Garuda - Garba Rujukan Digital

Comparative analysis of classification algorithms for chronic kidney disease diagnosis Zainuri Saringat; Aida Mustapha; R. D. Rohmat Saedudin; Noor Azah Samsudin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naïve Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.

Comparative analysis of classification algorithms for chronic kidney disease diagnosis Zainuri Saringat; Aida Mustapha; R. D. Rohmat Saedudin; Noor Azah Samsudin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naïve Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.

Comparative analysis of classification algorithms for chronic kidney disease diagnosis Zainuri Saringat; Aida Mustapha; R. D. Rohmat Saedudin; Noor Azah Samsudin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naïve Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.

Laptop Cooling Pad Temperature Monitoring System Shamsul Kamal Ahmad Khalid; Noor Azah Samsudin; Nor Amirul Amri Nordin; Muhammad Syariff Aripin
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: October 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i1.pp420-427

Cooling pads are commonly used to reduce temperature of laptop to avoid overheating problem. However, existing cooling pads are prone to various limitations: fixed voltage in the hardware component, inaccurate temperature readings and lacked of computer-based temperature monitoring functions. In this paper, a laptop cooling system with multivoltage fan speed controller using real-time processor temperature readings is proposed. A graphical user interface (GUI) and color coded LEDs are also implemented to provide visual inspection of the temperature values captured from the laptop. The temperature values are displayed in graph and tabular form. The performance of the proposed cooling pad with computer-based monitoring application is evaluated against two other types of existing cooling pad systems. The experiments have shown that the temperature values can be monitored clearly with the proposed GUI. More importantly, the proposed cooling pad system has the potential to achieve lower temperature faster than the rest of the existing cooling pad systems.

Autonomous coop cooling system using renewable energy and water recycling Shamsul Kamal Ahmad Khalid; Nurul Shafiqah Che Dan; Noor Azah Samsudin; Muhammad Syariff Aripin; Nor Amirul Amri Nordin
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 3: March 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i3.pp1303-1310

Extreme temperature in a chicken coop can significantly affect the growth and productivity of poultry. Therefore, the temperature inside the chicken coop need to be controlled to protect it from extreme temperatures. Most of the technology use electrical energy supplied to an evaporative cooling system to control the temperature of a coop. This paper presents an autonomous chicken coop cooling system using renewable energy and water recycling (REMACT). In this study, a monitoring system with necessary hardware, control application, powered with solar power source and water recycling, has been developed. The proposed cooling system consists of hardware part such as an Internet of Things (IOT) controller platform, temperature sensor, solar panel, water pump, water storage, water drain and pipe. When the temperature sensor detects extreme temperature more than 28℃ in a chicken coop, the water in storage tank will flow throughout the pipe and pass into water pump before it irrigates the chicken coop roof. When the temperature is below 22℃, the bulb will light up to transfer heat to the chicken coop and cause the temperature drop back to a healthy range. The water drain that is attached to the roof will collect the water and return the water back to the water storage again. The software components required by the project are Arduino IDE, Thinger.io, and Android Studio Framework. Several experiments have been conducted with hot and cold scenarios. The system was able to stabilise the temperature back to a healthy range. A usability testing result demonstrates 80% satisfactory rate. The findings from the experiments show that IoT, renewable energy and water recycling have the potential for temperature control of a chicken coop.

Augmented reality application for location finder guidance Anatun Nadrah Rosman; Noor Azah Samsudin; Azizan Ismail; Muhammad Syariff Aripin; Shamsul Kamal Ahmad Khalid
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 3: March 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i3.pp1237-1242

Finding directions to a specific location can be troublesome especially when we are not familiar with a new area. Conventionally, we may want to ask people around or possibly we use Global Positioning System (GPS) navigator. However, using GPS navigator may not be the best solution if the address is not entered accurately. Therefore, this paper presents an augmented reality (AR) application for location finder guidance. Instead, a user is only required to scan the address indicated on a surface such as card or flyer using smart phone camera.The proposed application has utilized various components of AR technology including multiple image target, virtual button and markerless features. The development of the AR application follows phases of activities in Multimedia Mobile Content Development (MMCD) model. The proposed application is found to be very interactive and convenient in finding directions to specific location.

