检索结果-内蒙古大学图书馆

Emerging Trends in Information technology and Engineering (ic-ETITE), Conference on

作者： Leo Dencelin Xavier Ramkumar Thirunavukarasu Department of Computer Science & Engineering Satyabhama Institute of Science and Technology Chennai India Associate Professor and Head School of Information Technology and Engineering VIT Vellore India

ISBN: (数字)9781728141428

ISBN: (纸本)9781728141435

Prediction based language models are considered as one of the major concepts in Natural Language processing which gains knowledge from unstructured text data. Extracting insights from sequential data such as biological sequences is an important problem in genomics, proteomics and classifying the secondary structures of protein, helps the researchers in aiding to understand protein functions. This is considered as one of the important preliminaries of Drug development. Traditional techniques such as sequential models, probabilistic techniques and statistical approaches were widely applied in structure prediction which extracts insights from sequence of amino acid. However, handheld feature extraction becomes a tedious task, which eventually leads to less accuracy. Our novel approach creates vectors using word embeddings which is assumed to consider contextual information of amino acids thereby improving the accuracy of secondary structure prediction approach. This is considered as an optimistic solution for secondary structure prediction problem. In this approach a variation of word embeddings - Continuous Bag of Words (CBOW) method is proposed which retains the sequential information of all amino acid in the protein chain. This vector is used as input features of Deep Neural Network classifier and class labels are classified into Helix, Sheet, Coil. We have tested this NLP based approach on GenBank dataset. The infrastructure required for this analysis was leveraged from Google Colab.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiagent Reinforcement Learning for Integrated Network: Applying to a Part of the Road Network of Krasnoyarsk City

Multiagent Reinforcement Learning for Integrated Network: Ap...

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Timofei I. Tislenko Daria V. Semenova Nataly A. Sergeeva Elena E. Goldenok Nadezhda V. Kononova School of Mathematics and Computer Science Siberian Federal University Krasnoyarsk Russian Federation Analytics Groups LLC «R.D.Science» Krasnoyarsk Russian Federation Department of Medical Cybernetics and Informatics Krasnoyarsk State Medical University Named After Professor V.F. Voyno- Yasenetsky Name of Organization Krasnoyarsk Russian Federation School of Space and Information Technology Siberian Federal University Krasnoyarsk Russian Federation

ISBN: (纸本)9781665451635

The article examines a mathematical model of the selecting phases process of traffic light facilities of the road network section. A Markov decision process with a finite number of actions and states is used as a mathematical model, and the minimization problem is reduced to the Multiagent Reinforcement Learning for Integrated Network (MARLIN) problem. A Q-learning algorithm was implemented and a series of computational experiments were conducted in the Anylogic simulation system for a real section of the Krasnoyarsk road network to study the model.

关键词： Q-learning Roads Computational modeling Urban areas Process control Traffic control Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Feeling Recognition by Facial Expression Using Deep Learning

引用

Journal of Physics: Conference Series 2021年第1期1717卷

作者： Dr. Shalini Gupta Dr. Shubha Jain Associate Professor Computer Science and Engineering Department Kanpur Institute of Technology KANPUR Associate Professor Computer Science and Engineering Department Axis Institute of Technology and Management KANPUR

The visible appearance of the emotion state, personality, purpose, psychological feature activity and psychopathology of an individual is the Facial expression. This plays an outgoing role in social affairs. Automatic recognition of facial expressions will be a vital part of natural human-machine interfaces. It should even be applied in activity science and in clinical apply. Fellows in nurturing automatic facial features Recognition system must perform detection and placement of faces during a disordered scene, facial feature extraction and facial features classification. Emotion recognition by facial features utilizes a Deep Learning system, which is enforced victimization Convolution Neural Network (CNN). The CNN model of the project relies on LeNet design. Kaggle facial features dataset with seven facial features labels as fear, anger, happy, surprise, sad, neutral and disgust is employed during this project. The system achieved 60.37 accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to choose an appropriate initial condition to simulate stochastic differential equations stably

引用

AIP Conference Proceedings 2024年第1期3094卷

作者： Guoguo Yang Kevin Burrage Pamela Burarge Xiaohua Ding LMAM and School of Mathematical Sciences Peking University Beijing China School of Mathematical Sciences Queensland University of Technology Brisbane Australia. Department of Computer Science University of Oxford Oxford UK (Visiting Professor). Department of Mathematics Harbin Institute of Technology Weihai China

