Zahid Halim

Measuring entertainment and automatic generation of entertaining games

Over the period of time computer games have became a major source of entertainment for humans. From the point of view of game developers there is a constant demand of writing games which are entertaining for the end users but entertainment itself is of subjective nature. It has always been difficult to quantify the entertainment value of the human player. The two factors which mainly influence the entertainment value are the type of the game and the contents of the game. In this paper we address the issues of measuring entertainment and automatic generation of computer games. We present some quantitative measures for entertainment in a genre of computer game and apply them as a guide for the evolution of new interesting games.

Clustering large probabilistic graphs using multi-population evolutionary algorithm

Determining valid clustering is an important research problem. This problem becomes complex if the underlying data has inherent uncertainties. The work presented in this paper deals with clustering large probabilistic graphs using multi-population evolutionary algorithm. The evolutionary algorithm (EA) initializes its multiple populations, each representing a deterministic version of the same probabilistic graph given to it as an input. Multiple deterministic versions of the same input graph are generated by applying different thresholds to the edges. Each chromosome of the multiple populations represents one complete clustering solution. For the purpose of clustering, EA is employed which is guided by pKwikCluster algorithm. The proposed approach is tested on two natively probabilistic graphs and nine synthetically converted probabilistic graphs using cluster validity indices of Davies-Bouldin index, Dunn index, and Silhouette coefficient. The proposed approach is also compared with two baseline clustering algorithms for uncertain data, Fuzzy-DBSCAN and uncertain K-mean and two state-of-the-art approaches for clustering probabilistic graphs. The results obtained suggest that the proposed solution gives better performance than the baseline methods and the state-of-the-art algorithms.

Multi-view document clustering via ensemble method

Multi-view clustering has become an important extension of ensemble clustering. In multi-view clustering, we apply clustering algorithms on different views of the data to obtain different cluster labels for the same set of objects. These results are then combined in such a manner that the final clustering gives better result than individual clustering of each multi-view data. Multi view clustering can be applied at various stages of the clustering paradigm. This paper proposes a novel multi-view clustering algorithm that combines different ensemble techniques. Our approach is based on computing different similarity matrices on the individual datasets and aggregates these to form a combined similarity matrix, which is then used to obtain the final clustering. We tested our approach on several datasets and perform a comparison with other state-of-the-art algorithms. Our results show that the proposed algorithm outperforms several other methods in terms of accuracy while maintaining the overall complexity of the individual approaches.

Fairness-Driven Queue Management: A Survey and Taxonomy

Providing congestion control in the Internet, while ensuring fairness among a myriad of heterogeneous flows, is a challenging task. The conventional wisdom is to rely on end-user applications cooperatively deploying congestion control mechanisms to achieve high network utilization and some degree of fairness among flows. However, as the Internet has evolved to encompass all of society, such a cooperative behavior from end-user applications is not always granted. Applications may simply act selfishly to be more competitive through bandwidth abuse. Bandwidth starvation may also arise unintentionally depending on the nature of traffic sources. The ensuing impact can be severe fairness hazard and even congestion collapse. Router-based queue management schemes driven by fairness objectives, thus, become an inescapable necessity for fairly sharing network resources. Given a significant volume of literature relating to fairness-driven queue management schemes, there has remained a need for a broader and coherent survey. This paper presents a systematic and comprehensive review of eminent fairness-driven queue management schemes from the inception of the concept and the preliminary work to the most recent work. We present a new taxonomy of categorizing fairness-driven queue management schemes. We discuss design approaches and key attributes of these schemes and provide their comparison and analysis. Based on the outcomes of this survey, we discuss a number of open issues and provide generic design guidelines and future directions for the research in this field.

Sonification: a novel approach towards data mining

The field of sonification is a subset of auditory display. It brings together interests from data mining, exploratory data analysis, human-computer interface and musical interfaces. Sonification is the mapping of data to sound; it is a rich and relatively unexplored technique for data mining. The idea behind sonification is that nonverbal sounds can be used to represent numerical data and provide support for information processing activities of many different kinds. In this paper we present three quantification rules for using sonification in data mining. We also present an RPAI (rain prediction auditory icon) algorithm to predict rain using auditory icon. This integrates two new areas of research i.e. sonification and climate data mining. Weather data mining (forecasting) gained a lot of interest in last couple of years due to its large applications on water, agriculture, energy, health and retail market. The use of climate data mining is new and is in its infancy stages of being used for a variety of businesses. This creates the opportunity to explore enhancements to decision strategies through a suite of research analysis and tool development. We perform experiments using RPAI algorithm on rain data from a metrological site and discuss the results

Malicious users' circle detection in social network based on spatio-temporal co-occurrence

Online social networks have witnessed massive increase from the point of view of users during last decade. However, it is also becoming center of attraction for spammers. It is a complex problem to trace spammers on a large scale. Since spammers communicate covertly so by analyzing simple graph of social network, they cannot be identified. In order to find the circle of people involved in the malicious messaging, we associate people on the basis of their spatio-temporal co-occurrence i.e. people frequently communicating with each other. In this paper, we associate people on the basis of their spatio-temporal co-occurrence and find the users involved in malicious communications.

