2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)最新文献

{"title":"Framework for detection of anomalies in mass moving objects by non-technical users utilizing contextual & spatio-temporal data","authors":"Minura Jinadasa, Suranga Nisiwasala, Suthan Senthinathan, Shiromi Arunatileka, D. Sandaruwan","doi":"10.1109/ICTER.2017.8257798","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257798","url":null,"abstract":"Increasing utility of wireless sensors and their decreasing cost with technological innovation has increased their presence in many mobile & wearable devices and many devices are able to sense and relate a variety of sensor data including GPS location to be used for decision making. However, much potential of this data remains unexploited due to inherent complexity of manipulating such information, which bars the majority of users benefiting from this. One potential application is the detection of anomalies by users from a non-technical background through definition of rules. As such, a methodology/framework, which could enable users to define rules/query information from sensors fused with other contextual data in a user-friendly manner would be highly useful in deriving value from this data. This research attempts to formulate a low-cost framework, which enables users without a strong technical background to make potential use of this. The research is performed using a case study; identification of anomalies in the behaviours and violations of rules by marine vessels in Sri Lankan waters. However, the framework is generalized to enable application to other contexts also. The framework also attempts to identify a possible method and a process to enable users enter geo spatial rules in an accurate as well as user friendly manner while allowing to enter rules of different levels of complexities accurately. The research attempts to solve this problem through the use of a map interface which enables users enter geo spatial data either plotting on a screen or as pairs of coordinates. Use of auto query forms with dynamically changing queries was proposed to enter conditions of rules and the interrelationships. The research was carried out using one prototype and two systems in three stages, using the input of one step to next. Both methods of spatial rule entry were deemed accepted by users considering the ease of use in direct plotting as well as accuracy in formal coordinate entry in the two methods. While auto query form was found as a suitable method with reasonable accuracy with accuracy increasing with the educational background of users and decreasing on several occasions with increased complexity (multiple conditions or ambiguity of underlying concept) of rules, the display of the rule query in user readable form at the bottom of the interface as well as enabling the user to dynamically view query results to refine the query showed increased accuracy.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129135790","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}

{"title":"Lane detection using hybrid colour segmentation and perpendicular traversal linear search algorithm","authors":"Lithmi Yapa, Ajantha S Atukorale","doi":"10.1109/ICTER.2017.8257814","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257814","url":null,"abstract":"Road lane recognition and departure tracking systems provide an additional level of assistance and security to have a safe drive. This Application identifies the roadway by recognizing the lanes on the road considering the current movements of the vehicle. This research contributes to resolving some of the outstanding challenges in real time lane detection systems. Research has proposed a perpendicular traversal linear search algorithm with hybrid colour segmentation to address appearance variations in lane marking occurs due to various weather conditions, shadows, and occlusions such as traffic on the road. Robustness of the application has been tested under various road conditions and experimental results have achieved an accuracy of 89% for the overall application performance.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121476300","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}

{"title":"Offline handwritten signature verification system using random forest classifier","authors":"Maduhansi Thenuwara, H. Nagahamulla","doi":"10.1109/ICTER.2017.8257828","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257828","url":null,"abstract":"This research was conducted to find a feasible solution to verify hand written signatures. The scope has been narrowed down to offline signatures which contains static inputs and outputs. Several classification methods such as Multinomial Naive Bayes Classifier (MNBC), Bernoulli Naive Bayes Classifier (BNBC), Logistic Regression Classifier (LRC), Stochastic Gradient Descent Classifier (SGDC) and Random Forest Classifier (RFC) were implemented to identify the most suitable classifier to verify hand written signatures. The classifiers were trained and tested using a signature database available for the public use. The best performance was obtained from RFC with and accuracy score 0.6. For an average, the system created has been successful in verifying signature images provided with a considerable accuracy level.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"286 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116442215","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}

