检索结果-内蒙古大学图书馆

10th International Conference on Information technology: IoT and Smart City, ICIT 2022

作者： Xing, Qi Luo, Yun Zhang, Zhaoyuan Zhang, Fan Beijing Institute of Computer Technology and Application China

ISBN: (纸本)9781450397438

Video inter-frame tampering detection is the most common type of forensics in video forensics. The traditional detection method is to detect tampering by extracting digital image features of video frames, such as SIFT, HOG, and ORB. The accuracy of frame discrimination and localization is limited. This paper introduces deep learning into the problem of tampering detection, and proposes a composite network model structure using the Siamese network Siamese and the bidirectional long short-term memory network autoencoder BiLSTM AutoEncoder to detect tampered frames. Among them, Siamese calculates the inter-frame distance by calculating the depth features of the frames extracted by VGG-16, and inputs them into BiLSTM AutoEncoder for frame sequence anomaly detection and localization. The model is experimented on two different datasets with good results, validating the model generalization performance. Compared with the classical method, this model obtains higher precision(93.7%) of tamper points, which verifies the superiority of this deep learning model. © 2022 ACM.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Emotional Information-Based Hybrid Recommendation System 11th

Emotional Information-Based Hybrid Recommendation System

引用

11th International Conference on Soft Computing for Problem Solving, SocProS 2022

作者： Sharma, Manika Mittal, Raman Bharati, Ambuj Saxena, Deepika Singh, Ashutosh Kumar Department of Computer Application National Institute of Technology Kurukshetra Haryana Kurukshetra136119 India

ISBN: (纸本)9789811965241

In this technology-driven times, recommender systems play a crucial role in providing better user experience and attracting as many users as possible on the website. We propose a hybrid approach for selecting movies that incorporates emotional data in this study. The model will include the benefits of both content-based filtering and collaborative filtering to make up a hybrid model, and then, an additional parameter which is emotions further enhances the accuracy and efficiency of the model. The model is evaluated and compared with some other approaches, and it appears to perform better in a real-time environment. The model also tries to eliminate some of the existing limitations up to some extent. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Computing and applications in Deep Learning: A Survey 22

Heterogeneous Computing and Applications in Deep Learning: A...

引用

5th International Conference on computer Science and Software Engineering, CSSE 2022

作者： Wu, Qiong Shen, Yuefeng Zhang, Mingqing Beijing Institute of Computer Technology and Application China

ISBN: (纸本)9781450397780

With the rapid development of deep learning, a variety of neural network models emerge in endlessly, which leads to a huge demand for computing resources. For the intensive numerical computation of neural networks, various computing devices represented by GPUs are favored by researchers. Heterogeneous computing is a kind of technology that can integrate a variety of computing devices with different architectures, and it will be further developed. Therefore, this paper reviews research on some key technologies of heterogeneous computing, including the architecture of heterogeneous computing, the programming language of heterogeneous computing, and the scheduling algorithm for heterogeneous systems. Then, we focus on the research of heterogeneous computing in deep learning, including the parallel technology of neural networks and optimization technology based on heterogeneous systems. Finally, the present research situation is discussed and analyzed, and the future research direction is prospected, aiming to provide some basis for related research. © 2022 ACM.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Real-Time Virtual Mouse using Hand Gestures for Unconventional Environment 14

Real-Time Virtual Mouse using Hand Gestures for Unconvention...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Neha Sabrin, T.K. Karande, Aarti Sardar Patel Institute of Technology Dept. of Masters of Computer Application Mumbai India

ISBN: (纸本)9798350335095

This research paper explores the implementation and potential benefits of a virtual mouse using hand gestures as an input device for individuals. The virtual mouse is a software-based interface, enabling users to control the cursor without physically touching a mouse. Hand gestures are recognized using sensors and machine learning algorithms that translate these gestures into cursor movements on the screen. The results show that the hand gesture method is accurate in recognizing different hand movements, providing individuals with new means of interacting with technology with a budget free and user-friendly solution. The developed system demonstrates significant potential for enhancing human-computer interaction in unconventional environments, such as underwater exploration, space stations, industrial settings, extreme weather conditions, and remote locations. © 2023 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Security in Mobile Traffic Networks Through Reverse Engineering 4

