检索结果-内蒙古大学图书馆

International Conference on Cutting-edge Technologies in Engineering (ICon-CuTE)

作者： Gaurav Verma Charu Taluja Abhishek Kumar Saxena Academic Consultancy Services Division Center for development of Advanced Computing Mohali India Shri Ramswaroop Memorial University Barabanki India

ISBN: (纸本)9781728100012

This paper presents a combination of K-mean s clustering, SVM and CNN based classification techniques for the crop disease / infection with target as Rice crop. Agricultural crops show variation in features of healthy crops in color, texture and growth. Manual inspection and monitoring of crops is incompatible for large farm sizes so aerial monitoring or camera imaging can prove to be helpful for agriculturists in pre-determination of crop diseases. The use of image processing algorithms involving K-means clustering, Support vector machine and Convolutional Neural Networks enables classification process. The supervised classification techniques involve prior training process which determines the accuracy. The training dataset involved initially with 10 image set which was increased to over 50 to obtain accuracy over 95 percent.

关键词： computer vision crops image classification image texture inspection pattern clustering plant diseases supervised learning support vector machines Support Vector Network crops image texture Semi-supervised Learning Image classification Cluster Analysis images computer vision Taxonomy Plant Diseases Sight Inspection Plant health maladjustment image set

来源：评论

学校读者我要写书评

暂无评论

Trust model for a cloud computing application and service

Trust model for a cloud computing application and service

引用

IEEE International Conference on Computational Intelligence and computing Research

作者： Rizwana A.R. Shaikh M. Sasikumar SIES Graduate School of Technology Nerul Research Scholar NMIMS Mumbai India Center for Development of Advanced Computing Kharghar India

ISBN: (纸本)9781467313421

Cloud computing has attracted great attention due its various features. There are various rising concerns in its growth, one of which is security. Trust between provider and a user is the most important factor to be considered for achieving security, which is also essential to promote the reputation of various cloud providers and their offered services. Here we present a trust based solution in terms of a trust model that can be used to calculate the security strength of a particular cloud service. The trust value acts as a means for selecting any cloud service.

关键词： Cloud computing Security Trust Trust Model

来源：评论

学校读者我要写书评

暂无评论

Attendance System with Emotion Detection: A case study with CNN and OpenCV

Attendance System with Emotion Detection: A case study with ...

引用

Proceedings of the International Conference on Data Science, Machine Learning and Artificial Intelligence

作者： Herman Kandjimi Abhinav Srivastava Hippolyte Muyingi Computer Science Namibia University of Science and Technology Windhoek Namibia Artificial Intelligence Center for Development of Advanced Computing Noida India

ISBN: (纸本)9781450387637

Multinational companies (MNC) take care of employees by taking feedback, in which each day's mood counts as a trivial factor. Traditional and common methods of collecting data are manual and take up employees productive time to complete. There is a solution that can help automate this *** study explores the implementation of Artificial Intelligence (AI) and Machine Learning (ML) models in an automated emotion and attendance system. The system is designed in such a way that companies can generate employee's mood/emotion data by facial recognition through a customized Convolutional Neural Network (CNN) model. The companies can place a camera on the entering and exit of each Block/Floor. Cameras can capture the image and provide input to OpenCV for easy integration and taking attendance. The captured image can further be used for mood detection and store in the database for each employee. The Human Resources (HR) department can track feedback from employee's facial expressions on the same day for social events, hikes, seminars, and new initiatives.