Substitution-based linguistic steganography based on antonyms Fawwaz Zamir Mansor; Azizan Ismail; Roshidi Din; Aida Mustapha; Noor Azah Samsudin
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 1: October 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v16.i1.pp530-538

The study of steganography focuses on strengthening the security in protecting content message by hiding the true intention behind the texts. However, existing linguistic steganography approach especially in synonym-based substitution is prone to attack. In this paper, a new substitution-based approach for linguistic steganography is proposed using antonyms. The antonym-based stego-text generation algorithm is implemented in a tool called the Antonym Substitution-based (ASb). Evaluation of ASb was carried out via veriﬁcation and validation. The results showed highly favorable performance of this approach.

Towards IR4.0 implementation in e-manufacturing: artificial intelligence application in steel plate fault detection Adeleke Abdullahi; Noor Azah Samsudin; Mohd Rasidi Ibrahim; Muhammad Syariff Aripin; Shamsul Kamal Ahmad Khalid; Zulaiha Ali Othman
Indonesian Journal of Electrical Engineering and Computer Science Vol 20, No 1: October 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v20.i1.pp430-436

Fault detection is the task of discovering patterns of a certain fault in industrial manufacturing. Early detection of fault is an essential task in industrial manufacturing. Traditionally, faults are detected by human experts. However, this method suffers from cost and time. In this era of Industrial revolution IR 4.0, machine learning (ML) methods and techniques are developed to solve fault detection problem. In this study, three standard ML models: LR, NB, and SVM are developed for the classification problem. The experimental dataset used in this study consists of steel plates faults. The dataset is retrieved from UCI machine learning repository. Three standard evaluation methods: accuracy, precision, and recall are validated on the classification models. Logistic regression (LR) model achieved the highest accuracy and precision scores of 94.5% and 0.756 respectively. In addition, the SVM model had the highest recall score of 0.317. The results showed the significant impact of AI/ML approach in steel plates fault diagnosis problem.

Comparative Analysis for Topic Classification in Juz Al-Baqarah Mohamad Izzuddin Rahman; Noor Azah Samsudin; Aida Mustapha; Adeleke Abdullahi
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: October 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i1.pp406-411

In Islam, Quran is the holy book that was revealed to the Prophet Muhammad. It functions as complete code of life for the Muslims. Remarks from Allah which contains more than 77,000 words that was passed down through Prophet Muhammad to the mankind for 23 years started in 610 ce. The Quran was divided into 114 chapters. Arabic language is the original text. The need for the Muslims across the world to find the meaning to understand the content in the Quran is necessary. Nevertheless, understanding the Quran is an interest for the Muslims as well as the attention of millions of people from the faiths. Following the generation, lots of content that related to the Quran has been broadcast by Muslims scholars in the way of the tafsirs, translation and the book of hadiths. Problem has happened at current is most Muslim in Malaysia do not understand sentences in the Quran due to language barrier. The purpose of this research is classified topic in each verses of the Quran sentence based on its specific theme. It involves the objective of text mining which are based on linguistic information and domain. The usage of corpus helps to perform various data mining tasks including information extraction, text categorization, the relationship of concepts, association discovery, the evaluation of pattern and assessed. This research project is aiming to create computing environment that enable us use to text mining the Quran. The classification experiment is using the Support Vector Machine to find themes in Juz’ Baqarah. The SVM performance is then compared against other classification algorithms such as Naive Bayes, J48 Decision Tree and K-Nearest Neighbours. This research project aims at creating an enabling computational environment for text mining the Qur’an and to facilitate users to understand every verse in Juz’ Baqarah.

A Simulation of Energy Recycling Concept in Automotive Application Using Hybrid Approach Noor Azah Samsudin; Muhammad Syariff Aripin; Shamsul Kamal Ahmad Khalid; Nor Amirul Amri Nordin
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: October 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i1.pp412-419

This paper presents development of a simulation to demonstrate a relatively new hybrid approach in improving energy resources that is applicable in automotive industry. The existing hybrid approach in automotive industry is considerably efficient in terms of energy saving by switching between fuel and electricity for energy resources. However, both energy resources confront various challenges. While the electricity resources require recharging, the fuel resources are scarce and expensive. Therefore, in this paper we aim to propose a relatively new hybrid approach, referred to as energy recycling concept equipped with coordination algorithm. To simulate the proposed energy recycling concept, a prototype of Electrical Control Unit (ECU) car is built. Then, an algorithm that coordinates battery charging is developed and integrated with the ECU. Finally, the simulation of the proposed energy recycling concept equipped with the coordination algorithm is evaluated on the prototype of the ECU car. The results show that the proposed energy recycling concept that allows switching between two sources of energy is applicable to operate the ECU car prototype.

Title

Found 12 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 12 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 12 Documents
Search