Skip to main content
main-content

Über dieses Buch

This volume of Advances in Intelligent Systems and Computing highlights papers presented at the 11th International Conference on Genetic and Evolutionary Computing (ICGEC 2017). Held from 6 to 8 November 2017 in Kaohsiung, Taiwan, the conference was co-sponsored by Springer, Fujian University of Technology in China, National University of Kaohsiung, Harbin Institute of Technology, National Kaohsiung University of Applied Sciences, and VŠB -Technical University of Ostrava. The conference was intended as an international forum for researchers and professionals engaged in all areas of genetic computing, intelligent computing, evolutionary and grid computing.

Inhaltsverzeichnis

Frontmatter

Evolutionary Computation

Frontmatter

A Many-Objective Evolutionary Algorithm with Reference Point-Based and Vector Angle-Based Selection

In this paper we proposed a many-objective evolutionary algorithm by combining the reference point-based selection in NSGA-III and the vector angle-based selection in VaEA. Performance of the proposed algorithm is verified by testing on the negative version of four DTLZ functions. The proposed algorithm is better than NSGA-III and is comparable to VaEA in terms of IGD. Besides, the proposed algorithm is more robust and can expand the front better.
Chen-Yu Lee, Jia-Fong Yeh, Tsung-Che Chiang

Freeway Travel Time Prediction by Using the GA-Based Hammerstein Recurrent Neural Network

Freeway travel time prediction has become a focus of research in recent years. However, we must understand that most conventional methods are very instinctive. They rely on the small amount of real-time data from the day of travel to look for historical data with similar characteristics and then use the similar data to make predictions. This approach is only applicable for a single day and cannot be used to predict the travel time on a day in the future (such as looking up the travel time for the coming Sunday on a Monday). This study therefore developed a Hammerstein recurrent neural network based on genetic algorithms that learns the freeway travel time for different dates. The trained model can then be used to predict freeway travel time for a future date. The experiment results demonstrated the validity of the proposed approach.
Ru-Kam Lee, Yi-Che Yang, Jun-Hong Chen, Yi-Chung Chen

A PIP-Based Approach for Optimizing a Group Stock Portfolio by Grouping Genetic Algorithm

Recently, some approaches have been proposed for finding a group stock portfolio (GSP). However, stock price series of stocks which are useful information may not be considered in those approaches. Hence, this study takes stock price series into consideration and presents a perceptually important point (PIP)-based approach for obtaining a GSP. Since the PIP is used, the proposed approach can handle stock price series with different lengths, which means that a more useful GSP could be found and provided to investors. Each chromosome is encoded by grouping, stock, and stock portfolio parts. To measure the similarity of series in groups, the series distance is designed and used as a part of fitness function. At last, experiments were conducted on a real dataset to show the advantages of the proposed approach.
Chun-Hao Chen, Chih-Hung Yu

A Novel Genetic Algorithm for Resource Allocation Optimization in Device-to-Device Communications

In this study, the resource blocks (RB) are allocated to user equipment (UE) according to the evolutional algorithms for long term evolution (LTE) systems. Genetic algorithm (GA) is one of the evolutionary algorithms, based on Darwinian models of natural selection and evolution. Therefore, we propose a novel GA for RB allocation to enhance the throughput of UEs and improve the system capacity performance. Simulation results show that the proposed GA with 100 populations, in 200 generations can converge to suboptimal solutions. Therefore, with comparing with the particle swarm optimization (PSO) algorithm the proposed GA can improve system capacity performance with 1.4 UEs.
Yung-Fa Huang, Tan-Hsu Tan, Bor-An Chen

Data Mining and Its Applications

Frontmatter

Mining Erasable Itemsets Using Bitmap Representation

This paper proposes a bitmap representation approach for modifying the erasable-itemset mining algorithm to increase its efficiency. The proposed approach uses the bitmap concept to save processing time. Through experimental evaluation, simulation datasets were used to compare the traditional erasable itemset mining and the proposed approach under various experimental conditions.
Wei-Ming Huang, Tzung-Pei Hong, Guo-Cheng Lan, Ming-Chao Chiang, Jerry Chun-Wei Lin