关键词： Artificial Intelligence(AI) Attendance System Convolutional Neural Network(CNN) Machine Learning facial recognition mood/emotion detection

来源：评论

学校读者我要写书评

暂无评论

Controlling an arduino robot using Brain Computer Interface

Controlling an arduino robot using Brain Computer Interface

引用

International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： Parth Gargava Karan Sindwani Sumit Soman Jaypee Institute of Information Technology Noida India VIT University Vellore India Center for Development of Advanced Computing Noida India

The ability to acquire Electroencephalogram (EEG) signals from the brain has led to the development of Brain Computer Interfaces (BCI), which capture signals generated by the physical processes in the brain and use them to control external devices. In this paper, we establish an application to control a robot on the Arduino platform by the use of a BCI system, which does not require training for individual users. We present the design and development of a BCI processing pipeline built on open-source platforms using the Emotiv EEG headset. Our system achieves around 96% accuracy using computationally inexpensive feature extraction and classification techniques, namely, band power and Support Vector Machines (SVM). We are also able to guide a robot's movement efficiently using multiple intents.

关键词： Electroencephalography Feature extraction Robots Brain-computer interfaces Support vector machines Accuracy Band-pass filters

来源：评论

学校读者我要写书评

暂无评论

Using informatics to improve medical device safety and systems thinking

引用

Biomedical Instrumentation and Technology 2014年第Horizons期48卷 38-43页

作者： Witz, Steven Buening, Natalie R. Catlin, Ann Christine Malloy, William Kindsfater, Julie L. Walroth, Todd Washington, Alana Zink, Richard Regenstrief Center for Healthcare Engineering Purdue University West LafayetteIN United States Stanford Hospital and Clinics StanfordCA United States Rosen Center for Advanced Computing Purdue University West LafayetteIN United States RL Roudebush VA Medical Center IndianapolisIN United States Aurora Health Care MilwaukeeWI United States Eskenazi Health IndianapolisIN United States St. Vincent Indianapolis Hospital IndianapolisIN United States CatalyzeCare Development and Implementation Regenstrief Center for Healthcare Engineering Purdue University West LafayetteIN United States

The infusion pump informatics (IPI) system represents an innovative collaboration among a community of practice and researchers at Purdue University; the Rosen center for advanced computing and the Regenstrief center for Healthcare Engineering. This six-year-old decision support system was started to address needs for better management of smart infusion pumps. IPI supports a systems approach to continuous improvement in the safety of medications administered with smart infusion pumps. Its design has been user driven and includes two essential components. The following cases are presented, which were provided by community members, illustrate how IPI is being used to improve performance in areas recommended as priorities for smart infusion pump implementation and use. Although the IPI system has only existed since 2008, the early experiences of members in the community to address issues of mutual benefit by using evidence generated through IPI are promising. The potential for practice improvement could not be practically replicated by a hospital working independently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MemDroid - LSTM Based Malware Detection Framework for Android Devices

MemDroid - LSTM Based Malware Detection Framework for Androi...

引用

IEEE Punecon

作者： Satheesh Kumar Sasidharan Ciza Thomas Cyber Security Group Center for Development of Advanced Computing(CDAC) Thiruvananthapuram India Directorate of Technical Education Govt of Kerala Thiruvananthapuram India

ISBN: (纸本)9781665444804

Android smartphones are very popular today due to its versatile features and cost-effectiveness. The popularity of the gadget has attracted malware writers to target the device for spreading malicious software. A large number of malicious software is being introduced daily into the cyber space intended to attack various Android devices and versions. Detection and classification of Android malware is an important problem for researchers due to the severity of threat that the malware poses to the Android users and their information. In this paper, an Android malware detection framework based on Long Short-Term Memory is proposed. We use the relatively recent Android malware database Androzoo for training the LSTM network. The Android system call sequences for malicious software are traced and converted into feature set vector to model the classifier. The experiment is carried out for different sequence lengths to identify the optimum one in order to achieve the highest detection rate. The proposed framework generates an accuracy of 99.23% for detecting Android malware apps. The result obtained is very promising, compared to similar frameworks. Our research work reiterates that Deep Learning based classifiers are more suitable for malware detection than traditional Machine Learning based models.

