cover
Contact Name
ComengApp Journal
Contact Email
comengappjournal@gmail.com
Phone
+62711580644
Journal Mail Official
comengappjournal@gmail.com
Editorial Address
-
Location
Kab. ogan ilir,
Sumatera selatan
INDONESIA
Computer Engineering and Applications Journal
Published by Universitas Sriwijaya
ISSN : 22524274     EISSN : 22525459     DOI : -
ComEngApp-Journal (Collaboration between University of Sriwijaya, Kirklareli University and IAES) is an international forum for scientists and engineers involved in all aspects of computer engineering and technology to publish high quality and refereed papers. This Journal is an open access journal that provides online publication (three times a year) of articles in all areas of the subject in computer engineering and application. ComEngApp-Journal wishes to provide good chances for academic and industry professionals to discuss recent progress in various areas of computer science and computer engineering.
Articles 120 Documents
NETWORK ATTACKS DETECTION BY HIERARCHICAL NEURAL NETWORK Javidi, Mohammad Masoud; Nattaj, Mohammad Hassan
Computer Engineering and Applications Journal Vol 4 No 2 (2015)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (460.132 KB) | DOI: 10.18495/comengapp.v4i2.108

Abstract

Intrusion detection is an emerging area of research in the computer security and net-works with the growing usage of internet in everyday life. Most intrusion detection systems (IDSs) mostly use a single classifier algorithm to classify the network traffic data as normal behavior or anomalous. However, these single classifier systems fail to provide the best possible attack detection rate with low false alarm rate. In this paper,we propose to use a hybrid intelligent approach using a combination of classifiers in order to make the decision intelligently, so that the overall performance of the resul-tant model is enhanced. The general procedure in this is to follow the supervised or un-supervised data filtering with classifier or cluster first on the whole training dataset and then the output are applied to another classifier to classify the data. In this re- search, we applied Neural Network with Supervised and Unsupervised Learning in order to implement the intrusion detection system. Moreover, in this project, we used the method of Parallelization with real time application of the system processors to detect the systems intrusions.Using this method enhanced the speed of the intrusion detection. In order to train and test the neural network, NSLKDD database was used. Creating some different intrusion detection systems, each of which considered as a single agent, we precisely proceeded with the signature-based intrusion detection of the network.In the proposed design, the attacks have been classified into 4 groups and each group is detected by an Agent equipped with intrusion detection system (IDS).These agents act independently and report the intrusion or non-intrusion in the system; the results achieved by the agents will be studied in the Final Analyst and at last the analyst reports that whether there has been an intrusion in the system or not. Keywords: Intrusion Detection, Multi-layer Perceptron, False Positives, Signature- based intrusion detection, Decision tree, Nave Bayes Classifier
AN IMPERIALIST COMPETITIVE ALGORITHM FOR THE WINNER DETERMINATION PROBLEM IN COMBINATORIAL AUCTION Mostafavi, Reza; Razavi, Seyed Naser; Balafar, Mohammad Ali
Computer Engineering and Applications Journal Vol 4 No 1 (2015)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (168.423 KB) | DOI: 10.18495/comengapp.v4i1.107

Abstract

Winner Determination problem (WDP) in combinatorial auction is an NP-complete problem. The NP-complete problems are often solved by using heuristic methods and approximation algorithms. This paper presents an imperialist competitive algorithm (ICA) for solving winner determination problem. Combinatorial auction (CA) is an auction that auctioneer considers many goods for sale and the bidder bids on the bundle of items. In this type of auction, the goal is finding winning bids that maximize the auctioneerâ??s income under the constraint that each item can be allocated to at most one bidder. To demonstrate, the postulated algorithm is applied over various benchmark problems. The ICA offers competitive results and finds good-quality solution in compare to genetic algorithm (GA), Memetic algorithm (MA), Nash equilibrium search approach (NESA) and Tabu search.
NETWORK SURVIVABILITY PERFORMANCE EVALUATION IN UNDERWATER SURVEILLANCE SYSTEM USING MARKOV MODEL Nabavi, Seyyed Yahya; Mohammadi, Reza; Keshtgari, Manijeh
Computer Engineering and Applications Journal Vol 3 No 3 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (558.704 KB) | DOI: 10.18495/comengapp.v3i3.98

