International Journal of Spatio-Temporal Data Science (7 papers in press)
Adaptive Background Modeling Technique for Moving Object Detection in Video under Dynamic Environment
by Dileep Yadav, Karan Singh
Abstract: This work proposes a novel method for detection of motion based object having dynamic scenario in the background. The suggested scheme has a strong potential for real-time applications especially for rafting, river, sea-beach, swimming pools, ponds, etc. Apart from these, this work is very beneficial for surveillance of border, tunnel, traffic in the sea, forest, restricted zones, deep zones, etc. This work develops a statistical p based background subtraction method and implemented in three stages. In the first stage, a background model is developed using few initial frames. In the second stage, this work classifies the foreground using the difference frame and the appropriate threshold value. An automatic threshold value is generated at run-time and updated iteratively. It also reduces the problem of using a constant threshold. In the third stage, morphological filters and connected component based region filtering technique is applied to enhance the detection quality. The extensive experimental result shows more accurate results of proposed method. It also demonstrates better performance against considered state-of-the-art methods.
Keywords: Cluttered Background; Adaptive Modeling; Background Subtraction; Outliers; Moving Object Segmentation; Visual Surveillance.
Performance Analysis of Moving Object Detection using BGS Techniques in Visual Surveillance
by Lavanya Sharma, Nirvikar Lohan
Abstract: Over the last decennium, the object detection is the pivotal step in any machine vision and image processing application. It is the initial step applied to extract informative pixel from the video stream. Many algorithms are available in literature for extraction of visual information or foreground object from video sequence. This paper also provides a detailed overview of both conventional and traditional approaches used for detection of object. This paper explores various related methods, major challenges, applications, resources such as datasets, web-sources etc. This paper presented a study of the moving object detection using background subtraction techniques in the video surveillance system that provide safety in cities, towns or home when video sequence is captured using IP cameras. The experimental work of this paper is performed over Change Detection, I2R, and Wallflower datasets. The experimental analysis also depicts a comparative study of some of the peer methods. This work demonstrates several performance metrics to check robustness of the methods.
Keywords: Digital Image processing; BGS techniques; object detection; object tracking; Fuzzy logic; and Artificial intelligence; Internet of Things; Smart cities; spatio-temporal data.
Color transformed clustering based water body extraction using IRS-1C LISS III Image
by Rubina Parveen, Subhash Kulkarni, V.D. Mytri
Abstract: Water plays a significant role in the sustainability and development of an area by maintaining global carbon cycle and climate variations. Due to the excessive use and pollution the risk of degradation and disappearance of water bodies is high. An assessment of surface water availability for monitoring the area is an essential task. This article extracts and delineates the water areas using Remote Sensing image processing methods. IRS-1C (Indian Remote Sensing Satellite Resource sat-1C) satellite LISS III (Linear imaging self-scanning sensor) data is used for the analysis. Water resource identification and delineation are the key challenges for the utilization and monitoring of water bodies, timely. Methods present in the literature are biased with user-defined thresholds. The objective of the proposed algorithm is to provide accurate information about surface water. Initially, the input image is subjected to color transformation clustering to extract all the similar hydrological characteristics geo-spatial features in the picture. Every cluster is then submitted to surface water detection by considering spectral information. Finally, the surface water bodies are outlined with sharp inter-regional boundaries and made visually vibrant. Thus the task of identification of water bodies is made simple, accurate and easy for the user. Qualitative analysis is found to be satisfactory. Statistical comparison of the results is conducted by comparing statistics obtained by structural filtering, normalized diﬀerence water index method and by spectral segmentation method. The excellent potential surface water areas can be extracted by using the proposed method.
Keywords: Color transformed clustering • LISS III data • Normalized Difference Vegetation Water Index.