Identifying Suspicious Cases in the Hong Kong Stock Market Using Commentators’ Stock News

Stock market is one of the most active secondary markets in the finance industry. Investors buy and sell stocks there. Regulators are in place to offer a fair place for trading. Unfortunately, market manipulation of different forms still exists. Limited researches worked on this area due to restriction in data supply. Exchanges and regulators do not offer full order book to the public. Without a full order book, it is difficult to locate the fraud intention of manipulator. This paper introduces a new method to identify suspicious cases: identifying suspicious cases by parsing the stock recommendation news written by stock commentators. Some suspicious cases are found in the study.
Li Quan, Jean Lai

A New Conceptual Model for Big Data Analysis

In today modern societies, everywhere has to deal in one way or another with Big Data. Academicians, researchers, industrialists and many others have developed and still developing variety of methods, approaches and solutions for such big in volume, fast in velocity, versatile in variety and value in vicinity known as Big Data problems. However much has to be done concerning with Big Data analysis. Therefore, in this paper we propose a new concept named as Big Data Reservoir which can be interpreted as Ocean in which all most all information is stored, transmitted, communicated and extracted to utilize in our daily life. As a starting point of our proposed new concept, in this paper we shall consider a stochastic model for input/output analysis of Big Data by using Water Storage Reservoir Model in the real world. Specifically, we shall investigate the Big Data information processing in terms of stochastic model in the theory of water storage or dam theory. Finally, we shall present some illustrations with simulation.
Thi Thi Zin, Pyke Tin, Hiromitsu Hama

An Hybrid Multi-Core/GPU-Based Mimetic Algorithm for Big Association Rule Mining

This paper addresses the problem of big association rule mining using an evolutionary approach. The mimetic method has been successfully applied to small and medium size databases. However, when applied on larger databases, the performance of this method becomes an important issue and current algorithms have very long execution times. Modern CPU/GPU architectures are composed of many cores, which are massively threaded and provide a large amount of computing power, suitable for improving the performance of optimization techniques. The parallelization of such method on GPU architecture is thus promising to deal with very large datasets in real time. In this paper, an approach is proposed where the rule evaluation process is parallelized on GPU, while the generation of rules is performed on a multi-core CPU. Furthermore, an intelligent strategy is proposed to partition the search space of rules in several independent sub-spaces to allow multiple CPU cores to explore the search space efficiently and without performing redundant work. Experimental results reveal that the suggested approach outperforms the sequential version by up to at 600 times for large datasets. Moreover, it outperforms the-state-of-the-art high performance computing based approaches when dealing with the big WebDocs dataset.
Youcef Djenouri, Asma Belhadi, Philippe Fournier-Viger, Jerry Chun-Wei Lin

Updating the Discovered High Average-Utility Patterns with Transaction Insertion

In this paper, we propose an algorithm to handle the transaction insertion for efficiently updating the discovered high average-utility upper-bound itemsets (HAUUBIs) based on the average-utility (AU)-list structure and the Fast UPdated (FUP) concept. The proposed algorithm divides the HAUUBIs existing in the original database and new transactions into four cases, and each case can be respectively maintained to identify the actual high average-utility itemsets (HAUIs) without multiple database scans and enormous candidate generation. Experiments showed that the proposed algorithm has better performance compared to state-of-the-art algorithm in terms of runtime and generates the similar number of candidates.
Tsu-Yang Wu, Jerry Chun-Wei Lin, Yinan Shao, Philippe Fournier-Viger, Tzung-Pei Hong

