By Topic

Computer Science and Software Engineering (JCSSE), 2012 International Joint Conference on

Date May 30 2012-June 1 2012

Filter Results

Displaying Results 1 - 25 of 73
  • Author index

    Page(s): 405 - 406
    Save to Project icon | Request Permissions | PDF file iconPDF (282 KB)  
    Freely Available from IEEE
  • [Blank page]

    Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (655 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (9130 KB)  
    Freely Available from IEEE
  • A novel approach to identify problematic call center conversations

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1626 KB) |  | HTML iconHTML  

    Voice based call centers enable customers to query for information by speaking to agents in the call center. Most often these call conversations are recorded for analysis with the intent of trying to identify things that can help improve the performance of the call center to serve the customer better. Today the recorded conversations are analyzed by humans by listening to call conversations, which is both time consuming, fatigue prone and not accurate. Additionally, humans are able to analyze only a small percentage of the total calls because of economics. In this paper, we propose a visual method to identify problem calls quickly. The idea is to sieve through all the calls and identify problem calls, these calls can then be further analyzed by human. We first model call conversations as a directed graph and then identify a structure associated with a normal call. All call conversations that do not have the structure of a normal call are then classified as being abnormal. In this paper, we use the speaking rate feature to model call conversation because it makes it easy to spot potential problem calls. We have experimented on real call center conversations acquired from a call center and the results are encouraging. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic online text selection for constructing text corpus with custom phonetic distribution

    Page(s): 6 - 11
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1910 KB) |  | HTML iconHTML  

    Performance of Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems depends on an appropriate text corpus. This article explains about the automated text corpus generation method using custom phonetic distribution. This distribution is defined by phoneme types, corpus size, the minimum criterion number of phonemes, and target phonetic distribution. Generally, the system selects text data from the Internet by continuously downloading them using a web crawler. The greedy algorithm is applied to extract the proper sentences, in order to fit with the target phonetic distribution until the appropriate text corpus is established. The experiment is done by using the text from the Large Vocabulary Continuous Speech Recognition (LVCSR) corpus for Thai language [1] to generate the target phonetic distribution. The result shows that the increased number of data drawn from the Internet is able to accomplish the target phonetic distribution and generates diphone coverage for 99.13%. This text corpus, then, can be used to generate the speech corpus efficiently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Available car parking space detection from webcam by using adaptive mixing features

    Page(s): 12 - 16
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1622 KB) |  | HTML iconHTML  

    This paper presents a robust approach for detection of available car parking spaces. With low quality of video camera as webcam and dynamic change of light around the car parking, it is hard to accurately detect or recognize the cars. Moreover the proposed appearance-based approach is efficient than recognition-based approach because it do not need to learn a huge of multi-view objects. In this paper, we propose adaptive background model-based object detection with dynamic mixing features of masked-area and edge orientation histogram (EOH) density. The average variance of variance of intensity change for dynamic background model is used to change ratio of mixing features dynamically. The masked-area density is density of predefined area of a parking slot that is weighted by Gaussian mask to robust density computation and the edge orientation histogram (EOH) density is density of the EOH in the predefined area that can be used under low contrast image as night scene. The experiments are performed both in simulation model and real scenes. The results show the proposed approach can handle dynamic change of light efficiently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of time-domain features for motor imagery movements using FCM and SVM

    Page(s): 17 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1075 KB) |  | HTML iconHTML  

    Brain-Machine Interface is a direct communication pathway between brain and an external electronic device. BMIs aim to translate brain activities into control commands. To design a system that translates brain waves and its activities to desired commands, motor imagery tasks classification is the core part. Classification accuracy not only depends on how capable the classifier is but also it is about the input data. Feature extraction is to highlight the properties of signal that make it distinct from the signal of the other mental tasks. Performance of BMIs directly depends on the effectiveness of the feature extraction and classification algorithms. If a feature provides large interclass difference for different classes, the applied classifier exhibits a better performance. In order to attain less computational complexity, five time-domain procedure, namely: Mean Absolute Value, Maximum peak value, Simple Square Integral, Willison Amplitude, and Waveform Length are used for feature extraction of EEG signals. Two classifiers are applied to assess the performance of each feature-subject. SVM with polynomial kernel is one of the applied nonlinear classifier and supervised FCM is the other one. The performance of each feature for input data are evaluated with both classifiers and classification accuracy is the considered common comparison parameter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hazardous signs and fire exit signs classification using appropriate shape coding algorithm and BPN

