iosr-JCE   Volume-16 ~ Issue-4 ~ July-August 2014

Abstract: Currently the digital images are used in various areas like medical, fashion, architecture, face recognition, finger print recognition and bio metrics. Recently the CBIR reduced the semantic gap between the low visual features and high level image semantics. In this paper we describe a novel framework for performing content-based image retrieval using Back Propagation Neural Network. Our method focuses on performing category search, though it could easily be ex- tended to other types of searches, and does not require relevance feedback in order to perform reasonably. It also emphasizes the importance of utilizing information collected from the sets of image database in medical system.

Keywords: Artificial Intelligence, ANN, Back Propagation,CBIR,IRS

[1] Ms. Sonali B. Maind, Ms. Priyanka Wankas, Research Paper on Basic of Artificial Neural Network, International Journal on Recent and Innovation Trends in Computing and Communication, Volume 2, Issue 1, pp. 96-100.
[2] Vinicias Goncalves Maltarollo, Kathia Maria Honorio and Alberico Borges Ferreira da Silva, Application of Artificial Neural Network in Chemical Problems, INTECH, Link: http://dx.doi.org/10.5772/51275
[3] http://en.wikipedia.org/wiki/Adaptive_learning
[4] http://en.wikipedia.org/wiki/Content-based_image_retrieval
[5] H. Chuctaya, et al., "M-CBIR: A Medical Content Based Image Retrieval System Using Metric Data Structures", Computer Science Society (SCCC), 30th IEEE International Conference of the Chilean, 2011

Abstract : Our aim is to connect laptops to projectors/TV/LED's wirelessly (without any physical media) and transfer video signals from them. For this, SSH connection is used in Raspberry Pi device and we have transferred command using CGI.

Index Terms: Raspberry Pi, WIFI, VNC, SSH.

[1] http://en.wikipedia.org/wiki/Raspberry_Pi
[2] https://learn.adafruit.com/adafruits-raspberry-pi-lesson-3-network-setup/setting-up-wifi-with-occidentalis
[3] http://myraspberrypiexperience.blogspot.com/p/setting-up-vnc.html
[4] http://www.penguintutor.com/linux/light-webserver

Abstract :This paper focuses on the area of Image Compression which is used in various Image Processing Applications. This paper presents a survey and study of various image compression techniques primarily, The Principal Component Analysis approach. The PCA approach can be implemented in two ways namely, PCA Statistical Approach and PCA Neural Network Approach. It also deals with various benefits of using image compression methods.

Keywords: Image Compression, Principal Component Analysis Approach, PCA Statistical Approach, PCA Neural Network Approach

[1] Subramanya A,"Image Compression Technique,"Potentials IEEE, Vol.20, Issue 1, pp 19-23, Feb-March 2001, David Jeff Jackson & Sidney Joel Hannah.

[2] David Jeff Jackson & Sidney Joel Hannah.," Compression Techniques," System Theory 1993, Proceedings SSST‟93 25th o theastem Symposium,pp 513-517, 7-9 March 1993

[3] Ming Yang Nickolaos Bourbakis ," An Overview of Lossless Digital Image Compression techniques," Circuits & Systems , 2005 48th Midwest Symposium , Vol.2, IEEE ,pp 1099-1102 ,7-10 Aug,2005.

[4] Ismail Avcibas, Nasir Memon, Bulent Sankur, Khalid Sayood, " AProgressive Lossless / Near Lossless Image Compression Algorithm,"IEEE Signal Processing Letters, vol. 9, No. 10, pp 312-314, October 2002.

[5] Milos Klima, Karel Fliegel, "Image Compression Techniques in the field of security Technology: Examples and Discussion, "Security Technology, 2004, 38th Annual 2004 Intn. Carnahan Conference, pp 278-284,11-14 Oct., 2004

Abstract : Mobile Ad hoc networks are the self-configuring network, in which there is no centralized access point. The mobile nodes itself act as routers for one another. MANET is basically a wireless ad hoc network with the routing capability. Scalability and Mobility have measure impact on the behavior of ad hoc routing protocols. Before deploying these protocols on the network, we must observe their performance under various circumstances. Simulation is a very effective and efficient technique for measuring their behavior in this decentralized infrastructure less network. This paper focuses on the characteristic measure of reactive routing protocols (DSR, AODV, DYMO, IERP and LAR1) for different criteria on application layer and transport layer of Internet .We compare the behavior of these protocols with the increasing number of nodes using Random Waypoint Mobility Model and taking pause time as the main criterion. Traffic load is constant and network load is varying in this analysis.

