Electronic Government, an International Journal (14 papers in press)
Factors Influencing the Adoption of E-government Services among Jordanian Citizens
by Mohammed Almaiah, Yacoub Nasereddin
Abstract: This work aims to study effective factors that could play an important role in the decision of Jordanian citizens to adopt e-government services. The study employed the UTAUT model with introducing new constructs, namely; website quality, trust of internet, trust of government, to study the adoption of e-government services in Jordan context. The data was collected using online survey from a total of 320 Jordanian citizen who are from both public and private sectors. The research model was evaluated using the structural equation modelling (SEM) technique. Based on the results, website quality, trust of internet, trust of government, performance expectancy, effort expectancy and facilitating conditions factors were shown to have a positive effect on behavioural intention to use e-government services. However, the influence of social influence was found to be insignificant on the participants behavioural intention to use. Additionally, the website quality factor was found to have a positive effect on the performance expectancy of e-government services. The findings of this study will guide researchers, policy makers and professionals towards the Jordanian citizen priorities in improving website design, website functions, website content quality, ease of use and security; thereby increasing the adoption of e-government services.
Keywords: E-government services; UTAUT model; website quality; SEM; Jordan.
Electronic Government and its impact on corruption perceptions in Latin America
by José Carlos Vázquez Parra, Florina Guadalupe Arredondo, Jorge De La Garza
Abstract: Corruption is a serious problem for the Latin American region, which means that governments make great efforts to reduce this malaise afflicting their countries. This article examines if there is a difference in the levels to which electronic government (e-government) and transparency are being implemented in two blocks of Latin American countries through conglomerate analysis and ANOVA analysis. In the results of the study, countries were divided into two groups, making it possible to verify that the first block, which has driven digital government more decisively, has lower levels of perceived corruption than the second block. It is therefore concluded that e-government can become a differentiator of corruption perceptions in this selection of countries.
Keywords: Transparency; corruption; government; governance; participation; citizenship; Latin America; inclusion; technology; good governance.
E-Government in the Public Cloud: Requirements and Opportunities
by Andreas Abraham, Felix Hörandner, Thomas Zefferer, Bernd Zwattendorfer
Abstract: Cloud computing promises various advantages compared to classical provisioning models and is therefore highly interesting for e-government services. For security and data protection reasons, adoption of cloud computing in public sectors has focused on private or community clouds so far, underusing the great potential of public clouds. In this article, we tackle this issue and show opportunities to unleash the full potential of public clouds also to the public sector. First, we perform a thorough literature survey to identify a comprehensive set of requirements for e-government services in public cloud environments. Then, we assess cloud-related technologies and propose strategies to satisfy these identified requirements, providing decision makers from the public sector a comprehensive overview that helps during design, migration, and development of e-government service to be deployed in public clouds.
Keywords: electronic government; e-government services; public cloud; cloud computing; e-government service requirements; implementation opportunities.
SOCIAL SPIDER BASED UNEQUAL CLUSTERING PROTOCOL FOR WIRELESS SENSOR ENVIRONMENT FOR SMART CITIES
by Buvanesvari R, Rijuvana Begum
Abstract: Wireless sensor networks involve a massive number of sensor nodes often deployed to observe the physical world. Energy efficiency is the challenging issue in the design of WSN. For attaining energy efficient characteristic, clustering techniques has been employed. But, it suffers from hot spot issue which defines that the cluster heads (CHs) closet to base station are burdened with more traffic compared to CHs located far away from BS due to multihop communication. To resolving this, we present a social spider-based unequal clustering protocol (SSUCP) for WSN. SSUCP is based on the nature of social spiders to select the proper CHs and cluster size. Based on the fitness functions and node parameters, the interested decision of selecting the proper CHs and cluster size were made. The SSUCP is implemented in MATLAB and an extensive experimentation takes place under three situations based on distance to BS for ensuring the consistent results of the proposed method. In addition, the SSUCP is validated in terms of energy efficiency and network lifetime analysis. The attained experimental outcome verified that the SSUCP is the superior one over the compared methods.