Abstract

Underwater Wireless Sensor Network (UWSN) is a useful technology that can be used in Underwater Surveillance System (USS). USSs are mostly used in military purposes for detecting underwater military activities. One of the most important issues in USS is mission reliability or survivability. Due to harsh underwater environment and mission critical nature of military applications, it is important to measure survivability of USS. Underwater sensor node failures can be detrimental for USS. To improve survivability in USS, we propose a fault-tolerant underwater sensor node model. To the best of our knowledge, this is the first fault-tolerant underwater sensor node model in USS that evaluates survivability of an USS.  We develop Markov models for characterizing USS survivability and MTTF (Mean Time to Failure) to facilitate USS. Performance evaluation results show the effectiveness of proposed model.
DATA MANAGEMENT CHALLENGES IN CLOUD ENVIRONMENTS Javidi, Mohamad Masood; Mansouri, Najme; Asadi Karam, Asghar
Computer Engineering and Applications Journal Vol 3 No 3 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (570.774 KB) | DOI: 10.18495/comengapp.v3i3.105

Abstract

Recently the cloud computing paradigm has been receiving special excitement and attention in the new researches. Cloud computing has the potential to change a large part of the IT activity, making software even more interesting as a service and shaping the way IT hardware is proposed and purchased. Developers with novel ideas for new Internet services no longer require the large capital outlays in hardware to present their service or the human expense to do it. These cloud applications apply large data centers and powerful servers that host Web applications and Web services. This report presents an overview of what cloud computing means, its history along with the advantages and disadvantages. In this paper we describe the problems and opportunities of deploying data management issues on these emerging cloud computing platforms. We study that large scale data analysis jobs, decision support systems, and application specific data marts are more likely to take benefit of cloud computing platforms than operational, transactional database systems.  
SURVEY ON MULTI AGENT ENERGY EFFICIENT CLUSTERING ALGORITHMS IN WIRELESS SENSOR NETWORKS Karimi, Nazli Bagherzadeh; Razavi, Seyed Naser
Computer Engineering and Applications Journal Vol 3 No 3 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (569.621 KB) | DOI: 10.18495/comengapp.v3i3.92

Abstract

In the last few years, there are many applications for Wireless Sensor Networks (WSNs). One of the main drawbacks of these networks is the limited battery power of sensor nodes. There are many cases to reduce energy consumption in WSNs. One of them is clustering. Sensor nodes partitioned into the clusters so that one is chosen as Cluster Head (CH). Clustering and selection of the proper node as CH is very significant in reducing energy consumption and increasing network lifetime. In this paper, we have surveyed a multi agent clustering algorithms and compared on various parameters like cluster size, cluster count, clusters equality, parameters used in CHs selection, algorithm complexity, types of algorithm used in clustering, nodes location awareness, inter-cluster and intra-cluster topologies, nodes homogeneity and MAC layer communications.
A NEW HADOOPBASED NETWORK MANAGEMENT SYSTEM WITHPOLICY APPROACH Namvarasl, Sahar; Abdi, Vajihe; Javidan, Reza
Computer Engineering and Applications Journal Vol 3 No 3 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (110.273 KB) | DOI: 10.18495/comengapp.v3i3.70

Abstract

In recent years with the improvement in the field of network technology and decreasing of technology cost, lots of data are produced. This massive amount of data needs mechanism for processing and mining information rapidly. In this paper a new Hadoop based network management system with policy approach which is considered hierarchical manager is presented. Storing and processing massive data efficiently are two capability of Hadoop technology by using HDFS and MapReduce. In this paper, processing time is considered as a main factor. As a result it is proved that this management system using policy approach increases the performance of entire system without putting on extra cost for implementation. This system in contrast with pure Hadoop and centralized system is several times more rapid.
AN IMPROVED MULTI-CYCLE DEADLOCK DETECTION AND RESOLUTION ALGORITHM FOR DISTRIBUTED SYSTEMS Askari, Mohsen; Oskouei, Rozita Jamili
Computer Engineering and Applications Journal Vol 3 No 3 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (974.61 KB) | DOI: 10.18495/comengapp.v3i3.89