Keywords: Ad hoc networks, Pause time, QualNet, Random Waypoint mobility, Routing protocols, Simulation

[1] Md. Saiful Azad, Farhat Anwar, Md. Arafatur Rahman, Aisha H. Abdalla, Akhmad Unggul Priantoro and Omer Mahmoud, Performance Comparison of Proactive and Reactive Multicast Routing Protocols over Wireless Mesh Networks, IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.6, June 2009.
[2] C. Sivaram Murthy and B. S. Manoj, Ad Hoc Wireless Networks, Architecture and Protocols (Prentice-Hall PTR, 2004).
[3] Ravinder Ahuja, Simulation based Performance Evaluation and Comparison of Reactive, Proactive and Hybrid Routing Protocols based on Random Waypoint Mobility Model, International Journal of Computer Applications (0975 – 8887)Volume 7– No.11, October 2010.
[4] Zhenqiang Ye, Srikanth V. Krishnamurthy and Satish K. Tripathi, A Framework for Reliable Routing in Mobile Ad Hoc Networks,Proceedings of the IEEE INFOCOM, 2003.
[5] Valentina Timcenko, Mirjana Stojanovic and Slavica Bostjancic Rakas, MANET Routing Protocols vs. Mobility Models:Performance Analysis and Comparison, Institute Mihailo Pupin,Volgina 15, 11060 Belgrade, SERBIA.

Abstract : Bluetooth Library Manager (BLM) is library management software which can be used in any library for maintaining different functions like book search, requisition submission, data entry etc. I have implemented this software on Android platform which has the advantage of portability and wide availability. I used Bluetooth as communication medium between the server and the client. BLM has additional capabilities (call, SMS, email) for communication between library card holder and the administration. I have implemented this specially for any educational institution which has a library having capacity not more than 20,000 users. An encryption algorithm is used to enhance the security of that software. This algorithm is used for the log-in purpose. Using the encryption algorithm we encrypt the password in the client side and the cipher-text and the username is send over Bluetooth to the server side. The decryption algorithm is used in the server side to decrypt the cipher-text. Then the decrypted password is matched with corresponding password of that user stored in the server side database. The user can successfully log-in into the system if and only if the password of the database matches with the decrypted password. The entire database of the library is implemented in a normalized way. Student can submit their requisition from there phone without using internet. They can contact their faculties and classmates via SMS, email or call and vice-versa. A student can check the availability using this software. She/he can also see the return-date of any book which is out of stock now and borrowed by another student. Faculties can also send any notification to any student via email or SMS.

Keywords: Android, Python, SL4A, Bluetooth, SQLite, Library Management System

...............................................................................................!

Abstract : Data hiding involves hiding of information in a cover media to obtain the indistinguishable media, in such a way that the cover media is supposed not to have any embedded image for its unintended recipients. Steganography and Watermarking are main parts of the fast developing area of information hiding. This paper is based on Steganography, Watermarking and Cryptography where the system ensures secured image transfer between the source and destination. Encrypted image bits are embedded into higher and random LSB layers, resulting in increased robustness against noise addition. On the other hand, multi-objective Genetic Algorithm operators are used to reduce distortion. The basic idea of this paper is to improve security. For this improvement image embedding position numbers are converted to optimized Arrays and these Arrays are embedded into the Audio file. Performance based on imperceptibility, security and hiding capacity has been evaluated and discussed.