Enhancing Data Security in Mobile Traffic Networks Through R...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Islam, Syed Arif Mohankumar, M. Khatuna Jannat, Umma Karpagam Academy of Higher Education Dept. of Computer Science Coimbatore India Sns College of Technology Dept. of Computer Application Coimbatore India

ISBN: (纸本)9798331529635

This research enhances mobile traffic network security using reverse engineering and encryption. It analyzes vulnerabilities in evolving mobile protocols (GSM, 4G, 5G) and applies encryption schemes like AES and RSA to secure data transmission. The study also explores secure key exchange mechanisms such as Diffie-Hellman (DH) and Elliptic Curve Cryptography (ECC) and evaluates Intrusion Detection Systems (IDS) for threat detection. Tests in a Python-simulated environment confirm the effectiveness of these solutions, providing insights into balancing security and performance in dynamic mobile networks. © 2024 IEEE.

关键词： Data Security Encryption Mobile Traffic Networks Reverse Engineering Vulnerability Assessment

来源：评论

学校读者我要写书评

暂无评论

A Method for the Fusion of Results from RFID and VLPR

A Method for the Fusion of Results from RFID and VLPR

引用

2022 International Conference on Scientific Computation and Applied Statistics, ICSCAS 2022

作者： Wang, Jia Zhang, Hong Zou, Huayi Jiang, Suiping Beijing Institute of Computer Technology and Application China

Radio Frequency Identification (RFID) and Vehicle License Plate Recognition (VLPR) are two main methods for vehicle identification. How to fusion the recognition results of the two methods is a problem that needs to be solved in practice. The existing fusion technology usually uses trigger acquisition for precise matching, or uses one recognition result as a reference to perform matching in another result set, while these technology does not provide a clearly algorithm or has certain limitations, and is not universal. A matching algorithm is presented in this paper, which takes advantage of the similarity metric between the results from RFID and VLPR, thus eliminating the drawbacks of existing match methods. The algorithm calculates the similarity metric of the results from RFID and VLPR by the vehicle license plate character graphics similarity, then find matching results from the two recognition results in a specific time window, finally work out precise matching result or similar matching result. The presented algorithm is simple but effective, with no need to triggering RFID and VLPR simultaneously. The algorithm can output both precise matches and similar matches. Through the verification results in the real road scene, the performance in the license plate similarity calculation and fusion matching process is consistent with expectations, which shows the effectiveness of the algorithm. © Published under licence by IOP Publishing Ltd.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Research on virtual reality fusion method based on spatial Marker location 9

Research on virtual reality fusion method based on spatial M...

引用

9th Symposium on Novel Photoelectronic Detection technology and applications

作者： Li, Shengyong Li, Dongxue Du, Linqing Guo, Haoqian Wang, Hongyu Shenyang University of Technology Shenyang110870 China Beijing Institute of Computer Technology and Application Beijing100854 China

ISBN: (纸本)9781510664432

Virtual reality fusion based on augmented reality has become a research hotspot, which is widely used in cultural relics exhibition, medical care and other fields. Spatial projection mapping matrix is the basis for projection equipment to project the prefabricated image onto the target surface. However, in practical operation, it is necessary to determine the relative position relationship between the projection equipment and the actual scene based on complex spatial target calibration. This paper aims to solve the problem of projection information dislocation and realize real-time tracking projection. A high-precision center positioning method based on the invariable characteristic of concentric circle intersection ratio is designed, and the mapping matrix from projection equipment to target is calculated based on PNP method. Finally, the distortion parameters of the lens are used to generate a projection pattern that can offset the projection distortion, so as to optimize the coincidence between the projection pattern and the real object, and achieve efficient and high-precision virtual reality fusion projection. © 2023 SPIE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Combined CNN LSTM with attention for speech emotion recognition based on feature-level fusion