    Page(s): 23 - 27
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1849 KB) |  | HTML iconHTML  

    This paper presents the hazardous signs and fire exit signs classification in vision-based fire protection and fire evacuation paths control system. The algorithm described here take an advantage of image sign features that their colors and shapes are very different from natural environments. The system is divided into three parts, first for image detection by CCD camera that is installed with user's cover head set. The camera is connected to user with their PDA and then sent this image data via on Wi-Fi Channel to fire protection control system center. The preprocessing process is used to reduce the noise effect and shape coding analysis with a continuous thinning algorithms are used in second part for reduced the sized of data and can be representatives for suitable features of image data to classify by an image binary data encoding algorithm. Finally, the Back Propagation Neural Network (BPN) techniques are used in image recognition and classification process and display the correct sign that meaning for suitable fire extinguishers and fire evacuation paths. By applying the present method, performance has been improved which more than 96% correctly in laboratory room. Some results from natural scenes are shown that system performance may be improved the capability to detect the image signs in longer range and more efficiency adjust in classification algorithms that can be support for real time capture image as VDO streaming. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human gesture recognition using Kinect camera

    Page(s): 28 - 32
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (923 KB) |  | HTML iconHTML  

    In this paper, we propose a comparison of human gesture recognition using data mining classification methods in video streaming. In particular, we are interested in a specific stream of vector of twenty body-joint positions which are representative of the human body captured by Kinect camera. The recognized gesture patterns of the study are stand, sit down, and lie down. Classification methods chosen for comparison study are backpropagation neural network, support vector machine, decision tree, and naive Bayes. Experimental results have shown that the backpropagation neural network method outperforms other classification methods and can achieve recognition with 100% accuracy. Moreover, the average accuracy of all classification methods used in this study is 93.72%, which confirms the high potential of using the Kinect camera in human body recognition applications. Our future work will use the knowledge obtained from these classifiers in time series analysis of gesture sequence for detecting fall motion in a smart home system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural computing-based pedestrian detection from image sequence

    Page(s): 39 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1505 KB) |  | HTML iconHTML  

    Preventing a traffic accident is a good way to solve many problems in the world for the current generation surrounding with many automotive technologies causing many people's death from the accident. The prevention makes an important impact to every society for making many people more safety and improving their lives' quality. In the fact, the primary cause is mostly drivers' carelessness and lacking of control, which might be because of addiction of drugs, resulting that a pedestrian walking on a road pains and then becomes dead. Therefore the problem can be solved using a computer for analysis and making a decision as a human called pedestrian detection. This study uses many several enhancement algorithms and processes for detecting integrated with an analysis based on a neural computing to decide whether a detected object is a pedestrian. Moreover the study shows an experimental result that the procedure is sufficient and efficient to be a fundamental knowledge for the next related work including a real-life traffic situation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Re-established Cost Function Training algorithm to enhance accuracy of minority class in imbalanced data learning

    Page(s): 39 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1298 KB) |  | HTML iconHTML  

    A new training algorithm to enhance the accuracy of minority class in imbalanced data learning problem was proposed. This algorithm is based on the observation that the cause of lower accuracy is due to the domination of the error terms, i.e. the square of difference between the target and the actual output, computed by those data in majority class in the cost function. To resolve this domination, our cost function is re-established at each epoch based on the errors of the data in minority and majority classes. Any datum whose corresponding term in the cost function produces an error is less than 5% is removed from cost function. Otherwise, it is put back into the cost function. Our algorithm that used multilayer perceptron and Levenberg-Marquardt (LM) as the learning algorithm was compared with classical LM and the recent algorithm RAMOBoost based on 15 well-known benchmarks. The experimental results of our approach produced higher accuracy than the other approaches in 13 cases with faster training speed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving Multimodal problems by Coincidence Algorithm

    Page(s): 45 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1038 KB) |  | HTML iconHTML  

    In general, Multimodal optimization is hard problems even for Evolutionary Algorithm. Using a Genetic Algorithm (GA) to solve these problems, the algorithm cannot converge to solutions easily. This work presents a study of Coincidence Algorithm (COIN) to solve these problems. COIN has an ability to retain multiple solutions in its model; hence it is suitable for Multimodal optimization problems. The experiment is carried out to illustrate this capability. The benchmarks are designed for comparing the problem solving behavior of COIN against a Genetic Algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web usage pattern analysis through web logs: A review