Keywords: Smart Cities; WSN; Social Spider; Hot spot issue; Clustering.
AN EFFICIENT HEALTHCARE FRAMEWORK FOR KIDNEY DISEASE USING HYBRID HARMONY SEARCH ALGORITHM
by Sujatha Pothula, Uthayakumar J, Prasad Koti, Dhavachelvan Poonurangam, Kalaipriyan T, Sariga A
Abstract: Prediction of kidney disease (KD) gains more importance in the medical decision support systems. As the medical dataset are massive in size, effective techniques are required to produce accurate results. This paper proposes a hybrid harmony search (HM-L) algorithm with Levi distribution to properly predict KD at appropriate time. In this research work, correlation-based feature selection (CFS) is used as a feature selection technique. The effectiveness of hybrid harmony search (HS) algorithm is validated by employing it against a set of dataset. The obtained results of applied datasets without and with feature selection are compared to one another. The experimental results imply that the HM-L algorithm attains significant results than existing methods such as HS algorithm, biogeography optimisation algorithm (BBO), grey wolf optimisation (GWO), AL particle swarm optimisation algorithm (ALPSO) and artificial bee colony (ABC) algorithm. The presented HM-L model attains a sensitivity of 96, specificity of 93.33, accuracy of 95, F-score of 96 and kappa value of 0.89.
Keywords: Feature selection; Harmony search algorithm; intelligent algorithms; Levi distribution.
OPTIMAL PARAMETER TUNING FOR PID CONTROLLER USING ACCELERATED GREY WOLF OPTIMIZATION IN SMART SENSOR ENVIRONMENTS
by Rajakumar R, Sivanandhakumar D, Uthayakumar J, Vengattaraman T, Dinesh K
Abstract: System lifetime is the crucial problem of wireless sensor networks (WSNs), and exploiting environmental energy provides a potential solution. Boost convertor can be employed in WSN to achieve energy efficiency. In order to achieve better performance, PID controller is combined with boost convertor. However, tuning the PID controller is crucial task whenever the input voltage fluctuates. In this work, a novel algorithm namely accelerated grey wolf optimisation (AGWO) is proposed to improve the convergence speed and to eradicate the local optima stagnation. AGWO algorithm utilises a balanced intensification and diversification techniques to eradicate the local optima struck. The observed results conveys that AGWO achieves minimum percentage overshoot (9%), settling time (0.894), rise time (0.50) and peak time (0.57) which is better compared to other comparative algorithms. Additionally, it has been observed that AGWO is able to achieve comparatively better success performance in a complex environment.
Keywords: WSN; Smart Sensors; Grey Wolf Optimization; PID Controller; Boost Convertor Problem.
SOCIAL INTERNET OF THINGS USING BIG DATA ANALYTICS AND SECURITY ASPECTS - A REVIEW
by DEVA ARUL S, IYAPPARAJA M
Abstract: The rapid development of technologies in todays world has become interesting that made millions of people to utilise the major advantages in it. Two main technologies that were emerging in modern society are big data and the social internet of things. Several researchers have studied and developed a major concept of using big data with SIoT and the security development of maintain a large amount of data. In this paper, deep survey regarding the concepts behind the big data analytics with the social internet of things (SIoT) was studied and analysed. Furthermore, the machine learning techniques that were used in previous works were analysed and comparisons of various methods are discussed. The performance comparison of various classifiers on different datasets is shown and SVM has more than 90% of accuracy when compared with other algorithms. KNN has 64% of accuracy which is lowest of any classifier than NB and NN.
Keywords: Big Data; Social Internet of Things (SIoT); Frequent Itemset Mining (FIM); Machine Learning.
