2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)最新文献_第7页

Prediction of Defaulters using Machine Learning on Azure ML 在Azure ML上使用机器学习预测违约

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284884

Abhishek Shivanna, D. Agrawal

{"title":"Prediction of Defaulters using Machine Learning on Azure ML","authors":"Abhishek Shivanna, D. Agrawal","doi":"10.1109/IEMCON51383.2020.9284884","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284884","url":null,"abstract":"Banks and lending institutions take risk in issuing new credit cards and loans to customers. Lending institutions at large need to have their own credit risk assessment system in accordance with Basel II guidelines. Many lending institutions lose a large amount of money as they do not have an accurate model to predict defaulters. The goal of credit risk management system is to accurately predict borrowers' ability to repay loans or make credit card payments in a timely manner. Researchers have taken multitude of approaches to solve this problem, and it continues to be an active area of research. Data mining and machine learning are emerging tools that are widely used by lending institutions to predict defaulters. These tools can effectively mine large dataset which is not feasible by traditional methods. In this work, we have used different algorithms including Deep Support Vector Machine (DSVM), Boosted Decision Tree (BDT), Averaged Perceptron (AP) and Bayes Point Machine (BPM) to build various models, in an attempt to better predict defaulters. Dataset, comprising of 25 attributes and 30k instances, was obtained from the repository of machine learning, University of California, Irvine (UCI). Our results show that, of all the four models used, DSVM can best predict defaulters. We believe that these models can be used to better predict defaulters by credit risk management system in banking and lending institutions.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"7 1","pages":"0320-0325"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88238519","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: 4

Limits of AI as Established by a Multi-Layered Symmetry-Based Model of Light 基于多层对称光模型的人工智能的局限性

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284955

Pravir Malik

{"title":"Limits of AI as Established by a Multi-Layered Symmetry-Based Model of Light","authors":"Pravir Malik","doi":"10.1109/IEMCON51383.2020.9284955","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284955","url":null,"abstract":"It has been said that the future of Life is about Artificial Intelligence (AI) and that as AI advances a point will be reached, the Singularity, when humans will no longer have a clue as to what is going on nor why. On the contrary, this article will make the case that the future of Life is enabled by the pre-existent complexity that exists in every iota of it. This pre-existent complexity derives from a multi-layered, symmetry-based model of light from which fundamental layers of matter and life – including the electromagnetic field, quantum particles, atoms, and cells - can be proposed to emerge. As such matter and life are an integral part of a unified light-based edifice proposed to have infinite-potential resident in it. By contrast contemporary AI is based on mind-based processes such as memory, computation, sensing, and learning that operate within a defined and limited conceptual space and are positioned to be substrate independent. This conceptual space and the operating principles that define it limit AI, which in its current incarnation cannot rival the kinds of creations and possibilities inherent in a multi-layered symmetry-based model of light. Unless the gap to such a unified light-based edifice is bridged, AI will always have limits within which its possibilities will be bound.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"73 1","pages":"0151-0158"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82351925","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

Robust Deep Learning Technique: U-Net Architecture for Pupil Segmentation 鲁棒深度学习技术:用于瞳孔分割的U-Net架构

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284947

Swathi Gowroju, Aarti, Sandeep Kumar

引用次数: 8

Analysis of Requirements for Autonomous Driving Systems 自动驾驶系统需求分析

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284853

Felix Müller, P. Nenninger, E. Sax

引用次数: 0

An Adapter for IBM Streams and Apache Spark to Facilitate Multi-level Data Analytics 一个适配器IBM流和Apache Spark，以促进多层次的数据分析

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284818

Yinchen Shi, Sazia Mahfuz, F. Zulkernine, Peter Nicholls

{"title":"An Adapter for IBM Streams and Apache Spark to Facilitate Multi-level Data Analytics","authors":"Yinchen Shi, Sazia Mahfuz, F. Zulkernine, Peter Nicholls","doi":"10.1109/IEMCON51383.2020.9284818","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284818","url":null,"abstract":"Data analytics with unsupervised clustering of data streams has provided revolutionary breakthroughs in fields like healthcare, and E-commerce. IBM Streams and Apache Spark are among the most useful and popular data analytics tools that help engineers and researchers extend the abilities to store, analyze, transform, and visualize data for business use. IBM Streams is capable of ingesting, filtering, analyzing, and associating massive volumes of continuous data streams and the Streams Processing Language (SPL) enables coding custom stream graphs to process data and handle real-time events. Apache Spark has unified analytics edge for large scale data processing with high performance for both batch and streaming data. We developed adapters without using third party tools to facilitate data transfer between IBM Streams and Apache Spark to support new and legacy data analytic systems. An example use case would be IBM Streams ingesting and processing realtime data streams, and then passing the data to Spark to train or update machine learning algorithms in real time that can be re-deployed in the IBM Streams data processing pipeline. This paper provides an overview of the structure of the data processing pipeline, describes the implementation details and the principle behind the design.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"2 1","pages":"0230-0235"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76309655","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

