthermore, sensors are used to help drivers park properly in the specified parking slot stopping them from blocking pathways or interfering with other vehicles nearby. With the fusion of AI and IoT, this parking system aims to reduce traffic congestion and minimize parking delays. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Boosting Deepfake Detection Features with Attention Units 23

Boosting Deepfake Detection Features with Attention Units

引用

5th World Symposium on Software engineering, WSSE 2023

作者： Waseem, Saima Abu-Bakar, Syed A.R. Omar, Zaid Ahmed, Bilal Ashfaq Baloch, Saba Faculty of Electrical Engineering Universiti Teknologi Malaysia Johor Malaysia Faculty of Computing Universiti Teknologi Malaysia Johor Malaysia

ISBN: (纸本)9798400708053

One of the emerging problems of deep learning technology is deepfake videos with easy access to powerful and inexpensive computing power;The internet is littered with fake material like fake photos, videos, and audios. People’s identities, privacy and reputations are at risk due to the widespread proliferation of fake media content. Since videos can have a potentially destructive effect on society, establishing their legitimacy is crucial. Thus, we investigate different attention mechanisms in this paper for deepfake detection. In videos, attention mechanisms are responsible for directing the convolutional Neural Network’s (CNNs) emphasis to the most critical parts of the frame in terms of both content and context. Therefore, we answer the question: How do you apply attention to deepfake detection? And what form of attention is effective for deepfake detection tasks? To address these concerns, we conduct research and experimental testing on videos that have been manipulated using four different methods drawn from the FaceForensics++ dataset. We conduct a cross-data evaluat ion for the network with and without attention to assess the network’s capacity to detect previously unseen manipulated images. The proposed approach outperformed conventional Convolutional Neural Networks for deepfake detection by 8% AUC performance. © 2023 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Paddy Plant Stress Identification Using Few-Shot Learning Framework 14

Paddy Plant Stress Identification Using Few-Shot Learning Fr...

引用

14th International Conference on Computer and Knowledge engineering, ICCKE 2024

作者： Moung, Ervin Gubin Sufian, Maisarah Mohd Farzamnia, Ali Naiidu, Pavindrah Naidu Narayanasamy Liaw, Valentino Angeline, Lorita Faculty of Computing and Informatics University Malaysia Sabah Sabah Kota Kinabalu Malaysia School of Computing and Engineering University of Huddersfield West YorkshireHD1 3DH United Kingdom Faculty of Engineering Universiti Malaysisa Sabah Sabah Kota Kinabalu Malaysia

ISBN: (纸本)9798331511272

The efficient identification of stress in paddy plant leaves is paramount for optimizing agricultural resources and ensuring robust crop yields in smart agriculture practices. This research explores the potential of few-shot learning (FSL) to address the inherent challenges posed by limited training data in stress identification. Three distinct FSL approaches - Siamese network, Matching network, and Model-Agnostic Meta Learning (MAML) - are evaluated for their accuracy in stress detection. The study introduces the importance of stress detection in smart agriculture and the challenges of limited training data. It then covers the methodology in five stages: dataset description, data pre-processing, FSL implementation, accuracy evaluation, and reporting. Among the FSL models, the Matching Network stands out with an impressive accuracy of 86% for 6-way 1-shot learning. This surpasses the performance of a Convolutional Neural Network (CNN) tested with a larger shot size (270-shots), which achieved an accuracy of 81%. These comparative results underscore the potential of FSL techniques in achieving precise stress identification, even when working with limited data. The objective of this research is to contribute valuable insights towards enhancing the efficiency of stress prediction in paddy leaves, thereby fostering healthier and more productive paddy crop production in smart agriculture. The findings presented here aim to inform the development of effective stress detection systems and advance the field of precision agriculture. ©2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Survey on Video Security:Examining Threats,Challenges,and Future Trends

引用

Computers, Materials & Continua 2024年第9期80卷 3591-3635页

作者： Ali Asghar Amna Shifa Mamoona Naveed Asghar Department of Artificial Intelligence Faculty of ComputingThe Islamia University of BahawalpurBahawalpur63100Pakistan School of Computer Science College of Science and EngineeringUniversity of GalwayGalwayH91 TK33Ireland

