16-18 Aug. 2017
Filter Results
-
Knowledge sharing mechanism in social networking for learning
Publication Year: 2017, Page(s):9 - 14Social media based learning resources are powerful tools for enhancing teaching and research activities in the university education system. This paper focuses on the development of a prototype web based learning resource with the purpose for users to exchange project software development knowledge. This study explores the efficiency of social networking systems as instructional tools in the comput... View full abstract»
-
Texture image classification using wavelet completed local binary pattern descriptor (WCLBP)
Publication Year: 2017, Page(s):15 - 20In this paper, a new texture descriptor inspired from completed local binary pattern (CLBP) is proposed and investigated for texture image classification task. A wavelet-CLBP (WCLBP) is proposed by integrating the CLBP with the redundant discrete wavelet transform (RDWT). Firstly, the images are decomposed using RDWT into four sub-bands. Then, the CLBP are extracted from the LL sub-bands coefficie... View full abstract»
-
Classification of cotton oil in the semi-refining process using image processing techniques: Image processing for industrial applications
Publication Year: 2017, Page(s):21 - 25This paper presents a steps model classification in the cotton oil semi-refining process by image processing. A simple system of efficient analysis was obtained, allowing its use on the factory floor, assisting in the process with respect to the assertiveness in the desired semi-refined state and its quality control. Two algorithms with different recognition patterns were analyzed: K-Nearest Neigh... View full abstract»
-
A hybrid remote display scheme for interactive applications in band-limited environment
Publication Year: 2017, Page(s):167 - 173In Desktop as a Service (DaaS), the screen delivery is an essential part that influences the users' experience. In this paper, we propose a novel remote display scheme which makes use of both video and image encoder to improve the quality of service for interactive applications in a band-limited environment. The proposed scheme approximates the frame buffer update size and decides the encoder for ... View full abstract»
-
FPGA implementation of a hardware XTEA light encryption engine in co-design computing systems
Publication Year: 2017, Page(s):26 - 30In the era of viruses and hackers targeting high-tech information transported across the Internet, security is becoming a paramount goal. A cryptographic system is a method of hiding information where only the person owning the related secret key can open it. There are several types of cryptography algorithms that differ from each other in security complexity, the size of key and words operated on... View full abstract»
-
Woven fabric data retrieval across museums in Thailand using knowledge graph
Publication Year: 2017, Page(s):31 - 35This research proposes the unified system to store and retrieve information related to weave fabric for museums in Thailand using the knowledge graph technique. We have studied the traditional systems that have been used in several museums such as Na Muen Sri Museum and Prince of Songkhla University weave fabric museum. After that we design and implement the unified database schema that can store ... View full abstract»
-
A real-time anomaly detection algorithm/or water quality data using dual time-moving windows
Publication Year: 2017, Page(s):36 - 41Anomaly data in real-time water quality monitoring systems can cause false alarms and significantly decrease system stability and reliability. We propose a novel anomaly detection algorithm for water quality data using dual time-moving windows, which can identify anomaly data from historical patterns in real-time. The algorithm is based on an autoregressive linear combination model, a prediction i... View full abstract»
-
Convolutional and recurrent neural networks for real-time data classification
Publication Year: 2017, Page(s):42 - 45In this paper, methods of classification of real-time data are provided by using convolutional and recurrent neural networks. During the last several years, artificial intelligence researchers and specialists achieved notable results in visual, voice and natural language processing tasks by using new methods and approaches of deep learning, such as convolutional and recurrent neural networks. Howe... View full abstract»
-
Real-time emotional state detection from facial expression on embedded devices
Publication Year: 2017, Page(s):46 - 51
Cited by: Papers (1)From the last decade, researches on human facial emotion recognition disclosed that computing models built on regression modelling can produce applicable performance. However, many systems need extensive computing power to be run that prevents its wide applications such as robots and smart devices. In this proposed system, a real-time automatic facial expression system was designed, implemented an... View full abstract»
-
Suitability of BlackBox dataset for style analysis in detection of source code plagiarism
Publication Year: 2017, Page(s):90 - 94Plagiarism is one of the most common problem that has been increasing in the field of higher education. Many research papers have highlighted the issue of plagiarism in context to its detection and source that is often obtained from the text books and online sources, there is a variety of easy ways for students to copy others' work. Coding style can be used to detect source code plagiarism because... View full abstract»
-
Modelling of wind turbine power output by using ANNs and ANFIS techniques
Publication Year: 2017, Page(s):126 - 131In this study, artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) were applied to estimate the wind turbine power output of a horizontal axis wind turbine. Hub-height wind speed, atmospheric air temperature and rotational speed values obtained from an operating wind power plant (WPP) were employed as input data in the model. According to the derived results, the mean... View full abstract»
-
Deriving a representative vector for ontology classes with instance word vector embeddings
Publication Year: 2017, Page(s):79 - 84
Cited by: Papers (2)Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative vector for ontology classes whose instances were ... View full abstract»
-
Robust speaker verification in reverberant conditions using estimated acoustic parameters — A maximum likelihood estimation and training on the fly approach