    Page(s): 49 - 53
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (983 KB) |  | HTML iconHTML  

    Web server log repositories are great source of knowledge, which keeps the record of web usage patterns of different web users. The Web usage pattern analysis is the process of identifying browsing patterns by analyzing the user's navigational behavior. The web server log files which store the information about the visitors of web sites is used as input for the web usage pattern analysis process. First these log files are preprocessed and converted into required formats so web usage mining techniques can apply on these web logs. This paper reviews the process of discovering useful patterns from the web server log file of an academic institute. The obtained results can be used in different applications like web traffic analysis, efficient website administration, site modifications, system improvement and personalization and business intelligence etc. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new mobile phone system architecture for the navigational travelling blind

    Page(s): 54 - 59
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1172 KB) |  | HTML iconHTML  

    This paper introduces a new mobile phone system architecture to aid the blind in travelling. The architecture has four main units: voice/speech recognition, Global Positioning System (GPS) and map services, ultrasonic sensor, and image processing service. These four subsystems function simultaneously within a single mobile device using web service interaction. The paper describes the instrument and component of the key design as well as implementation decisions. The feasibility of the architecture has been tested with Windows Phone 7 (HTC HD7), and cooperated with the real blind. Additionally, we have evaluated the performance of Hough Transform for straight line detection - the main component intensively using the processing power - and then we have optimized the Hough Transform to reduce the complexity leading to lower average response time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Delay prediction in Mobile Ad Hoc Network using trapezoidal fuzzy numbers

    Page(s): 60 - 64
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (836 KB) |  | HTML iconHTML  

    The end-to-end packet delay in mobile ad hoc network depends on many influential variables such as path length from source to destination, average number of neighbours of intermediate hops, interference from other transmissions and medium access control protocol etc. Hence, accurate prediction of end-to-end packet delay is very difficult but necessary for Quality of Service (QoS) routing in Mobile Ad Hoc Network (MANET) environment. In this article, we have tried to evaluate the applicability and capability of fuzzy logic based model for prediction of end-to-end packet delay in mobile ad hoc network environment. We have used trapezoidal fuzzy numbers for this purpose in our study. The data set were generated by Network Simulator for three different mobility models namely (i) Manhattan Grid mobility model, (ii) Gauss Markov and (iii) Random way Point mobility model. The routing algorithm used is Ad hoc On Demand Distance Vector (AODV) routing. Through our experiments, we have found that trapezoidal fuzzy number based model gives a reasonably good prediction result in terms of various performance evaluation criterion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design and analysis of a secure agent-based mobile bill payment protocol for bulk transactions

    Page(s): 71 - 76
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1299 KB) |  | HTML iconHTML  

    Nowadays, an agent-based mobile pa yment has become more popular. However, existing payment systems still lack of necessary mobile payment properties. Especially, they should be shorter and lightweight for making payment on the move. This paper introduces a new secure lightweight mobile bill payment protocol with assistance of an intermediary acting as an agent to collect and process payment requests made by clients. This protocol not only satisfies necessary transaction security properties, but it is also simple and compatible to existing mobile payment infrastructure. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Examining the network traffic of facebook homepage retrieval: An end user perspective

    Page(s): 77 - 81
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1428 KB) |  | HTML iconHTML  

    Facebook is one of the most famous social network sites hosting a number of users approaching a billion [1]. Facebook is a cloud-based web site which contains a number of advanced technologies behind the scene. Despite the fact that it is the web site that most users open for all-day and, in some places, all-night long, and its traffic is generally part of all types of networks - wired and wireless, PAN, LAN, MAN, and WAN -, there is virtually no research work or technical paper that report on client's perspective of what happen when users login onto their Facebook homepages. How many and in what order components loaded are, which and how many servers those components loaded are, or how many TCP streams used, are examples of questions which users and network administrators have a little knowledge of. Our work tries to answer the questions by examining every of over 2,000 packets per a single Facebook homepage retrieval using the Wireshark packet capturing software. From the captured packets, we thoroughly examined all objects that Facebook retrieved and categorized them into groups based on the characteristics. Our investigations found that Facebook retrieves these objects from both international and domestic servers, and over a number of parallel TCP streams. The results also showed that the Facebook traffic exhibited a two-spike bursty pattern, regardless of the loading time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving confidentiality of AES-CCMP in IEEE 802.11i

