检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 672-683页

作者： Ranjan, Priyesh Khan, Pritam Kumar, Sudhir Das, Sajal K. Department of Computer Science Missouri University of Science and Technology RollaMO65409 United States Department of Electrical Engineering Indian Institute of Technology Patna Patna801106 India

With the enhanced usage of artificial-intelligence-driven applications, the researchers often face challenges in improving the accuracy of data classification models, while trading off the complexity. In this article, we address the classification of time-series data using the long short-term memory (LSTM) network while focusing on the activation functions. While the existing activation functions, such as sigmoid and tanh, are used as LSTM internal activations, the customizability of these activations stays limited. This motivates us to propose a new family of activation functions, called log-sigmoid, inside the LSTM cell for time-series data classification and analyze its properties. We also present the use of a linear transformation (e.g., log tanh) of the proposed log-sigmoid activation as a replacement of the traditional tanh function in the LSTM cell. Both the cell activation and recurrent activation functions inside the LSTM cell are modified with log-sigmoid activation family while tuning the log bases. Furthermore, we report a comparative performance analysis of the LSTM model using the proposed and the state-of-the-art activation functions on multiple public time-series databases. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Device Identification using Network Traces in a Smart Home IoT Network 17

Device Identification using Network Traces in a Smart Home I...

引用

17th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Brahma, Jwngfu Matam, Rakesh Choudhury, Nikumani Indian Institute of Information Technology Dept. of Computer Science & Engineering Guwahati India Birla Institute of Technology & Science Dept. of Computer Science & Information Systems Hyderabad India

ISBN: (纸本)9798350307672

Device identification is a crucial aspect of securing networks, particularly in the context of the Internet of Things (IoT), where a vast variety of devices are interconnected. Recently, there has been significant research on developing techniques for identifying IoT devices based on their unique characteristics, called as device fingerprints. These techniques use machine learning algorithms, which can effectively learn and classify devices based on their features. However, device identification remains a challenging task due to the diversity of IoT devices and the constant evolution of their characteristics. This paper presents our attempt at device identification by analyzing distinct device characteristics observed during network communication and using different machine learning techniques. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Dynamic Attention-Based Deep Learning Model Segments Brain Tumors 12

A Cascaded Dynamic Attention-Based Deep Learning Model Segme...

引用

12th International Conference on Current Trends in Advanced Computing, ICCTAC 2024

作者： Choudhary, Kartik Singh, Kaptan Saxena, Amit Computer Science & Engineering Truba Institute of Engineering & Information Technology Bhopal India

ISBN: (纸本)9798350395808

Brain tumor diagnosis and treatment need segmentation, Precision automated segmentation of brain tumors is difficult due to their size, shape, unexpected placements, and fuzzy boundaries. U-Net is a popular medical picture segmentation model due to its simple architecture and high performance. Underutilized contextual information, limited local receptive fields, and lost spatial information are issues. For brain tumor segmentation, CDAU-Net, a novel model with Dynamic Convolution and Non-Local Attention Mechanism, addresses these issues. Two-stage cascaded three-dimensional U-Nets rebuild brain tumor spatial information at better resolution. The cascaded network's lateral connections receive maximal attention, improving its ability to collect long-distance interconnections and use tumor context information. Finally, dynamic convolutions with local adaptive capabilities replace normal convolutions in the cascaded network to increase local features capture. Extensive experiments were conducted on publicly available BraTS 2019 and 2020 datasets, comparing the proposed method with other representative approaches. Proposed method segments brain tumors. Brain tumor segmentation dice values of 0.897/0.903 for whole tumor, 0.826/0.828 for tumor core, and 0.781/0.786 for enhanced tumor segmentation worked in the BraTS 2019/2020 validation set. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Smoothed-LSTM: Advancing spatio-temporal NDVI prediction in semi-automated dataset for rice crop

Smoothed-LSTM: Advancing spatio-temporal NDVI prediction in ...