Abstract

Distributed systems exhibit a high degree of resource and data sharing creating a state in which deadlocks might make their appearance. Since deadlock detection and resolution  is one of the important concerns in distributed systems which lead to minimizing available resources, therefore instigating   the  system  throughput decrease.  Our  proposed algorithm detects and resolves  the  multi-cycle  deadlocks, whether the initiator is involved in the deadlock cycle directly or indirectly. Also the chance  of  phantom  deadlock  detection is minimized. This  algorithm  not  only  can manage the simultaneous execution of it but also detects the multi-cycle deadlocks in  the  distributed  systems. Our  algorithm introduces a modified probe and victim message  structure. Moreover,  no  extra  storage  required  to  store  prob message  in each node which is known as memory overhead in the distributed systems.
CODES CORRECTING AND SIMULTANEOUSLY DETECTING SOLID BURST ERRORS Das, P. K.
Computer Engineering and Applications Journal Vol 2 No 2 (2013)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (310.953 KB) | DOI: 10.18495/comengapp.v2i2.23

Abstract

Digital images are foremost source for information transfer. Due to advancement of the technology, images are now not treated as reliable source of information. Digital images can be edited according to the need. Adding and deleting content from an image is most easiest and popular way of creating image forgery, which is known as copy-move forgery. Digital Image Forensics is the field that deals with the authenticity of the images. Digital image forensics checks the integrity of the images by detecting various forgeries. In order to hide the traces of copy-move forgery there are editing operations like rotation, scaling, JPEG compression, Gaussian noise called as attacks, which are performed on the copied part of the image before pasting. Till now these attacks are not detected by the single method. The novel approach is proposed to detect image forgery by copy-move under above attacks by combining block-based and keypoint-based method. Keywords: Digital image forensics, copy-move forgery, passive blind approach, keypoint-based, block-based methods
PROPOSED DEVELOPEMENTS OF BLIND SIGNATURE SCHEME BASED ON ECC Amounas, F.; El Kinani, E. H.
Computer Engineering and Applications Journal Vol 2 No 2 (2013)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (328.965 KB) | DOI: 10.18495/comengapp.v2i2.24

Abstract

Detecting and gaining clues from the crime scene plays a major role in the process of investigation. Now a days with increase of cybercrime and fraud on the internet, digital forensics gaining importance. It needs to collect information the events happened at crime place. This paper deals with event reconstruction process which is useful for digital crime scene. The process of reconstruction is based on crime event and event characteristics. It also furnishes crime rate guess using some semi-formal techniques. Keyword: Digital Investigation, Digital Forensics, Events, Attack Trees, Reconstruction
AUTOMATIC IRANIAN VEHICLE LICENSE PLATE RECOGNITION SYSTEM BASED ON SUPPORT VECTOR MACHINE (SVM) ALGORITHMS Aghaie, Mahdi; Shokri, Fatemeh; Zade Tabari, Meisam Yadolah
Computer Engineering and Applications Journal Vol 2 No 2 (2013)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (900.924 KB) | DOI: 10.18495/comengapp.v2i2.25

Abstract

In the emerging trends the pervasive nature across the computing environment shows that the system is platform independent and device independent. The system development is designed with the help of Structured Query Language and middleware infrastructure that are used to collect the information from various nodes. An essential feature of this proposed middleware architecture suites the device independent as the major supporting capability to the system. This facilitates to add new device types in the system feels easy through the use of device self-description.  It mainly focuses on the issues related to the heterogeneity of the different devices composing a pervasive system: This aspect is investigated both at data management and at physical integration levels. Using the nontrivial approach aims at handling the related issues are resolved with the corresponding solution. Keyword: Perla, Cloud Monitoring, Middleware, Declarative Language

Page 1 of 12 | Total Record : 120