Keywords: Watermarking, Steganography, Artificial intelligence, Cryptography, Genetic algorithm

[1] N. Cvejic, T. Seppanen, "Increasing Robustness of LSB Audio Steganography Using a Novel Embedding Method", Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC04), 2004, vol. 2, pp. 533-540
[2] N. Cvejic, and T. Seppnen, "Reduced distortion bit-modification for LSB audio steganography", Journal of Universal Computer Science, January 2005, 11(1), pp. 56-65.
[3] Mohamed A. Ahmed, Miss Laiha Mat Kiah, B.B. Zaidan and A.A. Zaidan, "A Novel Embedding Method to Increase Capacity and Robustness of Low-bit Encoding Audio Steganography Technique Using Noise Gate Software Logic Algorithm", Journal of Applied Sciences, 2010, 10(4), pp. 59-64.
[4] K Bhowal, D Bhattacharyya, A J Pal, Tai-Hoon Kim, "A GA based audio steganography with enhanced security" Telecommunication Systems Journal, Springer, April 2013, 52(4), pp 2197-2204.
[5] Fridrich, Jessica and others. "Steganalysis of LSB Encoding in Color Images." Proceedings of the IEEE International Conference on Multimedia, New York: IEEE Press, 2000, pp-1279-1282

Abstract : Recent advances have given rise to the popularity and success of cloud computing. However, when outsourcing the data and business application to a third party causes the security and privacy issues to become a critical concern. Throughout the study at hand, the authors obtain a common goal to provide a comprehensive review of the existing security and privacy issues in cloud environments. We have identified five most representative security and privacy attributes (i.e., confidentiality, integrity, availability, accountability, and privacy-preservability). Beginning with these attributes, we present the relationships among them, the vulnerabilities that may be exploited by attackers, the threat models, as well as existing defense strategies in a cloud scenario. Future research directions are previously determined for each attribute.

Index Terms: cloud computing, security, privacy, trust, confidentiality, integrity, accountability, availability

[1]. Towards Secure and Dependable Storage Services in Cloud Computing Cong Wang, Student Member, IEEE, Qian Wang, Student Member, IEEE, Kui Ren, Member, IEEE, Ning Cao, Student Member, IEEE, and Wenjing Lou, Senior Member, IEEE
[2]. What's New About Cloud Computing Security Yanpei Chen, Vern Paxson, Randy H. Katz CS Division, EECS Dept. UC Berkeley {ychen2, vern, randy}@eecs.berkeley.edu
[3]. Securing Data Storage in Cloud Computing Hyun-Suk Yu
[4]. Identity-Based Authentication for Cloud Computing Hongwei Li1, Yuanshun Dai1,2, Ling Tian1, and Haomiao Yang1
[5]. A Study on Secure Data Storage Strategy in Cloud Computing Danwei Chen,Yanjun He First AuthorCollege of Computer Technology, Nanjing University of Posts and Telecommunications, chendw@njupt.edu.cn

Abstract : Decision trees are very significant for taking any type of verdict related to any field. Today there is ample amount of data but that data is uncooked data therefore to make it cooked data, data mining is done. Data mining concept has been used to enhance the quality of data. Various techniques are there in data mining for growth in information technology. Those techniques are classification; clustering, association rules etc. For classifying the data best method is to generate a decision tree. By using decision tree best decisions can be made as it is hierarchal structure which can be easy to interpret. A novel algorithm is implemented which gives results faster and has enhanced features than conventional algorithms of data mining. In new approach some features of Univariate algorithm (i.e. CART algorithm) and some features of Multivariate algorithm (i.e. M5P algorithm) plus an enhanced feature of new algorithm is included. The new feature of algorithm does enhancement in performance as using it performance is improved. In novel approach pruning of files is done due to which specific data can be accessed. Time is saved by using this algorithm and user can perform the task quickly and efficiently.

Keywords: CART, Data Mining, Decision Trees, M5P.

[1]. S.Anupama Kumar," A Naïve Based approach of Model Pruned trees on Learner‟s Response", I.J.Modern Education and Computer Science, Vol. 9, pp. 52-57, 2012
[2]. W. Nor Haizan W. Mohamed , " A Comparative Study of Reduced Error Pruning Method in Decision Tree Algorithms", IEEE International Conference on Control System,Computing and Engineering, pp.23 - 25 Nov. 2012
[3]. Dr. Neeraj Bhargava, "Decision Tree Analysis on J48 algorithm for Data Mining", International Journal of Advanced Research in Computer Science and Software Engineering, June 2013
[4]. Goyal Anshul, "Performance Comparison of Naïve Bayes and J48 Classification Algorithms", International Journal of Applied Engineering Research Vol. 7, no. 11, 2012
[5]. Chengjun Zhan, "Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm", IEEE transactions on intelligent transformation systems, Vol. 12, no. 4, December 2011