Videos represent the most prevailing form of digital media for communication,information dissemination,and ***,theirwidespread use has increased the risks of unauthorised access andmanipulation,posing significant *** response,various protection approaches have been developed to secure,authenticate,and ensure the integrity of digital *** study provides a comprehensive survey of the challenges associated with maintaining the confidentiality,integrity,and availability of video content,and examining how it can be *** then investigates current developments in the field of video security by exploring two critical research ***,it examine the techniques used by adversaries to compromise video data and evaluate their *** these attack methodologies is crucial for developing effective defense ***,it explores the various security approaches that can be employed to protect video data,enhancing its transparency,integrity,and *** compares the effectiveness of these approaches across different use cases,including surveillance,video on demand(VoD),and medical videos related to disease ***,it identifies potential research opportunities to enhance video data protection in response to the evolving threat *** this investigation,this study aims to contribute to the ongoing efforts in securing video data,providing insights that are vital for researchers,practitioners,and policymakers dedicated to enhancing the safety and reliability of video content in our digital world.

关键词： Attacks threats security services video manipulation video security

来源：评论

学校读者我要写书评

暂无评论

QEdgeProxy: QoS-Aware Load Balancing for IoT Services in the computing Continuum 8

QEdgeProxy: QoS-Aware Load Balancing for IoT Services in the...

引用

8th IEEE International Conference on Edge computing and Communications, EDGE 2024

作者： Cilic, Ivan Jukanovic, Valentin Zarko, Ivana Podnar Frangoudis, Pantelis Dustdar, Schahram University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Distributed Systems Group TU Wien Vienna Austria

ISBN: (纸本)9798350368499

While various service orchestration aspects within computing Continuum (CC) systems have been extensively addressed, including service placement, replication, and scheduling, an open challenge lies in ensuring uninterrupted data delivery from IoT devices to running service instances in this dynamic environment, while adhering to specific Quality of Service (QoS) requirements and balancing the load on service instances. To address this challenge, we introduce QEdgeProxy, an adaptive and QoS-aware load balancing framework specifically designed for routing client requests to appropriate IoT service instances in the CC. QEdgeProxy integrates naturally within Kubernetes, adapts to changes in dynamic environments, and manages to seamlessly deliver data to IoT service instances while consistently meeting QoS requirements and effectively distributing load across them. This is verified by extensive experiments over a realistic K3s cluster with instance failures and network variability, where QEdgeProxy outperforms both Kubernetes built-in mechanisms and a state-of-the-art solution, while introducing minimal computational overhead. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Robot See, Robot Do: Imitation Reward for Noisy Financial Environments

Robot See, Robot Do: Imitation Reward for Noisy Financial En...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Goluža, Sven Kovačevic, Tomislav Begušic, Stjepan Kostanjčar, Zvonko University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Financial and Risk Analytics Unska 3 Zagreb10000 Croatia

ISBN: (纸本)9798350362480

The sequential nature of decision-making in financial asset trading aligns naturally with the reinforcement learning (RL) framework, making RL a common approach in this domain. However, the low signal-to-noise ratio in financial markets results in noisy estimates of environment components, including the reward function, which hinders effective policy learning by RL agents. Given the critical importance of reward function design in RL problems, this paper introduces a novel and more robust reward function by leveraging imitation learning, where a trend labeling algorithm acts as an expert. We integrate imitation (expert's) feedback with reinforcement (agent's) feedback in a model-free RL algorithm, effectively embedding the imitation learning problem within the RL paradigm to handle the stochasticity of reward signals. Empirical results demonstrate that this novel approach improves financial performance metrics compared to traditional benchmarks and RL agents trained solely using reinforcement feedback. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Control Aspects in Programming by Demonstation for Robotic Deep- Micro- Hole Drilling 32

Control Aspects in Programming by Demonstation for Robotic D...

