研究者詳細 - ケッペン　マリオ

論文 - ケッペン　マリオ

分割表示83 件中 21 - 40 件目／全件表示 >>

Blockchain Scheme Based on Evolutionary Proof of Work 査読有り

Willa Ariela Syafruddin, Sajjad Dadkhah and Mario Köppen

2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings 771 - 776 2019年06月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019 IEEE. In recent years, applications of the Blockchain concept, esp. as ledger for bitcoin transactions, has already resulted in huge amounts of wasted electrical energy for performing the Proof-of-Work tasks (cryptographic puzzles). Here, we consider an alternative concept to have this energy used at least for a useful purpose, the solution of real-world optimization problems. By means of the Traveling Salesperson Problem as model problem, we propose a concept to use optimization algorithms in an iterative manner to provide the Proof-of-Work needed to expand the Blockchain by a new block. The basic idea is to improve the tour cost for the best tour found for block n, extended by adding one more city, as a requirement for the inclusion of a new block in the Blockchain. This allows for the design of limited Blockchains, solving the underlying combinatorial optimization problems at the same time. Independently, it calls in for new efficient optimization algorithms and can serve as a real-world contest. It is discussed that metaheuristic algorithms perform an attractive class of optimization algorithms that can be used for the proposed approach. Numerical experiments also demonstrate the growth in problem complexity being handled by a binary PSO, which is a basic requirement for the full concept to work in practice.

DOI： 10.1109/CEC.2019.8790128

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85071332795&origin=inward

Updatable indoor localization based on BLE signal fingerprint 査読有り

Benaissa B., Yoshida K., Koppen M., Hendrichovsky F.

Proceedings of the 2018 International Conference on Applied Smart Systems, ICASS 2018 2019年02月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2018 IEEE. The need for a robust indoor localization solution is mounting in the recent few year, as the IoT technology is growing fast. In this paper, we discuss existing indoor localization approaches, focusing on the signal strength fingerprint approaches, to which belongs the presented study and based on Bluetooth Low Energy signal. The proposed approach employs the Radial Basis Functions (RBF) to create model that describe the real signal strength-position relationship. The present method is fully implemented on a smart phone, namely, offline data collection, model computation and online position estimation. This allow updating the model by collecting more signal data, therefore improving the localization accuracy with small efforts. The presented results shows that updating the model effectively improves the accuracy of estimation.

DOI： 10.1109/ICASS.2018.8652035

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063516885&origin=inward

Entropy Analysis of Questionable Text Sources by Example of the Voynich Manuscript 査読有り

Natsuki Kouyama and Mario Köppen

Communications in Computer and Information Science 1100 3 - 13 2019年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019, Springer Nature Singapore Pte Ltd. The Voynich Manuscript (referred to as ‘VMS’) can be considered as one of the oldest puzzles which remained unsolved until now. While some say VMS is genuine, others say that it is just a hoax. In this research, we propose three methods to analyze VMS and verify the effectiveness of them. The reason for using this manuscript is that no one on this planet knows the meaning of the text of VMS, so we can tackle research without being biased. We analyze from the viewpoint of character frequency and entropy of VMS. Statistical analysis of word frequency already exists, in contrast, we adopt analysis based on a character unit. In that respect, there is diversity from other research. We stated the following three hypotheses as H1 through H3. H1: VMS is a Ciphertext. H2: VMS is close to a programming language. H3: VMS is close to a natural language. The experimental results demonstrate that our methods are valid and efficient. The methods can be applied to all text sources and different classes of them can be distinguished. The possibility that VMS is likely a Ciphertext can be rejected. This mysterious manuscript can be concluded as a meaningful human art, not a hoax. Moreover, the VMS is not encrypted. (However, we are not able to exclude being encoded.)

DOI： 10.1007/978-981-15-0399-3_1

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85076083001&origin=inward

Two-Factor Blockchain for Traceability Cacao Supply Chain 招待有り査読有り

Arsyad A.A., Dadkhah S., Köppen M.