Internet of Medical Things with Cloud based e-Health Services for Brain Tumor Detection Model using Deep Convolution Neural Network
by Ganesan M, Sivakumar N, Thirumaran M
Abstract: In the present days, e-health services offer various decision support systems in healthcare sector. These systems make use of internet of medical things (IoMT) devices and cloud platform to offer services to millions of people. In this paper, we develop an IoT with cloud-based brain tumour detection model using convolution neural network (CNN). Here, the input MRI brain images are captured by the use of medical equipments as well as IoT devices is used to transmit data to the cloud. In the cloud, the D-CNN model can be executed to identify the presence of disease and classify the brain tumour as malignant or benign. The presented D-CNN model is employed to a set of benchmark BRATS 2015 challenge dataset. The presented model attains maximum classifier performance with the sensitivity value of 97.17, specificity of 98.77 and accuracy of 98.07.
Keywords: e-Health services; Brain tumor; Cloud computing; CNN; Decision support; IoMT.
A PERFORMANCE ANALYSIS OF STEREO MATCHING ALGORITHMS FOR STEREO VISION APPLICATIONS IN SMART ENVIRONMENTS
by Kavitha V, Balakrishnan G
Abstract: Stereo vision is a subfield of computer vision that tends to an essential research issue of reproducing the three-dimensional directions and focuses for depth estimation. This paper gives a relative investigation of stereo vision and matching techniques, utilised to resolve the correspondence problem. The investigation of matching algorithms is done by the use of extensive experiments on the Middlebury benchmark dataset. The tests concentrated on an examination of three stereovision techniques namely mean shift algorithm (MSA), seed growing algorithm (SGA) and multi-curve fitting (MCF) algorithm. With a specific end goal to evaluate the execution, some statistics related insights were computed. The experimental results demonstrated that best outcome is attained by the MCF algorithm in terms of depth estimation, disparity estimation and CT. The presented MCF algorithm attains a minimum computation time (CT) of 2 s whereas the other MSA and SGA require a maximum CT of 8.9 s and 7 s, respectively. The simulation results verified that the MCF algorithm reduces the processing time in a significant way than the compared methods.
Keywords: Smart cities; Stereo matching; Stereo vision; Multi fitting; Middlebury.
An Analysis of Parallel Ensemble Diabetes Decision support system based on Voting Classifier for Classification Problem
by Sathurthi S, K. Saruladha
Abstract: Diabetes mellitus is one of the prominent health challenges in the world. Diabetes is a dangerous, metabolic disease that caused by human blood sugar level and progresses throughout life. In supervised learning-based systems have been proposed that incorporate ensemble learning techniques for diabetes prediction depends upon the diagnostic measurement of the diabetes patient. In this paper, voting classifier were used for combining the various ensemble and base classifiers for designing diabetes disease prediction. Voting mechanism helps to build the multiple ensemble and base classifier model. The accuracy of ensemble of ensemble classifiers has resulted in high rate of accuracy (79%) when compared to the ensemble of base classifiers (77%) with majority rule voting (MRV) and weighted majority voting (WMV) models. Hence, ensemble of ensemble classifier was chosen as the best model for diabetes healthcare prediction. This system has been experimented with Pima Indian diabetes UCI dataset and its implemented in python language.
Keywords: Base Classifiers; Ensemble Classifiers; Cross Validation; Bagging; Boosting; Decision Tree; Majority Rule Voting and Weighted Majority Voting.
A cooperative GA-SM based prediction model for healthcare services
by Durgadevi M, Kalpana Ramanujam
Abstract: Diabetes mellitus is a major health challenge around the world. The blood glucose level is one of the major factors in the human body and a significant increase in its level can cause many harmful effects in human life. It is expected that early diagnosis of diabetes mellitus can lead to rapid and effective treatment of glycemic control. As the number of people who suffer from diabetes mellitus increases significantly, a study on diabetes mellitus prediction was done through well-known methods in data mining (DM). In this paper, a genetic algorithm (GA)-based suppressor mutation (SM) optimisation rule miner has been proposed as a cooperative approach for prediction of diabetes mellitus. A novel fitness function has been incorporated into the GA-SM approach to generate a comprehensive optimal rule set while balancing accuracy, sensitivity and specificity. The proposed rule miner was compared against three rule-based algorithms, namely CN2, J48 and BF tree on the Pima Indians Diabetes Dataset with 768 patient records using ten-fold cross validation. The results obtained prove that the proposed GA-SM approach has outperformed CN2, J48 and BF tree with respect to accuracy and kappa.