引用

2024 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024

作者： Dey, Anamika Sarkar, Somrita Kumar, Debajyoti Mondal, Arijit Mitra, Pabitra Indian Institute of Technology Kharagpur Centre For Computational And Data Sciences Kharagpur India Indian Institute of Technology Department of Computer Science And Engineering Patna Bihta India Indian Institute of Technology Kharagpur Department of Computer Science And Engineering Kharagpur India

ISBN: (纸本)9798350389678

Accurate Normalized Difference Vegetation Index (NDVI) forecasting is crucial for effective agricultural planning. However, a good prediction of the same requires sufficient data, but structured data is not available in the public domain or open-source community. Also, most of the existing methods do not consider spatial information. This study presents a novel semi-automated dataset generation framework that utilizes Sentinel-2, POWER Data Access Viewer, and Google Earth Engine to create a comprehensive time-series dataset. We propose a smoothed long short-term memory (LSTM) model considering time series, historical meteorological, and spatial information. The proposed Smoothed-LSTM-based model outperforms Traditional-LSTM models, demonstrating its effectiveness in NDVI prediction for agricultural applications. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

An Integrated Mobility-Oriented Wireless Charging Scheme for Wireless Sensor Network 3

An Integrated Mobility-Oriented Wireless Charging Scheme for...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Mathada, Mallikarjuna Amgoth, Tarachand Indian Institute of Technology Indian School of Mines Department of Computer Science & Engineering Dhanbad India

ISBN: (纸本)9798350372120

Wireless charging is one of the most practical procedures to replenish the energy of the resource-constrained nodes in a Wireless Sensor Network (WSN) that contributes mainly towards enhanced network lifetime. After reviewing the existing methodologies of wireless charging schemes, it is noted that there is still a wide scope for improvement owing to various open sets of problems. Therefore, considering the mobility-oriented charging policy, this study presents a unique computational model that may restore energy for the energy-depleted sensor nodes. The proposed study introduces a scheme where both static and mobile chargers are used for energy replenishment using a Reinforcement Learning scheme. Further, the proposed scheme also introduces a dual topology scheme that can perform mobile charging on variable dynamic environmental conditions in WSN. The simulated outcome of the study shows the proposed model to acquire a 50% increase in residual energy, 28% enhanced charging efficiency, 92% reduced delay, and 43% effective packet delivery ratio under increasing number of sensor nodes. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Automatic Privacy-Preserved Contact Tracing in Body Area Networks using Blockchain 20

Automatic Privacy-Preserved Contact Tracing in Body Area Net...

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Pattanayak, Anupam Baruah, Barnana Dhal, Subhasish Indian Institute of Information Technology Computer Science and Engineering Guwahati India The Assam Kaziranga University Computer Science and Engineering Jorhat India

ISBN: (纸本)9798350305593

Outbreak of Covid-19 has opened up many research problems. One such problem is to find the number of people who have come in direct or indirect contact of a Covid-19 positive person. This problem is referred as contact tracing. The contact tracing should be done in such a way that privacy should not be compromised. This paper proposes a privacy-preserving contact tracing solution for body area network (BAN) enabled users using blockchain. Inter-BAN communications are recorded, encrypted and maintained in blockchain network in the form of adjacency matrix. Adjacency matrix helps to obtain many valuable information for tracing the direct and indirect contacts and to determine if a given user is a super spreader. The security of the proposed framework has been investigated thoroughly against the possible attacks and through AVISPA tool. Computation overhead of BAN user has been reported based on simulation. © 2023 IEEE.

关键词： Blockchain Body Area Network Contact Tracing Covid-19 Inter-BAN Communication Privacy

来源：评论

学校读者我要写书评

暂无评论

Joint View Selection, Multigroup Multicast Beamforming, and DIBR for RIS-Aided Multi-View Videos

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 6376-6393页

作者： Lee, Chi-Han Yang, De-Nian Lee, Guang-Siang Wang, Chih-Hang Liao, Wanjiun National Taiwan University Department of Electrical Engineering Taiwan Academia Sinica Institute of Information Science The Research Center for Information Technology Innovation Taiwan Academia Sinica Research Center for Information Technology Innovation Taiwan National Chung Cheng University Department of Computer Science and Information Engineering Taiwan