{"title":"Suppressing dengue via a drone system","authors":"A. Amarasinghe, C. Suduwella, Lasith Niroshan, Charitha Elvitigala, K. de Zoysa, C. Keppetiyagama","doi":"10.1109/ICTER.2017.8257797","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257797","url":null,"abstract":"Dengue is one of the rapidly spreading and deadly diseases in Sri Lanka, transmitted by the bite of infected female Aedes mosquitoes. Public Health Inspectors (PHIs) in Sri Lanka are facing a problem of identifying certain dengue mosquito breeding sites which are capable of retaining water. The goal of such inspection of suspected sites is to reduce the number of dengue patients by eradicating dengue mosquito habitats. A drone which has been created with the rapid advancement of technology, is one of the most cost effective apparatus to capture the mosquito breeding sites. It can inspect both accessible and inaccessible places to a human. With respect to the aforesaid context, this paper presents a simple and a novel approach to identify dengue mosquito breeding sites via drone images. The proposed approach captures the images of the water retention areas via a drone and generates the map, marking those areas in the map. The field test found that the proposed method, produces a satisfactory level of accuracy in identifying possible water retention areas and the final results depend on the drone camera tilt angle and the effect of shadows.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123363057","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}

{"title":"A framework for automated corpus compilation for KeyXtract: Twitter model","authors":"Tharindu Cyril Weerasooriya, N. Perera, S. Liyanage","doi":"10.1109/ICTER.2017.8257783","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257783","url":null,"abstract":"The corpus is a limiting factor for a keyword extraction process with a word matching stage. This paper proposes a framework to automate the corpus generation stage required for the Twitter Model of KeyXtract, an algorithm used for essential keyword extraction from tweets. The initial algorithm was designed with two manually compiled corpora that limited the adaptability of the system. The automated framework proposed in the present research is an extension to the keyword extraction process of KeyXtract and would address this limitation of the system. The design was carried out using open-class words of the source text and by matching them against the bag of words compiled by analyzing the tweets. The automated corpus had a total of 138 words, out of which 74 words were also found in the handpicked corpus (which had a total of 206 words). However, when the corpus was used with the keyword extraction system, the average F1 scores of the system showed a decrease of 0.07, proving that the automated corpus cannot perform parallel to the human-made corpus in complexity. This was because the human-made corpus was compiled using syntactic, semantic and pragmatic features while the automated framework focused only on the syntactic features. However, there were individual tweets in which the F1 score showed an increase. Thus, this was a promising first step in the corpus automation process. The automatic corpus generation framework could be made more accurate by including the semantic analysis of the lexical items. Thus, the present framework is able to substantially address the limitation of the corpus compilation which was present in the Twitter Model of KeyXtract.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123859484","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}

{"title":"Texture analysis of ultrasound images of chronic kidney disease","authors":"Fadil Iqbal, A. Pallewatte, J. Wansapura","doi":"10.1109/ICTER.2017.8257787","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257787","url":null,"abstract":"Chronic Kidney Disease of unknown aetiology (CKDu) is a prevalent disease in the North Central Province of Sri Lanka. Towards the latter stages of the disease, kidney function fails by 80%. During the initial stages of CKDu, interstitial fibrosis is formed and grows as the disease progresses. The cause of the disease remains elusive and early detection is vital to arrest the progressive decline of kidney function. The objective of this study is to construct a computer program to perform texture analysis on ultrasound kidney images and extract various features that can be used to distinguish between normal and diseased kidney patients. The computer program was developed using MATLAB and a user interface was created to perform mathematical operations such as: Fourier analysis to extract Root Mean Square and First Moment values and Grey Level Co-occurrence Matrix (GLCM) to extract Homogeneity and Sum Average values. A sample of ultrasound images were taken from 32 patients. Region of interest (ROI) selection was performed on entire kidney, cortex region and white (renal medulla or renal sinus) region separately. Among these methods Root Mean Square values over the entire kidney (p=0.03) and cortex region (p=0.0049) gave significant results in distinguishing between normal and diseased kidneys.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122468707","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}

