Indonesia Conference Directory

Corresponding Author
Lipur Sugiyanta

Institutions
Universitas Negeri Jakarta

Abstract
This research aimed to identify internal and external factors in making website development strategies. The case study location was at the Center for the Development of Maritime Transportation Human Resources. The research method uses a qualitative approach that combines qualitative methods and quantitative data input (combined methods), from document analysis, management perceptions, and information system referrals. Qualitative and quantitative data are used as SWOT analysis input materials. The results of the analysis form a strategy formulation by integrating the strengths and weaknesses of internal factors as well as opportunities and threats from external factors.

Keywords
Website, SWOT, Human Resource strategies

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/x76HmZ9K4pkR

Corresponding Author
Arwin Datumaya Wahyudi Sumari

Institutions
State Polytechnic of Malang, Malang, East Java, Indonesia

Faculty of Defense Technology, Indonesia Defense University, Sentul, West Java, Indonesia

Abstract
Predicting a cyberattack has been a challenge for various sectors including defense one. In this paper we propose a new method for making a prediction or an estimation the occurence of cyberattacks in terms of the attack type or category and when the attack(s) would be possible to occur. Our method based on Cognitive Artificial Intelligence (CAI) approach called as Knowledge Growing System (KGS). For this purpose, we use simulation data based on a riil data. From the simulation results, we can conclude that CAI is able to deliver an estimation of the occurence of future possible cyberattack.

Keywords
Attack Prediction, Cogntiive Artificial Intelligence, CYber Defense, Knowledge Growing System

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/EyYf6nTQCKLG

Corresponding Author
Dimas Rossiawan Hendra Putra

Institutions
Politeknik Negeri Malang

Abstract
Human face recognition is one of the challenging topics in the areas of pattern recognition, image processing and computer vision. Before recognizing the human face, its necessary to detect a face then extract the face features.Extraction of facial features using geometric distance on facial features such as eyebrows, eyes, nose and mouth compared with extraction based of skin color on human faces and using Naïve Bayes Classifier as its classification method. This paper presents a comparison of the two methods in terms feature extraction with geometry and skin color for getting accuracy.

Keywords
Face Recognition, Geometric Feature, Color feature, Naïve Bayes Classifier

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/4PVgZRG9MjpH

Corresponding Author
Wisnu Agung Prasetyo

Institutions
State University of Malang

Abstract
Students academic abilities differ from one another. There are students who have high academic abilities, so they can take good lectures. However, it is not uncommon to find students with low academic abilities, thus making it difficult for them to take lectures. Furthermore, among students with both categories there are students with average or normal academic ability level. Students with low academic ability level will leave them in college. If this condition continues, it will make them difficult to pass or complete in every course they take. The worst possibility is it will be very difficult for students to finish their education (graduation) and even drop out in the middle of the study. This is where the special handling of the instructor is really needed for them. In this study a comparison is made between two classification methods, namely Decision Tree J48 and k-Nearest Neighbour (KNN). The classification process is done by the Rapid Miner application. The results obtained are the Decision Tree J48 method is better than the KNN. One of the reason is that Decision Tree J48 does better classification on handling large and nominal dataset.

Keywords
Classification, KNN, J48, Decision Tree, Student

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/gjVqzAEeT6hD

Corresponding Author
Dimas Rossiawan Hendra Putra

Institutions
Polinema

Abstract
Human face recognition is one of the most challenging topics in the areas of pattern recognition, image processing and computer vision. Before recognizing the human face, it is necessary to detect a face then extract the face features. Many methods have been created and developed in order to perform face detection and two of the most popular methods are Haar Cascade Classifiers and Histogram of Oriented Gradients (HOG), which have a very low rate of false negative. This paper presents a comparison of the two methods in terms of precision, recall, f-1 score and accuracy using confusion matrix

Keywords
Human Face Detection, Haar Cascade Classifier, Histogram of Oriented Gradients (HOG), confusion matrix, accuracy

