Fog Computing-Based IoT for Health Monitoring System

Paul, Anand,Pinjari, Hameed,Hong, Won-Hwa,Seo, Hyun Cheol,Rho, Seungmin Hindawi Limited 2018 Journal of sensors Vol.2018 No.-

<P>Wireless sensor networks (WSNs) are widely used in the area of health informatics. Wireless and wearable sensors have become prevalent devices to monitor patients at risk for chronic diseases. This helps ascertain that patients comply by the treatment plans and also safeguard them during sudden attacks. The amount of data that are gathered from various sensors is numerous. In this paper, we propose to use fog computing to help monitor patients suffering from chronic diseases such that the data are collected and processed in an efficient manner. The main challenge would be to only sort out context-sensitive data that are relevant to the health of the patient. Just having a simple sensor-to-cloud architecture is not viable, and this is where having a fog computing layer makes a difference. This increases the efficiency of the entire system, as it not only reduces the amount of data that is transported back and forth between the cloud and the sensors but also eliminates the risk that a data center failure bears with it. We also analyze the security and deployment issues of this fog computing layer.</P>

Bioinspired Mechanisms in Wireless Ad Hoc and Sensor Networks

Paul, Anand,Chen, Daniel Bo-Wei,Wang, Wanmin Hindawi Limited 2015 Journal of sensors Vol.2015 No.-

Interactive scheduling for mobile multimedia service in M2M environment

Paul, Anand,Rho, Seungmin,Bharnitharan, K. Springer-Verlag 2014 MULTIMEDIA TOOLS AND APPLICATIONS Vol.71 No.1

Time-and-ID-Based Proxy Reencryption Scheme

Mtonga, Kambombo,Paul, Anand,Rho, Seungmin Hindawi Limited 2014 Journal of applied mathematics (JAM) Vol.2014 No.-

<P>Time- and ID-based proxy reencryption scheme is proposed in this paper in which a type-based proxy reencryption enables the delegator to implement fine-grained policies with one key pair without any additional trust on the proxy. However, in some applications, the time within which the data was sampled or collected is very critical. In such applications, for example, healthcare and criminal investigations, the delegatee may be interested in only some of the messages with some types sampled within some time bound instead of the entire subset. Hence, in order to carter for such situations, in this paper, we propose a time-and-identity-based proxy reencryption scheme that takes into account the time within which the data was collected as a factor to consider when categorizing data in addition to its type. Our scheme is based on Boneh and Boyen identity-based scheme (BB-IBE) and Matsuo’s proxy reencryption scheme for identity-based encryption (IBE to IBE). We prove that our scheme is semantically secure in the standard model.</P>

Constrained application for mobility management using embedded devices in the Internet of Things based urban planning in smart cities

Din, Sadia,Paul, Anand,Hong, Won-Hwa,Seo, Hyuncheol Elsevier 2019 Sustainable cities and society Vol.44 No.-

<P><B>Abstract</B></P> <P>The Constrained Application Protocol (CoAP) has been widely used, as the number of embedded sensors or devices increases. To support mobility management in web based Internet-of-Things environment is critical issue. For this purpose, a CoAP-based mobility management protocol, named CoMP has been proposed, but this protocol was designed for a single sensor node mobility. However, it does not perform well in group-based mobility. To overcome this limitation, we propose a CoAP-based group mobility management protocol, named CoMP-G. In the proposed scheme, one of the body sensor will function as a coordinator and it will exchange all the control messages with web-of-things mobility management system (WMMS) on behalf of other body sensors. Besides, each WMMS maintains the information of the group of body sensors. From the numerical analysis, we proved that the proposed scheme gives the best performance in terms of total signaling and handover delay from the existing CoMP protocol.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Constrained Application for Mobility Management. </LI> <LI> Information Retention of the group of body sensor. </LI> <LI> Web-of-things mobility management system (WMMS) on behalf of other body sensors. </LI> </UL> </P>

이미지에서 기계 학습 기법을 활용한 특정 부품영역 탐지 기술 개발

Faisal Saeed,Anand Paul,Anand Kumar Balasubramaniam,김동인(Kim Dong-In),김대기(Kim Dae-gi),방종원(Bang Jong-Won),우진철(Woo jin-chael) 대한전자공학회 2018 대한전자공학회 학술대회 Vol.2018 No.11

With the growing pace in the industrial sector, the need of the smart environment is also increasing. While production of industrial products, quality always matters. Fault detection in the industrial images is very hot topic in era of current research. Faulty images mean the images of the products which have some fault like missing screw, misplaced labels etc. To detect fault in the images, we proposed a method. Our proposed method is based on deep neural networks which is using convolutional neural network for detection. We also used RoI concept to make detection faster and more accurate. We simulated our environment using python language. Our proposed model has almost 99%.

