International Journal of Informatics and Communication Technology (IJ-ICT)
Not a member yet
494 research outputs found
Sort by
Diagnosing MERS-CoV using dempster-shafer method
Get PDFMERS-CoV (Middle East Respiratory Syndrome-Coronavirus) is a respiratory syndrome disease caused by the coronavirus which attacks the respiratory tract from mild to severe. MERS-CoV was first reported in Saudi Arabia; total cases of MERS-CoV have continued to increase. In Indonesia, the MERS-CoV enters through the pilgrimage of Hajj and Umrah. But not many people know about this disease and its symptoms. For this reason, an expert system was developed to diagnose MERS-CoV using the Dempster-Shafer method. The system can detect the disease from the symptoms inputted by user. The output of the system is the value of the probability of the disease, the level of the disease and the suggested. The levels of the disease are Stage 1, Stage 2, and Stage 3 where each has a different treatment based on the level of the disease. The system contains information about MERS-CoV in the form of videos and text. The system was built using the PHP programming language. The testing result shows that all system functionalities have been fulfilled. The expert validation testing had obtained at 76.7%, which prove that the system is good enough in diagnosing MERS-CoV and the results obtained from the questionnaire is at an average of 84.13% which is very good in helping users in diagnosing disease. The expert system that has been developed can help people in diagnosing the disease before consulting with a doctor.MERS-CoV (Middle East Respiratory Syndrome-Coronavirus) is arespiratory syndrome disease caused by the coronavirus which attacks therespiratory tract from mild to severe. MERS-CoV was first reported in SaudiArabia; total cases of MERS-CoV have continued to increase. In Indonesia,the MERS-CoV enters through the pilgrimage of Hajj and Umrah. But notmany people know about this disease and its symptoms. For this reason, anexpert system was developed to diagnose MERS-CoV using the DempsterShafer method. The system can detect the disease from the symptomsinputted by user. The output of the system is the value of the probability ofthe disease, the level of the disease and the suggested. The levels of thedisease are Stage 1, Stage 2, and Stage 3 where each has a different treatmentbased on the level of the disease. The system contains information aboutMERS-CoV in the form of videos and text. The system was built using thePHP programming language. The testing result shows that all systemfunctionalities have been fulfilled. The expert validation testing had obtainedat 76.7%, which prove that the system is good enough in diagnosing MERSCoV and the results obtained from the questionnaire is at an average of84.13% which is very good in helping users in diagnosing disease. Theexpert system that has been developed can help people in diagnosing thedisease before consulting with a doctor.
Comparative analysis on different software piracy prevention techniques
Get PDFNumerous type of software piracy known today, have several prevention techniques which has been established against them. Although, different software piracy techniques have been established, but the choice of which one should be the best to develop any software is the challenge for most software developers. Consequently, example of the types of piracy in software development can be categorise as follows: cracks and serials, softlifting and hard disk loading, internet piracy and software forging, mischaneling, reverse engineering, and tampering. We have several types of prevention techniques which aimed to resolved piracy in software development, although the methods have been wrecked. In this work a critical analysis has been carryout on different software piracy techniques and a simple model software was designed using the best technique to validate the results of the analysis
Heart disease prediction model with k-nearest neighbor algorithm
Get PDFIn this study, the author proposed k-nearest neighbor (KNN) based heart disease prediction model. The author conducted an experiment to evaluate the performance of the proposed model. Moreover, the result of the experimental evaluation of the predictive performance of the proposed model is analyzed. To conduct the study, the author obtained heart disease data from Kaggle machine learning data repository. The dataset consists of 1025 observations of which 499 or 48.68% is heart disease negative and 526 or 51.32% is heart disease positive. Finally, the performance of KNN algorithm is analyzed on the test set. The result of performance analysis on the experimental results on the Kaggle heart disease data repository shows that the accuracy of the KNN is 91.99
Fuzzy logic decission maker for automatic feeder and water quality monitoring system
Get PDFFeeding is one of the most important factors in vanammei shrimp culture. Feeding time must be scheduled regulary and it is prohibit from being late. Because it can affect to the development and growth of vanammei shrimp. The Research of monitoring and control system of vanammei shrimp feeding continues to be developed. The development of hardware and software in this study prioritizes monitoring of pH conditions, oxygen levels, and pond temperatures. The measurement results of pH, oxygen levels and pond temperature can be used as decision makers for vanammei shrimp feeding schedules. The decision making system using the Fuzzy Logic method. The development of control devices for feeding aims to set a schedule for feeding automatically. The use of monitoring devices and automatic Feeder control of shrimp feeding can reduce the accumulation of leftover shrimp feed, so that feeding can be more efficient
Data mining techniques for lung and breast cancer diagnosis: A review
Get PDFToday, cancer counted as the riskier disease than the other diseases in the globe. There are many cancer forms like leukemia, skin cancer, and stomach cancer but lung and breast cancer are the most common forms that many people suffered from. Cancer is the disease that cell has grown rapidly and abnormally that is why treating it is somehow tough in some cases but it can be controlled if it is detected in the initial stage. Data-mining classification algorithms had a vital role in predicting and recognizing both benign and malignant cell. Several classifiers are available to classify the usual and unusual cells such as decision-tree, artificial-neural net, SVM, and KNN. This paper presents a systematic review about the most well-known data-mining classification algorithms for lung and breast cancer diagnose. A brief review about KDD and the data-mining concept has demonstrated. The Decision-Tree (D-Tree), ANN, Support-vector-machine, and naïve Bayes classifier that is widely utilized in the biomedical field has been reviewed along with the some algorithms such as C4.5, Cart, and Iterative -Dichotomiser 3 ‘ID3’. A comparison has been done among various reviewed papers in terms of accuracy that used various data-mining classification algorithms to propose the lung and breast cancer diagnosis system. The experimental results of the reviewed papers showed that the Multilayer Perceptron (MLP) and Logistic Regression (LR) gave a higher accuracy of 99.04% and 98.1%, respectively