Abstract : In most of the search engines documents are retrieved and ranked on the basis of relevance. They are not necessarily ranked on the basis of similarity between the query and the respective document. The ranked documents are in the form of a list. So there is a need to rank the retrieved documents. We implement Language model that is efficient to retrieve the text documents satisfying given query. The ranking of documents is based on the similarity coefficient calculated using language model. To cluster the ranked retrieved documents, we use FITC (Frequent Item set-based text Clustering) algorithm. The algorithm partitions the documents and returns the cluster in each partition. The algorithm identifies clusters with no overlap. The system accepts user request and returns all the relevant documents partitioned in the form of clusters which satisfy the query. The results of applying the algorithm to document retrieval demonstrate that the algorithm identifies non-overlapping clusters and is therefore of widespread use in many of the search engines. Keywords: Clustering algorithms, Frequent Itemset-based text Clustering, Language model

[1] D. Wang, T. Li, S. Zhu, Y. Gong, "iHelp : An Intelligent Online Helpdesk System," IEEE Trans. on System, Man and Cybernetics– Part B: Cybernetics, vol.41, no. 1, pp. 173-182, Feb. 2011.
[2] S.Murali Krishn, S.Durga Bhavani "An Efficient Approach for Text Clustering Based on Frequent Itemsets," European Journal of Scientific Research, 1450-216X Vol.42 No.3 (2010), pp.385-396
[3] D. Bridge, M. Goker, L. Mcginty, B. Smyth, "Case-based recommender systems," Knowl. Eng. Rev., vol. 20, no. 3, pp.315–320, Sep. 2005.
[4] P. Cunningham and B. Smyth, "A comparison of model-based and incremental case-based approaches to electronic fault diagnosis," Dept. Comput. Sci., Trinity College Dublin, Dublin, Ireland, Tech. Rep. TCDCS- 94-21, 1994
[5] K. Beyer, J. Goldstein, R. Ramakrishnan, and U. Shaft, "When is nearest neighbor meaningful?" in Proc. ICDT, 199, pp. 217– 235.
[6] S. Agrawal , S. Chaudhuri , G. Das, and A. Gionis, "Automated ranking of database query results," in Proc. CIDR, 2003, pp. 888–899.

Abstract : Blogging sites are very popular in today's world; users interact with each other and create social relationships between them. Data mining methods can be used to extract the blogging sites. Users can be active or dormant in a blog environment, they could be directly influenced by the motivators or not. Direct DCP and Indirect DCP both can be calculated. Some influential user's motivates the other normal users on the basis of some features through which rating could be high and it could be increase the business in terms of monetary. Determining the Content Power Users (CPU) is very essential now a day. It represents the blogging atmosphere which is used to calculate the influential users.

Keywords: Blogging sites, Content Power User, Direct DCP, Document Content Power, Data mining, Indirect DCP.

[1]. Apoorva Vikrant Kulkarni et al (2013) "Blog Content and User Engagement-An Insight Using Statistical Analysis", International Journal of Engineering and Technology (IJET) Vol.5, No.3, Jun-Jul 2013
[2]. Eunyoung Moon et al (2010) "A quality Method to Find Influencers Using Similarity Based Approach in the Blogosphere", IEEE International Conference on Social Computing/IEEE International Conference on Privacy, Security, Risk and Trust
[3]. Hsiu-Ju Chen (2009) "Blogger‟s Social Presence Framing and Blog Visitor‟s Responses", IEEE Computer Society, Eight IEEE/ACIS International Conference on Computer and Information Science
[4]. Malik Muhammad Saad Missen et al (2010) "Opinion Detection in Blogs: What Still Missing?", International Conference on Advances in Social Networks Analysis and Mining
[5]. Malik Muhammad Saad Missen et al (2009) "Sentence-Level Opinion-Topic Association for Opinion Detection in Blogs", International Conference on Advanced Information Networking and Applications Workshops

Abstract : There has been an increasing demand for e-learning technologies and especially for digital watermarking. Using the digital watermarking technology in e-learning is increasingly becoming an important part of the strategy for trusting on-line materials and activities, especially the on-line certificate both easy and cheaply in flexible e-learning way. This paper sets out to develop and create a novel approach to digital watermarking for e-learning certificate that can increase the trustworthiness of e-learning systems in institutions all over the world. This approach will enable these institutions to create an on-line certificate and to add a watermark that can be trusted by other institutions. The most important driving force is concern over protecting copyright, such as for video, audio and other works now available in digital form; it might be that the ease with which perfect copies can be made will lead to large-scale illegal copying, which will in turn undermine the creation of new books, films, pictures etc. the main aims of this paper is to introduce high-quality protected on-line certificates using two kinds of digital watermarking (visible digital watermarking and invisible digital watermarking) in e-learning systems. In addition, this study aims to enable institutions to offer e-learning certificate and to embed digital watermarking systematically.