Image and Multimedia Processing

Frontmatter

Applying Image Processing Technology to Region Area Estimation

This paper proposes a method to measure a region area of field by using aerial images. An unmanned aerial vehicle (UAV) and image processing technology is used to capture images of the land and measure its area. The main advantage of using UAV to capture images is the higher degree of freedom; it can accord user’s operation to capture from various angles and heights to obtain more diversified information. Even taking pictures of a dangerous area, the user can remote the UAV in a safer place, and get the information of the area or the UAV in real time. In the experiment, an UAV is used to get images of the playground grassland which region area is known, and capture a group of images with same area from 70 to 120 m height every ten meters. In image processing process, edge detection and morphology are used to find the range of the interest region, and then count the number of pixels of it. We can get the relation between the different height and per pixels of the real area. Experimental results show that the average deviations of estimating unknown area are less than 2%.
Yi-Nung Chung, Yun-Jhong Hu, Xian-Zhi Tsai, Chao-Hsing Hsu, Chien-Wen Lai

Face Recognition under Lighting Variation Conditions Using Tan-Triggs Method and Local Intensity Area Descriptor

Lighting variation is a specific and difficult case of face recognition. A good combination of an illumination preprocessing method and a local descriptor, face recognition system can considerably improve prediction performance. Recently, a new descriptor, named local intensity area descriptor (LIAD), has been introduced for face recognition in ideal and noise conditions. It has been proven to be insensitive to ideal and noise images and has low histogram dimensionality. However, it is not robust against illumination changes. To overcome this problem, in this paper, we propose an approach using an illumination normalization method developed by authors Tan and Triggs to normalize face images before encoding the processed images based on LIAD. The recognition was performed by a nearest-neighbor classifier with chi-square statistic as the dissimilarity measurement. Experimental results, conducted on FERET database, confirmed that our proposed approach performs better than traditional LIAD method and local binary patterns, local directional pattern, local phase quantization, and local ternary patterns using the same approach with respect to illumination variation.
Chi-Kien Tran, Duc-Tinh Pham, Chin-Dar Tseng, Tsair-Fwu Lee

Analysis of the Dynamic Co-purchase Network Based on Image Shape Feature

E-commerce has become popular and profitable because it provides lots of convenience for both retailers and buyers. We introduce an idea that co-purchase network may have correlation with image shape feature. We develop a simple image shape retrieval model to automatically identify the items that the buyer would be interested. The results provide new insights into user behavior. Based on the results, we found that people would buy items which are similar in shape with the item that they have already selected. Based on this finding, it can provide more personalized recommendation of co-purchase items to the customer.
Xiaoyin Li, Jean Lai

VQ Compression Enhancer with Huffman Coding

Vector quantization (VQ) is an effective and important compression technique with high compression efficiency and widely used in many multimedia applications. VQ compression is a fixed-length algorithm for image block coding. In this paper, we employ the Huffman Coding technology to enhance VQ compression rate and get a better compression performance due to the reversibility of the Huffman Coding. The proposed method exploits the correlation between neighboring VQ indices with similarity. The similarity draws a large number of small differences from the current index with that of its adjacent neighbors; thereby, increasing the compression ratio due to the great quantity of small differences. The experimental results reveal that the proposed combination technique adaptively provides better compression ratios at high compression gains than that of VQ compression. The proposed method is superior in smoother pictures with the compression gains greater than 100%; even for the complex images the compression gain can be increased more than 25%. Therefore, the VQ-Huffman method can really enhance the efficiency of VQ compression.
Chin-Feng Lee, Chin-Chen Chang, Qun-Feng Zeng

Adaptive Steganography Method Based on Two Tiers Pixel Value Differencing

The pixel value differencing (PVD) scheme provided high embedding payload with imperceptibility in the stego images. In their approach, they used two pixels differencing to represent the complexity of pixels, and applied it to estimate how many bit will be hidden into. As the difference with small value, it means that two pixels can not tolerated with larger change, therefore, few secret bit should be embedded into these pixels. PVD scheme did not completely take pixel tolerance into consideration because of only applying one criterion, pixel differencing. In this paper, a new data hiding scheme using PVD operation and incorporating with pixel tolerance into a cover image is proposed. The pixel tolerance indicates that a greater pixel-value is more change of gray-value could be tolerated. Following up this idea, our proposed scheme applies a threshold (TH) and two quantization tables to hide secret data into a block with two pixels using modified k-bits LSB. The number of k-bits is adaptive and depends on the quantization tables setting. The adjustment strategy is to maintain the differencing value in the same range. The experimental results show that our scheme is superior to those in the previous literature.
Chi-Yao Weng, Yen-Chia Huang, Chin-Feng Lee, Dong-Peng Lin

