检索结果-内蒙古大学图书馆

Deepq: Residue analysis of localization images in large scale solid state physical environments

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2022年第1期2393卷

作者： S. Manikandan K. S. R. Radhika M. P. Thiruvenkatasuresh G. Sivakumar 1Department of Information Technology E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India 2Computer Science and Engineering SRKR Engineering College Bhmavaram Andhra Pradesh India 3Dept. of Computer Science and Engineering Erode Sengunthar Engineering College ErodeTamilnadu India

Deep Learning is the process to led machine learning, natural language processing and neural networks. The various deep learning models, computer vision systems and artificial intelligence services are used to study of various real time applications. Due to lack of computing resource the conventional neural network are produces delay in progress and reduce the GPUs performance and throughput. In this paper we review difference deep learning approaches with increases GPUs performance and apply various image processing classification and localization techniques. The high availability and GPUs performance can be verified by state-of-arts results using conventional deep learning methods.

关键词：

Task-Oriented Multi-User Semantic Communications

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xie, Huiqiang Qin, Zhijin Tao, Xiaoming Letaief, Khaled B. School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Peng Cheng Laboratory Shenzhen518066 China

While semantic communications have shown the potential in the case of single-modal single-users, its applications to the multi-user scenario remain limited. In this paper, we investigate deep learning (DL) based multi-user semantic communication systems for transmitting single-modal data and multimodal data, respectively. We will adopt three intelligent tasks, including, image retrieval, machine translation, and visual question answering (VQA) as the transmission goal of semantic communication systems. We will then propose a Transformer based unique framework to unify the structure of transmitters for different tasks. For the single-modal multi-user system, we will propose two Transformer based models, named, DeepSC-IR and DeepSC-MT, to perform image retrieval and machine translation, respectively. In this case, DeepSC-IR is trained to optimize the distance in embedding space between images and DeepSC-MT is trained to minimize the semantic errors by recovering the semantic meaning of sentences. For the multimodal multi-user system, we develop a Transformer enabled model, named, DeepSC-VQA, for the VQA task by extracting text-image information at the transmitters and fusing it at the receiver. In particular, a novel layer-wise Transformer is designed to help fuse multimodal data by adding connection between each of the encoder and decoder layers. Numerical results will show that the proposed models are superior to traditional communications in terms of the robustness to channels, computational complexity, transmission delay, and the task-execution performance at various task-specific metrics. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Multi-label classification via adaptive resonance theory-based clustering

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Masuyama, Naoki Nojima, Yusuke Loo, Chu Kiong Ishibuchi, Hisao Graduate School of Engineering Osaka Prefecture University 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

—This paper proposes a multi-label classification algorithm capable of continual learning by applying an Adaptive Resonance Theory (ART)-based clustering algorithm and the Bayesian approach for label probability computation. The ART-based clustering algorithm adaptively and continually generates prototype nodes corresponding to given data, and the generated nodes are used as classifiers. The label probability computation independently counts the number of label appearances for each class and calculates the Bayesian probabilities. Thus, the label probability computation can cope with an increase in the number of labels. Experimental results with synthetic and real-world multi-label datasets show that the proposed algorithm has competitive classification performance to other well-known algorithms while realizing continual learning. © 2021, CC BY-NC-ND.

关键词： Classification (of information)

Design implementation of smart fish pond monitoring system using IoT

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2523卷

作者： S. V. Tresa Sangeetha P. G. Kuppusamy V. Chandrasekaran A. Sangeerani Devi 1Department of Engineering University of Technology and Applied Science-Al Mudabah Muladdah South Batinah Sultanate of Oman. 2Department of Electronics and Communication Engineering Siddharth Institute of Engineering and Technology Puttur Andhra Pradesh India 3Department of Medical Electronics Velalar College of Engineering and Technology Thindal Tamil Nadu India 4Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India

The present approach aims to provide safe and safe production of high-quality seafood by keeping regular levels of water in the fish tank by helping fish pool owners. The flow of high or low water into the fish pond solves the problem of killing fish in a fish tank for the long term. Every grade of water can impact animal health alone. The water flow in fish ponds describes how to check it every day. We need to check the parameters of the water on a regular basis. It symbolizes high water quality standards and bad water quality ponds and how they need to be improved. It is advised that the precondition for increasing output should be given priority to guarantee sustained fresh quality. Water quality parameters therefore maintain a balance; culture is the cornerstone for living creatures' health and growth. The water quality metrics should be monitored and evaluated regularly.

关键词：

Custom written sentiment analysis supported Twitter data

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2022年第1期2464卷

作者： M. Nithya M. Pachhaiammal Priya V. Lalitha S. Samundeswari 1Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India 2Department of Computer Science and Engineering Sri Sairam Institute of Technology Chennai India 3Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India 4)Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India

This paper helps to make the created Twitter Data more understandable. It streams real-time tweets, or can fetch tweets from specific topics or keywords. It then analyses the data using a custom-written sentiment analysis algorithm, and eventually displays the results with a series of dynamic *** data visualizations. It has a wide range of uses, for analyzing the effectiveness so for marketing campaign, to compare two competing topics.