Keywords: E-learning, Visible and Invisible Digital Watermarking, Moodle, E-Learning Certificate

[1] M. Zlomek, Video Watermarking, doctoral diss, Computer Science, Prague University, 2007.
[2] S. Thaker, Software Watermarking Via Assembly Code Transformations, doctoral diss, San Jose State University, 2004.
[3] M. Arnold, et al., Digital Watermarking and Content Protection (2nd edn. Artech House, 2003).
[4] N. Mandhani, Watermarking Using Decimal Sequences Bachelor of Engineering, doctoral diss, Andhra Univ, India, 2004.
[5] R. Chang, and C. Wang, The renovation of the digital watermarking technique, Tamsui Oxford Journal of Mathematical Sciences, 21(2), 2005, 291—304.

Abstract : Social networking is an essential part of life for people around the world these days. Social networking is a form of social media, used for interactive, educational, informational or entertaining purposes. Even though social media comes in many forms all of them are related to each other. Social networking is also a tool to create and join groups, learn about latest news and events, play games, chat and to share music and video. Some social networks provide facilities to the users' to partition their group of friends based on social community, organization, geographical location, or how well they knows each other. The main challenge in social network is the sharing of data among heterogeneous users. The proposed method provide a systematic mechanism to identify and resolve privacy conflicts for data sharing, and different access control mechanisms.

Keywords: Social Networks, Privacy, Access Control, Security

[1]. Facebook Privacy Policy. http://www.facebook.com/policy.php/.
[2]. Google+ Privacy Policy . http://www.google.com/intl/en/+/policy/.
[3]. D. Boyd and N. B. Ellison. Social network sites: Definition, history, and scholarship. Journal Of Computer-Mediated Communication, 13(1):210–230, 2007.
[4]. H.Hu., G.-J. Ahn, and J. Jorgensen. Enabling Collaborative Data sharing in Google+. Technical Report ASU-SCIDSE-12-1, April 2012.http://sefcom.asu.edu/mpac/mpac+.pdf.
[5]. B.Carminati,E.Ferrari,and A.perego,"Rule-based access control for Social networks". In On the Move to Meaningful Internet Systems 2006: OTM 2006 Workshops, pages 1734–1744. Springer, 2006.

Abstract : Global spread of Information Technologyincreases security challenges; over intrusion detection system against sophisticated attacks. This has become of paramount importance since single mode intrusion detection systems have a lot of difficulties in protecting Network from sophisticated attackers. However, this paper propose a Multi-Level Based Hybridized Intrusion Detection System whereby the incoming packets will be examinedfor attacks at two layers; both at Network level as Network Intrusion Detection (NID) and further double check those that escape through the initial test at the second level using Bayes' theorem at Host level as Host based Intrusion Detection (HID). This will help to prevent against intrusion, minimize false alarms and maximize the numbers of detected bad events. It handle masses of information (often in real-time) so as to report the abnormal use of networks and computer systems in a real time before it get out of hand.

Keywords: Intrusion, Hybridized, Packet, IntrusionDetection and prevention System, Network Intrusion Detection, Host basedIntrusion Detection, Multi-Level Based Hybridized Intrusion Detection System (MHIDS).

[1] C. Srilatha, A. Ajith & P. T. Johnson, Feature deduction and ensemble design of intrusion detection systems, Elsevier, Computers & Security (2004), www.elsevier.com/locate/cose

[2] H. Debar, M. Dacier and A. Wespi, "Towards a taxonomyof intrusion-detection systems" Computer Networks, vol. 31,pg. 805-822, 1999.

