Computer Engineering and Applications Journal (ComEngApp, Universitas Sriwijaya)
Not a member yet
102 research outputs found
Sort by
Automated Continuous IoT-Based Monitoring System for Vaname Shrimp Cultivation Management
No full textShrimp cultivation in Indonesia has been increasing since the introduction of white leg shrimp or often known as vaname (Penaeus vannamei) from the South Pacific waters. The use of a cultivation model with a circular pond with a diameter of 10 meters has begun to attract shrimp farmers in the northern coastal areas of Java, including Tuban Regency. There are several water quality parameters that affects survival rate such as Dissolved Oxygen (DO), Temperature, and Total Dissolved Solids (TDS). Shrimp pond farmers in Tuban Regency have used digital measuring tools to monitor the environmental conditions. However, these measurements cannot be carried out continuously for 24 hours. This often causes delays in identifying problems that occur in ponds and eventually impacts on reducing biomass weight, resulting in not achieving harvest targets. In this study, a continuous monitoring system for water quality management was designed and implemented. The system consists of an IoT-based water quality monitoring device combined with a Shrimp Aquaculture Management Information System. Based on the system that has been built, it is found that the system has been able to acquire all sensor parameters and send them to the server. The results of calibration and prediction using linear regression show that the average data reading error is achieving 14% for DO sensors, and 1% each for temperature and TDS sensors. The aggregated data is presented in tabular and graphic formats so that daily monitoring and predictions can be carried out in ponds
Simulation Design of Artificial Intelligence Controlled Goods Transport Robot
No full textTechnological advances enable scientists and researchers to develop more automated systems for life\u27s convenience. Transportation is among those conveniences needed in daily activities, including warehouses. The easy-to-build and straightforward transport robot are desired to ease human workers\u27 working conditions. The application of artificial intelligence (AI), Fuzzy Logic Controller, and Neural Network ensures the robot is able to finish assigned tasks better and faster. This paper shows the concept design of an AI-controlled good transport robot applied in the warehouse. The design is made as fast and straightforward forward possible, and the feasibility of the proposed method is proven by simulation in Scilab FLT and Neuroph
Weighting Facial Features Extraction using Geometric Average
No full textHuman facial feature extraction is an important process in the face recognition system. The quality of the results from the extraction of human facial features is determined by the degree of accuracy. The weighting of human facial features is used to test the accuracy of the methods used. This research produces the process of weighting the facial features automatically. The results obtained are the same as those seen by the human eyes. Â
Creating a Business Value while Transforming Data Assets using Machine Learning
No full textMachine learning enables computers to learn from large amounts of data without specific programming. Besides its commercial application, companies are starting to recognize machine learning importance and possibilities in order to transform their data assets into business value. This study explores integration of machine learning into business core processes, while enabling predictive analytics that can increase business values and provide competitive advantage. It proposes machine learning algorithm based on regression analysis for a business solution in large enterprise company in Macedonia, while predicting real-value outcome from a given array of business inputs. The results show that most of the machine learning predictive values for the desired process output deviated from 0 to 15% of actual employees\u27 decision. Hence, it verifies the appropriateness of the chosen approach, with predictive accuracy that can be meaningful in practice. As a machine learning case study in business context, it contains valuable information that can help companies understand the significance of machine learning for enterprise computing. It also points out some potential pitfalls of machine learning misuse
Exploration based Genetic Algorithm for Job Scheduling on Grid Computing
No full textGrid computing presents a new trend to distribute and Internet computing to coordinate large scale heterogeneous resources providing sharing and problem solving in dynamic, multi- institutional virtual organizations. Scheduling is one of the most important problems in computational grid to increase the performance. Genetic Algorithm is adaptive method that can be used to solve optimization problems, based on the genetic process of biological organisms. The objective of this research is to develop a job scheduling algorithm using genetic algorithm with high exploration processes. To evaluate the proposed scheduling algorithm this study conducted a simulation using GridSim Simulator and a number of different workload. The research found that genetic algorithm get best results when increasing the mutation and these result directly proportional with the increase in the number of job. The paper concluded that, the mutation and exploration process has a good effect on the final execution time when we have large number of jobs. However, in small number of job mutation has no effects
Performance evaluation of popular l1-minimization algorithms in the context of Compressed Sensing
