2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)最新文献

Handwritten Form Recognition Using Artificial Neural Network 基于人工神经网络的手写表单识别

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342638

Narayana Darapaneni, Malarvizhi Subramaniyan, Aafia Mariam, Sai Venkateshwaran, Nandini Ravi, A. Paduri, Sumathi Gunasekaran, Asha

{"title":"Handwritten Form Recognition Using Artificial Neural Network","authors":"Narayana Darapaneni, Malarvizhi Subramaniyan, Aafia Mariam, Sai Venkateshwaran, Nandini Ravi, A. Paduri, Sumathi Gunasekaran, Asha","doi":"10.1109/ICIIS51140.2020.9342638","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342638","url":null,"abstract":"Form Recognizer aims to build a deep learning model to extract handwritten text from a scanned Permanent Account Number (PAN) application form and convert them into digital format or editable text and store it in an excel file for further processing like statistical analysis or machine learning. The Learning model is based on the Convolution Neural Network (CNN) for the feature extraction and higher end classification. To accomplish this task, the handwritten forms are scanned, preprocessed to remove noise and handwritten fields are extracted. OpenCV is used to get the contours of the characters in the extracted images. This approach gives better accuracy than using plain CNN without out contours. The CNN model gives an accuracy of 91% on merger of numbers, uppercase and lower-case alphabets of EMINST dataset. Further, handwritten form recognizer system is built by incorporating this learning model, which is in turn integrated with preprocessing and segmentation methods. Finally, the output of the system is stored in a CSV file.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121055798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Efficient Design Approaches for Sharp Pseudo-Quadrature Mirror Filter banks using Hybrid Evolutionary Algorithms 基于混合进化算法的锐利伪正交镜滤波器组的高效设计方法

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342684

S. Kalathil, S. Urooj, S. Hitam

引用次数: 0

Single Image Super-Resolution using Residual Channel Attention Network 基于残差通道注意网络的单幅图像超分辨率

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342688

Hritam Basak, Rohit Kundu, Anish Agarwal, S. Giri

{"title":"Single Image Super-Resolution using Residual Channel Attention Network","authors":"Hritam Basak, Rohit Kundu, Anish Agarwal, S. Giri","doi":"10.1109/ICIIS51140.2020.9342688","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342688","url":null,"abstract":"Single Image Super-resolution refers to the method of converting one low-resolution image to its high-resolution counterpart which is a very challenging task since a low-resolution image can yield several possible high-resolution images. Super-resolution has applications in several paradigms like biomedical engineering, face recognition, satellite imaging among others. Several techniques exist in literature with recent research focusing on using deep convolutional neural networks along with residual learning techniques for enhancing performance. In this paper, we propose a deep learning-based approach for the problem, wherein we use a fully convolutional attention network coupled with residual in the residual block (RIR), Residual Channel Attention Block (RCAB), and long and short skip connections. The RIR block allows us to bypass the redundant low-frequency features and focuses on the important high-frequency information. We have used the DIV2k dataset for training our network and then tested our model on five publicly available datasets for validating our results: Set5, Set14, B100, Manga109, and Urban 100. The proposed methodology achieves commendable results compared to other existing deep learning-based methodologies in this domain.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123684987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Fuzzy Controller for Traffic Management in 5G Networks 5G网络流量管理的模糊控制器

