检索结果-内蒙古大学图书馆

Forecasting air pollution load in Delhi using data analysis tools

Procedia computer science 2018年 132卷 1077-1085页

作者： Nidhi Sharma Shweta Taneja Vaishali Sagar Arshita Bhatt Associate Professor Deptt. of Applied Chemistry Bhagwan Parshuram Instt. Of Technology Rohini New Delhi-110085 Assistant Professor Deptt. of Computer Science Bhagwan Parshuram Instt. Of Technology Rohini New Delhi-110085

The enormity of air pollution has always been a matter of concern due to rapid development and urbanization over a long period. The increasing level of pollutants in ambient air in 2016-2017 has deteriorated the air quality of Delhi at an alarming rate. This brought us to focus our study on air quality in Delhi region. The prediction of future air quality has been carried out by analyzing the pollutants using data analysis techniques. In our previous study, we had analyzed the data from 2011-2015. Detailed analysis from 2009-2017 of air pollutants has been proposed in this extended paper along with the critical observation of 2016-2017 air pollutants trend in Delhi. Descriptive analysis and predictive analysis have been used to study the trends of various air pollutants like sulphur dioxide (SO 2 ), nitrogen dioxide (NO 2 ), suspended particulate matter (PM), ozone (O 3 ) carbon monoxide (CO), benzene, and forecast the future trend. We have observed through data analytics techniques that SO 2 is likely to increase by 1.24ug/m 3 , NO 2 is likely to increase by 16.77ug/m 3 , O3 is likely to increase by 6.11 mg/m 3 , benzene is likely to reduce by 1.33 mg/m 3 and NO 2 is predicted to reduce by 0.169 mg/m 3 in the coming years.

关键词： Air pollution Ambient air Descriptive analysis Predictive analysis Time series regression forecasting

来源：评论

学校读者我要写书评

暂无评论

Plane-based surface regularization for urban 3D reconstruction 28

Plane-based surface regularization for urban 3D reconstructi...

引用

28th British Machine Vision Conference, BMVC 2017

作者： Holzmann, Thomas Oswald, Martin R. Pollefeys, Marc Fraundorfer, Friedrich Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Department of Computer Science ETH Zurich Zurich Switzerland Microsoft Redmond United States

ISBN: (纸本)190172560X

We propose a method for urban 3D reconstruction that is a hybrid between a volumetric 3D reconstruction approach and a plane fitting approach in order to obtain a denoised and compact representation of the scene. In our hybrid approach, a single global optimization, using visibility as main information, defines whether the final reconstructed surface should align with a detected plane or rather follow the details of the input data. Our method is based on an established tetrahedral occupancy labeling approach which we taylor for urban reconstruction by adding the possibility to favor an alignment of the surface with detected planes. We further add novel regularization terms that favor Manhattan-like structures and which allow to control the level of detail of the output model. A variety of experiments demonstrate state-of-the-art performance and show that our approach is suitable for both indoor and outdoor environments. © 2017. The copyright of this document resides with its authors.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

An IoT Based Gradient Descent Approach for Precision Crop Suggestion using MLP

引用

Journal of Physics: Conference Series 2019年第1期1362卷

作者： P. Kanaga Priya N. Yuvaraj PG Student Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Associate Professor Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

Agriculture plays a prime role in providing food to a massive population. It has a predominant role in improving the economic development of our nation. In recent days due to the changes in weather pattern, the crop cultivation has become the greatest challenge. This directly or indirectly affects the productivity of the crops. Hence to overcome from this and to the improve productivity of the crops new technologies can be brought up for usage. The usage of these new technologies will convert traditional farming practices into precision farming. The new technology specified here includes the data analysis and Internet of Things (IoT). As it is revealed that it improves the productivity of the crops by maintaining the finest crop health. Although changes had been adopted in the recent agricultural practices the major issue yet not gets resolved. One such main issue yet to be resolved is cultivating precise crop at the precise time. This can be done with the help of deep learning algorithm such as Artificial Neural Network (ANN), which is found to be an effective one for predicting the precise crop. Hence the proposed system aims at helping the farmers by providing valuable insights to them. These insights can be driven with the help of parameters such as soil moisture level, humidity, temperature and pH collected from the sensors using IoT. In addition to these other parameters include soil type, land type, and the area sown. The crop prediction Graphical User Interface (GUI) system will take these valuable inputs and give suggestions using the crop suggestion user interface. The prediction is made using the Deep Neural Network (DNN) which predicts about the crop to be get cultivated, fertilizer to be used, production range etc. The crop suggestion system greatly helps the farmers to take a valuable decision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Model for Earlier Prediction of Cardiac Functionalities Using Multilayer Perceptron