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/e4dqGA7fywZ2

Corresponding Author
sofffa zahara

Institutions
Universitas Islam Majapahit

Abstract
Long Short Term Memory(LSTM) is known as optimized Recurrent Neural Network(RNN) architectures that overcome the lack of RNN-s about maintaining long period of memories information. As part of machine learning networks, LSTM also notable as the right choice for time-series prediction. Currently, machine learning is a burning issue in economic world, abundant studies such predicting macroeconomic and microeconomics indicators are emerge. Inflation rate has been used for decision making for central banks also private sector. In Indonesia, CPI(Consumer Price Index) is one of best practice inflation indicators besides Wholesale Price Index and The Gross Domestic Product(GDP). Since CPI data could be used as a direction for next inflation move, we conducted CPI prediction model using Long Short Term Memory Method. The network model input consists of 28 variables of staple price in Surabaya and the output is CPI value. In the interest of predictive accuracy improvement, we used several optimization algorithm i.e. Stochastic Gradient Descent(sgd), Root Mean Square Propagation(RMSProp), Adaptive Gradient(AdaGrad), Adaptive moment(Adam), Adadelta, Nesterov Adam(Nadam) and Adamax. The result indicate that Nesterov Adam has 0.069 MSE-s value, less than other algorithm which indicate the most accurate optimization algorithm to predict CPI value.

Keywords
Long Short Term Memory; Inflation; Consumer Price Index; Deep Learning

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/tBmf6yDEjMQ7

Corresponding Author
Fathur Zaini Rachman

Institutions
a) Electrical Engineering Department, State Polytechnic of Balikpapan
Jl. Soekarno Hatta km.8, Balikpapan 76126, Indonesia
*fathur.zaini[at]poltekba.ac.id

Abstract
In this system using a method that is the application of a multisensor system in detecting the presence of fire, smoke and temperature in the room. The sensors used include KY-026 fire sensor, MQ-9 smoke sensor and DS18b20 temperature sensor. Then the system also implements an intelligent system that is fuzzy logic to process sensor reading data. The three sensor inputs will be processed through the fuzzification stage, then rule evaluation deffuzification. The output of this system is in the form of firm values, namely the values 1 to 5 from the results of the multisensory defuzzification in each module. So that the average error of the defuzzification result is 0.99% after being compared with the MATLAB output. This system is expected to be able to provide early warning of the threat of fire, reduce the risk of casualties, and be able to be implemented to a wider scale or scope.

Keywords
fuzzy, multisensory, KY-026 fire sensor, MQ-9 smoke sensor, DS18b20 sensor.

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/WBQ9FkNybVrC

Corresponding Author
MUHAMMAD BISRI MUSTHAFA

Institutions
State Polytechnic of Malang

Abstract
BAN-PT is an Indonesian body with the main task to assess the quality of Indonesian university. The assessment result is called accreditation, which has 5 years of validation time. In order to monitor the quality, University has an internal mechanism which is called an internal quality assurance system (SPMI in Indonesian). Usually, SPMI assesses the quality periodically, one or two times each year. This process needs much effort, i.e. time, manpower, and financial cost. Sometimes, internal auditor of the university does not have sufficient knowledge, as much as BAN-PT accessor. This condition causes a lack of assessment accuracy, then causes the quality of SPMI itself. In the other hand, University has abundant of condition data, saved in PDDIKTI database. This paper proposes to exploit the availability of data in this case. Therefore university able to monitor the quality by machine learning process periodically without much effort as manual SPMI process. Furthermore, this paper evaluates two machine learning methods, i.e. naive Bayes and KNN. This proposal exploits several data: student, academic, admission, and alumna. KNN and naive Bayes work in registrant and capacity ratio, student registration ratio, average student GPA in late five years, and on-time graduation scale. The experiment results show the accuracy of naive Bayes and KNN are 78.57% and 57.14% respectively.

Keywords
SPMI; PDDIKTI; KNN; naive Bayes

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/F3vRKmZbt4aX

Corresponding Author
luki ardiantoro

Institutions
Universitas Islam Majapahit, Mojokerto

Abstract
FP-Growth algorithm is widely used to analyze pattern from huge amount of data with (frequent) repeated items. Objective of this research is to analyze playing pattern a badminton player, one of a popular sport in Indonesia. Data set is generated from technical stroke during the game. The model used in this study was Jonathan Christie a top Indonesian badminton player. The method of data collection is done by dividing the playing field in various areas of the game, because each stroke is suitable to be done in a particular area. Observations are made by using the software, to calculate and classify the types of stroke that carried out by athlete. Result of this research; tactical approach for Jonathan Christie during this match was described. The data obtained will be very useful for the coach to improve the athletes performance. Another advantage obtained is the analysis of athletes performance can be done with a quantitative approach, so that it can enrich the current methods. The conclusion, FP-Growth is able to describe the game pattern of a badminton athlete.