引用

Multimedia Tools and applications 2024年第21期83卷 59839-59859页

作者： Liu, Yanlin Chen, Aibin Zhou, Guoxiong Yi, Jizheng Xiang, Jin Wang, Yaru Institute of Artificial Intelligence Application College of Computer and Information Engineering Central South University of Forestry and Technology Hunan Changsha410004 China Hunan Key Laboratory of Intelligent Logistics Technology Central South University of Forestry and Technology Hunan Changsha410004 China

According to the problem that emotional features cannot be well represented by a single feature and it is difficult to extract in the task of Speech Emotion Recognition (SER), we propose a Feature-Level (FL) fusion method for 9 types of acoustic features and a combined CNN-LSTM network with attention (CNN-A-LSTM). The feature vector set after feature-level fusion is used as the input of CNN-A-LSTM network, which contains prosodic features and spectral features. High-level Statistical Functions (HSFs) are also added to receive global features. The feature extraction network CNN-A-LSTM can more effectively read time-series input and extract speech emotion information. Finally, Softmax is applied as a classifier to obtain the final emotion classification results. The experiment is verified on SAVEE and CASIA datasets. The experimental results show that the method in this paper has the best effect compared with the state-of-the-art, and the accuracy rates of 94.5% and 96.7% are respectively gained on SAVEE and CASIA. The above results prove the effectiveness of the algorithm in this paper with some generalization. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Study on Intelligent Decision Architecture of Online Data Acquisition and Analysis System 3

Study on Intelligent Decision Architecture of Online Data Ac...

引用

3rd International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2024

作者： Yu, Chenglong Liu, Daoyuan Yan, Hongpo Li, Qiang Gong, Maozhen Beijing Institute of Computer Technology and Application Beijing China Jincheng Nanjing Engineering Institute of Aircraft System Nanjing China

ISBN: (纸本)9798331529222

To better improve the production capacity and control efficiency of discrete manufacturing workshops, a decision system architecture based on online acquisition and data analysis is proposed, and its architecture and operation process are described. Furthermore, the key supporting function such as manufacturing data detection and acquisition based on internet of things, data analysis for production control, production optimization decision based on data analysis were further studied. Ultimately, a prototype system was built, as well as its functionality was validated by the past actual data. It has good reference value to provides technical support and software foundation for subsequent research and performance verification. ©2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Multiprocessor Task Scheduling Optimization for Cyber-Physical System Using an Improved Salp Swarm Optimization Algorithm

引用

SN computer Science 2024年第1期5卷 184页

作者： Acharya, Biswaranjan Panda, Sucheta Ray, Niranjan K. Department of Computer Application Veer Surendra Sai University of Technology Burla Odisha Sambalpur 768018 India School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar 751024 India

Salp Swarm Algorithm (SSA) is a bio-inspired optimization algorithm used in this paper to optimize the multiprocessor scheduling process in the current cyber-physical system. Although SSA is mainly utilized in terms of local search, in our case, an improved version has been introduced with the use of a Local Search Algorithm (LSA) and binary SSA, namely Improved SSA (ISSA). More to the point, eight optimization algorithms are compared with this proposed ISSA namely SSA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Jaya Algorithm (JAYA), Chaotic Squirrel Search Algorithm (CSSA), Quantum-inspired Binary Chaotic Salp Swarm Algorithm (QBCSSA) and Space Transformation Search (STS) with SSA is termed as STS-SSA. The performance of ISSA along with the other 6 meta-heuristic and 2 improved versions of SSA algorithms are compared with 12 traditional benchmark functions and evaluated for 100 and 300 dimensions. Convergent curves have also been demonstrated and the proposed ISSA has been shown to find a global optimum within the very initial phase of iterations. For calculating the efficiency of the proposed algorithm, the gear train design problem has been employed. The proposed algorithm has demonstrated higher accuracy rates and better convergent values than the other applied algorithms. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Benchmark function Cyber-physical system Gear train strategy Global optima Grid computing Local search algorithm (LSA) Multiprocessor task scheduling Salp swarm algorithm

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：