关键词：

Use of agile software development method to manage academic resources

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2022年第1期2481卷

作者： Anupriya Sharma Ghai Divya Kapil Lakshita Sejwal Atika Gupta Swati Devliyal 1Department of Computer Applications Graphic Era Hill University Dehradun India 2Department of Computer Science & Engineering KCC Institute of Technology & Management Noida India 3Department of Computer Science and Engineering Graphic Era University Dehradun India

Agile is a method that moves quickly, lightly, and approachable in developing a software process. The primary goal of agile methodology is to produce high-quality software in a quicker time. It is using this methodology for developing the Academic Resource in a system provided by software for maintaining academic and financial records of data efficiently and conveniently. The administration of any academic association must make records of students registered and the staff of the university on paper and keep them safe, which is a tedious task due to the increase in manual work that reduced the utilization of the efficiency of staff. This paper describes a systematic approach to developing a user-friendly, flexible, and easy-to-maintain environment for academic resources using agile's extreme programming. The execution of the different tasks to develop the system is used to widen the horizons in Agile Methodologies step by step.

关键词：

Novel method of Braille-based system for visually impaired people

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2022年第1期2519卷

作者： X. S. Asha Shiny K. Vanisree P. Sivakumar J. Lenin 1Department of Computer Science and Engineering Nalla Malla Reddy Engineering College Hyderabad Telangana India 2Department of Electronics and Communication Engineering Samskruti College of Engineering and Technology Telangana India 3Department of Electronics and Communication Engineering GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India 4Department of Information Technology Al Musanna College of Technology Muladdah Muscat Sultanate of Oman

This work mainly aims to solve many problems in communicating in the lives of a person with vision impairment. Most of us face India today as the home for the biggest number of blind people in the world. Day by day, technology is mostly developed in mobile communication, which has an important function to play. Only visually challenged persons can read the message on the touch screen of the display in the messaging application. However, the system quality is not acceptable since the blind persons are unable to properly distinguish the text. Braille technology is still utilised for reading purposes solely by the blinds. In our method of reading and answering messages from visually challenged persons utilising our Braille system. Blind persons can reach the messaging application on mobile phones like ordinary people with Braille technology. At the same time, keypads employing one message per user can deliver the information via Message simply based on the keypad selections. This technology allows untrained individuals to utilise the messaging application on a mobile system and then to utilise GSM to communicate with Easily Blind People.

关键词：

Reconfigurable Massive MIMO: Harnessing the Power of the Electromagnetic Domain for Enhanced information Transfer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ying, Keke Gao, Zhen Chen, Sheng Gao, Xinyu Matthaiou, Michail Zhang, Rui Schober, Robert The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The Advanced Research Institute of Multidisciplinary Science School of Information and Electronics Beijing Institute of Technology Beijing100081 China The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom The Huawei Technologies Company Ltd. Beijing100085 China The Centre for Wireless Innovation Queen's University Belfast BelfastBT3 9DT United Kingdom The School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China The Shenzhen Research Institute of Big Data China Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore The Institute for Digital Communications Friedrich-Alexander-University Erlangen-Nürnberg Erlangen91054 Germany

The capacity of commercial massive multiple-input multiple-output (mMIMO) systems is constrained by the limited array aperture at the base station, and cannot meet the ever-increasing traffic demands of wireless networks. Given the array aperture, holographic MIMO with infinitesimal antenna spacing can maximize the capacity, but is physically unrealizable. As a promising alternative, reconfigurable mMIMO is proposed to harness the unexploited power of the electromagnetic (EM) domain for enhanced information transfer. Specifically, the reconfigurable pixel antenna technology provides each antenna with an adjustable EM radiation (EMR) pattern, introducing extra degrees of freedom for information transfer in the EM domain. In this article, we present the concept and benefits of availing the EMR domain for mMIMO transmission. Moreover, we propose a viable architecture for reconfigurable mMIMO systems, and the associated system model and downlink precoding are also discussed. In particular, a three-level precoding scheme is proposed, and simulation results verify its considerable spectral and energy efficiency advantages compared to traditional mMIMO systems. Finally, we further discuss the challenges, insights, and prospects of deploying reconfigurable mMIMO, along with the associated hardware, algorithms, and fundamental theory. Copyright © 2023, The Authors. All rights reserved.

关键词： MIMO systems

Binary neural network in robotic manipulation: Flexible object manipulation for humanoid robot using partially binarized auto-encoder on FPGA

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ohara, Satoshi Ogata, Tetsuya Awano, Hiromitsu The Department of Information Systems Engineering Graduate School of Information Science and Technology Osaka University 1-5 Yamadaoka Suita Osaka565-0871 Japan The Department of Intermedia Art and Science School of Fundamental Science and Engineering Waseda University 3-4-1 Ohkubo Shinjuku Tokyo169-8555 Japan The Department of Communication and Computer Engineering Graduate School of Infomatics Kyoto University Yoshida-hon-machi Sakyo Kyoto606-8501 Japan

A neural network based flexible object manipulation system for a humanoid robot on FPGA is proposed. Although the manipulations of flexible objects using robots attract ever increasing attention since these tasks are the basic and essential activities in our daily life, it has been put into practice only recently with the help of deep neural networks. However such systems have relied on GPU accelerators, which cannot be implemented into the space limited robotic body. Although field programmable gate arrays (FPGAs) are known to be energy efficient and suitable for embedded systems, the model size should be drastically reduced since FPGAs have limited on-chip memory. To this end, we propose "partially" binarized deep convolutional auto-encoder technique, where only an encoder part is binarized to compress model size without degrading the inference accuracy. The model implemented on Xilinx ZCU102 achieves 41.1 frames per second with a power consumption of 3.1 W, which corresponds to 10× and 3.7× improvements from the systems implemented on Core i7 6700K and RTX 2080 Ti, respectively. © 2021, CC BY.

关键词： Field programmable gate arrays (FPGA)