A method for choosing an appropriate initial condition to simulate stochastic differential equations stably is proposed. We apply Lyapunov stability and asymptotic stability theories to show how to choose initial conditions without causing blow up of numerical simulations, and carry out specific analysis through the stochastic nonlinear Kubo oscillator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modified Chorological Coded Data Compression Methodology for Wireless Sensor Networks

引用

Journal of Physics: Conference Series 2021年第1期1770卷

作者： S. Jancy Suji Helen Mercy Paul Selven A. Viji Amutha Mary M.D Antopraveena M.S. Roobini Assistant Professor Department of Computer Science and Engineering Sathyabama Institute of Science and Technology ChennaiIndia Associate Professor Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

Wireless Sensor Network (WSN) is a fast evolving current technology which is being employed in various applications. Despite its wide usage, WSNs have a few challenges to overcome to be called as an ideal technology. Some of the challenges are battery life time, memory storage and deployment issues. Batteries are the primary source of power supply to WSN and one of the major challenges is the energy constraint. This paper aims to propose a few techniques to better the energy efficiency of the sensor networks by saving sensor energy using data compression methodology. In this paper, a modified chorological coded data compression methodology is proposed (MCDC). This algorithm deals with assigning the sequence value to the given input information. If the assigned sequence value is a double digit number, it is converted in to single digit number. Double digit numbers and single digit numbers are combined. Separate location tables are generated for all double digit and single digit numbers. This procedure continues until all the sequence values are changed in to single digit number. Then the final single digit is assign with an equivalent Sequence Code (SC). MCDC algorithm is compared with DELTA compression and RUNLENGTH compression and a better compression ratio was achieved when compared with DELTA compression and RUNLENGTH compression algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical analysis of online learning through cloud environment in higher education institutions using R Programming during COVID-19

引用

AIP Conference Proceedings 2022年第1期2516卷

作者： Ananthi Claral Mary T. Arul Leena Rose P. J. Armstrong Doss D. 1Research Scholar Associate Professor Department of Computer Science College of Science & Humanities SRM Institute of Science & Technology Chengalpattu India 2Research Scholar Associate Professor Department of Computer Science College of Science & Humanities SRM Institute of Science & Technology Chengalpattu India 3Head Department of Business Administration Madras Christian College Chennai India

Online learning through cloud platforms takes place on the cloud – a virtual space that is not tied to any computer. The cloud-based learning management systems bring vast benefits at all educational levels. These systems provide a powerful teaching tool. More educators are adopting them as their main learning management system, and students find them very intuitive to use. An online learning system based on cloud computing infrastructure is possible and it can significantly progress the effectiveness of investment that can make this system into a righteous path and accomplish a win-win situation for students and teachers. This online study comprises of several segments, namely, demographic details of the students, their usage of smart devices, device ownership, device connectivity and number of hours the device is connected in online. It consists of approximately 360 respondents. The statistical analysis was performed using R programming. The results indicated that most of the respondents utilize smartphones to access online classes through cloud platform. During pandemic circumstances the smart devices facilitated faculties and students of higher education sectors to teach and learn their subjects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure K-NN Query on Encrypted Cloud Data with Multiple Keys

引用

Journal of Physics: Conference Series 2021年第1期1770卷

作者： R. Vignesh D. Deepa Suja Cherukullath Mana B. Keerthi Samhitha Assistant Professor Department of Computer Science and Engineering Sathyabama Institute of Science and Technology

Cloud computing has become an undeniably famous assistance for its adaptability and versatility, which rouses numerous associations, foundations and organizations to want to re-appropriate data administrations to cloud stage. Simultaneously, much consideration has been paid to adapt to the extraordinary security and protection issues in recloud cloud. The general methodology is to scramble data by the data owner (DO) before re-appropriating; the approved query user play out an unpredictable arrangement of encryption and decoding tasks during question execution. In any case, the above plans have accepted that the question clients are completely trusted and have the entrance to the key for scrambling and unscrambling recloud data. It will achieve a few issues in reality. So we propose a novel plan for secure KNN inquiry on encoded cloud data with various keys, in which the data owner and each question client all hold their own various keys, and don't impart them to one another; in the interim, the data owner scrambles and decodes re-appropriated data utilizing the key of his own. Our plan is built by set of conventions to jelly the data classification and question over scrambled cloud data without key-sharing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inferring the 3D Standing Spine Posture from 2D Radiographs