Lecture Notes on Data Engineering and Communications Technologies 23 332 - 339 2019年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019, Springer Nature Switzerland AG. The primary aim of food traceability is to increase food safety but traceability systems can also bring other benefits to production systems and supply chains. Technology has helped supply chain distribution to be successful and more competitive in the global market by improving their customers satisfaction level and providing more reasonable prices compared to their competitors. However, nowadays supply chains are long and complex and include many different actors, beginning with the farmers, followed by collectors, traders, manufacturers. At the end, the processed products are difficult to trace back to their origins in a trusted way. Best way so far is the continuous medial or legal documentation of the chain of transactions, available only to a limited circle of persons. The recent efforts toward blockchain-based trust management open a new perspective here. Here, we propose a solution to link legal documentation and blockchain technology within a traceability system, with the specific application case of cacao and chocolate production in mind. For improved data security, the common blockchain concept is extended to a two-factor blockchain, where both blockchains are connected via digital watermarking of the documentation media, one blockchain traces the documentation steps, the other the watermarking embedding. By a unique reading-verification approach, the integrity of their relatedness can be proven, thus improving also reliability of the whole product tracing.

DOI： 10.1007/978-3-319-98557-2_30

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85083448691&origin=inward

Crack identification using extended IsoGeometric analysis and particle swarm optimization 招待有り査読有り

Khatir S., Wahab M., Benaissa B., Köppen M.

Lecture Notes in Mechanical Engineering 210 - 222 2019年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© Springer Nature Singapore Pte Ltd. 2019. The eXtended isogeometric analysis (X-IGA) combined with Particle swarm optimization (PSO) is used for crack identification in twodimensional linear elastic problems based on inverse problem. The application of fracture mechanics test under mode II loading is performed. The X-IGA possesses the advantages of the combination between eXtended Finite Element Method (X-FEM) and the Isogeometric Analysis (IGA). The objective function minimizes the gap between the calculated and measured displacements. Convergence studies at various positions of crack on the plate are calculated and the results shows that the proposed technique can detect damage with minimum accuracy 95% for the position and maximum accuracy 98%.

DOI： 10.1007/978-981-13-0411-8_21

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85068357903&origin=inward

Convolutional Neural Network Application in Smart Farming 査読有り

Yudhi Adhitya, Setya Widyawan Prakosa, Mario Köppen and Jenq Shiou Leu

Communications in Computer and Information Science 1100 287 - 297 2019年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2019, Springer Nature Singapore Pte Ltd. The agricultural sector has a very pivotal role, furthermore very important in the global economy country in the world. The uses of machine learning become trending, and massive improvement technology has widely used in modern agricultural technology. Artificial Intelligent techniques are being used extensively in the agricultural sector as one purpose to increase the accuracy and to find solutions to the problems. As implementation of Artificial Intelligent (AI) based on Convolutional Neural Networks (CNN) application in several fields, indicates that CNN based machine learning scheme is adaptable and implemented on an agricultural area. In this contribution, we apply CNN based feature extraction on cocoa beans images. Cocoa beans images used in this study were cocoa beans (Theobroma Cacao L.) in various quality classes originating from districts in South Sulawesi, Indonesia, and we separate those images 30% for training and the remaining 70% for testing. From our assessment, the result shows that we can achieve 82.14% accuracy to classify seven classes of cocoa beans images using 5 CNN layers.

DOI： 10.1007/978-981-15-0399-3_23

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85076106191&origin=inward

An Efficient Replay Method to Prevent SURF-Based Face Detection 招待有り査読有り

Dadkhah S., Koppen M., Sadeghi S., Yoshida K.

Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018 18 - 25 2018年12月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2018 IEEE. During the past couple of years, a considerable number of digital images are gathered by search engines, or uploaded by users in different social websites. These images could contain a variety of variables such as different faces, scenes, and unusual objects. The advancement of digital face recognition algorithms is sensational, recognition algorithms used by some of the social websites are even stronger than most secret service establishments. However, there is always a concern about how to protect the user's privacy when they do not want to be recognized automatically by these services. In this research, a SURF-based face recognition algorithm along with a featurebased attack to mislead this type of scheme is proposed. The recognition algorithm use different machine learning technique along with second layer descriptor counting function which makes it more powerful. However the primary focus of this research is to provide a method which can mislead this type of recognition systems with a smallest possible degradation to the image representation. The experimental results show that the proposed plan is successful to fool the SURF algorithm and its recognition system by 70%.

DOI： 10.1109/APWConCSE.2018.00012

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85074295713&origin=inward

An efficient ward-based copy-move forgery detection method for digital image forensic 査読有り

Dadkhah S., Koppen M., Sadeghi S., Yoshida K., Jalab H., Manaf A.

