IJITCS Vol. 8, No. 10, Oct. 2016
Cover page and Table of Contents: PDF (size: 184KB)
An evolving weighted neuro-neo-fuzzy-ANARX model and its learning procedures are introduced in the article. This system is basically used for time series forecasting. It's based on neo-fuzzy elements. This system may be considered as a pool of elements that process data in a parallel manner. The proposed evolving system may provide online processing data streams.[...] Read more.
Stock market prediction has been an interesting research topic for many years. Finding an efficient and effective means of predicting the stock market found its way in different social networking platforms such as Twitter. Studies have shown that public moods and sentiments can affect one's opinion. This study explored the tweets of the Filipino public and its possible effects on the movement of the closing Index of the Philippine Stock Exchange. Sentiment Analysis was used in processing individual tweets and determining its polarity - either positive or negative. Tweets were given a positive and negative probability scores depending on the features that matched the trained classifier. Granger causality testing identified whether or not the past values of the Twitter time series were useful in predicting the future price of the PSE Index. Two prediction models were created based on the p-values and regression algorithms. The results suggested that the tweets collected using geo location and local news sources proved to be causative of the future values of the Philippine Stock Exchange closing Index.[...] Read more.
Wireless sensor network (WSN) has emerged as potential technology for their applications in battlefields, infrastructure building, traffic surveillance, habitat monitoring, health, and smart homes. Unattended nature of these networks makes them vulnerable to variety of attacks, the inherent stringent resources makes conventional security measure infeasible. An attacker can capture a sensor node to install number of clone nodes with same privacy information causing serious security threats and deterioration in network lifetime. Current, security scheme along with distinct advantages suffer from number of limitations. A good counter attacks measure should not only cater for security and energy-efficiency but network lifetime as well. In this paper, we propose a next-node selection method which consider residual energy and clone attacks ratio in addition to distance, in order to overcome the limitation of fixed path based shortest routing. These factors are also considered while selecting the witness header in WSNs. Results demonstrate the efficacy of the proposed schemes in terms of network lifetime.[...] Read more.
The operation flow of particle swarm optimization (PSO) is presented, at the same time the PSO algorithm and GA algorithm are used to find the optimal value of the standard function, simulation results show that the PSO algorithm has better global search performance and faster search efficiency. The inertia weight decreasing strategy of PSO algorithm is studied, the simulation results show that the concave function decreasing strategy can accelerate the convergence rate of the algorithm. The stability control of the DC-side voltage is very important for the static var generator (SVG) compensation, but the disadvantages of the traditional PI control are fixed parameters and poor adaptability of dynamic response, PSO algorithm is introduced to the optimization of PI parameters, so online PSO-PI control and off-line PSO-PI control are obtained, the SVG voltage loop transfer function is used as the controlled object. The simulation results show that the PSO-PI control can satisfy the time varying system of the controlled object with strong adaptability.[...] Read more.
Optimizing K-means is still an active area of research for purpose of clustering. Recent developments in Cloud Computing have resulted in emergence of Big Data Analytics. There is a fresh need of simple, fast yet accurate algorithm for clustering huge amount of data. This paper proposes optimization of K-means through reduction of the points which are considered for re-clustering in each iteration. The work is generalization of earlier work by Poteras et al who proposed this idea. The suggested scheme has an improved average runtime. The cost per iteration reduces as number of iterations grow which makes the proposal very scalable.[...] Read more.
This paper introduces a new approach based on blind source separation (BSS) to mitigate intentional interference in BFSK digital communication systems using frequency hopping spread spectrum technique. The use of BSS is possible thanks to adopting an adequate selection block to distinguish between the useful signal and other undesirable signals, hence, circumvent the problem of ambiguity of permutation. An analytical calculation of the probability of error to predict the performance is done. The simulation results showed the effectiveness of this approach, whatever the level of the JSR and without using the fast frequency hopping alternative or error-correcting codes.[...] Read more.
Data governance is one of the strongest pillars in Data management program which goes hand in hand with data quality. In industrial Data Lake huge amount of unstructured data is getting ingested at high velocity from different source systems. Similarly, through multiple channels of data are getting queried and transformed from Data Lake. Based on 3Vs of big data it's a real challenge to set up a rule based on traditional data governance system for an Enterprise. In today's world governance on semi structured or unstructured data on Industrial Data lake is a real issue to the Enterprise in terms of query, create, maintain and storage effectively and secured way. On the other hand different stakeholders i.e. Business, IT and Policy team want to visualize the same data in different view to analyze, imposes constraints, and to place effective workflow mechanism for approval to the policy makers. In this paper author proposed property graph based governance architecture and process model so that real time unstructured data can effectively govern, visualize, manage and queried from Industrial Data Lake.[...] Read more.
In recent years, the mining research over data stream has been prominent as they can be applied in many alternative areas in the real worlds. In this paper, we have proposed an algorithm called MFIWDSIM for mining frequent itemsets with weights over a data stream using Inverted Matrix . The main idea is moving data stream to an inverted matrix saved in the computer disks so that the algorithms can mine on it many times with different support thresholds as well as alternative minimum weights. Moreover, this inverted matrix can be accessed to mine in different times for user's requirements without recalculation. By analyzing and evaluating, the MFIWDSIM can be seen as the better algorithm compared to WSWFP-stream  for mining frequent itemsets with weights over data stream.[...] Read more.
Data and Information has seen exponential growth in the past few years which has led to its importance in processing it in the creation of knowledge. Representing knowledge in a required format is the need for the building a knowledgebase (KB) for Expert Systems. In this paper we carried a survey on the knowledge representation models that will help us choose a suitable model for designing and developing a KB. A detailed study is conducted on six models and comparison of the models on some non-functional attributes are carried out to enable knowledge workers to decide on the model selection.[...] Read more.
Semantic search engines(SSE) are more efficient than other web engines because in this era of busy life everyone wants an exact answer to his question which only semantic engines can provide. The immense increase in the volume of data, traditional search engines has increased the number of answers to satisfy the user. This creates the problem to search for the desired answer. To solve this problem, the trend of developing semantic search engines is increasing day by day. Semantic search engines work to extract the best answer of user queries which exactly fits with it. Traditional search engines are keyword based which means that they do not know the meaning of the words which we type in our queries. Due to this reason, the semantic search engines super pass the conventional search engines because they give us meaningful and well-defined information. In this paper, we will discuss the background of Semantic searching, about semantic search engines; the technology used for the semantic search engines and some of the existing semantic search engines on various factors are compared.[...] Read more.