引用

32nd Mediterranean Conference on Control and Automation, MED 2024

作者： Maric, Bruno Petric, Frano Orsag, Matko University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (纸本)9798350395440

This paper explores control aspects in a collab-orative robotic system designed to replicate human operators' drilling skills in deep- micro- hole tasks, focusing on the glass-container mould industry. To replicate human performance, we develop a single-DOF Impedance-based drill controller for a standard industrial position-controlled robot, enhancing safe and smooth interactions between the drill bit and the mould. To address high feed rates observed in worker demonstrations and prevent bit breaks, we focus on minimizing non-axial motion during drilling on an off-the-shelf available industrial manipulator KUKA KR 10. This involves analyzing the impact of joint dynamics on drill motion and designing a control system for the robot's low-level control to achieve axial drill motion. We show that the proposed joint control system that takes into account relationship between joint and tool dynamics outperforms available robot low-level control in minimizing non-axial motion, leading to the robot being able to outperform the human in deep- micro- hole drilling. © 2024 IEEE.

关键词： Molds

来源：评论

学校读者我要写书评

暂无评论

An Approach for Early Detection of Schizophrenia 15

An Approach for Early Detection of Schizophrenia

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Paranagama, Sachin Uditha, Isiwara Daundasekara, Pamodya Hettiarachchi, Shehani Weerasinghe, Lokesha Kasthurirathna, Dharshana Sri Lanka Institue Of Information Technology Faculty Of Computing Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350370249

Schizophrenia is a chronic mental disorder with distorted thinking, hallucinations, and social difficulties. Early diagnosis is vital, but current methods are limited. This research proposes a web-based application integrating machine learning, emotion recognition, and game-based elements to track symptoms and aid in early diagnosis. Interactive exercises focus on specific symptoms like cognitive evaluation, emotional analysis, and memory assessment. By combining computer science, psychology, and machine learning, the project aims to improve early detection and ultimately enhance the quality of life for affected individuals. Key components include using Deep Convolutional Neural Network (DCNN) architecture for recognizing facial and physical expressions associated with schizophrenia with an 87% accuracy rate, and utilizing Vector Regressor (SVR) with a 93% accuracy rate, along with Vision Transformer (ViT) and Custom CNN models for cognitive assessment, achieving accuracy rates of 99% and 98%, respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Determination of the Impact of Video Encoding Parameters on QoE Using Passive Viewing Tests 32

Determination of the Impact of Video Encoding Parameters on ...

引用

32nd International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2024

作者： Arih, Dominik Barisic, Ilija Suznjevic, Mirko University of Zagreb Faculty of Electrical Engineering and Computing Croatia University of Zagreb Academy of Dramatic Arts Department of Dramaturgy Croatia

ISBN: (纸本)9789532901382

Optimizing video encoding parameters is essential for cloud gaming service providers to deliver high-quality gaming experiences to their users. In this study, we conducted a passive Quality of Experience testing on a publicly available dataset of cloud gaming sessions to evaluate the impact of video encoding parameters on the Quality of Experience ratings of the samples. Participants assessed the quality of video streams utilizing a selected methodology, and statistical analysis was conducted to ascertain how various parameters affected the average quality ratings of diverse game genres. We further investigated the impact of quality settings on the participants' willingness to play. Additionally, we explored the applicability of passive viewing tests by comparing our QoE analysis results with previous research that used active viewing tests in cloud gaming evaluations. © 2024 University of Split, FESB.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

OUT-OF-DISTRIBUTION DETECTION BY LEVERAGING BETWEEN-LAYER TRANSFORMATION SMOOTHNESS 12

OUT-OF-DISTRIBUTION DETECTION BY LEVERAGING BETWEEN-LAYER TR...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Jelenić, Fran Jukić, Josip Tutek, Martin Puljiz, Mate Šnajder, Jan TakeLab Croatia Faculty of Electrical Engineering and Computing University of Zagreb Croatia UKP Lab Technical University of Darmstadt Germany

Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training. We present a novel method for detecting OOD data in Transformers based on transformation smoothness between intermediate layers of a network (BLOOD), which is applicable to pre-trained models without access to training data. BLOOD utilizes the tendency of between-layer representation transformations of in-distribution (ID) data to be smoother than the corresponding transformations of OOD data, a property that we also demonstrate empirically. We evaluate BLOOD on several text classification tasks with Transformer networks and demonstrate that it outperforms methods with comparable resource requirements. Our analysis also suggests that when learning simpler tasks, OOD data transformations maintain their original sharpness, whereas sharpness increases with more complex tasks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Metadata

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：