Keywords
FP-Growth, badminton, game pattern.

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/RzWFdpKJwTxt

Corresponding Author
Sutiah Sutiah

Institutions
(a,c)Faculty of Tarbiyah and Teaching Training Universitas Islam Negeri (UIN) Maulana Malik IbrahimMalang
(b)Informatics Engineering Department
Faculty of Science and Technology Universitas Islam Negeri (UIN) Maulana Malik Ibrahim Malang
(d)Psicology Department
Faculty of Psicology Universitas Islam Negeri (UIN) Maulana Malik IbrahimMalang

Abstract
The research aims to assess the development and implementation of Fuzzy Topsis optimization on core competency detection expert systems and student learning achievement majoring in Islamic religious education at PTKIN. In the learning process of KKNI based curriculum designed to detect the level of development of core competencies and achievements study students at the faculty or PAI study Program at PTKIN. The main product development of this research is expert system application With the Fuzzy Topsis method of measuring the indicator Development of Core Competencies (Hard skills and soft skills) and Learning factors that have an effect on student learning achievements. The results of this expert system can help students and lecturers Independently to detect how the level of development students core complications, detecting internal learning factors and external influences and measures how they influence to student learning achievements. Optimizing Results of Fuzzy TOPSIS shows optimal results with an accuracy rate of 92%.

Keywords
Fuzzy Topsis; Optimization; Indicator Development

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/HrA6yMkCLBxd

Corresponding Author
Kholid Fathoni

Institutions
Politeknik Elektronika Negeri Surabaya

Abstract
Sunan Ampel is a religious figure and one of the legendary members of Walisongo in Surabaya even on Java. The history of Sunan Ampel is rarely known by the public or even very little information is known about him. This is because the existing references are still limited, difficult to obtain and not interactive. Therefore we need media that can describe the history of Sunan Ampel interactively and not based on textbooks. This can be overcome by developing game-based Sunan Ampel historical applications. This game is built with two-dimensional characters and the genre of Role Playing Game. There are 3 phases in the history game Sunan Ampel, namely: the phase in Wonokromo, the phase in Yellow Flower, and the phase in Ampel. Some NPCs are involved such as some wild animals, residents, Kibang Kuning and Prabu Brawijaya. The blackbox testing of interface and game design results show that all game features are running well on desktop platforms and the games storyline has illustrated some of the history of Sunan Ampel.

Keywords
History of Sunan Ampel, Surabaya, Game Applications, Role Playing Games, Desktop Platform

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/98g6GrMYFDmA

Corresponding Author
Nur Yusuf Oktavia

Institutions
Dept. of Electrical Engineering
Institut Teknologi Sepuluh Nopember Surabaya

Abstract
Currently, emotions recognition has been attracting a lot of interest for researchers in various field, so as in the study of human-computer interaction (HCI). One of an interesting issue in HCI emotions study is the use of physiological signals, such as electrocardiograph (ECG), blood vessel pressure (BVP), electroencephalograph (EEG), and any others signals to recognize emotions. Among all physiological signals, EEG is known to be the most reliable modality to understand emotions processing and perceptions. Therefore, this study observed emotions recognition through EEG signals by investigating emotions cue from time domain features extraction for differentiating two class of emotions, namely, happy and sad. We developed an EEG based emotion dataset from 12 participants with 4 recording channels of EEG cap, i.e., AF3, AF4, O1, and O2. The time domain features of mean, standard deviation and number of peaks were extracted from alpha and beta frequency bands. For the recognition, we train the features set into Naïve Bayes learning classifier. From the results, it was shown that feature of mean gives the highest contribution to the classification. Moreover, from the observation of frequency bands, the combination of alpha and beta bands tend to provide better accuracy in emotion recognition rather than using alpha or beta frequency alone. The highest classification result of Naïve Bayes reached 87.5% accuracy of emotions recognition with 66% split testing option.