关键词： Training Deep learning Databases IEEE Sections Conferences Neural networks Malware

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification by analyzing Dynamic Variations in Gait Sequences

arXiv

引用

arXiv 2020年

作者： Bharadwaj, Sandesh V. Chanda, Kunal Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai600127 India Center for Development of Advanced Computing Kolkata700091 India

Gait recognition is a biometric technology that identifies individuals in a video sequence by analysing their style of walking or limb movement. However, this identification is generally sensitive to appearance changes and conventional feature descriptors such as Gait Energy Image (GEI) lose some of the dynamic information in the gait sequence. Active Energy Image (AEI) focuses more on dynamic motion changes than GEI and is more suited to deal with appearance changes. We proposed a new approach, which allows recognizing people by analysing the dynamic motion variations and identifying people without using a database of predicted changes. In the proposed method, the active energy image is calculated by averaging the difference frames of the silhouette sequence and divided into multiple segments. Affine moment invariants are computed as gait features for each section. Next, matching weights are calculated based on the similarity between extracted features and those in the database. Finally, the subject is identified by the weighted combination of similarities in all segments. The CASIA-B Gait Database is used as the principal dataset for the experimental analysis. Copyright © 2020, The Authors. All rights reserved.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Quality Analysis of Object Oriented Cohesion Metrics

Quality Analysis of Object Oriented Cohesion Metrics

引用

International Conference on the Quality of Information and Communications Technology (QUATIC)

作者： Padmaja Joshi Rushikesh K. Joshi Center for Development of Advanced Computing (C-DAC) Mumbai Computer Science and Engineering Department Indian Institute of Technology Bombay Mumbai India

Numerous class cohesion metrics can be found in the literature. However, they end up capturing different aspects of cohesion. Which metric is best suited for a given situation is always a critical question. This work focuses on exploring the strengths and weaknesses of each of the selected cohesion metrics. The issues of their applicability to capture varying strengths of cohesion and ability to identify disparate classes are addressed. The metrics are classified into five categories based on their computational approaches. Diversity and similarity among these metrics are brought out. The discussion demonstrates uses of cohesion metrics with the help of typical representative situations.

关键词： Measurement units Electronic mail Computer science

来源：评论

学校读者我要写书评

暂无评论

Parallelization of finite volume computations for heat transfer application using unstructured mesh partitioning algorithms

Parallelization of finite volume computations for heat trans...

引用

International Conference on High Performance computing

作者： C. Singh Verma V.C.V. Rao Center for Development of Advanced Computing Pune University Campus Pune India Department of Computer Science University of Minnesota Minneapolis MN USA

An effective parallelization of finite volume computations for heat transfer application using unstructured triangular meshes and mesh partitioning algorithms are presented. The mesh partitioning software (METIS) is employed to create nearly load balanced subdomains and to minimize the interprocessor communications. Efficient data structures are developed to handle the neighboring element information at the interfaces of all subdomains and a simple strategy to overlap the computations to communications has been implemented for improving the performance of the program. The explicit time integration method is used and the results for the rectangular domain and L-shaped domain have been presented. The code (PHEAT2D) is written in Fortran90 and MPI for message passing is used. The algorithm is tested on distributed memory MIMD machine, PARAM OPENFRAME.

关键词： Concurrent computing Heat transfer Application software Temperature control Partitioning algorithms Data structures Computer interfaces Algorithm design and analysis Parallel processing Equations

来源：评论

学校读者我要写书评

暂无评论

Preserving Edge Information in Binary Images

Preserving Edge Information in Binary Images

引用

2008 9th International Conference on Signal Processing(ICSP’2008)

作者： Yumnam Kirani Singh Center for Development of Advanced Computing Plot:E-2/1 Block-GPSalt Lake Electronics Complex Kolkata-91India

In the existing methods of binarization,most edge information is lost and the resulted binary image gets *** carry most of the information in an ***,some techniques for the preservation of edge information in images are proposed and *** are based on the filtering operation by some newly developed edge preserving filters followed by thresholding *** resulted image is a binary image having most of the edges making the binary image more *** proposed method gives better binary image compared to popular method of Otsu's binarization in most of the images.

关键词： Preserving Edge Information in Binary Images

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：