No full textCompressed sensing (CS) is a data acquisition technique that is gaining popularity because of the fact that the reconstruction of the original signal is possible even if it was sampled at a sub-Nyquist rate. In contrast to the traditional sampling method, in CS we take a few measurements from the signal and the original signal can then be reconstructed from these measurements by using an optimization technique called l1-minimization. Computer engineers and mathematician have been equally fascinated by this latest trend in digital signal processing. In this work we perform an evaluation of different l1-minimization algorithms for their performance in reconstructing the signal in the context of CS. The algorithms that have been evaluated are PALM (Primal Augmented Lagrangian Multiplier method), DALM (Dual Augmented Lagrangian Multiplier method) and ISTA (Iterative Soft Thresholding Algorithm). The evaluation is done based on three parameters which are execution time, PSNR and RMSE
E-mail spam filtering by a new hybrid feature selection method using IG and CNB wrapper
No full textThe growing volume of spam emails has resulted in the necessity for more accurate and efficient email classification system. The purpose of this research is presenting an machine learning approach for enhancing the accuracy of automatic spam detecting and filtering and separating them from legitimate messages. In this regard, for reducing the error rate and increasing the efficiency, the hybrid architecture on feature selection has been used. Features used in these systems, are the body of text messages. Proposed system of this research has used the combination of two filtering models, Filter and Wrapper, with Information Gain (IG) filter and Complement Naïve Bayes (CNB) wrapper as feature selectors. In addition, Multinomial Naïve Bayes (MNB) classifier, Discriminative Multinomial Naïve Bayes (DMNB) classifier, Support Vector Machine (SVM) classifier and Random Forest classifier are used for classification. Finally, the output results of this classifiers and feature selection methods are examined and the best design is selected and it is compared with another similar works by considering different parameters. The optimal accuracy of the proposed system is evaluated equal to 99%
Two phase privacy preserving data mining
No full textThe paper proposes a framework to improve the privacy preserving data mining. The approach adopted provides security at both the ends i.e. at the data transmission time as well as in the data mining process using two phases. The secure data transmission is handled using elliptic curve cryptography (ECC) and the privacy is preserved using k-anonymity. The proposed framework ensures highly secure environment. We observed that the framework outperforms other approaches [8] discussed in the literature at both ends i.e. at security and privacy of data. Since most of the approaches have considered either secure transmission or privacy preserving data mining but very few have considered both. We have used WEKA 3.6.9 for experimentation and analysis of our approach. We have also analyzed the case of k-anonymity when the numbers of records in a group are less than k (hiding factor) by inserting fake records. The obtained results have shown the pattern that the insertion of fake records leads to more accuracy as compared to full suppression of records. Since, full suppression may hide important information in cases where records are less than k, on the other hand in the process of fake records insertion; records are available even if number of records in a group is less than k
An Analysis of Adaptive Approach for Document Binarization
No full textAbstract Binarization is an initial step in document image analysis for differentiate text area from background. Determination of binarization technique is really important to retrieve all the text information especially from degraded document image. This paper explains about adaptive binarization using Gatos’s method. Gatos’s method is doing preprocessing, foreground estimation using Sauvola’s method, background estimation, upsampling, final thresholding and postprocessing. In this paper, Sauvola’s method is final thresholding from Wiener filter image result and source image, and count F-Measure from both of these binary image results. By using optimum constant value on k value, n local window, Ksw and Ksw1, Gatos’s method can produced binary image better than Sauvola’s method based on F-Measure value. Sauvola’s method produces average value F=84,62%, Sauvola’s method with Wiener filter produces average value F=99.06% and Gatos’s method produces average value F=99,43%. Keyword : Degraded Document Image, Adaptive Approcah for Binarization, Gatos’s Method, Sauvola’s MethodDOI: 10.18495/comengapp.22.18519
An Immune Based Patient Anomaly Detection using RFID Technology
No full textDetecting of anomalies patients data are important to gives early alert to hospital, in this paper will explore on anomalies patient data detecting and processing using artificial computer intelligent system. Artificial Immune System (AIS) is an intelligent computational technique refers to human immunology system and has been used in many areas such as computer system, pattern recognition, stock market trading, etc. In this case, real value negative selection algorithm (RNSA) of artificial immune system used for detecting anomalies patient body parameters such as temperature. Patient data from monitoring system or database classified into real valued, real negative selection algorithm results is real values deduction by RNSA distance, the algorithm used is minimum distance and the value of detector generated for the algorithm. The real valued compared with the distance of data, if the distance is less than a RNSA detector distance then data classified into abnormal. To develop real time detecting and monitoring system, Radio Frequency Identification (RFID) technology has been used in this system. Keywords: AIS, RNSA, RFID, AbnormalDOI:Â 10.18495/comengapp.21.12114