An approach to partial occlusion using deep metric learning
Get PDFThe human face can be used as an identification and authentication tool in biometric systems. Face recognition in forensics is a challenging task due to the presence of partial occlusion features like wearing a hat, sunglasses, scarf, and beard. In forensics, criminal identification having partial occlusion features is the most difficult task to perform. In this paper, a combination of the histogram of gradients (HOG) with Euclidean distance is proposed. Deep metric learning is the process of measuring the similarity between the samples using optimal distance metrics for learning tasks. In the proposed system, a deep metric learning technique like HOG is used to generate a 128d real feature vector. Euclidean distance is then applied between the feature vectors and a tolerance threshold is set to decide whether it is a match or mismatch. Experiments are carried out on disguised faces in the wild (DFW) dataset collected from IIIT Delhi which consists of 1000 subjects in which 600 subjects were used for testing and the remaining 400 subjects were used for training purposes. The proposed system provides a recognition accuracy of 89.8% and it outperforms compared with other existing methods
An efficient forward error correction code for wireless sensor networks
No full textThe main requirements in the design of wireless sensor network applications are to minimize energy consumption and maximize battery lifetime. Power is primarily consumed during wireless transmission and reception. Automatic repeat request (ARQ) and forward error correction (FEC) are the two basic methods to recover erroneous packets. As energy conservation is a major issue of concern in wireless sensor networks, repeat transmission because the error in the data received is not an option, and FEC would be preferred over ARQ. FEC is applied in situations where retransmissions are relatively costly or impossible. A successful data transmission means a higher energy saving and a long-life network. This paper presents a novel linear block forward error correction code for wireless sensor network applications called Low Complexity Parity Check (LCPC). The LCPC code offers lower encoding and decoding complexity than other types of codes. To validate the performance of the LCPC code, the proposed coding scheme was investigated at different values of data transmission with different types of modulations over Additive white Gaussian noise (AWGN) and Rayleigh fading channels. The simulation results show that the proposed code outperforms the renowned LDPC (8, 4), (255,175), and (576, 288) codes
Automated smart car parking system for smart cities demand employs internet of things technology
Get PDFThe use of smart cities rises quickly with the fast progress of the Internet of Things (IoT) advances. The smart city idea essentially getting city life; as well raises the capability of municipal jobs and facilities plus form viable economic progress of the city. The point of convergence of this paper is to introduce an automated smart automobile parking system for smart cities demand employs internet of things (IoT) technology. The offered automobile parking system covers an IoT entity sent nearby for getting sorted out the existing parking spots which are quicker contrasted with different frameworks. It is a viewpoint gave as an iOS application for reservation, entrance, supervision, and leaving the car park places
Electronic control of water resources using smart field irrigation systems
Get PDFMost of the research showed that the reason behind the agricultural lesions is the over usage of water in irrigation the matter which cause the appearance of fungicide on plants and salinity of the soil. From this point emerged the need for adapt some systems to work in farms in order to reduces the expenses of the product, improve its quality and lessen the consumption of water. Internet webs have been a preceding means in such a scope; and they also showed flexibility in designing such systems. In this paper; a smart irrigation system that depend on the values of moisture content and the agricultural constants (Feld Capacity, Wilt Point of the plant, Bulk Density, Depth of the root of the plant, the consumption of each water dripper and the passing area) in making the decision of irrigation and running the water pump, depending on the quantity of water to be added and the duration of irrigation time, and it is better. Field humidity levels at 0.32. This system was built by using the microcontroller ESP-32S&ESP8266 and moister sensor. The data was uploaded to Adafruit server for the sake of remote monitoring by MQTT protocol
Educational data mining in moodle data
Get PDFThe main purpose of this research paper is to analyze the moodle data and identify the most influencing features to develop the predictive model. The research applies a wrapper-based feature selection method called Boruta for the selection of best predicting features. Data were collected from eighty-one students who were enrolled in the course called Human Computer Interaction (COMP341), offered by the Department of Computer Science and Engineering at Kathmandu University, Nepal. Kathmandu University uses Moodle as an e-learning platform. The dataset contained eight features where Assignment.Click, Chat.Click, File.Click, Forum.Click, System.Click, Url.Click, and Wiki.Click was used as the independent features and Grade as the dependent feature. Five classification algorithms such as K Nearest Neighbour, Naïve Bayes, and Support Vector Machine (SVM), Random Forest, and CART decision tree were applied in the moodle data. The finding shows that SVM has the highest accuracy in comparison to other algorithms. It suggested that File.Click and System.Click was the most significant feature. This type of research helps in the early identification of students’ performance. The growing popularity of the teaching-learning process through an online learning system has attracted researchers to work in the field of Educational Data Mining (EDM). Varieties of data are generated through several online activities that can be analyzed to understand the student’s performance which helps in the overall teaching-learning process. Academicians especially course instructors who use e-learning platforms for the delivery of the course contents and the learners who use these platforms are highly benefited from this research