[3] F. E. Heba, D. Ashraf, E. H. Abouland A. Ajith, Principle Components Analysis and Support Vector Machinebased Intrusion Detection System, 10th International Conference on Intelligent Systems Design and Applications, 978-1-4244-8136-1/10/IEEE, 2019 Pg 363-367

[4] K. S. Sandeep, C. Nishant and S. Pragya, Concept and Proposed Architecture of Hybrid Intrusion Detection System using Data Mining, International Journal of Engineering and Advanced Technology (IJEAT). ISSN: 2249 – 8958, 2(5), 2013

[5] H. Deber, M. Dacier and A. Wespi., Towards a Taxonomy of Intrusion Detection Systems, Computer Networks, Vol 31 1999 pg 805-822

Abstract : Cloud computing is summed up as a different model for allowing favorable, network as per demand to use shared devices of computational resources which are collected and then released with marginal management effort or interaction with any client or any service provider. Cloud main objective is to cogitate on the demand of provision of the IT infrastructure. Cloud Computing tends to play fundamental role in different fields using new ideas, virtual world, e-business, networking engines used for searching on the web. It is used in ongoing settings where they are created without giving importance to a common programming model or take away of applications.

[1] VVinothina,Dr.RSridaran,DrPadmavathiGanpathi,"A Survey on Resource Allocation in Cloud Computing", IJACSA, Vol3, No.6,2012.

[2] M Asad Afreen, Krzysztof Pawlikowski, Andears Willig," A Framework for Resource Allocation Strategies in Cloud Computing Environment", 35th IEEE Annual Computer Software and Applications Conference Workshop, 2011.

[3] Jianpeng Dai, Bin Hu, Lipeng Zhu, Haiyun Han, Jianbo Liu," Research on Dynamic Resource Allocation with Cooperation Strategy in Cloud Computing, 3rd International Conference on System Science, Engineering and Manufacturing Informatization, 2012.

[4] N R Ram Mohan, E Baburaj, "Resource Allocation Techniques in Cloud Computing- Research Challenges for Applications", 4th International Conference on Computational Intelligence and Communication Network, 2012.

[5] Aman Kumar, Emmanuel S Pilli, R C Joshi," An Efficient Framework for Resource Allocation in Cloud Computing", IEEE, 31661. [6] Swapnil M Parikh," A Survey on Cloud Computing Resource Allocation Techniques", Nirma University International Conference on Engineering, 2013.

Abstract : In Delay Tolerant Networks (DTNs) the core challenge is to cope with lack of persistent connectivity and yet be able to deliver messages from source to destination. In particular, routing schemes that leverage relays' memory and mobility area customary solution in order to improve message delivery delay. When large files need to be transferred from source to destination, not all packets may be available at the source prior to the first transmission. This motivates us to study general packet arrivals at the source, derive performance analysis of replication based routing policies and study their optimization under two-hop routing. In particular, we determine the conditions for optimality in terms of probability of successful delivery and mean delay and we devise optimal policies, so-called piecewise-threshold policies. We account for linear block-codes and rateless random linear coding to efficiently generate red undancy, as well as for an energy constraint in the optimization. We numerically assess the higher efficiency of piecewise-threshold policies compared with other policies by developing heuristic optimization of the thresholds for all flavors of coding considered. Keywords: Delay tolerant networks, mobile ad hoc networks, optimal scheduling, rateless codes, network coding.

[1]. E. Altman, F. De Pellegrini, and L. Sassatelli, "Dynamic control of coding in delay tolerant networks," in Proc. 2010 IEEE INFOCOM, pp. 1–5.
[2]. E. Altman and F. De Pellegrini, "Forward correction and Fountain codes in delay tolerant networks," in Proc. 2009 IEEE INFOCOM, pp. 1–5.
[3]. T. Spyropoulos, K. Psounis, and C. Raghavendra, "Efficient routing in intermittently connected mobile networks: the multi-copy case," ACM/IEEE Trans. Netw., vol. 16, no. 1, pp. 77–90, Feb. 2008.
[4]. E. Altman, T. Bas¸ar, and F. De Pellegrini, "Optimal monotone forwarding policies in delay tolerant mobile ad-hoc networks," in Proc. 2008 ACM/ICST Inter-Perf.
[5]. J. Metzner, "An improved broadcast retransmission protocol," IEEE Trans. Commun., vol. 32, no. 6, pp. 679–683, June 1984.