DeepCleanNet: Training Deep Convolutional Neural Network with Extremely Noisy Labels

Bekhzod Olimov,Anand Paul,김정홍 한국멀티미디어학회 2020 멀티미디어학회논문지 Vol.23 No.11

In recent years, Convolutional Neural Networks (CNNs) have been successfully implemented in different tasks of computer vision. Since CNN models are the representatives of supervised learning algorithms, they demand large amount of data in order to train the classifiers. Thus, obtaining data with correct labels is imperative to attain the state-of-the-art performance of the CNN models. However, labelling datasets is quite tedious and expensive process, therefore real-life datasets often exhibit incorrect labels. Although the issue of poorly labelled datasets has been studied before, we have noticed that the methods are very complex and hard to reproduce. Therefore, in this research work, we propose Deep CleanNet - a considerably simple system that achieves competitive results when compared to the existing methods. We use K-means clustering algorithm for selecting data with correct labels and train the new dataset using a deep CNN model. The technique achieves competitive results in both training and validation stages. We conducted experiments using MNIST database of handwritten digits with 50% corrupted labels and achieved up to 10 and 20% increase in training and validation sets accuracy scores, respectively.

An immersive learning model using evolutionary learning

Bhattacharjee, Deblina,Paul, Anand,Kim, Jeong Hong,Karthigaikumar, P. Elsevier 2018 Computers & electrical engineering Vol.65 No.-

<P><B>Abstract</B></P> <P>In this article, we have proposed an educational model using virtual reality on a mobile platform by personalizing the simulated environments as per user actions. We have also proposed an evolutionary learning algorithm based on which the user learning path is designed and the corresponding simulated learning environment is modified. The main objective of this study is to create a personalized learning path for each student as per their calibre and make the learning immersive and retainable using virtual reality. Our proposed model emulates the innate natural learning process in humans and uses that to customize the virtual simulations of the lessons by applying the evolutionary learning technique. A quasi-experimental study is conducted by taking different case studies to establish the effectiveness of our learning model. The results show that our learning model is immersive and gives long term retention while enhancing creativity through reinforced customization of the simulations.</P> <P><B>Highlights</B></P> <P> <UL> <LI> An evolutionary virtual reality model for m-learning is proposed. </LI> <LI> An evolutionary learning algorithm with reinforcement is proposed. </LI> <LI> The algorithm personalizes the learning path of every user based on his actions. </LI> <LI> The virtual environment evolves using the reinforcement signal and user action. </LI> <LI> Results show increased retention by 83.75% across 3 case study groups. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P> The immersive virtual reality framework for an m-learning educational model consisting of an evolutionary learning network giving a personalized learning path for every student.</P> <P>[DISPLAY OMISSION]</P>

Proactive Secret Sharing for Mobile Ad-hoc Networks

Rosemary Koikara,Anand Paul,Eun-Jun Yoon(윤은준),Kee-Young Yoo(유기영) 대한전자공학회 2018 대한전자공학회 학술대회 Vol.2018 No.6

Semisupervised Particle Swarm Optimization for Classification

Zhang, Xiangrong,Jiao, Licheng,Paul, Anand,Yuan, Yongfu,Wei, Zhengli,Song, Qiang Hindawi Limited 2014 Mathematical problems in engineering Vol.2014 No.-

<P>A semisupervised classification method based on particle swarm optimization (PSO) is proposed. The semisupervised PSO simultaneously uses limited labeled samples and large amounts of unlabeled samples to find a collection of prototypes (or centroids) that are considered to precisely represent the patterns of the whole data, and then, in principle of the “nearest neighborhood,” the unlabeled data can be classified with the obtained prototypes. In order to validate the performance of the proposed method, we compare the classification accuracy of PSO classifier, k-nearest neighbor algorithm, and support vector machine on six UCI datasets, four typical artificial datasets, and the USPS handwritten dataset. Experimental results demonstrate that the proposed method has good performance even with very limited labeled samples due to the usage of both discriminant information provided by labeled samples and the structure information provided by unlabeled samples.</P>