{"title":"Hybrid framework for master data management","authors":"L. K. Fernando, P. Haddela","doi":"10.1109/ICTER.2017.8257785","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257785","url":null,"abstract":"Master data management and real-time data warehousing are gaining increased prominence within the worlds of business and technology. Past research efforts have shed light towards development of many master data management approaches. On the other hand, growth of technology has demanded real-time analytics and real-time processing of data. This trend has shed light in developing multiple real-time data warehousing approaches to perform real-time analytics based on an organization's requirements. With the evolution of real-time data warehousing, Master Data Management was an issue for large organizations' when both systems are working in the same business environment. Since both systems focus on real-time integration, similar, duplicated and parallel data extraction processes were executed by these applications. This was due to the fact that master Data Management was designed to focus on the operational aspect and real-time data warehouse was designed to focus on analysis aspect of the organization. Hence, each had its own ways of managing master data. These duplicated extractions caused data quality issues in these parallel applications. This research provides a framework that combines both master data management and real-time data warehousing and ultimately proposing to build a Hybrid Real-Time Data Warehousing Architecture in order to achieve enterprise wide master data management.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131141020","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}

{"title":"The best preferred product location recommendation according to user context and the preferences","authors":"E.J.C. Indunil, V. S. Gunasekara, K.A.T.S. Jayampathy, H. Jayasooriya, A.K.G.P.K. Wimalasooriya, T. Gunathilaka","doi":"10.1109/ICTER.2017.8257820","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257820","url":null,"abstract":"Currently the Smartphones are more popular among the community with the available technologies such as sensor-based interactions and smart apps. The other kinds of trends in such apps lead on context awareness and the personalization for recommending the services for the users based on their context and the preferences. Further, the researches are going on tracking the location of a person and guiding them to the nearby places where the products and the services are available according to their preferences. To accomplish such tasks, tracking and analyzing of the user preferences on different categories of products is required. This paper describes a mobile-based solution; NavToPref where the user preferences and the contextual information are gathered from their mobile phones and recommend and guide them to the nearby locations where the most preferred products are available. Analyzing the metadata of the sites of the frequently and mostly searched products, their top preferred categories of products are identified. This is done by the analysis of the browsing history. Further from their mobile devices, their own contextual information such as whether, location, identified special events from the Google calendar are collected to achieve more personalization on product recommendation. By analyzing the identified preferred products and the user context at the moment, the best preferred product/service locations are notified in the Google map with the shortest path for each product location from the users current location and allows the user to navigate to such locations. If someone is looking for a best promotional deal for shopping, that information is notified along with the recommendation.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133666606","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}

{"title":"Artificial neural networks for daily electricity demand prediction of Sri Lanka","authors":"S. L. Karunathilake, H. Nagahamulla","doi":"10.1109/ICTER.2017.8257823","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257823","url":null,"abstract":"As a developing country, energy is a factor that need to be utilized effectively and efficiently. Electricity is one of the main sources of energy in Sri Lanka. Thus accurate models to forecast future electricity demand is essential. This research focus on predicting the next day electricity demand for Sri Lanka. The study uses daily electrical consumption data for 11 years and use an Artificial Neural Network (ANN) model trained with back propagation algorithm and a Multiple Regression model to predict daily electrical consumption. The performance of the two models were compared using Root Mean Square Error (RMSE) Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2), The ANN model shows better performance with lower RMSE and MAPE values than Multiple Regression Model.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121111872","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}

{"title":"Cloud motion tracking for short-term on-site cloud coverage prediction","authors":"D. M. L. H. Dissawa, M. Ekanayake, G. Godaliyadda, J. Ekanayake, A. Agalgaonkar","doi":"10.1109/ICTER.2017.8257803","DOIUrl":"https://doi.org/10.1109/ICTER.2017.8257803","url":null,"abstract":"A technique for cloud motion tracking and cloud motion prediction using ground-based sky images is presented. This cloud motion prediction technique primarily targets irradiance prediction as an application in Electrical Engineering. A sequence of whole sky images is processed to determine the time taken by clouds to reach the sun position on the image. Cross-correlation technique was used to track individual clouds from one image frame to next frame. Using Harris features detection algorithm cloud features were found and the deformation vectors were produced. To find the velocity vectors of each feature points Lukas-Kanade optical flow algorithm is proposed. Using the optical flow algorithm, 3 min ahead cloud position was estimated.","PeriodicalId":140093,"journal":{"name":"2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121852969","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}