    Page(s): 82 - 86
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1253 KB) |  | HTML iconHTML  

    This paper proposed a new method for Advanced Encryption Standard-Counter Mode with Cipher Block Chaining Message Authentication Code Protocol (AES-CCMP) to eliminate security issues in current method including small effective key length and predictable structure of Nonce which increases the probability of Time-Memory Trade-Off (TMTO) attack. Proposed method suggests three solutions to overcome the mentioned weaknesses including random NonceKey, four way handshake alteration and Pseudo Random Function (PRF). Besides, proposed and classic methods are compared in terms of TMTO attack probability, avalanche effect, changes in neighbor blocks, memory usage and execution time. According to the results, the proposed method is completely resistant to TMTO attack. In addition, avalanche effect and change in neighbor blocks of proposed method are so near to optimized state and also, classic and proposed methods are approximately the same in case of memory usage and execution time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interactive voice uncertainties for emergency communication suspends automation

    Page(s): 87 - 92
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (947 KB) |  | HTML iconHTML  

    Freedom Fone (FF) is an Interactive Voice Response (IVR) System that integrates with the Global System for Mobile (GSM) telecommunications [1]. Sahana is a disaster information management expert system working with Internet technologies [2]. The Project intent was to mediate information between the FF and Sahana through the Emergency Data Exchange Language (EDXL) interoperable content standard [3]. It goal was to equip Sarvodaya, Sri Lanka's largest humanitarian organization, with voice-enabled disaster communication. The 3.52 Mean Opinion Score (MOS) for voice quality was an early automation challenge in introducing Automatic Speech Recognition (ASR). A 4.0 MOS was determined as a cut-point for classifying reliable voice data [4]. The Percent Difficult (PD) in an emulated speaker-independent scenario was 29.44% and a speaker-dependent scenario was 13.24%. Replacing human operators with ASR software proved inefficient [5] and [6]. This paper discusses uncertainties that are barriers to integrating voice enabled automated emergency communication services for response resource analysis and decision support. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measuring self-healing delay of Java-implemented multi-homed SCTP association

    Page(s): 93 - 97
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1147 KB) |  | HTML iconHTML  

    Multi-homing is a new feature of SCTP not existed in UDP or TCP. It allows multiple IP addresses to be attached to a single connection to improve stability of data transfer. It significantly enhances reliability and redundancy of transport layer in several levels - from multiple physical network interface cards to complete different logical end-to-end paths. Recently, SCTP protocol was officially made available to millions of Oracle's Java JDK developers. This hints a possibility of great increases of Java-based SCTP multi-homed traffic on the future Internet. This research work investigates behaviors, processes, and performance of self-healing ability of Java-based version of multi-homed SCTP association. A simple multi-homed data transfer program written in Java had been developed and a number of LAN-based experiments had been conducted. Experimental results show, firstly, that client-side and server-side faults dissimilarly affect SCTP recovery process and time. Secondly, HEARTBEAT packet exchanges play a major role for SCTP self-healing process. Thirdly, an average recovery time of the client-side disruption is 0.5 seconds and that of the server-side disruption is 45 seconds. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SARIMA based network bandwidth anomaly detection

    Page(s): 104 - 108
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (927 KB) |  | HTML iconHTML  

    Network bandwidth is considered a valuable resource in most computer systems. To precisely detect network anomalies (with a few false alarms), an intrusion detection system requires reliable methods. A potential solution in predicting network bandwidth usage is using a time-series model with a threshold. This paper proposes a network anomaly detection technique based on SARIMA, a time-series model, to capture seasonal behavior of bandwidth usage of most networks. Our proposed SARIMA based anomaly detection is capable of detecting network bandwidth anomalies effectively when a threshold equals to 8.5 percents of maximum bandwidth in a day. Our result yields 3.57 percents of false alarms. We concluded that SARIMA is a better instrumental tool for intrusion detection comparing to ARIMA. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The most promising scheduling algorithm to provide guaranteed QoS to all types of traffic in multiservice 4G wireless networks