arXiv

引用

arXiv 2020年

作者： Bayat, Amirhossein Sekuboyina, Anjany Paetzold, Johannes C. Payer, Christian Stern, Darko Urschler, Martin Kirschke, Jan S. Menze, Bjoern H. Department of Informatics Technical University of Munich Germany Department of Neuroradiology Klinikum rechts der Isar Germany Institute of Computer Graphics and Vision Graz University of Technology Austria School of Computer Science University of Auckland New Zealand

The treatment of degenerative spinal disorders requires an understanding of the individual spinal anatomy and curvature in 3D. An upright spinal pose (i.e. standing) under natural weight bearing is crucial for such bio-mechanical analysis. 3D volumetric imaging modalities (e.g. CT and MRI) are performed in patients lying down. On the other hand, radiographs are captured in an upright pose, but result in 2D projections. This work aims to integrate the two realms, i.e. it combines the upright spinal curvature from radiographs with the 3D vertebral shape from CT imaging for synthesizing an upright 3D model of spine, loaded naturally. Specifically, we propose a novel neural network architecture working vertebra-wise, termed TransVert, which takes orthogonal 2D radiographs and infers the spine’s 3D posture. We validate our architecture on digitally reconstructed radiographs, achieving a 3D reconstruction Dice of 95.52%, indicating an almost perfect 2D-to-3D domain translation. Deploying our model on clinical radiographs, we successfully synthesise full-3D, upright, patient-specific spine models for the first time. Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Deep Learning for Weapon Identification in Security Systems

引用

Journal of Physics: Conference Series 2021年第1期2089卷

作者： Makkena Brahmaiah Srinivasa Rao Madala Ch Mastan Chowdary M.Tech. Scholar Department of Computer Science and Engineering Professor & HOD Department of Computer Science and Engineering Asst. Professor Department of Computer Science and Engineering PACE Institute of Technology and Sciences

As crime rates rise at large events and possibly lonely places, security is always a top concern in every field. A wide range of issues may be solved with the use of computer vision, including anomalous detection and monitoring. Intelligence monitoring is becoming more dependent on video surveillance systems that can recognise and analyse scene and anomaly occurrences. Using SSD and Faster RCNN techniques, this paper provides automated gun (or weapon) identification. Use of two different kinds of datasets is included in the proposed approach. As opposed to the first dataset, the second one comprises pictures that have been manually tagged. However, the trade-off between speed and precision in real-world situations determines whether or not each method will be useful.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Click Fraud Detection Approaches to analyze the Ad Clicks Performed by Malicious Code

引用

Journal of Physics: Conference Series 2021年第1期2089卷

作者： Mahesh Bathula Rama Chaithanya Tanguturi Srinivasa Rao Madala M.Tech. Scholar Department of Computer Science and Engineering PACE Institute of Technology and Sciences Professor Department of Computer Science and Engineering PACE Institute of Technology and Sciences Professor & HOD Department of Computer Science and Engineering PACE Institute of Technology and Sciences

Mobile PR is an important component of the mobile app ecosystem. A major threat to this ecosystem's long-term health is click fraud, which involves clicking on ads while infected with malware or using an automated bot to do it for you. The methods used to identify click fraud now focus on looking at server requests. Although these methods have the potential to produce huge numbers of false negatives, they may easily be avoided if clicks are hidden behind proxies or distributed globally. AdSherlock is a customer-side (inside the app) efficient and deployable click fraud detection system for mobile applications that we provide in this work. AdSherlock separates the computationally expensive click request identification procedures into an offline and online approach. AdSherlock uses URL (Uniform Resource Locator) tokenization in the Offline phase to create accurate and probabilistic patterns. These models are used to identify click requests online, and an ad request tree model is used to detect click fraud after that. In order to develop and evaluate the AdSherlock prototype, we utilise actual applications. It injects the online detector directly into an executable software package using binary instrumentation technology (BIT). The findings show that AdSherlock outperforms current state-of-the-art methods for detecting click fraud with little false positives. Advertisement requests identification, mobile advertising fraud detection are some of the keywords used in this article.

关键词：

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：