Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Development of soil moisture measurement with wireless sensor web-based concept Julham Julham; Hikmah Adwin Adam; Arif Ridho Lubis; Muharman Lubis
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 2: February 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i2.pp514-520

Abstract

Measurement of soil moisture commonly by applying the soil moisture sensors is to measure the condition of the ground around which is relatively not wide. Therefore if applied for the large-scale, repeated measurements are required in accordance with the determined point. As a result it takes time to get the whole results. With the existence of wireless sensor technology then this problem can be overcome. This wireless sensor system will create a network consisting of nodes and server. In this study the server part is a server computer that requires a web server application together with its script to display and store data, while the node part is the data reader system. In the data system reader module, the sensor device is required as the input that is SEN0114, the processor is a microcontroller, while the wireless uses Wi-Fi module that is ESP8266. Wi-Fi topology used later is infrastructure (using access points). In this research, it begins by testing the sensor and then testing the data validation between the node and the server. SEN0114 sensor has different value from the American Standard Method (ASM) that is 0.922%. While the data validation test of the measurement result is Wi-Fi ESP8266 module which has a maximum distance of 14 meters toward the access points.
Management maintenance system for remote control based on microcontroller and virtual private server Idham Kamil; Julham Julham; Muharman Lubis; Arif Ridho Lubis
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 3: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v16.i3.pp1349-1355

Abstract

Open loop shaped control system is a form of system control without any feedback from the system. One example is the on-off condition which functions to connect and disconnect electricity. The condition to be studied is a dc motor that can be set to live and die via internet server-based client service. The server in this system is a virtual private server (VPS) device that will provide a source of service to the client in the form of a collection of information on dc motor conditions. In addition, its function is also to record the working time of the dc motor. So that a schedule can be determined when the dc motor is maintained. While the client is a control unit consisting of a microcontroller device, an ethernet module enc28j60 and a dc motor. In general the working principle of the system is beginning with the user accessing the desired VPS IP address through a web browser application. From the web browser the user chooses a dc motor to be activated. But before the client has been connected to the VPS regularly (every second), the point is to always get the latest dc motor condition information. Then the microcontroller will set the dc motor in active or off condition. The research method used is research and development. The results obtained from this study are that the amount of bandwidth needed for communication between VPS and microcontrollers via the internet network, when the control unit works is 6.02 kbps, while the response time for dc motor is 3.16 seconds and the response time for dc motor 2 is 3.46 seconds.
The effect of the TF-IDF algorithm in times series in forecasting word on social media Arif Ridho Lubis; Mahyuddin K. M. Nasution; Opim Salim Sitompul; Elviawaty Muisa Zamzami
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 2: May 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i2.pp976-984

Abstract

Forecasting is one of the main topics in data mining or machine learning in which forecasting, a group of data used, has a label class or target. Thus, many algorithms for solving forecasting problems are categorized as supervised learning with the aim of conducting training. In this case, the things that were supervised were the label or target data playing a role as a 'supervisor' who supervise the training process in achieving a certain level of accuracy or precision. Time series is a method that is generally used to forecast based on time and can forecast words in social media. In this study had conducted the word forecasting on twitter with 1734 tweets which were interpreted as weighted documents using the TF-IDF algorithm with a frequency that often comes out in tweets so the TF-IDF value is getting smaller and vice versa. After getting the word weight value of the tweets, a time series forecast was performed with the test data of 1734 tweets that the results referred to 1203 categories of Slack words and 531 verb tweets as training data resulting in good accuracy. The division of word forecasting was classified into two groups i.e. inactive users and active users. The results obtained were processed with a MAPE calculation process of 50% for inactive users and 0.1980198% for active users.
Dealing with Voters’ Privacy Preferences and Readiness in Electronic Voting Muharman Lubis; Arif Ridho Lubis
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v11.i3.pp994-1003

Abstract

Various countries have been encouraged to adopt electronic voting because it can reduce operational cost and time spent for tabulation process. In the current research, it has been mentioned several problem arised in term of technical aspects, voters’ trust, machine vulnerabilities and privacy right in which experts argued the election system have been compromised. In short term, the certain faction will try to exploit the system weaknesses for their own benefit, while in the long term, it can create public distrust to the government, which decrease the voters turn out, break the participation willingness and downgrade the quality of voting. Thus, the government should deal with previous issues in the election before adopting electronic approach while at the same time align with voters’ expectation to provide better election in serve citizen through comprehensive analysis. This study provide initial step to analyse the readiness of electronic voting from the social perspective in response to how Indonesia view the initiative to adopt new tech in voting system.
Decision Making in the Tea Leaves Diseases Detection Using Mamdani Fuzzy Inference Method Arif Ridho Lubis; Santi Prayudani; Muharman Lubis; Al Khowarizmi
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 3: December 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i3.pp1273-1281

Abstract

The tea plants (Camellia Sinensis) are small tree species that use leaves and leaf buds to produce tea harvested through a monoculture system. It is an agriculture practice to cultivate one types of crop or livestock, variety or breed on a farm annually. Moreover, the emergence of pests, pathogens and diseases cause serious damages to tea plants significantly to its productivity and quality to optimum worst. All parts of the tea plant such as leaves, stems, roots, flowers and fruits are exposed to these harm lead to loss of yield 7 until 10% per year. The intensity of these attacks vary greatly on particular climate, the degree slope and the plant material used. Therefore, this study analyzes tea leaves as a common part used in recipes to create unique taste and flavor in tea production, especially in agro-industry. The decision making method used is Fuzzy Mamdani Inference as one of model with functional hierarchy with initial input based on established criteria. Fuzzy logic will provide tolerance to the set of value, so that small changes will not result in significant category differences, only affect the membership level on the variable value. Previous method using probabilities have shown 78% tea leaves have been attacked by category C (Gray Blight) while using Mamdani indicated 86% of tea leaves have been infected. In this case, this result pointed out that Fuzzy Mamdani Inferences have more optimal result compare to the previous method.
Deep neural networks approach with transfer learning to detect fake accounts social media on Twitter Arif Ridho Lubis; Santi Prayudani; Muhammad Luthfi Hamzah; Yuyun Yusnida Lase; Muharman Lubis; Al-Khowarizmi Al-Khowarizmi; Gabriel Ardi Hutagalung
Indonesian Journal of Electrical Engineering and Computer Science Vol 33, No 1: January 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v33.i1.pp269-277

Abstract

The massive use of social media makes people take actions that have a negative impact on cyberspace, such as creating fake accounts that aim to commit crimes such as spam and fraud to spread false information. Fake accounts are difficult to detect in the traditional way because fake accounts always use photos, names, and unreal information, there are several criteria that can identify a fake account such as no information, few followers, and minimal activity. In the traditional model, it is difficult to detect fake accounts on many Twitters social media accounts, so the application of the deep learning model with the convolutional neural network (CNN) algorithm and the application of deep learning can help detect fake accounts. This study will use data on Twitter social media so that this research produces good accuracy for the scenarios described at the methodology stage. This research produces an accuracy of 86% for the deep learning model with the CNN algorithm, and with the traditional model, it produces an accuracy of 51% while the use of transfer learning produces an accuracy of 93.9%.