Evaluating the Performance of a Neural Network-based Multi-criteria Recommender System
by Mohammed Hassan, Mohamed Hamada
Abstract: Frequent use of Internet applications and rapid increase in volumes of resources have made it difficult for online users to effectively make decisions on the kinds of information or items to select. Recommender systems (RSs) are intelligent decision-support tools that exploit preferences of users and suggest items that might be interesting to them. RSs are one of the various solutions proposed to address the problems of information overload. Traditionally, RSs use single rating techniques to predict and represent preferences of users for items that are not yet seen. Multi-criteria RSs use multiple ratings to various attributes of items for improving prediction and recommendation accuracy of the systems. However, one major challenge of multi-criteria RSs is the choice of an efficient approach for modelling the criteria ratings. Therefore, this paper aimed at employing artificial neural networks to model the criteria ratings and determine the predictive performance of the systems based on aggregation function approach. Seven evaluation metrics have been used to evaluate and measure the accuracy of the systems. The empirical results of the study have shown that the proposed technique has the highest prediction and recommendation than the corresponding traditional technique.
Keywords: Recommender Systems; Artificial Neural Networks; Prediction Accuracy; Aggregation Function; Multi-criteria Recommendation.
Special Issue on: Remote Sensing Big Data Theory, Methods and Applications
Application of AHP-VIKOR and GMDH Framework to develop an indicator to identify utilization potential of Wave energy converter with respect to location
by Tilottama Chakraborty, Mrinmoy Majumder, Ankit Khare
Abstract: The potential of Analytical Hierarchy Process (AHP)- rough number based compromise ranking method (also known as VIKOR) Multi Criteria Decision Making (MCDM) and Group Method of Data Handling (GMDH) Multimodal predictive method in development of an indicator for smart representation of "utilization potential" of wave energy converters with respect to specific locations. The significant parameters were identified by their consideration in different case studies and their influence on converter efficiency. The soft-computation methods like AHP-VIKOR and GMDH are used to find the relative priority values of the parameters and to develop an automatic framework for estimation of the indicator which is made directly proportional to the ability of the converter to utilize existing potential of wave energy in a specific location. The results from the multi-method estimation model were validated with the help of Multi Linear Regression Equation and some real time case analysis. With an accuracy of above, 99% the ensemble MCDM-ANN model depicts a reliability which ensures the author of its wide application for the real benefits like cost reduction and efficiency maximization of converters in the utilization of the potential energy of the locations.
Keywords: Analytical Hierarchy Process (AHP); VIKOR; Group Method of Data Handling (GMDH); Ensemble Modeling; Wave Energy Converter.
State of Art on Efficient Document Co-editing in Cloud Collaboration
by Tanuja Kumari Sharma, Hemraj Saini
Abstract: Cloud collaboration is an important technique which helps distant place authorize users to share their work, information and files over the cloud at the same instant of time. This technique reduces the communication cost because the mutual sharing work office can set up easily over the network at distant locations. The focus of this study is to remove the problem of the deadlock or long time waiting zone condition for requests edit threads, by the users in collaborative structure. The co-authoring or co-editing process generates a major problem in form of writing confliction in concurrent and single user editor system in cloud collaboration process, hence multi-version approach is implementing as a solution here on conflicting common event, so that simultaneous access to object get maintain for a long time in cloud collaboration co-editing environment. In this study cloud collaboration architecture is discussing in detail which describes the efficient working of central cloud, remote cloud and local cloud in collaborating environment. All the services in this cloud architecture communicate through important interfaces. This overall study is helpful due to involvement of central cloud which helps to minimize the storage space of data in the cloud and this also resolve a redundancy factor.
Keywords: Single user editor system; Co-authoring; Co-editing; Multi-version; Cloud collaboration; Quality of service; User domain; Cloud domain; Central cloud.
Topic Based Hierarchical Summarization of Twitter
by BUSHRA SIDDIQUE, Nadeem Akhtar
Abstract: Twitter has become a rich source of information now days. The data generated however is so large in volume that it is not possible to manually go through each and every tweet to understand the context of data. One of the ways to get insight into the bulk of data at hand is to know the topics contained in it. As in the context of Twitter, we define topics to be long-lasting subjects around which the conversations of people revolve, such as sports, music and politics amongst others. However, the topics identified may be large in number and might be cumbersome for human interpretation. Considering these views, in this paper we address the information overload problem of Twitter data and propose a topic based hierarchical summarization framework for the same. In contrast to imposing restrictions on topic models to depict the hierarchical structure, we propose an algorithm which constructs a topic hierarchy out of any given number of topics. We showcase the effectiveness of the proposed algorithm for the Twitter dataset prepared for Egyptair MS181 flight incident.
Keywords: Twitter; topic based summarization; topic hierarchy.