引用

Journal of Physics: Conference Series 2019年第1期1362卷

作者： Sivaranjani, R Yuvaraj, DrN PG Student Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Associate Professor Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

Cardiovascular Disease is the silent killer and it is one of the leading cause for global death annually. The percentage of premature death varies from 7% in high-income countries and 43% in low-income countries. It is mainly due to lifestyle changing factors such as obesity, diabetes, etc. While working to reduce earlier deaths, it is revealed, how important the earlier prediction of heart disease is. In the medical field, diagnosing heart disease earlier is a difficult task for medical practitioner since it depends on combining clinical and pathological data. The purpose of this paper is to implement a medical prediction support system for predicting cardiac disease. Deep learning approach based computational model is designed for diagnosis. This proposed system has three main steps. First, a dataset with 13 attributes (13 clinical features) from the website is collected. Second, the datasets are trained using an algorithm called artificial neural network with backpropagation technique. It can have one or more hidden layers in order to get higher accuracy. Finally, Cardiac Function Prediction System (CFPS) which is an interactive GUI is developed, where the user can enter the clinical features and get to know the current status of a patient’s health. This system enhances medical care and reduces the treatment cost. This system will act as a promising tool for the medical practitioner for proper diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Chatbot Model to Enhance the Emotion Detection in social media using Bi-directional Recurrent Neural Network

引用

Journal of Physics: Conference Series 2019年第1期1362卷

作者： M. Balaji N. Yuvaraj PG Student Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Associate Professor Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

A Chatbot is like a digital assistant, can be pretrained or have self learning capability. It can be trained to understand the user queries and respond in natural language of the user during a conversation. Chatbot can actively help human to involve in a digital conversation since it can make use of the natural language processing. The existing Chatbot enhances the communication but it does not improvise the information when it is needed. And sometimes they go beyond the topic during conversation which is a major drawback. The proposed bot could identify the emotional status of the users and can provide suggestions using Bi-directional Recurrent Neural Network and tensor flow library functions. The popularity of the chat bots lets our system to be used for much variety of applications. These chat bots be used to automate the various fields like e-learning, e-government and web based models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effective Credit Card Forgery Prevention Using Multilevel Authentication

引用

IOP Conference Series: Materials science and Engineering 2019年第1期590卷

作者： M. Ajay Chowdary M. Kundan A. Viji Amutha Mary U.G Student Department of Computer Science & Engineering Sathyabama Institute of Science and Technology Chennai India U.G Student Department of Computer Science & Engineering Sathyabama Institute of Science and Technology Chennai India Assistant Professor Department of Computer Science & Engineering Sathyabama Institute of Science and Technology Chennai India

In the present system, credit card forgery is frequently happening, there is no big security is implemented at all. In the proposing system, Multi level security is implemented. It includes the Hex Keypad, GPS, and RFID. The secure information inside can be further secured with secondary system that consisting of formal fingerprint scanner. Modifying process is our Implementation, rather having multiple sensors integrated output in one process, which is actually time consuming, and we implement RFID with Keypad Matrix. POS based payment system. OTP is also verified from the Android application of the user so as to track the location of original user. Payment is made to the receiver only if both the User's Card & Mobile are in the same location. This system will avoid payment made by the attackers when Credit card is lost or when your details are hacked.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a module for broadband detection of digital transmissions for a radio broadcast monitoring system using parallel computing means

引用

IOP Conference Series: Materials science and Engineering 2021年第1期1047卷

作者： A N Sokolova E V Soboleva M M Nimatulaev M V Petukhova Department of Applied Mathematics and Computer Science Vyatka State University Kirov Russia Department of Digital Technologies in Education Vyatka State University Kirov Russia Department of Business Informatics Financial University under the Government of the Russian Federation Moscow Russia Associate Professor of the Department of Information Technology in the Agro-Industrial Complex Russian State Agrarian University–Moscow Timiryazev Agricultural Academy Moscow Russia

Short-wave communication is a means of trunk, zone, mobile and industrial communication for general and departmental use. Taking into account its technical potential, economic efficiency, strategic role as a necessary reserve, the task of monitoring the use of radio frequency resources in the short-wave range remains relevant. The main problem is the search for digital modes of transmission in the entire shortwave band. The purpose of the study is to develop a module for broadband signal detection operating in real time and integrate it into an operating radio monitoring system. The methodology of the work includes an analysis of the literature of foreign and domestic authors on solving monitoring problems, methods for detecting signals in the short-wave range; method of systematization and generalization of facts about the problems of choosing software and hardware for broadband signal detection. The features of short-wave communication have been studied, and the choice of comparison of signals has been made in this paper. The choice was made taking into account the computational complexity of the algorithms. Modules of broadband and narrowband signal detectors have been developed, the places of their integration into the existing radio monitoring system, as well as interfaces for their interaction, have been determined. During the pilot industrial operation the developed modules effectively coped with the solution of the problems of radio monitoring of the short-wave range in real time, so appropriate conclusions are formulated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Firefly Based Optimization in Web Page Recommendation System