Intelligent Systems

Frontmatter

A House Price Prediction for Integrated Web Service System of Taiwan Districts

Buying a house is not an easy thing for the most people. If you want to buy a house, you must to consider many factors. Such as the house pattern and location. These factors directly or indirectly affect the value of the house value. The current sale of the house only to provide the price and details of house information. There is no provision of the housing prices trend. Hence, this system is a network service for combine the house price forecast and the sale of house information. House buyers make good choice by this house price prediction service. This system use analytical method and forecasting model to forecast house prices. In experimental results, we use hit rate to verification if the forecast interval is reasonable. More than half of six city’s hit rate above 75%. It is means our system can help people to buy satisfied house.
Chia-Chen Fan, Shyan-Ming Yuan, Xuebai Zhang, Yu-Chuan Lin

Commonsense-Knowledge Based Inference Engine

Nowadays, more and more industries achieve automatic large-scale production, and also more and more robots undertake the responsibilities of domestic chores. When machines run in industries or robots work in home, they should have abilities to make judgement and abilities to learn from experience, if they want to do their jobs well. In this study, a commonsense knowledge base (CKB) and an inference engine that can support decision making with the commonsense knowledge are built. They can understand human languages, and equip with inferencing abilities, and learning abilities.
Zhengdao Peng, Jean Lai

Analysis of Users’ Emotions Through Physiology

Most of the existing studies focus on physical activities recognition, such as running, cycling, swimming, etc. But what affects our health, it is not only physical activities, it is also emotional states that we experience throughout the day. These emotional states build our behavior and affect our physical health significantly. Therefore, emotion recognition draws more and more attention of researchers in recent years. In this paper, we propose a system that uses off-the-shelf wearable sensors, including heart rate, galvanic skin response, and body temperature sensors to read physiological signals from the users and applies machine learning techniques to recognize their emotional states. We consider three types of emotional states and conduct experiments on real-life scenarios with ten users. Experimental results show that the proposed system achieves high recognition accuracy.
Bohdan Myroniv, Cheng-Wei Wu, Yi Ren, Yu-Chee Tseng

Research on Temperature Rising Prediction of Distribution Transformer by Artificial Neural Networks

In order to predict the temperature rising of the distribution transformer by applying the artificial neural networks (ANNs) method analyze experimental data with the actual measured data and compared with the actual measured value to reach the relative errors investigation. The historical data of the working day are divided into three periods according to the varying loadings trend of load change emotion as the peak period, the general time period and the valley period. In experimental results, The average relative error of the peak period is 2.05%, the average relative error of the general period is 1.69%, the average relative error of the valley period is 1.25 %, and the working day average relative error is 1.60% for a day 24 hours. By Ann’s derivation the result has a very good prediction rate at temperature rising of distribution transformer.
Wenxin Zhang, Jeng-Shyang Pan, Yen-Ming Tseng

Development of Audio and Visual Attention Assessment System in Combination with Brain Wave Instrument: Apply to Children with Attention Deficit Hyperactivity Disorder

The main purpose of this study mainly for children with attention deficit hyperactivity disorder (ADHD) to attention test, combined the development of the Visual and Audio Attention Test System (VAAT). We use Conners Kiddie Continuous Performance Test Second Edition (K-CPT 2) and VAAT testing 16 children with ADHD between 4 to 7 years old and compare the results to observe the K-CPT 2 and VAAT assessment at the same time. We observe the differences in visual and audio of VAAT when they do wrong or do right response via the brain wave variability. The experimental results show that most of the children have inattention in K-CPT 2. The K-CPT 2 and VAAT raw scores at the same time efficient of the response time, standard deviation and change rates are significant. It appears positive correlation. Our system provides good assessment for children with ADHD.
Chin-Ling Chen, Yung-Wen Tang, Yong-Feng Zhou, Yue-Xun Chen