International Conference Image and Vision Computing New Zealand 2017-December 1 - 6 2018年07月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2017 IEEE. In recent years, with the improvement of digital manipulation tools, image forgeries have become a genuine social issue. Copy-move forgery is an important type of digital manipulation which is done by duplicating some parts of the image with the purpose of hiding specific information. Verifying the authenticity of the digital image can become vital for different forensic organizations. In this paper, an efficient copy-move detection algorithm with three level of Ward linkage based clustering is proposed. The proposed algorithm extracts the local image features with the help of Scale-invariant feature transform algorithm (SIFT). In the proposed method, a Ward-based clustering scheme followed by three levels of false-descriptor elimination is applied. The proposed elimination system utilizes Euclidean distance to improve the accuracy of the region detection scheme. The efficiency of the proposed algorithm is examined against several different post-processing attacks such as multilevel forgeries, noises, and JPEG compression. Experimental results illustrate that the proposed algorithm improves the detection accuracy by eliminating false descriptors.

DOI： 10.1109/IVCNZ.2017.8402472

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85050008851&origin=inward

Phone Application for Indoor Localization Based on Ble Signal Fingerprint 査読有り

Benaissa B., Hendrichovsky F., Yishida K., Köppen M., Sinčák P.

2018 9th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2018 - Proceedings 2018-January 1 - 5 2018年03月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2018 IEEE. Indoor position of devices and persons is a very valuable information for context-aware devices and human activity recognition. The need of such information grows bigger by the advancement of IoT technologies. In this paper, we discuss existing indoor positioning approaches and their applications, give specific interest to the signal strength fingerprint approaches, to which belongs the presented paper. Bluetooth Low Energy Beacons are used as the source of the signal, and the Radial Basis Functions method is employed to create a model that relates to signal strength and position. The proposed approach allows the possibility of making all the computation on a smartphone application, namely, offline data collection and model computation, and online position estimation. Besides, it allows updating the model later.

DOI： 10.1109/NTMS.2018.8328729

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85047863726&origin=inward

Bad Ai: Investigating the Effect of Half-Toning Techniques on Unwanted Face Detection Systems 査読有り

Dadkhah S., Köeppen M., Sadeghi S., Yoshida K.

2018 9th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2018 - Proceedings 2018-January 1 - 5 2018年03月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Currently, automatic face detection systems are widely used in various social media. The improvement of the automated intelligent face recognition can easily result in the invasion of the user 's privacy if the predefined functions for their so- called artificial intelligent systems are designed with no respect to the user privacy, this means that users do not get the right to prevent these types of automatic face detection. The problem does not stop here, and recently some organization attempted to use automated face recognition system as a digital personal judgment tools. For instance, judging if a person is criminal only based on the attributes of his/her face. In the present technology, spreading the personal information such as individual digital images are fast and inevitable. Thus, in this paper, some of the techniques to evade automatic face recognition is investigated. The focused of this article is to highlight the advantages of different Half-Toning algorithms concerning avoiding unwanted automated face detection/recognition. In the experimental phase, the result of varying filtering and modification algorithms compared to the proposed filtering technique.

DOI： 10.1109/NTMS.2018.8328726

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85050981631&origin=inward

Does the Jaya algorithm really need no parameters? 招待有り査読有り

Syafruddin W.A., Köppen M., Benaissa B.

IJCCI 2018 - Proceedings of the 10th International Joint Conference on Computational Intelligence 264 - 268 2018年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved. Jaya algorithm is a swarm optimization algorithm, formulated on the concept where the solution obtained for a given problem moves toward the best solution and away from the worst solution. Despite being a very simple algorithm, it has shown excellent performance for various application. It has been claimed that Jaya algorithm is parameter-free. Here, we want to investigate the question whether introducing parameters in Jaya might be of advantage. Results show the comparison of the results for different benchmark function, indicating that, apart from a few exceptions, generally no significant improvement of Jaya can be achieved this way. The conclusion is that we have to consider the operation of Jaya differently from a modified PSO and more in the sense of a stochastic gradient descent.

DOI： 10.5220/0006960702640268

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85059195277&origin=inward

Fairness aspects of secondary radio spectrum access 査読有り

Köppen M., Tsuru M.