Improving energy revenue and security by employing SDNS for the Low Voltage distribution network for residential users in South Africa 通过在南非住宅用户的低压配电网络中使用SDNS来提高能源收入和安全性

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284835

Noah.S. Fakude, K. Ogudo

{"title":"Improving energy revenue and security by employing SDNS for the Low Voltage distribution network for residential users in South Africa","authors":"Noah.S. Fakude, K. Ogudo","doi":"10.1109/IEMCON51383.2020.9284835","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284835","url":null,"abstract":"Energy management is a key element in energy distribution utilities. Whilst revenue collection is significant in the industry, safety and energy security are of top priority. With the diffusion and the adoption rate of new domestic electrical appliances and the rate of population growth, the energy demand by residential consumers skyrockets. To keep the electrical network continually distributing, there is a need to control and manage energy usage from the consumption side. This paper proposes a Smart Distribution Network System (SDNS), which employs the Master-Slave metering hierarchy for load management by controlling the usage limits in real-time. The SDNS is a digitalized electrical network concept that allows the existing power network to operate at an optimum level during peak periods and limits unnecessary consumption excesses. The system ensures maximum revenue returns to utilities and energy security to consumers by keeping the network in operation with no disturbances. A standard traditional grid was used to model the smart system using a MATLAB tool. The grid was put under test in heavy load conditions, first with no enhancement and again with the enhancement of the proposed SNDS system. Results were recorded for both simulation tests, then the conclusion was drawn from the discussion of results compared to examining the effectiveness of the system.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"8 2 1","pages":"0420-0426"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80565269","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

An Overview of UPnP-based IoT Security: Threats, Vulnerabilities, and Prospective Solutions 基于upnp的物联网安全概述:威胁、漏洞和未来解决方案

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284885

Golam Kayas, M. Hossain, J. Payton, S. Islam

引用次数: 6

Low-Complexity High-Accuracy 5G and LTE Multichannel Spectrum Analysis Aided by Unsupervised Machine Learning 基于无监督机器学习的低复杂度高精度5G和LTE多通道频谱分析

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284843

Benjamin Imanilov

引用次数: 0

State-of-the-Art VANET Trust Models: Challenges and Recommendations 最先进的VANET信任模型:挑战和建议

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284953

Hritik Sateesh, P. Zavarsky

{"title":"State-of-the-Art VANET Trust Models: Challenges and Recommendations","authors":"Hritik Sateesh, P. Zavarsky","doi":"10.1109/IEMCON51383.2020.9284953","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284953","url":null,"abstract":"Research on trust models in Vehicular Ad-hoc Networks (VANET) was mainly focused on entity-centric, data-centric, and combined trust models until the latter half of the previous decade. There are a number of attacks these conventional trust models cannot hold back. The popularity of blockchain technology in the last few years resulted in the research on blockchain-based trust management models for VANET. Meanwhile, zero trust solutions claimed to overcome the problems of the traditional perimeter security model. With the perimeter security model, information systems within an organization's internal network are inherently trusted and the ones that belong outside the organization are consequently deemed untrusted. The zero trust architecture overcomes these flaws by simply not trusting any entity regardless of the entity belonging inside the organization's perimeter or outside. This paper discusses the various trust management models for VANET, their drawbacks and proposes a private blockchain technology to improve the performance and highlight the need for a central governing authority. The paper also investigates the challenges of implementing a zero-trust architecture for vehicular communications and brings forth the idea of using the concepts of zero trust to provide state-of-the-art security for VANET's supporting infrastructure. Additionally, this study surveys the benefits and challenges of developing the VANET architecture based on software-defined networking (SDN).","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"162 1","pages":"0757-0764"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75949063","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

Power Adaptation for Full-Duplex Relay-Aided D2D Communications with Direct Link 直接链路全双工中继辅助D2D通信的功率自适应

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Pub Date : 2020-11-04 DOI: 10.1109/IEMCON51383.2020.9284956

Yasmine H. Hussein, E. Maher, A. El-Mahdy

引用次数: 0