    Page(s): 109 - 115
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (401 KB) |  | HTML iconHTML  

    There is a growing interest of wireless operators to migrate their existing 3G networks to different 4G technologies such as WiMAX and LTE. In this heterogeneous environment of wireless networks and architectures, one of the major concerns is how to allocate network resources efficiently to diverse traffic classes with different QoS constraints. Further it has been convincingly demonstrated through numerous high quality studies that multimedia traffic found in modern wireless networks exhibits Long-Range Dependence (LRD) and self-similarity, a phenomenon which cant' be captured by traditional traffic modeling based on simplistic Poisson model. Unlike most existing studies that are primarily based on simplistic Poisson model and traditional scheduling algorithms, this research presents an analytical performance model for multiple queue systems with self-similar traffic input scheduled by a novel and promising scheduling mechanism. Our proposed model is substantiated on G/M/1 queuing system that considers multiple classes of traffic exhibiting long-range dependence and self-similar characteristics. We analyze the model on the basis of newly proposed scheduling scheme. We present closed form expressions of expected waiting times for multiple traffic classes. We develop a finite queue Markov chain for the proposed scheduling scheme. We develop a discrete event simulator to understand the behavior of multiple classes of self-similar traffic under this newly proposed scheduling mechanism. The results indicate that our proposed scheduling algorithm provides preferential treatment to real-time applications such as voice and video but not to that extent that data applications are starving for bandwidth and outperforms all other scheduling schemes that are available in the market. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a streaming content delivery network

    Page(s): 116 - 119
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (961 KB) |  | HTML iconHTML  

    The distribution of multimedia streaming requires efficient management strategies in multisite environment with multiple senders and receivers. The intermediate nodes between senders and receivers act as the Streaming Routers (SR1). They play an important role in the distribution of required contents by relaying and dropping video frames which depends on the network characteristics of peer receivers. In the highly changing network conditions, the SRs can leave or join the system anytime in the middle of stream transmission. In this scenario, it becomes a tedious task to manage the SRs when frequent switching of streaming sources occur. The coordination among streaming sources is also a challenging task. The emphasis of this work is to create the self-configured streaming system for the high quality streaming and highly unstable heterogeneous environment. The goal of self-configuration is to eliminate or minimize the configuration effort required by the system administrator. The application independent approach is taken so that various ranges of applications can be used without altering the system. We are conducting experiments over the PlanetLab. This paper describes an architectural design of a streaming content delivery network along with the experiments conducted on the PlanetLab testbed environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards the selection of future 4G mobile service provider from customers' perspective

    Page(s): 120 - 125
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (977 KB) |  | HTML iconHTML  

    Mobile communication is clearly one of the most astounding mass consumption phenomena of the last decades, which transversal diffusion has embraced all social classes. This paper focuses on the market dynamics of mobile telecommunications market from consumer's perspective and we seek to explain the diffusion of technology intensive mobile communications among Saudi culture. We investigate the role of Tri Component Attitude Model and Standard Learning Hierarchy to evaluate the stages a consumer passes through before adopting an innovation. The myriad product and service choices available in mobile communication industry empowers consumers to switch products on the most fleeting of whims. In recent years there have been many articles about the changing face of telecommunications and how they provide consumers with more choices and better quality trends as they rapidly evolve with the changing needs of today's consumers. It has come to our understanding that the role of Tri Component Attitude Model on consumer behavior is largely neglected in telecom market. Another goal of this research is to study the role of Customer Relationship Management (CRM) in Saudi Arabia telecommunication market. This study concentrates on major service providers of mobile and wireless internet services how they are rated by the customers in terms of CRM. It is empirically testified that the quality of customer service significantly effects customer satisfaction and predisposes them positively towards the brand hence increasing their loyalty. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An implementation of Coincidence Algorithm on Graphic Processing Units

    Page(s): 126 - 130
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1498 KB) |  | HTML iconHTML  

    Genetic Algorithms (GAs) are powerful search techniques. However when they are applied to complex problems, they consume large computation power. One of the choices to make them faster is to use a parallel implementation. This paper presents a parallel implementation of Combinatorial Optimisation with Coincidence Algorithm (COIN) on Graphic Processing Units. COIN is a modern GA. It has a wide range of applications. The result from the experiment shows a good speedup in comparison to a sequential implementation on modern processors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.