Lecture Notes on Data Engineering and Communications Technologies 8 445 - 455 2018年01月

担当区分：責任著者記述言語：英語掲載種別：記事・総説・解説・論説等（学術雑誌）

© Springer International Publishing AG 2018. We consider the allocation of secondary radio spectrum under fairness constraints. Two neutrality aspects apply here: the provider allocates independent of the packet utility of the secondary user, and: all secondary users are given the same unbiased opportunity to access the available spectrum. The first means that the standard fairness models do not apply directly, the second that we are more interested in the chance of a secondary user to place a number of packets together, i.e. a numerical value from (0, 1]. This leads us to a formulation of the underlying combinatorial optimization problem as an “multi-user knapsack proble” (MUK). For short, it means that several users put their items into the same knapsack and the fairness is related to the share of packed items for each user. We discuss how common ideas from other fairness models can be applied to this new problem, esp. the concept of fairness as convex mean maximization. A number of example cases are studied to demonstrate feasibility of the proposed approach.

DOI： 10.1007/978-3-319-65636-6_40

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85090368536&origin=inward

Activity and Emotion Recognition for Elderly Health Monitoring 査読有り

Brahim Benaissa, Mario Köppen and Kaori Yoshida

International Journal of Affective Engineering ( Japan Society of Kansei Engineering ) 17(2) 81 - 88 2017年11月

記述言語：英語掲載種別：研究論文（学術雑誌）

The problems facing elderly who are living independently, are considered to be one of the most important motivations of the activity recognition research. The advances in sensing technologies allow collecting several types of data and communicate it wirelessly. However, most existing activity recognition systems requires pre-calculated pattern recognition models. This paper lays the theoretical foundations of a real-time methodology for activity and emotional recognition based on body and environment sensors simultaneously, then tackles one aspect of the method which is the path estimation using chest-mounted IMU sensor, for which a zero velocity update criteria is proposed. Finally path estimation results for sitting down, laying down, falling down and standing up are discussed.

DOI： 10.5057/ijae.IJAE-D-17-00020

Application of proper orthogonal decomposition and radial basis functions for crack size estimation using particle swarm optimization 査読有り

Benaissa B., Köppen M., Abdel Wahab M., Khatir S.

Journal of Physics: Conference Series 842 ( 1 ) 2017年06月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© Published under licence by IOP Publishing Ltd. Complex engineering problems require simulations, which are computationally expensive in cases of inverse identification tasks since they commonly requires hundreds of thousands of simulations. This paper propose a method based on model reduction for crack size estimation, combining the proper orthogonal decomposition method with radial basis functions. The reduced model is validated by comparing the obtained boundary displacements with the corresponding results from a finite element model. This inverse procedure is formulated as the minimization of the difference between the measured and computed values of displacement at selected boundary nodes, called sensor points, using particle swarm optimization algorithm. Convex and a non-convex specimens have been considered for investigations of crack presence, and identification of its size, different crack sizes have been tested to demonstrate the efficiency of the proposed approach.

DOI： 10.1088/1742-6596/842/1/012014

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85021221228&origin=inward

Detecting malicious URLs using machine learning techniques 査読有り

Vanhoenshoven F., Napoles G., Falcon R., Vanhoof K., Koppen M.

2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 2017年02月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2016 IEEE. The World Wide Web supports a wide range of criminal activities such as spam-advertised e-commerce, financial fraud and malware dissemination. Although the precise motivations behind these schemes may differ, the common denominator lies in the fact that unsuspecting users visit their sites. These visits can be driven by email, web search results or links from other web pages. In all cases, however, the user is required to take some action, such as clicking on a desired Uniform Resource Locator (URL). In order to identify these malicious sites, the web security community has developed blacklisting services. These blacklists are in turn constructed by an array of techniques including manual reporting, honeypots, and web crawlers combined with site analysis heuristics. Inevitably, many malicious sites are not blacklisted either because they are too recent or were never or incorrectly evaluated. In this paper, we address the detection of malicious URLs as a binary classification problem and study the performance of several well-known classifiers, namely Naïve Bayes, Support Vector Machines, Multi-Layer Perceptron, Decision Trees, Random Forest and k-Nearest Neighbors. Furthermore, we adopted a public dataset comprising 2.4 million URLs (instances) and 3.2 million features. The numerical simulations have shown that most classification methods achieve acceptable prediction rates without requiring either advanced feature selection techniques or the involvement of a domain expert. In particular, Random Forest and Multi-Layer Perceptron attain the highest accuracy.