Keywords
Emotion from EEG, Statistical features, Naïve Bayes Classifier

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/UmjkqupE2tLy

Corresponding Author
Mimin Fatchiyatur Rohmah

Institutions
1,4 Informatics Engineering Universitas Islam Majapahit
2 Informatics Engineering Udayana,
3 Electronics Engineering,Udayana

Email: 1 miminfr[at]unim.com, 2 ikgdarmaputra[at]unud.ac.id, 3 rukmisari[at]unud.ac.id, 4 ipan.ardianto[at]unim.com

Abstract
An economic indicators regarding information on prices of goods and services paid by consumers are known as the Consumer Price Index (CPI). In this study the researchers predicted the Consumer Price Index for Foodstuffs in Cities and Districts in East Java using the Gaussian-Radial Basis Function Kernel for 2019. As a comparison, Foodstuff Type CPI issued by the Central Statistics Agency and as an input variable taken from the prices of basic commodities in three districts namely Banyuwangi District, Jember District and Sumenep District and five cities namely Kediri City, Madiun City, Malang City, Probolinggo City and Surabaya City from 2016 to 2018. The SVR method aims to find a function as a regression function hyperplane that matches the input data by making the least error possible. Forecasting data using the SVR method, the data is divided into training data and testing data. With the RBF kernel where the function is to produce CPI predictions with the smallest Mean Squared Error (MSE) in the City of Kediri of 0.0067 and the Mean Absolute Percentage Error (MAPE) of 0.0191. The average MSE and MAPE for the three districts and five cities are 0.011275 and the average MAPE is 0.0322125.

Keywords
Consumer Price Index, Support Vector Regression, Mean Absolute Percentage Error, Mean Square Error, Gaussian-Radial Basis Function.

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/JMm4Vp6KfaeC

Corresponding Author
Wulan Sri Lestari

Institutions
a) Magister Teknologi Informasi Department, STMIK Mikroskil
Jalan Thamrin 112, Medan 20212, Indonesia
wulan.lestari[at]mikroskil.ac.id

Abstract
Collaborative deep learning is an approach that used to overcome the amount of training data needed in building a better deep learning model. In collaborative deep learning, the central server collects user data and run the deep learning algorithm centrally to get more accurate models. However, centralized training data collection can raise serious of privacy leakage problem and damage to the integrity of training data. In this paper we introduce the privacy preserving collaborative deep learning model using verifiable (k, t, n) multi-secret sharing based on the Elliptic Curve Diffie Helman and SHA3-256 as a hash function. Where all training data will be formed into n shares using a session key generated from the private key and public key Elliptic Curve Diffie helman to protect the privacy and avoid all training data using SHA3-256 for the verification process before sending to server. The test results show the integrity of damaged training data and colluding participants can be verified using the Elliptic Curve Diffie Helman and SHA3-256. Therefore proposed model can protect the privacy and integrity of training data and maintain the accuracy of the deep learning model.

Keywords
Data Privacy; Data Integrity; Collaborative Deep Learning; Verifiable Multi-Secret Sharing

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/FGVLbCJH3dkn

Corresponding Author
Mustika Mentari

Institutions
a,b,c) Departement of Information Technology, Politeknik Negeri Malang
*must.mentari[at]polinema.ac.id

Abstract
Maps are one form of an image that often encountered in various interests. For example, many books on tourist attractions or other information that provide maps as a media of information. However, sometimes people with visual impairments such as presbyopia, hypermetropia, or astigmatism have difficulty reading the map which is usually given in small size, multi orientation (multi-scale and multi-direction). Therefore, this study tries to provide a solution through an application that converts image to text in image conditions that have many orientations and different things are briefly called heterogeneous text. The Optical Character Recognition (OCR) system that was built beginning with taking pictures made through a cellphone camera as the first step in obtaining a digital map file, then enters the preprocessing, text segmentation, feature extraction from each different character, then continues to the classification stage. This OCR system for recognizing text with multiple orientations will help people make digital maps easier to read, especially for people who have presbyopia, hypermetropia, or astigmatism vision problems. The proposed model achieves good average accuracy for classifying the characters in various orientation successfully.