Publication Year: 2017, Page(s):52 - 57Speaker recognition has been developed into a relatively mature state over the past few decades through continuous research and development work. Existing methods typically use the robust features extracted from noise and reverberation free speech signals, and therefore can achieve high recognition accuracy only in idealised conditions. Excessive reverberation as often occurs in many real world ap... View full abstract»
-
Mitigating wind noise in outdoor microphone signals using a singular spectral subspace method
Publication Year: 2017, Page(s):149 - 154Wind noise is one of the major concerns of outdoor microphone signal acquisition. Filtering and removal of wind noise are known to be difficult due to its broadband and time varying nature. This paper proposes the use of singular spectrum analysis to address the problem of microphone wind noise removal and/or separation. The paper is presented from the context of reducing microphone wind noise whe... View full abstract»
-
Automatic sunspots detection on SODISM solar images
Publication Year: 2017, Page(s):115 - 119The surface of the sun often shows visible sunspots which are located in magnetically active regions of the Sun, and whose number is an indicator of the Sun's magnetic activity. The detection and classification of sunspots are useful techniques in the monitoring and prediction of solar activity. The automated detection of sunspots from digital images is complicated by their irregularities in shape... View full abstract»
-
Adaptive technique for web page change detection using multi-threaded crawlers
Publication Year: 2017, Page(s):120 - 125World Wide Web is getting dense as many new web pages and resources are created on a daily basis. Keeping track of the changes in the web content has become an immense challenge and is a research problem with a great significance. Even the search engines require to detect changes in the web to keep search indexes up to date. Numerous researches have been carried out on optimizing the change detect... View full abstract»
-
Deploying smartAcademy: A cloud integrated methodology to develop smart IT graduates to meet the ICT enabled industrial needs in Middle East
Publication Year: 2017, Page(s):205 - 210Nowadays the term `cloud computing' is becoming as an imperative element for any organizational setup. In this paper, we recommend a service based cloud model to meet the education oriented technological needs of academic institutions in Middle East. In this new globalized economy, academic institutions must provide high quality teaching-learning infrastructure to prepare students for the growing ... View full abstract»
-
Improvement of data sharing efficacy of P2P streaming mobile networks for news-broadcast-on-demand services
Publication Year: 2017, Page(s):132 - 137Data sharing efficacy of P2P streaming mobile networks is sensitive to the content access paradigm of applications. This paper considers a news-broadcast-on-demand (NBOD) application, where news clips are categorized into several news channels according to their categories, and each user (subscriber) is allowed to set her/his own watching policy (such as favorite topics, recommended most, news sou... View full abstract»
-
Intelligent feature selection technique for segmentation of fundus images
Publication Year: 2017, Page(s):138 - 143We propose a technique for selecting effective features for fundus image segmentation. The technique has made it possible to conduct smart feature analysis with the aid of color subspaces when solving a problem of selecting the regions of interest. The relevance of the problem is associated with enhancing the effectiveness of laser coagulation surgery. The technique is based on the texture analysi... View full abstract»
-
Adverse weather avoidance considering flight level changes
Publication Year: 2017, Page(s):144 - 148
Cited by: Papers (1)Adverse weather has serious implication for passenger and aircraft safety. This paper presents an improved weather avoidance system using a genetic algorithm-based technique. A cost model has been developed to estimate the impact of flight level changes to passenger and to consider other factors such as delay costs, weather impact costs, missed connection and schedules of other aircraft. The propo... View full abstract»
-
A hybrid recommendation system for E-commerce based on product description and user profile
Publication Year: 2017, Page(s):95 - 100
Cited by: Papers (1)E-commerce is an online trading system that eases transactions for both sellers and consumers without having to meet in person. The prevalence of e-commerce has increased competition amongst sellers, hence the users of e-commerce has to increase their performance, one of them by using recommendation system. This research develops a hybrid recommendation system for e-commerce that implements Conten... View full abstract»
-
Convolution neural network in precision agriculture for plant image recognition and classification
Publication Year: 2017, Page(s):1 - 3
Cited by: Papers (1)Agriculture is essential to the continued existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Precision Agriculture is thought to be solution required to achieve the production rate required. There has been a si... View full abstract»
-
A fuzzy neural network approach to estimate PMSG based and DFIG based wind turbines' power generation
Publication Year: 2017, Page(s):101 - 106Neural networks and fuzzy systems are amalgamate their advantages and to eliminate its individual disadvantages. Neural networks have its computational characteristics of learning in the fuzzy systems and receive from them the interpretation and clarity of systems representation. Thus, the disadvantages of the fuzzy systems are fulfilled by the capacities of the neural networks. These techniques a... View full abstract»
-
An integrated framework of conceptual modeling for performance improvement of the information systems
Publication Year: 2017, Page(s):174 - 180The traditional approaches have supported separate streams of conceptual modeling of the functional and non-functional requirements during the information systems development. Therefore, it is proposed the algorithm of the Integrated Framework for Conceptual Modeling (IFCMod) that consists five components for integration of the functional requirements (FRs) and the non-functional requirements (NFR... View full abstract»
-
A new hybrid model for dynamic pricing strategies of perishable products
Publication Year: 2017, Page(s):85 - 89The aim of this paper is to mitigation of spoilage rates of perishable products by applying dynamic pricing strategies. The present study is conducted with a deterministic model approach in consideration of various factors, such as interaction between freshness/staleness degrees of different groups of products, elasticity of demand against price and sensitivity of demand towards freshness degree. ... View full abstract»