Firefly Based Optimization in Web Page Recommendation System

引用

International Conference on Communication, Computing and Internet of Things (IC3IoT)

作者： Vasanth Muralikrishnan Bhavithra Janakiraman II M.E CSE Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Pollachi Assistant Professor (SS) Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Pollachi

ISBN: (纸本)9781538624609;9781538624593

the personalized web page recommendation for individuals is evident these days. Web servers are loaded with recommendation systems that analyze and recommend web pages to the users. They use data that are implicitly obtained as a result of web browsing patterns of the uses for recommending web pages. The cluster based association rule mining based system collects the web logs and generates a cluster of similar users and recommends pages to the users by actively analyzing them in the online. However, the time for analyzing it in online is more. To optimize this and increase the accuracy of the recommendation systems, a method that applies Naïve Bayes technique for clustering and firefly algorithm based similarity measure for optimization is designed. Web logs are initially clustered in offline by Naïve Bayes clustering technique. To find the similarity between the active user queries with other users in the same cluster in online, firefly algorithm based similarity measure is used. Firefly algorithm meticulously searches the generated cluster of web logs of the active user and recommends top pages. Firefly algorithm utilizes time efficiently, thus it is used for processing in online. When web pages are obtained, they are ranked and the top pages that are more relevant to the query are recommended. Efficiency of the system is evaluated using the measures like precision, recall, f - score, Matthews correlation and fallout rate. Experimental evaluation with real data set shows that the proposed system produced better recommendations and uses less time for computation in online.

关键词： Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A Genetic Algorithm Based Approach for Hindi Word Sense Disambiguation

A Genetic Algorithm Based Approach for Hindi Word Sense Disa...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Anidhya Athaiya Deepa Modi Gunjan Pareek M.Tech Scholar Department of Computer Science and Engineering wami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan Assistant Professor Department of Computer Science and Engineering Swami Keshvanand Institute of Technology Management & Gramothan Jaipur Rajasthan

ISBN: (纸本)9781538647660

Word Sense Disambiguation (WSD) is the procedure of selecting precise sense or meaning for a word in a given context. Word sense disambiguation goes about as an establishment to different AI applications as data mining, information recovery, and machine interpretation. The issue solicits to figure out which sense from the polysemous word is appropriate in a given context. Previously a few methodologies have been proposed for WSD in English, German and so forth, however, work on WSD in Hindi is limited. In this work, a genetic algorithm based approach is presented for Hindi WSD. The feature of dynamic setting window is used which contains left and right expression of a vague word. The cardinal supposition of this approach is that the target word must have a common topic in its neighborhood. For finding all possible senses of an ambiguous word, WordNet created by IIT Bombay is used.

关键词： Genetic algorithms Sociology Statistics Biological cells Microsoft Windows Conferences Testing

来源：评论

学校读者我要写书评

暂无评论

Analysis of KNN Algorithm with Mapreduce Technique on Big Data

引用

IOP Conference Series: Materials science and Engineering 2019年第1期590卷

作者： Tatikonda Bhavana J. Padmavathy R. Sethuraman J.K. Jeevitha UG Scholar Sathyabama Institute of Science and Technology Chennai. Assistant Professor Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai. Assistant Professor PSNA College Engineering and Technology

Due the fast growth of new technology application like social media analysis, web data analysis and medical information network analysis, here the various types of data are processed frequently. The large amount of effective data management and analysis is very vital goal. To reduce the data processing complexity, time complexity, and space complexity in Big Data, the paper going to propose the k-nearest neighbor join (KNN) operation. KNN is used to find the K nearest points in S. It is a computational task that will handle the large range of applications such as knowledge discovery or data mining. When the volume and the dimension of data increases, then only distributed approaches can perform the big operations in a given time. Recent works have done on implementing the efficient solutions using the map reduce programming model because it is used for distributing the large scale data processing. Although these works provide different solutions for the same problem, each one has particular constraints and properties. This paper compares the existing of different computation of KNN on MapReduce. First the paper compares the solutions in to three steps for KNN computation on MapReduce: 1) Data processing, 2) Data partitioning and 3) Computation. The Experiment in this paper explains the variety of different data sets, and analyzes the data volume, data dimension and the value of k from many perspectives like time and space complexity, and accuracy.

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：