APTIKOM Journal on Computer Science and Information Technologies (CSIT)
APTIKOM Journal on Computer Science and Information Technologies is a peer-reviewed international journal that publish original research article, review papers, short communications that will have an immediate impact on the ongoing research in all areas of Computer Science, Informatics, Electronics Engineering, Communication Network and Information Technologies. The journal is published four-monthly (March, July and November) by the Indonesian Association of Higher Education Institutions in Computer Science and Information Technology (APTIKOM).
Articles
61 Documents
<![CDATA[IMAGE INPAINT USING PATCH SPARSITY ]]>
<![CDATA[Suryawanshi, Shital D.]]>;
<![CDATA[Baviskar, P. V.]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The process of removing the specific object or area or repairing the damaged area in an image is known as image inpainting. This algorithm [5] is proposed for removing objects from digital image. The challenge is to fill in the hole that is left behind in a visually plausible way. We first note that patch sparsity based synthesis contains the essential process required to replicate both texture and structure [8]; the success of structure propagation however is highly dependent on the order in which the filling proceeds. We propose a best algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting.The actual color values are computed using patch sparsity based synthesis. In this paper the simultaneous propagation of texture and structure information [2] is achieved by a single, efficient algorithm. For best results selected image should have sufficient background information]]>
<![CDATA[A REVIEW ON DEEP LEARNING ALGORITHMS FOR SPEECH AND FACIAL EMOTION RECOGNITION ]]>
<![CDATA[Latha, Charlyn Pushpa]]>;
<![CDATA[Priya, Mohana]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Deep Learning is the recent machine learning technique that tries to model high level abstractions in databy using multiple processing layers with complex structures. It is also known as deep structured learning,hierarchical learning or deep machine learning. The term ?deep learning" indicates the method used in trainingmulti-layered neural networks. Deep Learning technique has obtained remarkable success in the field of facerecognition with 97.5% accuracy. Facial Electromyogram (FEMG) signals are used to detect the different emotionsof humans. Some of the deep learning techniques discussed in this paper are Deep Boltzmann Machine (DBM), DeepBelief Networks (DBN), Convolutional Neural Networks (CNN) and Stacked Auto Encoders respectively. This paperfocuses on the review of some of the deep learning techniques used by various researchers which paved the way toimprove the classification accuracy of the FEMG signals as well as the speech signals]]>
<![CDATA[DEVELOPMENT OF ARDUINO-BASED DATA ACQUISITION SYSTEM FOR ENVIRONMENTAL MONITORING USING ZIGBEE COMMUNICATION PROTOCOL ]]>
<![CDATA[A, Busari Sherif]]>;
<![CDATA[F, Dunmoye Abibat]]>;
<![CDATA[F., Akingbade Kayode]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Data Acquisition Systems (DAS) are used for a variety of applications such as environmental monitoring,indoor climate control, health management and medical diagnostics, traffic surveillance and emergency response,disaster management among others. This paper presents the design of a DAS for monitoring environmentaltemperature, pressure and relative humidity. The system employs Arduino Uno microcontroller for signal processingand Zigbee transceivers operating on the 2.4 GHz license-free Industrial, Scientific and Medical (ISM) band ascommunication modules at both the transmitter and receiver ends. While the transmitter board houses the sensors, aGPS module and an LCD, the receiver system is interfaced with a PC which runs a developed MATLAB GUI for datadisplay and analysis and it incorporates an SD card for data storage. The battery-powered system is a low cost, lowpower consumption system which serves as a mini-weather station with real-time data logging, wirelesscommunication and tracking capabilities.]]>
<![CDATA[AN APPROACH OF NEURAL NETWORK FOR ELECTROCARDIOGRAM CLASSIFICATION ]]>
<![CDATA[Gautam, Mayank Kumar]]>;
<![CDATA[Giri, Vinod Kumar]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[ECG is basically the graphical representation of the electrical activity of cardiac muscles duringcontraction and release stages. It helps in determination of the cardiac arrhythmias in a well manner. Due to thisearly detection of arrhythmias can be done properly. In other words we can say that the bio-potentials generated bythe cardiac muscles results in an electrical signal called Electro-cardiogram (ECG). It acts as a vital physiologicalparameter, which is being used exclusively to know the state of the cardiac patients. Feature extraction of ECG playsa vital role in the manual as well as automatic analysis of ECG. In this paper the study of the concept of patternrecognition of ECG is done. It refers to the classification of data patterns and characterizing them into classes ofpredefined set. The analysis ECG signal falls under the application of pattern recognition. The ECG signal generatedwaveform gives almost all information about activity of the heart. The ECG signal feature extraction parameters suchas spectral entropy, Poincare plot and Lyapunov exponent are used for study in this paper .This paper also includesartificial neural network as a classifier for identifying the abnormalities of heart disease.]]>
<![CDATA[INTELLIGENT MULTI-COLOURED LIGHTING SYSTEM DESIGN WITH FUZZY LOGIC CONTROLLER ]]>
<![CDATA[Mutua, Paul W.]]>;
<![CDATA[Mbuthia, Mwangi]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[This paper describes the design of an intelligent energy efficient lighting system that uses multi-colouredLEDs and a fuzzy logic controller to produce light of the required luminance level and colour in a typical roomspace. The lighting system incorporates automatic control of a room?s window shade opening, convenientlyharvesting daylight. Appropriate room occupancy sensors were set to dim off the LEDs if there are no people in theroom. A movement sensor was also considered for dimming the LEDs if the persons in the room are asleep. A colourdecoder was included in the control system, to determine the LEDs? output light colour and dim them off if the colourrequirement is not selected. The colour decoder also closes the window shade if required light colour is not white.Two Fuzzy Logic controllers were used in the system; one to control opening of the room?s window shade viamicrocontroller, and the other to control the LEDs? output luminance. The study was limited to simulation of thedesign in a MATLAB software environment using Fuzzy Logic Toolbox and Simulink blocks. The simulation testresults confirmed that the LEDs? output luminance decreases as the amount of daylight entering the room increases.The designed system intelligently saves lighting electrical energy while maintaining the room?s comfortableillumination levels and colour requirements.]]>
<![CDATA[DETECTION OF COMPROMISED NODES IN WIRELESS SENSOR NETWORKS USING GPSR PROTOCOL AND ITERATIVE FILTERING ALGORITHM ]]>
<![CDATA[Ramalakshmi, R.]]>;
<![CDATA[Prabhu, S. Subash]]>;
<![CDATA[Balasubramanianb, C.]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 1 No 3 (2016): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The sensor network is used to observe surrounding area gathered and spread the information to other sink.The advantage of this network is used to improve life time and energy. The first sensor node or group of sensor nodesin the network runs out of energy. The aggregator node can send aggregate value to the base station. The sensornode can be used to assign initial weights for each node. This sensor node calculates weight for each node. Whichsensor node weight should be lowest amount they can act as a cluster head. The joint node can send false data to theaggregator node and then these node controls to adversary. The dependability at any given instant represents ancomprehensive behavior of participate to be various types of defects and misconduct. The adversary can sendinformation to aggregator node then complexity will be occurred. These nodes are used to reduce the energy andband width.]]>
<![CDATA[AN IMPROVED APPROXIMATION ALGORITHM FOR CO-LOCATION MINING IN UNCERTAIN DATA SETS USING PROBABILISTIC APPROACH ]]>
<![CDATA[Sheshikala, M.]]>;
<![CDATA[Rao, D. Rajeswara]]>;