Keywords
Optical Character Recognition, Map, Multi Orientation, heterogeneous text ,k-nearest neighbor

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/4xrtEUj28FGy

Corresponding Author
Dadang Syarif Sihabudin Sahid

Institutions
a) Department of Information Technology, Politeknik Caltex Riau
Jl. Umbansari No. 1, Rumbai, Pekanbaru, Riau-Indonesia
*dadang[at]pcr.ac.id
b) Department of Mathematics, Universitas Islam Negeri Sultan Syarif Kasim
Pekanbaru, Riau-Indonesia
c) Department of Electrical Engineering, Politeknik Caltex Riau
Jl. Umbansari No. 1, Rumbai, Pekanbaru, Riau-Indonesia

Abstract
Flow experience as a psychological theory has been implemented in various fields. According the theory, flow is represented as anxiety, boredom, and flow. Considering psychological condition in learning activities can improve student performance. Thus, involving flow in learning particularly in e-learning becomes important. The challenge is how to identify flow state during students interaction with e-learning. In previous study, flow was measured by conducting questionnaire series after a learning process. This is inefficient. Additionally, this is often unnatural, since it cannot capture students learning behaviour. Therefore, this study presented flow experience identification when students interact with e-learning using rough set and machine learning approaches. Rough set is an efficient tool to solve uncertainty, imprecision, and vagueness. While, the fuzzy rule and decision tree, parts of machine learning methods were implemented as a comparison. As the results, the accuracy level of the rough set is 92.92%, fuzzy rule is 91.86% and decision tree is 92.39%. As a conclusion, this study showed that flow experience could be identified with high accuracy. In the context of e-learning, it can be used by e-learning to provide an adaptation. Appropriate adaptation is expected can keep the psychological condition of the students in the flow state.

Keywords
flow experience; rough set; machine learning; e-learning

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/rYhN67QyTH3R

Corresponding Author
Lukmanul Khakim

Institutions
State Polytechnic of Semarang

Abstract
Data is a collection of information that is incorporated into one and has a very important meaning to the owner, every data owner will surely keep the data very carefully and will be stored in a very secure place, with Some extra strict levels of security. Here will be done research and designing a security access data in the management of shared resources that are cloud-based or the term is cloud computing. In this security, the object to be secured is the user data that functions as access to login to the cloud system with an Advanced Encryption Standard (AES) encryption method with a key length of 256 bits. However, before the data is encrypted with the AES method, the data will be encrypted in advance with the MD5 method, and after that it will be carried out the second encryption with the AES method. In general, the method of securing a login data is only using MD5 encryption, but as technology progresses, securing data, especially login data, must be more layered in terms of its This research to meet data security in the case of encryption of login data.

Keywords
Data, Cloud Computing, Encryption, AES, MD5

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/tcHP2uDjUJKz

Corresponding Author
Vivi Nur Wijayaningrum

Institutions
Department of Information Technology, Politeknik Negeri Malang
*vivinurw[at]gmail.com

Abstract
Teaching and learning activities in the classroom require data collection on student attendance. The process of data collection on student attendance during lecture hours at the Information Technology Department, Politeknik Negeri Malang, is the responsibility of the lecturer. The lecturer calls and records students one by one to be written in an attendance form, then the form will be recapitulated to the system by administrative staff. This causes frequent errors in the recapitulation of student attendance. Errors in the recapitulation of data and a large number of attendance data that must be recapitulated will certainly make the process ineffective and inefficient. This study uses a smart card to facilitate the process of identifying students during teaching and learning activities in the classroom. Students use smart cards to record their attendance before and after lecture hours. The smart card will be connected to the card reader using NFC which is also connected to a PC using a USB port. The data used includes lecture schedules, courses, classes, lecturers, and students that are stored in the database. The result of a smart monitoring system is the ability to manage data on the system, as well as recording attendance data.

Keywords
authentication, smart card, student attendance

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/eKt9MPudxNpT

Corresponding Author
Kholid Fathoni

Institutions
Politeknik Elektronika Negeri Surabaya

Abstract
Khalid ibn al-walid was a hero of Islam who was very meritorious and inherited many exemplary values, namely sincerity, struggle and intelligence. But many people dont know this hero. This is due to the widely available media introduction of Khalid ibn al-Walid figures such as history books and comic books that are less interesting. This can be overcome by developing an interactive historical game Khalid ibn al-Walid. This game is built with 3D characters using the arcade genre and the First Person Shooter viewpoint. There are 4 parts in this game namely Prologue, Phase Before Islam, Islamic Phase, Epilogue. The test results show that all game features can work properly. Then the game was tested on 10 users and they stated that they had received information about Khalid ibn al-Walid from this game.

Keywords
Khalid ibn al-walids history, 3D games, arcade, First Person Shooter

Topic
Computer Science and Engineering

Link: https://ifory.id/abstract/rcat8JjWD3kg