DOI： 10.1109/SSCI.2016.7850079

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85016035948&origin=inward

Electromagnetismlike mechanism descriptor with fourier transform for a passive copy-move forgery detection in digital image forensics 査読有り

Dadkhah S., Köppen M., Jalab H., Sadeghi S., Manaf A., Uliyan D.

ICPRAM 2017 - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods 2017-January 612 - 619 2017年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Copyright © 2017 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved. Copy-move forgery is a special type of forgery that involves duplicating one region of an image by covering it with a copy of another region from the same image. This study develops a simple and powerful descriptor called Electromagnetismlike mechanism descriptor (EMag), for locating tampered areas in copy-move forgery on the basis of Fourier transform within a reasonable amount of time. EMag is based on the collective attraction-repulsion mechanism, which considers each images pixel as an electrical charge. The main component of EMag is the degree of the attraction-repulsion force between the current pixel and its neighbours. In the proposed algorithm, the image is divided into similar non-overlapping blocks, and then the final force for each block is evaluated and used to construct the tampered image features vector. The experimental results demonstrate the efficiency of the proposed algorithm in terms of detection time and detection accuracy. The detection rate of the proposed algorithm is improved by reduction of false positive rate (FPR) and increment of true positive rate (TPR).

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85042790532&origin=inward

Non-swarm intelligence search algorithm based on the foraging behaviors of fruit flies 査読有り

Ohnishi K., Fujiwara A., Koeppen M.

2016 IEEE Congress on Evolutionary Computation, CEC 2016 1509 - 1516 2016年11月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2016 IEEE. In the present study, we examine the foraging behavior of the fruit fly (Drosophila), which unlike social insects, independently and autonomously forages. Moreover, we propose a new population-based, non-swarm intelligence search algorithm that mimics the foraging behaviors of fruit flies. We find that the time that a fruit fly stays in a food source region follows a power-law. A power-law distribution satisfies the scale-free property, so the observed behaviors of fruit flies can be called scale-free behaviors, which are modeled by the proposed algorithm. We examine the effect of scale-free behaviors on search performance by applying the proposed algorithm to 28 test functions with two real parameters. The results reveal that the scale-free property is related to a balance between exploration and exploitation and affects the search performance. Moreover, particular parameter values for fixing the scale-free property yield a better search performance for most of the test functions considered herein. The present paper does not provide a competent search algorithm for solving static optimization problems, but rather introduces a novel temporal property of individual behaviors, i.e., a scale-free property, which is expected to provide a new way to think about search algorithms.

DOI： 10.1109/CEC.2016.7743968

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85008252458&origin=inward

Applied Soft Computing: Preface 招待有り査読有り

Polat K., Asyali M., Muthusamy H., Rajendra Acharya U., Köppen M.

Applied Soft Computing Journal 37 939 - 941 2015年12月

Neural Signature of Efficiency Relations 査読有り

Basterrech, Sebastian and Ohnishi, Kei and Koppen, Mario

Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on 2090 - 2095 2015年10月

Message from the ADMNET 2015 Workshop Organizers 査読有り

Nariyoshi Yamai, Mario Köppen and Youngseok Lee

Published in: 2015 IEEE 39th Annual Computer Software and Applications Conference ( IEEE ) 3 2015年09月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Taichung, Taiwan 2015年07月01日 - 2015年07月05日

The ADMNET workshop series is focusing on the discussion of the advance of the state-of-the-art, research and development in the area of architecture, design, deployment and management of networks and Internet-based applications. This workshop is also a forum for designers, developers and administrators of the networks and applications. ADMNET covers a wide field of topics such as Network Architecture and Design, QoS, Scalability Solutions, Fairness, Optimality, and other aspects of Network Resource Sharing, Network Deployment, Management and Operation, Network Security, Network Applications and their Operation, Meta-Heuristics and Soft Computing Approaches for Networking Technologies, Network Metrics, Network Growth and Percolation Models, Modeling of Users and Network-Based Services, Digital Convergence, ITIL, User Policy and Service Level Agreements, Computer Ethics and Education.

DOI： 10.1109/COMPSAC.2015.294

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84962079693&origin=inward

　前のページ - 次のページ　

1
2
3
4
5