Keywords: Diabetes Mellitus;Data Mining;Genetic Algorithm;Suppressor Mutation.
Empower Good Governance with Public Assessed Schemes by Improved Sentiment Analysis Accuracy
by V.S.Siva Rama Rao Akula, Ranjana P
Abstract: Many government schemes were unsuccessful because lack of proper feedback on the ongoing schemes, where billion dollars investment is going to be in vain. Sentiment analysis is one of best approach to analyse opinions of the peoples on various government schemes. Sentiment analysis and machine learning techniques emerged to analyse huge social media corpora to track people's views on government policies, products and services. Sentiment analysis process consists of various phases which include data discovery, data collection, data pre-processing, and data analysis. Stemming is a process to generate the morphemes in natural language sentences for various applications such as sentiment analysis, information retrieval, and domain analysis. The stemming process involved two major errors, which are over-stemming and under-stemming errors. Most of sentiment analysis natural languages processing applications used Lancaster and Porter stemming algorithms where more than one word inflected into same morpheme, which causes the etymology behaviour of the stemming word and prone to classify the tweets false positives and false negative. The proposed un-prejudice light stemming algorithm prevent etymology behaviour of morpheme and sustain its meaning during stemming process by selecting a word which has maximum number of synonyms in lexical database.
Keywords: Empower Government; Government Schemes; NLP ; Social-media Networks; Under-Stemming; Over-Stemming; Stemmer Weight; Sentiment Analysis.
Smart Learning using Personalized Recommendations in Web Based Learning Systems Using Artificial Bee Colony Algorithm to improve Learning Performance
by Maganti Venkatesh, Sathyalakshmi Sivaji
Abstract: Many of e-learning systems in their web-based courses do not have personalisation based on individual needs and their capabilities. Main challenging aspect of personalised delivery of e-learning is concerned with an adaptive course delivery along with content delivery. Personalised e-learning environment provide recommendations to learning community for supporting and also helping them go through the process of e-learning, as it plays a crucial role in promotion of smart learning in smart cities. In this work, a novel framework namely, personalised bee recommender for e-learning (PBReL) based on artificial bee colony (ABC) optimisation is proposed to build a structure of recommendation by using K-means clustering. Many other recommender system are available that made use of ABC to identify its optimal learning path. Experiments are carried out by using web links and contents of Moodle-based learning management system (LMS). Results show that the proposed framework obtains higher precision and coverage.
Keywords: E-learning; Personalization; Recommender Systems; K-Means Clustering; Artificial Bee Colony (ABC) optimization algorithm and Moodle-based Learning Management System (LMS).
Identification and characterization of Choroidal Neovascularization (CNV) using eHealth data through an optimal classifier
by Anitha G, Lakshmanaprabu SK, Mohamed Ismail
Abstract: Over the years, health informatics and eHealth gained more popularity in health care application. The collection of eHealth data becomes easier due to the advancement of digital technology. In this paper, the e-Health based supporting system is developed for the classification of a retinal disease called CNV. CNV is a retinal disease caused due to the growth of abnormal blood vessels in the choroidal layer. A good classifier for CNV data makes the process of identifying the disease easier and it will help the medical practitioners to give the treatment at the right time. A comparison has been done among different machine learning classifiers such as support vector machine (SVM), k-nearest neighbours (kNN), neural network (NN), ensemble and naive Bayes classifiers and they are tested and evaluated based on accuracy and training time. From the results, it is observed that kNN classifier outperforms the other classifiers in all aspects.
Keywords: Choroidal Neovascularization; Optical Coherence Tomography; machine learning classifiers; support vector machine; kNN classifier; Naive Bayes Classifier.