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342630

Jayalakshmi G. Naragund, M. Vijayalakshmi, Suvarna G. Kanakaraddi

{"title":"Fuzzy Controller for Traffic Management in 5G Networks","authors":"Jayalakshmi G. Naragund, M. Vijayalakshmi, Suvarna G. Kanakaraddi","doi":"10.1109/ICIIS51140.2020.9342630","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342630","url":null,"abstract":"Communication system is evolving day by day and now entire globe communication is based on internet. Office work, academic activities in engineering field, business, banking system, government offices and different digital gazettes are performing regular processes using internet. So, data traffic volume goes on increasing exponentially and needs high capacity networks. 5th Generation (5G) networks are optimistic system to accommodate requirements of increasing demand. Complexity and challenges will also increase as system grows. Hence imminent insights and predictions are important to govern the 5G system systematically and avoid disasters in the coming days. Computational intelligence techniques are required to forecast solutions to run the system smoothly. Fuzzy logic controller is one such system to handle the dynamics and the non-linearity processes in 5G network. Authors propose novel fuzzy control algorithm to allocate the resources for User Equipment (UE) in 5G wireless network. Nowadays in the internet, multimedia data is the preferred traffic and that has contributed more to the volume of data. So Real time (RT) and Non Real time (NRT) types of requests are considered in this research. Radio Resource Control (RRC) connection management and communication protocol is used by wireless base station gNodeB (gNB) of 5G networks. The function of RRC is controlled by proposed fuzzy control algorithm. Fuzzy rules are designed, applied and analyzed for different combinations of inputs and outputs. Proposed RT First queue scheduling is used to process the RT and NRT requests. It is compared with First Come First Serve (FCFS) scheduling. RT First queue scheduling shows average response time 40% less than FCFS.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125482209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Novel RE Teams Selection Process For User-Centric Requirements Elicitation Frameworks Based On Big-Five Personality Assessment Model 基于大五人格评估模型的以用户为中心的需求激发框架的RE团队选择过程

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342649

M. A. Iqbal, Asadullah Shah

{"title":"A Novel RE Teams Selection Process For User-Centric Requirements Elicitation Frameworks Based On Big-Five Personality Assessment Model","authors":"M. A. Iqbal, Asadullah Shah","doi":"10.1109/ICIIS51140.2020.9342649","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342649","url":null,"abstract":"The requirements elicitation team selection process is considered as the key factor for planning the activities of work tasks performed by the requirements engineering teams. Consequently, the selection of most appropriate requirements elicitation teams for user-centric requirements elicitation frameworks plays a critical role in improving the quality of requirements elicitation frameworks. This paper presents an innovative process for requirements elicitation team’s selection for user-centric requirements elicitation frameworks. The presented process uses big-five personality assessment model to select the most appropriate requirements elicitation teams for such frameworks. The presented team selection process takes input from the software development industry data advertised for the induction of requirements analysts and computes the most relevant big-five personality traits for requirements engineering teams. The big-five personality traits predicted by the proposed process have been benchmarked with the predictions of the already available processes. The results obtained by using the proposed process have been found substantially improved to better support the requirements engineering works.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114902256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hand Gesture Recognition with Gaussian Scaling and Kirsch Edge Rotation 基于高斯缩放和基尔希边缘旋转的手势识别

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342716

S. Narayan, S. Vipparthi, A. P. Mazumdar

引用次数: 0

Facile Diabetic Retinopathy Detection using MRHE-FEED and Classification using Deep Convolutional Neural Network 基于MRHE-FEED的糖尿病视网膜病变快速检测与深度卷积神经网络分类

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342676

Muhammad Zubair, M. U. Naik, G. C. Mouli

{"title":"Facile Diabetic Retinopathy Detection using MRHE-FEED and Classification using Deep Convolutional Neural Network","authors":"Muhammad Zubair, M. U. Naik, G. C. Mouli","doi":"10.1109/ICIIS51140.2020.9342676","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342676","url":null,"abstract":"Diabetic Retinopathy (DR) is an intricacy of diabetes that affects the eyes. In this paper, we have proposed a hybrid pre-processing and feature extraction technique named as Microaneurysm Retinal vein Haemorrhage Exudate (MRHE) extraction using Feature Enhancement and Edge Detection (FEED) which can extract all the features in a single step and with very less complexity. To classify the presence of DR, we have used an efficient Deep Convolutional Neural Network (D-CNN), model. The D-CNN model is trained with four salient features namely retinal veins, MA’s, exudates, and haemorrhages which were extracted from the raw images using image-processing techniques. After training and testing the D-CNN model, we were able to classify the presence of DR based on the features extracted from the testing data. To implement this proposed method, we have used a dataset from the STructured Analysis of the Retina (STARE) Database, which comprises of retinal images taken under various imaging conditions using fundus photography. To demonstrate the legitimacy of the proposed method, we have compared our method with the existing DR detection and classification methods such as SVM, ANN, etc.. Performance evaluation results in terms of Accuracy and Recall show that the proposed algorithm outperforms other existing DR classification methods.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116229940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