Fraudulent call detection for mobile networks

Telecommunication industry has witnessed an enormous growth in terms of number of subscribers and revenue over the past few years. Still there are certain trends in the revenue of the telecommunication that show an instant fall, reason being change in customer behavior. Telecom operators are subjected to fraud in various forms, among the leading are subscription and superimposition fraud. In the U.S the sum of losses caused by fraudulent activity for the telecom industry is over 650 million dollars a year. The aim in this work is to cater the subscription fraud and bring the figures well within the desired range. In this work we use machine learning techniques to address the issue. Our solution uses a neural network to detect fraudulent behavior for subscription fraud. The neural network takes as input time series data of individual customers to predict their normal behavior. The crucial aspects of the networks predictions being accurate are the fraud profiles; some test cases are created which are used to make the neural network learn a fraudulent behavior.

Employing artificial neural networks for constructing metadata-based model to automatically select an appropriate data visualization technique

Display Omitted Solution to automatically select appropriate visualization technique based on metadata is presented.A purpose built dataset extracted from existing knowledge in the field is used to train classifiers.A comparison of the results obtained from the best ANN architecture is performed with five other classifiers.The proposed system outperforms four classifiers in terms of accuracy and five classifiers based on running time.The work brings new perspective in the field of visualization. Advances in computing technology have been instrumental in creating an assortment of powerful information visualization techniques. However, the selection of a suitable and effective visualization technique for a specific dataset and a data mining task is not trivial. This work automatically selects an appropriate visualization technique based on the given metadata and the task that a user intends to perform. The appropriate visualization is predicted based on an artificial neural network (ANN)-based model which classifies the input data into one of the eight predefined classes. A purpose built dataset extracted from the existing knowledge in the discipline is utilized to train the neural network. The dataset covers eight visualization techniques, including: histogram, line chart, pie chart, scatter plot, parallel coordinates, map, treemap, and linked graph. Various architectures using different numbers of hidden units, hidden layers, and input and output data formats have been evaluated to find the optimal neural network architecture. The performance of neural networks is measured using: confusion matrix, accuracy, precision, and sensitivity of the classification. Optimal neural network architecture is determined by convergence time and number of iterations. The results obtained from the best ANN architecture are compared with five other classifiers, k-nearest neighbor, nave Bayes, decision tree, random forest, and support vector machine. The proposed system outperforms four classifiers in terms of accuracy and all five classifiers based on execution time. The trained neural network is also tested on twenty real-world benchmark datasets, where the proposed approach also provides two alternate visualizations, in addition to the most suitable one, for a particular dataset. A qualitative comparison with the state-of-the-art approaches is also presented. The results show that the proposed technique assists in selecting an appropriate visualization technique for a given dataset with high accuracy.

A Kinect-Based Sign Language Hand Gesture Recognition System for Hearing- and Speech-Impaired: A Pilot Study of Pakistani Sign Language

Sign language provides hearing and speech impaired individuals with an interface to communicate with other members of the society. Unfortunately, sign language is not understood by most of the common people. For this, a gadget based on image processing and pattern recognition can provide with a vital aid for detecting and translating sign language into a vocal language. This work presents a system for detecting and understanding the sign language gestures by a custom built software tool and later translating the gesture into a vocal language. For the purpose of recognizing a particular gesture, the system employs a Dynamic Time Warping (DTW) algorithm and an off-the-shelf software tool is employed for vocal language generation. Microsoft® Kinect is the primary tool used to capture video stream of a user. The proposed method is capable of successfully detecting gestures stored in the dictionary with an accuracy of 91%. The proposed system has the ability to define and add custom made gestures. Based on an experiment in which 10 individuals with impairments used the system to communicate with 5 people with no disability, 87% agreed that the system was useful.

Evolutionary Search in the Space of Rules for Creation of New Two-Player Board Games

Games have always been a popular test bed for artificial intelligence techniques. Game developers are always in constant search for techniques that can automatically create computer games minimizing the developers task. In this work we present an evolutionary strategy based solution towards the automatic generation of two player board games. To guide the evolutionary process towards games, which are entertaining, we propose a set of metrics. These metrics are based upon different theories of entertainment in computer games. This work also compares the entertainment value of the evolved games with the existing popular board based games. Further to verify the entertainment value of the evolved games with the entertainment value of the human user a human user survey is conducted. In addition to the user survey we check the learnability of the evolved games using an artificial neural network based controller. The proposed metrics and the evolutionary process can be employed for generating new and entertaining board games, provided an initial search space is given to the evolutionary algorithm.