Decision Support Systems

Frontmatter

Markov Queuing Theory Approach to Internet of Things Reliability

In today world a new buzzword Internet of Things has been on the news nearly every day. Some researchers are even using Internet of Every Things. Its potentialities and applicability are now on the cutting edge technology. Also, all most all of business, health care, academic institutions are in one way or another, having to deal with the Internet of Things. So the Internet of Things reliability becomes an important factor. In this paper we proposed a Markov Queuing approach to analyze the Internet of Thing reliability. Since queuing theory investigates the delay and availability of functioning things and Markov concepts take the dependency of Things in the Internet, the combination of these two concepts will make the problem clear and soluble. For illustration, we present some experimental results.
Thi Thi Zin, Pyke Tin, Hiromitsu Hama

Some Characteristics of Nanyaseik Area Corundum and Other Assorted Gemstones in Myanmar

The rock sequence of the study area consists of medium to high grade metamorphic rocks, marble, gneiss and intrusive igneous rocks, mainly biotite microgranite and serpentinite. Although the primary occurrences of gemstones in this area seem to be scarce, the secondary placers gem-bearing deposits are noteworthy. The Nanya rubies are characterized by their distinct colours of which, the commonest colour being, light pinkish red and intense red and rarely pigeon’s blood red. A glassy texture with excellent transparency makes the stone more attractive. In crystal forms, rubies usually have rounded corners, rhombohedrons, pinacoids and not well developed prism faces. Habitually, rhombohedral faces display coarse striations and some with pitted surfaces. It is probable that the Nanyaseik area is situated near the plate boundaries and within the northern splay of the Sagaing fault. Moreover, it also forms a segment of Jade Mine region. Therefore, it is reasonable that the pressure had played an important role more effectively than the temperature in the process of metamorphism.
Htin Lynn Aung, Thi Thi Zin

Exploring Gemstones in Northern Part of Myanmar

The primary occurrences of gemstones in Nanyaseik area seem to be scarce, the secondary placer gem-bearing deposits are noteworthy. All gemstone occurrences from Nanyaseik area are mainly recovered from secondary deposits (gravels). Gemstones are found as detrital fragments in gem-bearing soil horizons known as byones. According to the drainage characteristics of this area and its environs gem-bearing alluvium had been probably descended from northwestern and western watersheds that created those secondary deposits, especially at the junctions of major streams and their tributaries where local people wash the byone and extract gems. These gems include precious rubies, sapphires (including padparadscha) and others; spinel, tourmaline, zircon, quartz, diopside and almandine garnet.
Htin Lynn Aung, Thi Thi Zin

Encryption and Security

Frontmatter

Attacks and Solutions of a Mutual Authentication with Anonymity for Roaming Service with Smart Cards in Wireless Communications

Recently, Liu et al. proposed a mutual authentication protocol with user anonymity for wireless communication. In their paper, the authors claimed that the protocol can resist several kinds of attacks even the secret information stored in the smart card is disclosed. However, we still find two vulnerabilities in this paper. First, this protocol still fails to protect user anonymity. Second, this protocol is vulnerable to an off-line password guessing attack if an adversary can derive the secret information stored in a smart card. To solve the problems, we propose a simple but effective patch to their protocol.
Tsu-Yang Wu, Bin Xiang, Guangjie Wang, Chien-Ming Chen, Eric Ke Wang

Comments on Islam Et Al.’s Certificateless Designated Server Based Public Key Encryption with Keyword Search Scheme

Recently, Islam et al. proposed a certificateless designated server based public key encryption with keyword search (CL-dPEKS) scheme which combines the concepts of dPEKS and certificateless public key cryptosystem. In this paper, we show that their scheme does not provide the ciphertext and the trapdoor indistinguishabilities, two important security notions of dPEKS. Concretely, we demonstrate that their CL-dPEKS scheme suffered from off-line keyword guessing attacks on ciphertext and trapdoor by outside adversary and malicious server.
Tsu-Yang Wu, Chao Meng, King-Hang Wang, Chien-Ming Chen, Jeng-Shyang Pan

Backmatter

Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise