Page 4 (data 91 to 120 of 328) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 NEXT >>

91	Computer Science	ABS-161
Code Comment Assessment Development for Basic Programming Subject using Online Judge Rosa Ariani S., Rani Megasari, Erna Piantari, M. Nabillah Fihira R. Universitas Pendidikan Indonesia Abstract The computer program source code must have a good documentation on it in order to be more understandable by others. One of the documentation is comments. Therefore, the university students need to learn and able to write comments. Some university students are familiar with online judge as a tool for learning programming. Online judge usually does not check how the source code written instead of the output only. This research is aimed for implementing comment analysis module for online judge in order it can check the comments in the source code which is uploaded by students. The comments on this module are categorized as two parts. There are header and process comments. The comments data have taken from online judge which is used before as learning tool for basic programming subject. The data are divided into two groups. There are training group and test group. This module gives mark to the source code comments based on the categorized and similarity score between comments and the given problem. Keywords: code comment, comment assessment, basic programming subject, online judge, source code PermaLink | Plain Format | Corresponding Author (Rosa Ariani Sukamto)

92	Computer Science	ABS-162
Classification of Farmers‘ Eligibility as Recipents of Subsidized Fertilizer Assistance with C4.5 Algorithm Diah Nur Yunita (a1), Anna Hendri Soleliza Jones (a2,*), Dewi Soyusiawaty (a3) a) Department of Informatics, Ahmad Dahlan University a1) diahnuryunita[at]gmail.com a2*) annahendri[at]tif.uad.ac.id a3) dewi.soyusiawaty[at]tif.uad.ac.id Abstract Farmers are the main actors in agricultural development, have a major contribution in realizing Indonesias agricultural vision. To support the realization of agricultural production and productivity targets, the governments supports is by issuing policies to provide subsidized fertilizer assistance. The criteria for farmers who are eligible to receive subsidized fertilizer assistance are having land less than 1.9 hectares, have been a members of farmer groups, and having work as a farmer or a private employees. Data collection was carried out using the method of observation and interviews with farmer groups in Gunung Kidul. Data classification is done by applying the C4.5 algorithm to 300 data of prospective farmers receiving subsidized fertilizer assistance. Application development includes interface design, making data flow diagrams, implementation and testing. From the research that has been done by applying the C4.5 Algorithm with 300 data and 113 as a training data. Produce a data classification of farmers who are eligible to receive assistance at 88% accurate and targeted to the needs of farmers. This means that the C4.5 algorithm can be used as a classification for determining the eligibility of farmers to receive subsidized fertilizer. Keywords: Keywords: Algorithm C4.5, Classification, Subsidized fertilizer, Farmers PermaLink | Plain Format | Corresponding Author (ANNA HENDRI SOLELIZA JONES)

93	Computer Science	ABS-171
The Artificial Neural Networks (ANN) for Batik Detection Based on Textural Features 1)Anita Ahmad Kasim;2)Muhammad Bakri;3)Anindita Septiarini 1)Departemen of Information Technology, Tadulako University, Palu, Indonesia 2)Department of Architecture, Tadulako University, Palu, Indonesia 3)Department of Computer Science, Mulawarman University, Samarinda, Indonesia Abstract The problem in this research is the difficulty in distinguishing batik motifs from non-batik motifs for people who do not understand batik motifs. The classification of batik motifs can be done by processing digital images of batik motifs using artificial neural network methods for the classification of batik image motifs. This study aims to utilize artificial neural networks to distinguish batik motifs and non-batik fabric motifs. Several important steps are needed, namely the process of acquiring batik and non-batik images, pre-transforming batik and non-batik images to gray scale forms, texture feature extraction in gray scale images and detection of motifs using networks artificial nerve. Image acquisition is done by collecting batik and not batik images from several different motifs. The preprocessing process is done by changing the image size to 256 x 256. Sixteen texture features are used, namely Angular Second Moment (ASM), contrast, correlation and Inverse Different Moment (IDM) with 45 ° angle intervals, namely 0 °, 45 °, 90 ° and 135 °. Processing data sets is divided into 70 percent as training data and 30 percent as testing data. Artificial neural network models used in this research use the Backpropagation learning algorithm by comparing the Scaled conjugate gradient algorithm (trainscg) training method and the Levenberg-Marquardt algorithm (trainlm) training method. The results obtained for the accuracy of the batik detection model using the Scaled conjugate gradient algorithm (trainscg) training method were higher with an accuracy value of 86.7%, compared to the Levenberg-Marquardt algorithm (trainlm) method by 73.5%. Keywords: batik,textura features,ANN PermaLink | Plain Format | Corresponding Author (Anita Ahmad Kasim)

94	Computer Science	ABS-184
Predicting Fetal Condition from Cardiotocography Results Using the Random Forest Method Syifa Fauziyah Nurul Islam (a*), Intan Nurma Yulita (b) a,b) Department of Computer Science, Padjadjaran University, Sumedang 45363, Indonesia *syifafauziyah899[at]gmail.com Abstract Cardiotocography is an important process in pregnancy as fetal monitoring. It monitors the babys heart rate in a healthy condition or not. Apart from that, this can also measure whether the movements carried out by the baby in the womb are normal or not. This study extracted the recording data by cardiotocographs. The attributes of fetal data that have been recorded amount to 22. They were used as the indicators in determining the conditions of the fetus whether under normal circumstances, suspect or pathologic. The prediction of the fetus condition was based on the Random Forest method. Also, the method was compared with the Naïve Bayes and Decision Tree methods. The accuracy of the Random Forest method reached 95.12%. It was higher compared to using other methods. Keywords: Cardiotocography; Radom Forest; Naive bayes; Decision Tree PermaLink | Plain Format | Corresponding Author (Syifa Fauziyah Nurul Islam)

95	Computer Science	ABS-187
Breast Cancer Classification: Comparison of Bayesian Networks, Multilayer Perceptron, and Boosting Method Intan Nurma Yulita(*), Shofiyyah Nadhiroh *Faculty of Mathematics and Natural Science, Padjadjaran University Jalan Raya Bandung Sumedang KM.21, Jawa Barat 45363, Indonesia Abstract Cancer is a dangerous disease that should not be underestimated. The early stages of this disease are often asymptomatic. Early detection of cancer is an important examination so that the disease does not develop into a serious and dangerous disease. This study detected the presence of cancer through five predictors. This study classified the diagnosis results based on five indicators namely radius, texture, perimeter, area, and smoothness. By using these five indicators, the detection was carried out through a classification mechanism using the boosting method. The result had obtained an accuracy of 93.67%. The accuracy was higher than other classification methods such as Bayesian Networks and Multilayer Perceptron. Both of them only obtained an accuracy of 89.63%, and 92.79%, respectively. It showed that the ensemble method mechanism of boosting had proven to be more effective in classifying the presence or absence of breast cancer Keywords: Breast cancer; Classification; Boosting; Bayesian Networks; Multilayer Perceptron PermaLink | Plain Format | Corresponding Author (Shofiyyah Nadhiroh)

96	Computer Science	ABS-188
Web-Based Literacy Information Systems as Strategies to Improve Society Reading Interest Ricky Firmansyah (a*), Nanang Hunaifi (b), Dinda Amalia (c) a) AMIK BSI Bandung Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia *rickyapr[at]yahoo.co.id b) AMIK BSI Bandung Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia masnaing[at]gmail.com c) STIE Wikara Jl. Jend. Ahmad Yani No.21 Purwakarta dindaamalia.s326nus[at]yahoo.com Abstract The reading ability of 9-14 years children in Indonesia ranks 40th out of 40 countries studied by the Program for International Student Assessment (PISA). Reading interest must be accustomed regularly at least for yourself, efforts to increase the reading interest need to be fostered from an early age. Gerakan Literasi Sekolah (GLS) was launched to increase the reading interest for school residents, especially students. However, the implementation of GLS in schools is still not utilizing information technology. This research focuses on how to design a web-based literacy information system to increase students reading interest in junior high schools. This web-based literacy information system is designed with Unified Modeling Language (UML) architecture diagrams, implemented using the PHP language and MySQL database system. The system was tested using Black box Testing and a questionnaire for public testing. The results of this study are the literacy information system has been developed that is used to increase student reading interest, where 82.91% of respondents agreed that this system provides convenience in facilitating work and uploading book reviews made by users. Keywords: internet; literacy; information system; reading interest; website PermaLink | Plain Format | Corresponding Author (Ricky Firmansyah)

97	Computer Science	ABS-189
Neural Network Classification for Breast Cancer Analysis Paquita Putri Ramadhani , Intan Nurma Yulita Department of Computer Science, Padjadjaran University, Sumedang 45363,Indonesia Abstract Breast cancer is a type of cancer that has a high mortality rate. Cancer is caused by a lump from a collection of cells that grows and attacks the surrounding tissue. Most breast lumps are benign, but the benign breast lumps can increase the risk of developing breast cancer. It is important for everyone to check for a lump in the breast. It is done to find out whether the lump is potentially cancer or not. Early detection can provide better handling. The diagnosis of breast cancer by a doctor is done by analyzing several factors. To help the doctor in diagnosing the data efficiently, this study implemented machine learning. The diagnosis was based on the features of digital image computation in the process of fine-needle aspiration (FNA) of a breast mass. The data came from 569 patients. The study used the neural networks classification method with multilayer perceptron algorithms. The results were obtained that the use of neural networks gave higher accuracy if it compared it in the ZeroR method. Their accuracies were 95.96%, and 62.74%, respectively. Keywords: Breast cancer, Neural Network Classification, ZeroR dan Multilayer Perceptron PermaLink | Plain Format | Corresponding Author (Paquita Putri Ramadhani)

98	Computer Science	ABS-190
Web-Based Orphanage Fundraising Information System Phitsa Mauliana (a*), Ricky Firmansyah (b), Ai Surtika Dewi (c) a) AMIK BSI BANDUNG Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia *phitsa.phu[at]gmail.com b) AMIK BSI BANDUNG Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia rickyapr[at]yahoo.co.id b) STIE Wikara Jl. Jend. Ahmad Yani No.21 Purwakarta 41114, Indonesia surtikadewiai[at]gmail.com Abstract Today in Indonesia there are still many orphanages which have many financial, facilities, and affection limitations considering the orphanage is a place where children are abandoned by their parents. Donations are needed to support the growing number of foster children such as food, foster education, and electricity/water fees and so on. One funds source for orphanages in various countries comes from several online donation sites on the internet. This research proposes the "e-Panti" web-based orphanage information system as a means of raising donations. Through this system, benefactors will be able to see profiles of orphanages, lists of orphans, orphanage activities, and how to make donations. This system was developed by the waterfall method which was designed using the Unified Modeling Language (UML) architecture diagram and implemented into the PHP web programming languages using MySQL database system. The system is tested using Black box testing to ensure system functionality and user acceptance tests using questionnaires. The results of this study are the development of the "e-Panti" web-based orphanage information system with a user acceptance rate of 77.50% based on the the questionnaire results. Keywords: donation; information system; internet; orphanage; website PermaLink | Plain Format | Corresponding Author (Phitsa Mauliana)

99	Computer Science	ABS-193
Facial Action Point Detection Using Convolutional Neural Network Yaya Wihardi, Rahmandani, Erlangga, Dimas Saptahadi Universitas Pendidikan Indonesia University of Alabama at Birmingham Abstract Facial action point detection is a very important task in computer vision due to various application such as in facial expression recognition, facial motion capture, and another human face analysis. This research aimed to propose a deep learning approach to identify and localize facial action points in sequences of images by using convolutional neural network. The result provide an evidence that the model can detect the points with 87% of accuracy. Keywords: Facial Action Point, CNN, Deep Learning PermaLink | Plain Format | Corresponding Author (Yaya Wihardi)

100	Computer Science	ABS-196
Support Vector Machine for Diagnosis Autism Spectrum Disorder in Toddlers Intan Nurma Yulita, Aditya Rizky Fadillah Padjadjaran University Abstract Autism spectrum disorder (ASD) is a developmental disorder that affects communication and behavior. ASD can be seen in children since toddlers. The knowing toddler has ASD is very important. It can anticipate as early as possible to minimize the worsening of ASD. It can be done by early detection. The mechanism is recognizing patterns form existing data to build detection models. The system can be built using machine learning mechanism. It has been widely used to help diagnose medical data. Support Vector Machine (SVM) is a method in machine learning. This study implemented it in the data which came from 1054 ASD patients. The study also compared the method to other machine learning methods. The results were obtained that SVM accuracy is higher than others. The SVM obtained an accuracy of 99.90%. It shows that SVM promising tool for the diagnosis of ASD. Keywords: Autism Spectrum disorder, Machine Learning, Support Vector Machine, Toddler PermaLink | Plain Format | Corresponding Author (Intan Nurma Yulita)

101	Computer Science	ABS-197
Online Information System for Archiving Documents and Letters Requests at the sub-District Level Nanang Hunaifi (*a), Agung Baitul Hikmah (b), Maxsi Ary (c) a) AMIK BSI BANDUNG Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia *masnaing[at]gmail.com b) AMIK BSI Tasikmalaya Jl. Tanuwijaya No.4, Tasikmalaya 46113, Indonesia agung.abl[at]bsi.ac.id a) AMIK BSI BANDUNG Jl. Sekolah Internasional 1-2, Bandung 40282, Indonesia maxsiary[at]gmail.com Abstract Population registration management is the government responsibility, so that each resident is registered administratively in accordance with the Act. However, to make a certificate, the people may not be directly served. The issue of extortion and complicated processes makes the people feel the data management is a complicated and make people often ignore it, this is a loss for all parties. One of the negative impacts of not recording population data is that there is a dual identity of the population that can be misused; unknown newcomers are often used for terrorism activities, obstruction of other arrangements that require a certificate of population. Currently the data processing and archiving process is still done manually. This research aims to develop a document archiving information system and online mail application at the sub-district level. This system was designed with the waterfall method and Unified Modeling Language (UML) modeling, and then implemented using the PHP MySQL web programming. Black box is used as a functional testing of information systems. The results of this study is the document archiving information systems and online mail requests have been developed with positive responses from users by 84.50% based on the user acceptance test level questionnaire. Keywords: egoverment; information system; internet; population; website PermaLink | Plain Format | Corresponding Author (Nanang Hunaifi)

102	Computer Science	ABS-198
Computer Support Strategic Planning in Collaborative IS-Business Strategic Alignment Asep Wahyudin, Riki Winardi Garna, Rani Megasari Department of Computer Science, Universitas Pendidikan Indonesia Abstract Aligning systems and information technology with organizational business strategies requires accurate strategic planning that can provide knowledge about the strengths that must be utilized, the shortcomings that must be minimized, opportunities that must be maximized, and what obstacles are faced by an organization. Formulating strategic planning is not easy, complex and requires a long process of time. Efforts can be made to avoid mistakes in the formulation of strategic planning and failure in its implementation is to involve all elements in the organization collaboratively. This research focuses on the process of aligning business strategies and information systems strategies carried out by promoting collaborative patterns aided by computer support systems for strategic planning as virtual media. Share vision, share viewpoints, share knowledge, active partnerships, active communication, and partnership approaches are the basic collaborative patterns of the system. The focus group discussion mechanism is used as a method in the system and is realized into work stages, namely stakeholder initiation and teamwork organized, data gathering, knowledge generated and review, and vision conference. The results of the research are useful as a virtual collaborative model in the information system strategic planning process, can be further developed involving intelligence agents, is a future development of this research. Keywords: computer support strategic planning, collaborative, business strategy and information systems alignment, strategic information system planning PermaLink | Plain Format | Corresponding Author (Asep Wahyudin)

103	Computer Science	ABS-199
Personalized Stress Detection using Multimodal Dataset from Wearable Sensor Fitri Indra Indikawati Universitas Ahmad Dahlan Abstract Stress detection is an interesting topic because of its huge impact on human health, both mentally and physically. Physiological changes on the human body can be observed and used to recognize stress. Various approaches utilize a different kind of data to detect physiological changes, i.e. visual data, audio data, interview result, textual data, or sensor data. Wearable sensors for collecting physiological data are becoming more prominent in recent years due to their functionality and non-intrusive nature. By utilizing data from wearable sensors, we have developed a personalized stress detection system. Our system performs classification on stress level based on multimodal data from Empatica E4 wearable sensor. By evaluating the performance of the system, we demonstrate that our system can perform personalized stress detection using a real multimodal dataset from wearable sensor. Keywords: stress detection, wearable sensor, classification PermaLink | Plain Format | Corresponding Author (Fitri Indra Indikawati)

104	Computer Science	ABS-204
A COMPARATIVE STUDY OF BLINDHIDE AND FILTERFIRST ALGORITHM IN DIGITAL IMAGES FOR STEGANOGRAPHY TECHNIQUES Purwantoro(a*), Garno(a), Ari Suntia(a), Munir(b) (a)Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Singaperbangsa Karawang *purwantoro.masbro[at]staff.unsika.ac.id, garno[at]staff.unsika.ac.id, 1441177004113[at]student.unsika.ac.id (b)Departement of Computer Science Education, Universitas Pendidikan Indonesia munir[at]upi.edu Abstract The study was conducted in the field of hiding messages using the media image. This model is often referred to as steganography technique. Image media used for insertion are BMP (Bitmap Picture) format images, JPEG (Joint Photographic Expert Group) and PNG (Portable Network Graphics). The secret message form that is inserted is in the txt format. The application used for insertion is the Digital Invisible Ink Toolkit. Research parameters include image quality testing, and quantitative testing on each Blindhide algorithm and the Filterfirst algorithm. Image Quality test results using MSE, PSNR, showed significant differences, while the value of SC showed differences but not substantial. The results of testing and analysis evaluations that have been carried out on each image turned out to be an average value of the MSE value of the Blindhide algorithm 0.024 greater than the Filterfirst algorithm 0.023, PSNR Blindhide algorithm 31.91 smaller than the Filterfirst 32.03 algorithm, SC Blindhide algorithm 0.99986 smaller than the Filterfirst algorithm 0.99988. This shows that the insertion of a secret message into the image using the Filterfirst algorithm is safer and will not be suspected. Keywords: Steganography, Embedding, Blindhide, Filterfirst, Digital Invisible Ink Toolkit PermaLink | Plain Format | Corresponding Author (Garno Garno)

105	Computer Science	ABS-207
Sentiment Analysis of The Body Shaming Beauty Vlog Comments Jajam Haerul Jaman (a*), Hannie (b), Martina Sari Simatupang (c) Computer Science Faculty of Singaperbangsa Karawang University Abstract Body shaming is a form of mocking/insulting action by commenting on the shape or size of the body and the appearance of someone so that someone feels embarrassed. Problems with comments that contain body shaming elements are important things to study as text processing. Sentiment analysis can be used as a solution to identify body shaming comments with the classification method using the Naïve Bayes Classifier algorithm. Naïve Bayes Classifier uses the concept of probability of each class in its classification learning, so that the distance between classes is not large. The purpose of this study is to predict or classify comment data based on shaming and non shaming sentiment classes. The test in this study was carried out with ten different scenarios using the R programming language with RStudio tools which were then evaluated using confusion matrix to determine the best classifier model.. The evaluation results with confusion matrix found that the best model classifier is a scenario with a comparison of training data and testing data 90:10 and applying stemming at the preprocessing. This scenario achieves an accuracy of 98.48% with an error rate of 1.52%. Recall is 99.53%, specificity is 66.67%, precision is 98.90%, and F-measure is 99.21%. Keywords: Body Shaming; Naïve Bayes Classifier; Sentiment Analysis PermaLink | Plain Format | Corresponding Author (Jajam Haerul Jaman)

106	Computer Science	ABS-211
STUDENTS SKILLS COMPETENCY TEST PREDICTION USING C4.5 ALGORITHM Ultach Enri (*), Jajam Haerul Jaman, Muhammad Rizky Ananda Faculty of Computer Science, Universitas Singaperbangsa Karawang, Karawang 41361, Indonesia Abstract Skills Competency (UKK) is part of government intervention in ensuring the quality of education in the Secondary Vocational School aims to measure the achievement of a certain level of competency in students’ appropriate competency skills. The C4.5 algorithm is the algorithm for classification learning machine learning and data mining that generate either a decision tree, each attribute selection is used in determining the best criteria for classifying the tuple. Feature selection is done to reduce irrelevant features and reduce the dimensions of the features in the data. The purpose of the research is to find out how competent the students’ in their vocation as well as new strategies for educators in providing a more effective learning. Students’ competency expertise data from department of computer engineering and networks in SMK TI Muhammadiyah Cikampek will be used. Overall the results of the validation of the model experiments that have the best influence is supplied with a set of test accuracy values of 96.875%, and 13 optimal attributes are selected. The utilization of the feature selection is to reduce the size of the input data that will be managed on processing and analysis. Therefore, in this study the C4.5 algorithm with feature selection can provide good and effective results. Keywords: C4.5 Algorithm, Data Mining, Feature Selection PermaLink | Plain Format | Corresponding Author (Ultach Enri)

107	Computer Science	ABS-215
Objective Quality Assessment of Multi-Resolution Video based on H.264/AVC and H.265/HEVC Encoding Adhi Rizal (a*), Aries Suharso (a), Panji Abujabbar (a), Munir (b) (a) Faculty of Computer Science, Universitas Singaperbangsa Karawang, Karawang 41361, Indonesia *adhi.rizal[at]staff.unsika.ac.id (b)Department of Computer Science Education, Universitas Pendidikan Indonesia munir[at]upi.edu Abstract It is predicted that every year, online video traffic will continue increase significantly. This causes before digital video transmitted over the internet, a compression mechanism is required by using specific encoding technique so that it does not overload the senders and receivers traffic. Furthermore, this process is also needed to produce high quality video with low bitrate. At present, the latest video encoding techniques is H.264/AVC and the currently developing video encoding is H.265/HEVC. Therefore, this paper aims to carry out objective assessment by evaluating the encoding performance of the new standard compared to its predecessor H.264/AVC. In addition to produce a comprehensive investigation, we compared several resolutions (1080p, 720p, and 480p) with a combination of CRF (Constant Rate Factor) values and different encoder presets. Then to find out the performance of both techniques we used several test parameters such as encoding duration, compression ratio, bitrate, MSE, and PSNR. The results showed that H.264 was faster in terms of time needed to carried out the encoding process. Furthermore, the quality of the video output produced by H.264 also better, but not significant, only a slight difference with H.265 and it is cannot be seen directly. In addition, the compression ratio and bitrate of H.265 was better than its predecessor with a difference of 38.5% and 52.7%, respectively. Finally, if the user wants to prioritize better quality video output without having to sacrifice a lot of compression time and small file size, then our recommendation is to use H.265 encoding and by selecting an HD resolution configuration (720p) with medium presets and 18 CRF value. Keywords: objective quality assessment, video encoding, H.264/AVC, H.265/HEVC, CRF, encoder preset PermaLink | Plain Format | Corresponding Author (Adhi Rizal)

108	Computer Science	ABS-230
Analysis and Design of N-Ram Digital Games for problem-based solving for Early Childhood Geometry Learning Taufik Ridwan, Endang Hidayat Study Program of System and Information Technology Universitas Pendidikan Indonesia, Study Program of Elementary School Teacher Training Universitas Pendidikan Indonesia Abstract Development and growth in children have to be stimulated properly in order to occur optimally. One aspect that must be considered is the cognitive aspect. In the growth and development phase, children spend most of their time to play. Generally, Children have the high ability to learn and curiosity. They tend to like games that attract attention to be played. At his age, children can’t be separated from objects in their environment, including objects in geometric shapes such as balls, cupboards, beams, tubes, coins, cubes, tubes, cabinets, and many more in play. Learning to recognize geometric shapes helps children to understand, describe, and describe objects that are around them. Therefore, at this time children need to get interesting positive stimulus to hone their intelligence. Now, many childrem can’t be separated form gadgets. Many of them become addicted to gadget and games. This paper tries to analyze and design a prototype of Digital Edu Games for children that can be used to help learn geometry based on specific problem solving approaches. Children will learn geometry through pairing and adjusting pictures accordingly, arranging drawings, and building a geometric shape. The method used in this study is Research and Development (R&D) with a waterfall approach in software development. The objectives of this study are: (1) analyzing the needs of games for learning geometry for children; (2) designing N-Ram for children. This research has benefits in developing learning media through Digital Edu Games combined with games in the form of games on gadgets. Keywords: digital games, learning media, geometry, children PermaLink | Plain Format | Corresponding Author (Taufik Ridwan)

109	Computer Science	ABS-235
Classification algorithm for forest fires prediction in The District of Kapuas Hulu Betha Nurina Sari, Aji Primajaya Universitas Singaperbangsa Karawang Abstract Forest fires are one of the disasters that needs to be anticipated in the Kapuas Hulu area. Forest fire prediction is one of the any forms of early warning in order to prevent from forest fires. C5.0 Classification algorithm can be used to build prediction models for forest fires. The purpose of this study is to apply C5.0 for prediction of forest fires. The method used is Knowledge Discovery in Datamining which consists of data selecting, data cleaning, data transformation, data mining, Knowledge Presentation. The results obtained are C5.0 able to produce prediction models of forest fires. Keywords: Classification Algorithm, Datamining, Forest Fire, Kapuas Hulu PermaLink | Plain Format | Corresponding Author (Betha Nurina Sari)

110	Computer Science	ABS-237
COMPARISON OF ROUND ROBIN AND LEAST CONNECTION ALGORITHM ON HAPROXY FOR LOAD BALANCING WEB SERVER Arip Solehudin(a*), Purwantoro(a), Fahmi Yuda Fauzi(a), Munir(,b) a) Faculty of Computer Science, Universitas Singaperbangsa Karawang, Karawang 41361, Indonesia *arip.solehudin[at]staff.unsika.ac.id, purwantoro.masbro[at]staff.unsika.ac.id, fahmi.yuda15047[at]student.unsika.ac.id b)Department of Computer Science Education, Universitas Pendidikan Indonesia munir[at]upi.edu Abstract Technology development is currently experiencing a fairly rapid increase, Therefore at the high school in Karawang intends to hold a grade promotion test using the Computer Based Test (CBT). However, in its implementation there are problems one of which is the server load. This is caused by user requests that exceed the servers capabilities. To overcome these problems, we use web server load balancing using haproxy. But the use of web server load balancing, often experience data inconsistencies per server. Therefore, database replication is also used that can guarantee data consistency in web server load balancing. This research uses descriptive approach with PPDIOO network system design method. There are 2 load balancing algorithms compared, namely round robin and least connection. Based on the httperf test results, throughput parameters of the two algorithms obtain the same average value of 99.5 Kb / second. In testing the response time parameter the least connection algorithm is superior at 6.9 ms compared to round robin which has an average value of 7.2 ms, but in testing the CPU Utilization parameter the round robin algorithm is superior at 23.7% compared to the least connection algorithm at 24.3%. Keywords: Computer Based Test, web server load balancing, database replication PermaLink | Plain Format | Corresponding Author (Arip Solehudin)

111	Computer Science	ABS-243
Decision-Making Framework for Validation of Data Collection Process in a Survey You Ari Faeni, Fadhil Hidayat School of Electrical Engineering and Informatics , Bandung Institute of Technology Abstract Survey is a method for estimating the parameters of a population. To produce the right statistics, it needs a validation process in collecting data in a survey. Some methods are used to validate one of them is to use a decision-making method with GPS data. This study uses Systematic Literature Review (SLR) to understand about research trends, methods, and data used in decision-making with GPS data. After reviewing 27 chosen journals and proceedings, this study concludes that there are several methods used to make a decision with GPS data such as decision tree, random forest, neural network, and support vector machine (SVM); Health, environment, Transportation, and agriculture are several fields of business that used GPS data to make a decision; The data analyzed consist of position, time, speed, track, and distance. Based on SLR result, we propose method to validate the data collection process of a survey using 3 methods (SVM, decision tree and random forest) will be used to analyze position, time, track and personal data of the surveyor. Keywords: Decision Making, Systematic Literature Review, GPS data, Validation of a survey PermaLink | Plain Format | Corresponding Author (You Ari Faeni)

112	Computer Science	ABS-246
An Android-based on House sales Monitoring System in Housing Area Chaerur Rozikin (a), Ultach Enri (a), a) Lecturer of Informatics Engineering, Faculty of Computer Science, University of Singaperbangsa Karawang Abstract With many of salespersons offering houses, it will be an advantage and it will make the houses will be sold faster. During this time the coordination between salespersons only using WhatsApp. The coordination is needed for mapping and recording of booked houses and has not been booked by the buyers manually and the data will be saved in the marketing center office. Problem will be shown up when there are two or more buyers booked the same block and number of a house and they paid the booking fee and each of those buyers coordinated with different salespersons, and the claims of who booked the house first will come up as the result. To solve that problem, an android-based on House sales Monitoring System needed to be developed. The Android-based application will be developed in this research aims to help the monitoring of house sales and provides the information of booked houses, has not been booked, and provides buyers data. Software development Life Cycle (SDLC) will be used as a system development Methods with Prototyping model with Communication, Quick Plan, Modeling Quick Design, Construction of Prototyping, dan Development Delivery and Feedback steps. The result of this research is an application software helping sales and marketing in monitoring the house sales. Based on interview with salespersons as much as 96% said that the application interface is easy to use and can help them in the process of the house sales monitoring. And based on the WhiteBox testing, there are no logic error in the application and it run well. Keywords: Marketing Staff, Houses, Application, Android, monitoring PermaLink | Plain Format | Corresponding Author (rozikin chaerur)

113	Computer Science	ABS-247
Hybrid Trust-based Defense Mechanisms Against Sybil Attack in Vehicular Ad-hoc Networks Agria Rhamdhan, Fadhil Hidayat Institut Teknologi Bandung Abstract The application of IoT in Vehicular Ad-Hoc Networks (VANET) allows the realization of intelligent transportation systems to ensure the comfort and safety of road users. But as an implication, attacks that can interfere with this aim certainly need to be a significant concern. It is because the stakes are not only network security but also the safety of the driver and its passengers. One of the attacks which had a substantial impact on VANET was the Sybil attack. Sybil attackers illegally change into several different identities to carry out malicious activities such as disrupting routing, causing traffic jams, bottlenecks, and even accidents. Various security methods are introduced to VANET to detect Sybil attacks, but there are still several issues that have not been resolved. In this paper, we proposed the design of a defense mechanism against Sybil attacks. This mechanism aims to be suitable for application on IoT networks that have limited resources an also considering accuracy, privacy, safety, and real-world implementations. The proposed design uses a hybrid scheme with a trust-based method. Each node has an obfuscated identity to guarantee privacy. The trust center in the form of a Road Side Unit (RSU) will give a reputation value to each identity that will be evaluated periodically when in the range. Nodes form a fully distributed network when there is no RSU. It will use a data-centric neighbor trust scheme where its neighbors will assess each node based on the exchanging data. Each node reports on suspicious nodes to the RSU for evaluation. This mechanism allows RSU to evaluate suspicious node, which decides to isolate that Sybil node out of network. Keywords: Sybil Attack, Vehicle Ad-hoc Networks, IoT PermaLink | Plain Format | Corresponding Author (agria rhamdhan)

114	Computer Science Education	ABS-5
The development of role-playing game multimedia using q-learning algorithm based inquiry training model in sql database subject for vocational high school Enjang Ali Nurdin, Muhammad Fadlian Amhar Program Studi Pendidikan Ilmu KOmputer FPMIPA UPI Abstract The purpose of this research is to develop a Role-Playing Game (RPG) multimedia based Inquiry Training Model (ITM) with a Q-Learning algorithm for subjects Structured Query Language (SQL) on vocational high school in department of software engineering. The design of study is done with phase analysis, design, development, implementation, and assessment. At this stage of the analysis carried out literature studies, field and acquisition of information about the curriculum and syllabus that applicable. Results of analysis used for designing materials, flowcharts, and storyboard. Multimedia learning related to the ITM phase. RPG game elements in the form used as a multimedia approach for learning. Q-Learning algorithm is added to the multimedia as a user interaction to provide advice in the RPG. To obtain multimedia learning assessment in the context of the development, validation is done by theexpert in media and content. The next assessment phase is limited trials conducted in a single unit in which student access to multimedia learning in groups. Respondent assessors are 14 people in class XI vocational high school no 11, Bandung. The results showed values in the range of "Very Good" according to expert in media and content also the student assesment. Keywords: multimedia learning; RPG; Inquiry Training Model; Q-Learning algorithm, PermaLink | Plain Format | Corresponding Author (Enjang Ali Nurdin)

115	Computer Science Education	ABS-18
Instilling Healthy Lifestyle Behavior into Prospective Physical Education Teachers through the 30 Day Fitness Challenge Application Tatang Muhtar, Tedi Supriyadi, Ayi Suherman Universitas Pendidikan Indonesia Abstract The utilization of Information and Communication Technology for the millennials is a requirement, one of which is in the learning of Physical Education (Penjas – Pendidikan Jasmani). The teachers are expected to develop the competencies in the mastery and utilization of ICT in the learning process. Therefore, this research aims at exploring the prospective physical education teachers’ skills in the utilization of ICT in the process of physical education learning as an effort to instill healthy lifestyle behavior into prospective physical education teachers by using an Android-based 30 Day Fitness Challenge application.. The procedure of this research are: 1) searching the application, 2) understanding of the application, 3) conducting learning process through the application and 4) evaluating of the learning outcomes. This research was conducted in one of the universities in Sumedang Regency by involving 100 students of prospective physical education teachers, consisting of 65 male students and 35 female students. The findings revealed that the use of this application had an effect on healthy lifestyle behavior with the indicators, for example, 1) the subjects had the understanding of the steps in instilling healhy lifestyle behavior, 2) the increase in motivation affected the importance of healthy lifestyle behavior, and 3) the subjects were getting used to conduct sport activities through this application. Therefore the utilization of the 30 Day Fitness Challenge application was able to instill the healthy lifestyle character in the prospective physical education teachers in Sumedang Regency. Keywords: Android-based application, healthy lifestyle behavior, physical education PermaLink | Plain Format | Corresponding Author (Tatang Muhtar)

116	Computer Science Education	ABS-276
Implementation of the Concept of Snakes and Ladders Game in Multimedia-based Learning Design as a Technology Enhance Learning that Fulfills Didactic Requirements Enjun Junaeti, Eka Fitrajaya Rahman, Ziady Mubaraq, Luthfi Fadhilah, Fatwa Muhammad Abdillah Universitas Pendidikan Indonesia Abstract Efficiency, enhancement, and transformation are identified as potential advantages in the use of technology in enhancing learning and teaching, so this has become an attraction for researchers to continue to develop technology enhance learning (TEL). Nevertheless, the issues in related to types of technology intervention, ways of conceived enhancement, and associative evidence require further deep thought so that TEL does not become a tool to substitute the existing pattern of teaching and learning. This study aims to implement the concept of the snakes and ladders game in the design of multimedia-based learning as a TEL that meets the didactic requirements. As an evaluation of meeting the requirements, the design is implemented in the development of multimedia about linear space created by following the ADDIE framework and used in the learning process in the classroom. Based on the results of the study, it was found that the multimedia developed had fulfilled the didactic requirements, namely: to have the opportunity to develop fundamental knowledge, to integrate theory into practice, and to develop critical thinking skills. Keywords: snakes and ladders game; TEL design; didactic requirement PermaLink | Plain Format | Corresponding Author (Enjun Junaeti)

117	Computer Science Education	ABS-46
Designing School Knowledge Management System: Waterfall Model Novi Sofia Fitriasari (a*), Rani Megasari(b), Erna Piantari(b) (a) Program Studi Sistem Informasi Kelautan Kampus Universitas Pendidikan Indonesia di Serang Jl.Ciracas Nomor 18, Serang 42116, Indonesia. (b) Departemen Pendidikan Ilmu Komputer Universitas Pendidikan Indonesia Jl. Setiabudhi No. 229, Bandung 40154 Abstract Utilizing Information and Communication Technology (ICT) for self-development is a teacher competence that must be have in 4.0 industry era. Moreover, in this era, internet technology is a core of ICT and become a challenge for teacher. ICT is be used for self-development is a factor that can be affect the teacher knowledge so that it can improve the learning quality in schools. Knowledge Management System (KMS) is an integrated system which is related to activities for gathering, acquisition, manage, storing and sharing knowledge. This system is a solution for improving quality learning process. Therefore, in this research it will be designed School Knowledge Management System (School KMS) using waterfall model. School KMS provide services for discovery service (discover and retrieval knowledge), publication service (upload and write together), collaboration (service forum or portal for Community of Practice), and learning service (online learning service). Keywords: KMS, Knowledge Services, School, 4.0 industry Era, Waterfall model PermaLink | Plain Format | Corresponding Author (Novi Sofia Fitriasari)

118	Computer Science Education	ABS-50
Kahoot:Taxonomy of gamification element perspective Novi Sofia Fitriasari (a*), RR.Deni Widjayatri(b) a)Program Studi Sistem Informasi Kelautan Kampus Universitas Pendidikan Indonesia di Serang, Jl.Ciracas Nomor 18, Serang 42116, Indonesia b) Program Studi Pendidikan Guru dan Anak Usia Dini Kampus Universitas Pendidikan Indonesia di Serang, Jl.Ciracas Nomor 18, Serang 42116, Indonesia Abstract Kahoot is an internet-based application that can be used to evaluate learning in the classroom. The advantages of kahoot from other learning evaluation applications are packaged in the form of a game. Learning in the form of a game or what is called gamification has at least 3 elements, namely Game based rules, Game mechanics level and Game thinking competition. Therefore in this study discuss more details about kahoot seen from the Taxonomy of gamification element perspective. Keywords: Kahoot, Gamification, Game Based Rules, Game Mechanics Level, Game Thinking Competition PermaLink | Plain Format | Corresponding Author (Novi Sofia Fitriasari)

119	Computer Science Education	ABS-73
Implementation of WEB-based Learning To Develop Student Learning Independence Through Performance Assessment Rochanda Wiradinata;Jajo Firman Raharjo;Nurul Senja W.F Universitas Swadaya Gunung Jati Cirebon Abstract Abstract. Learning is an important factor in achieving educational goals, not only as a means of supporting improvements in the past, but it has been a process that anticipates improving the quality of education in the future that increases progressively. The rapid development in the field of information and communication technology, today goes hand in hand with the advancement of science and technology in the era of learning society or learning society. The existing E-learning system is only able to present the same teaching material to all users without considering their characteristics. On the other hand, there was a lot of criticism of the way the lecturers who conveyed the concept only about nothing and the students were only burdened with a lot of training assignments without any related understanding. Presentation of material contained in textbooks and practice questions does not need to help students to learn to understand it effectively and be improved. The purpose of this study is to discuss site-based learning which includes a needs analysis and technology analysis of website-based learning, formulating the task of analyzing teaching materials, developing teaching materials and sending teaching materials and supporting as a draft in website-based learning, improving the quality of learning, learning and Learn more about teaching material so that it can be accessed anywhere and anytime and by anyone This research is a development research that uses a 4-D model developed by Thiagarajan, which defines, designs, develops and develops to develop website-based learning that involves compiling teaching materials published in websites through performance evaluations evaluated to improve student learning independence in corporate accounting courses. The results of this study indicate that with teaching materials based on WEB that have validated validity by material experts, design experts, practicum experts show that students are independent in learning both from material reading sessions, discussions, work assignments and projects. Learning completeness is indicated by the results of the completeness test which agree that students complete independently and classically. Keywords: WEB Based Learning, Bank Reconciliation Lecture, Development Research, Performance Assessment PermaLink | Plain Format | Corresponding Author (Rochanda Wiradinata)

120	Computer Science Education	ABS-96
An Implementation of Hamming Code on Marker Based Augmented Reality for Introducing Local Wisdom of Batik Wiwid Widyanto, Rosa Ariani Sukamto, Isma Widiaty, Alejandro Rosales Pérez, Lala Septem Riza Universitas Pendidikan Indonesia, Bandung, Indonesia School of Engineering and Science, Tecnologico de Monterrey, Monterrey, Mexico Abstract Batik is a fabric made with anti-wax dyeing techniques and is one of the many cultural heritage of Indonesia that has high artistic value and has become the hallmark of a nation that must be preserved. One way to preserve it, is to introduce batik. In order to make it more attractive, we can use multimedia as media to introduce batik. Augmented reality (AR) is a technology that adds virtual objects into the real world. This technology could provide a new way of delivering information to users, which is more interactive. So, it is expected to increase the sense of desire to know batik and its local wisdom. In this research, a system of marker-based tracking AR used to introduce batik and its local wisdom (called batikAR) was made. One type of AR is marker-based tracking methods. These methods use a marker as a reference display objects/ information. To track markers, there are several steps that must be performed on every frame received from the camera android smartphone. The phase of tracking in this study includes: conversion of images from the camera frame into a grayscale image, thresholding, the contour detection, perspective transformations, and finally decoding using the Hamming Code algorithm. According to the experimentations that were conducted, user responses to the application batikAR are good enough. Moreover, tracking markers on this system could properly track 100% of each marker in normal circumstances, within a certain range depending on the size of the marker and at an angle of 450. However it is unaffected by ambient light conditions. Therefore, we can state that the system can be used as an alternative teaching methods for introducing batik and its local wisdom. Keywords: Image processing, Augmented reality, Local Wisdom, Learning media PermaLink | Plain Format | Corresponding Author (Lala Septem Riza)

Page 4 (data 91 to 120 of 328) | Displayed ini 30 data/page
<< PREV 1 2 3 4 5 6 7 8 9 10 11 NEXT >>

Powered By Konfrenzi 1.832K-Build2 © 2025 All Rights Reserved