<![CDATA[Kadampur, Md. Ali]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 2 No 1 (2017): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[complete data. Many of the real world data is Uncertain, for example, Demographic data, Sensor networksdata, GIS data etc.,. Handling such data is a challenge for knowledge discovery particularly in colocation mining.One straightforward method is to find the Probabilistic Prevalent colocations (PPCs). This method tries to find allcolocations that are to be generated from a random world. For this we first apply an approximation error to find allthe PPCs which reduce the computations. Next find all the possible worlds and split them into two different worldsand compute the prevalence probability. These worlds are used to compare with a minimum probability threshold todecide whether it is Probabilistic Prevalent colocation (PPCs) or not. The experimental results on the selected dataset show the significant improvement in computational time in comparison to some of the existing methods used incolocation mining.]]>
<![CDATA[DETECTION OF CRIMES USING UNSUPERVISED LEARNING TECHNIQUES ]]>
<![CDATA[Babu, R. Buli]]>;
<![CDATA[Snehal, G.]]>;
<![CDATA[Kiran, Aditya Satya]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 2 No 1 (2017): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Data mining can be used to detect model crime problems. This paper is about the importance of datamining about its techniques and how we can easily solve the crime. Crime data will be stored in criminal?s database.To analyze the data easily we have data mining technique that is clustering. Clustering is a method to group identicalcharacteristics in which the similarity is maximized or minimized. In clustering techniques also we have different typeof algorithm, but in this paper we are using the k-means algorithm and expectation-maximization algorithm. We areusing these techniques because these two techniques come under the partition algorithm. Partition algorithm is oneof the best methods to solve crimes and to find the similar data and group it. K-means algorithm is used to partitionthe grouped object based on their means. Expectation-maximization algorithm is the extension of k-means algorithmhere we partition the data based on their parameters.]]>
<![CDATA[A SECURITY APPROACH FOR SMART GRID ON REVIEW ]]>
<![CDATA[Suman, Santosh Kumar]]>;
<![CDATA[Aqib, Mohd.]]>;
<![CDATA[Singh, Sumit Kumar]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 2 No 1 (2017): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Aim of this paper the infrastructure for the traditional grid & smart grid. Together depend uponmanagement and control system but the main modification is in the security system because it activities the benefits ofthe cyber world for realizing its objectives, it also faces security attacks. Therefore security of the smart grid becomesforemost concern. Even the best smart grid infrastructure along with best management and control mechanisms willprove to be ineffective if security of the smart grid is not taken care of. In this discusses about the importance ofprotection in smart grid. It presents a review of progress made by researchers and governments and the technologiesused in the area. It identifies the security issues involved with the current infrastructure. It points out about the areasin security where the research is still needed and discusses some observations regarding improvement of security insmart grid.]]>
<![CDATA[SPEECH SCRAMBLING BASED ON CHAOTIC MAPPING AND RANDOM PERMUTATION FOR MODERN MOBILE COMMUNICATION SYSTEMS ]]>
<![CDATA[G, Dhanya]]>;
<![CDATA[Jayakumari, J]]>
<![CDATA[ APTIKOM Journal on Computer Science and Information Technologies Vol 2 No 1 (2017): APTIKOM Journal on Computer Science and Information Technologies (CSIT) ]]>
Publisher : <![CDATA[APTIKOM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The expanding significance of securing data over the network has promoted growth of strong encryptionalgorithms. To enhance the information protection in network communications, this paper presents a Randompermutation, chaotic mapping and pseudo random binary scrambling. It involves transforming the intelligible speechsignal into an unintelligible form to protect it from interrupters. In this report, suggest a simple and secure procedureto secure the speech signal. The speech scrambling process makes use of two Permutations. In the first step, Randompermutation algorithm is used to swap the rows of the original speech followed by swapping of rows using chaoticBernoulli mapping. This produces an intermediary scrambled speech. In the second measure, pseudo random binarygenerator is used to make the final scrambled signal. Various analysis tests are then executed to determine thequality of the encrypted image. The test results determine the efficiency of the proposed speech scrambling process.]]>