The rapid development of multi-view videos (MVV) transmission is an irresistible trend. Concurrently, reconfigurable intelligent surface (RIS)-assisted wireless communication has drawn significant attention. We observe that the view selection based on the base station and the view synthesis based on depth-image-based rendering (DIBR) can effectively reduce power consumption. Therefore, this paper studies the view selection and synthesis for RIS-aided MVV in multigroup multicast beamforming. To deal with this complicated scenario, we investigate a problem, named the joint View selection, Multicast beamforming, and DIBR (JVMD), to minimize the total multicast beamforming power, the view transmission operation power, and view synthesis, subject to quality-of-service (QoS), RIS phase shifts, view selection, and DIBR constraints. Unfortunately, the mathematical model is a complicated mixed discrete-continuous optimization problem. To tackle this challenging problem, we designed an algorithm, named View selection, Beamforming, RIS phase, and DIBR (VBRD) algorithm. First, we deal with the discrete optimization problem of selecting the view. VBRD uses the dual-based approximation methodology to round back a primal's integer solution. Then, in the continuous optimization problem, we apply the alternating optimization (AO) method to determine beamforming, RIS phase, and DIBR. Finally, simulation results show the performance of exploiting view synthesis for RIS-assisted wireless communication. © 2002-2012 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

A Secure Fingerprint Transmission Protocol for Insecure Communication Channels 1

引用

2nd International Conference on Intelligent Computing Systems and Applications, ICICSA 2023

作者： Singh, Laiphrakpam Dolendro Arshad Ahmed, Md. Louis, Teresa Ali, Azad Thounaojam, Dalton Meitei Patgiri, Ripon Singh, Khoirom Motilal Department of Computer Science and Engineering National Institute of Technology Silchar Silchar India Department of CSE Indian Institute of Information Technology Manipur Senapati India

ISBN: (数字)9789819754120

ISBN: (纸本)9789819754113

A fingerprint is a recognizable pattern of ridges and valleys on a person’s finger surface. A person’s fingerprints are distinct and unchangeable throughout a person’s life unless distorted through external injury. The fingerprint is one of the most commonly utilized biometric identification techniques. As fingerprints are used in realistic authentication, securing fingerprints is a paramount concern. Moreover, enciphering the whole fingerprint image collected through a fingerprint scanner would require extensive computation. Research has shown that minutiae points are used to determine the uniqueness of a fingerprint. A method is proposed to store and transmit fingerprint data securely. The proposed technique enciphers only the internal angles subtended by the relevant minutiae points and the information about the type of minutiae points. The proposed techniques reduce the computation involved as only the internal angles information and type of minutiae points are enciphered rather than the whole scanned fingerprint image. Statistical and security analyses conducted on the cipher data suggest the proposed encryption is secure. A digital signature is incorporated while transmitting the fingerprint information, thereby maintaining the data integrity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Forward and Backward Contact Tracing in Body Area Networks Using Blockchain 2

Privacy-Preserving Forward and Backward Contact Tracing in B...

引用

2nd IEEE International Conference on Data, Decision and Systems, ICDDS 2023

ISBN: (纸本)9798350314168

Preventing the outbreak of any pandemic like Covid-19 is a challenging task. Contact tracing is a technique where all the people who have come in close proximity of a given person is found. Contact tracing is classified into two types: forward contact tracing and backward contact tracing. Forward contact tracing finds all the people who have come in touch with a specific Covid positive person after a specific time. Backward contact tracing finds all the people who had come in touch with the specific Covid positive person before a specific time. Forward contact tracing helps to find the users who are at high risk of getting infected. Backward contact tracing helps to find asymptotic infected person who in turn had come in touch with several other persons who needs to be traced. Backward contact tracing also helps to identify asymptotic super-spreader who has caused several new infections. We have proposed a privacy preserving forward and backward contact tracing scheme for body area network (BAN) users using blockchain. Here, the inter-BAN communications are recorded in the form of adjacency matrix which is a suitable data structure for contact tracing. The blocks that contain the all the encrypted interban communication records, in the blockchain, within a given time window, are retrieved by the miner and the necessary tuples in the adjacency matrices in the blocks are returned to the trusted authority. Trusted authority decrypts the adjacency matrix row elements and returns the valid user ids to the public administration. Security of the proposed scheme has been analyzed against common attacks and verified using AVISPA tool. Simulation based computational overhead of the BAN users has also been reported. © 2023 IEEE.

关键词： Blockchain

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：