DAFNA: Decentralized Auction based Fog Node Allocation in 5G Era DAFNA: 5G时代基于去中心化拍卖的雾节点分配

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342683

G. Baranwal, D. Kumar

{"title":"DAFNA: Decentralized Auction based Fog Node Allocation in 5G Era","authors":"G. Baranwal, D. Kumar","doi":"10.1109/ICIIS51140.2020.9342683","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342683","url":null,"abstract":"IoT applications such as smart city, smart healthcare, m-learning, m-tourism, augmented reality etc. require distributed edge computing technologies such as fog computing, mobile edge computing (MEC), cloudlet etc., to handle delay-sensitive applications. These applications are not feasible without 5G technologies because they need high-speed communication and the number of their users is also very large. In fog computing, fog nodes are allocated to the IoT users for running their heavy jobs. Many variants of a centralized reverse auction are reported in the literature for allocation of fog nodes. However, these auction methods have some major drawbacks such as one-point failure, utilization of only winner’s resources in a single round of auction, and a large number of message exchanges among participating entities in auction. Therefore, in this work, we have proposed a Decentralized Auction based Fog Node Allocation mechanism (DAFNA) that inherits all the properties of a traditional auction as well as improves the utilization of fog resources. In DAFNA, the concept of contention window and waiting time is used that makes the auction decentralized in nature. DAFNA allows fog resource providers to participate in more than one auction simultaneously for the same resource that improves the utilization of the resource. In addition, DAFNA also reduces the number of message exchanges among participating entities in auction in comparison with traditional auction. A case study is given to show the working of the proposed auction. The proposed auction mechanism is an application of 5G because it is decentralized in nature and requires speedy communication among participating entities.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122683911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Estimation of Fault Location Using PPU for Bolted and Non-bolted Faults in a LVDC Microgrid 基于PPU的LVDC微电网螺栓和非螺栓故障定位估计

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342709

Geeth Nischal Gottimukkala, M. Chandra, S. Mohapatro

引用次数: 0

Convolution Neural Networks: A Comparative Study for Image Classification 卷积神经网络:图像分类的比较研究

2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS) Pub Date : 2020-11-26 DOI: 10.1109/ICIIS51140.2020.9342667

Narayana Darapaneni, B. Krishnamurthy, A. Paduri

{"title":"Convolution Neural Networks: A Comparative Study for Image Classification","authors":"Narayana Darapaneni, B. Krishnamurthy, A. Paduri","doi":"10.1109/ICIIS51140.2020.9342667","DOIUrl":"https://doi.org/10.1109/ICIIS51140.2020.9342667","url":null,"abstract":"Wide range of convolution neural network architectures are available for image classification, segmentation and object detection. Most of the architecture focus on accuracy as primary factor for implementation. However, when it comes to real time application deployment, there are other primary factors like memory and performance which is equally important. Also, each CNN architecture showcases its advantages and limitations but comparison over their peers are not equally considered. The goal of this paper is to provide a comparative study of various CNN architecture for image classification and serve as a guide for selection based on applications requirement and hardware capabilities. In this paper, we discuss about 18 different CNN state of art architectures that are widely used. In order to access model suitability for a given problem, CIFAR-10 image dataset is trained on different architectures with a specified set of hyper-parameters to measure the accuracy, performance and memory consumption. The experiment findings are presented to suggest suitable CNN architecture based on application/hardware attributes.","PeriodicalId":352858,"journal":{"name":"2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129557700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9