International Journal of artificial intelligence research (IJAIR)
Not a member yet
271 research outputs found
Sort by
A Systematic Literature Review Method On AES Algorithm for Data Sharing Encryption On Cloud Computing
Get PDFCloud computing is one revolution in information technology (IT) that can share resources, services and data through a network among users. Because users have same rights on the network to transfer data, data are vulnerable to be attacked by unauthorized person. Lately, data security in a system only concentrates on data storage on cloud by utilizing internet security, but a little concentration is found during data transfer. By considering security as a serious problem, an encryption-based proposed system is presented to secure during data transfer. Authors propose an approach to boost system security during data transfer in order to prevent data theft by unauthorized person. To prevent an attack by unauthorized person, Advanced Encryption Standard (AES) will be proposed to secure data transfer and storage in cloud computing. For better future, authors will propose Systematic Literature Review (SLR) to generate suggestions and opportunities in AES cloud computing
A protocol for Enhanced imaging and Quantification of Cervical Cell Under Scanning electron Microscope
Get PDFThe application of Field Emission Scanning Electron Microscopy and Energy Dispersive X-Ray (FE-SEM/EDX) for the characterization of biological samples can produce promising results for classification purpose. The limitations of the established sample preparation technique of cervical cells for FE-SEM/EDX study that differentiate between normal and abnormal cells prompted the development of a proposed protocol for the preparation of cervical cells. The proposed protocol was conducted by a McDowell-Trump fixative prepared in 0.1M phosphate buffer without osmium tetroxide at 4°C for 2 h in the fixation process. Morphologically, the cervical cells scanned under the FE-SEM/EDX did not present blackening effects, and the structure of the cells was not broken based on the FE-SEM images. Quantitatively, the possible elemental distributions in the cells, such as carbon, nitrogen, oxygen, and sodium, are detected in samples prepared by the proposed protocol. The analysed elements were validated using the Attenuated Total Reflection and Fourier Transform Infrared (ATR/FTIR) spectroscopy. Moreover, by avoiding osmium tetroxide fixation, the time required for sample preparation decreased significantly. This sample preparation protocol can be used for normal and abnormal cervical cells in achieving better results in terms of morphological, detected elemental distribution, and rapid in time
Solution of class imbalance of k-nearest neighbor for data of new student admission selection
Get PDFThe objective of this research is to correct the inconsistencies associated with the response differences by each examiner with respect to the assessment of each hafiz candidate. To carry out this research, 259 students were selected within a week using 4testers. However, the examiners are also tasked with another essential mandate which must be immediately fulfilled asides testing candidates for hafiz. In order to overcome this problem, the Educational Data Mining (EDM) system is applied during classification. The problems associated with the use of this technique however, is the limited number of attributes and the imbalance data class. This study was proposed to apply the kNN (k-Nearest Neighbor) technique. The results obtained indicates that kNN can provide recommendations to testers who are students and it is suitable for the solving the problem associated with class imbalance as indicated by the application of Shuffled and Stratified sampling techniques which has values of accuracy, precision, recall and AUC > 0.8%
Journal Classification Using Cosine Similarity Method on Title and Abstract with Frequency-Based Stopword RemovalÂ
Get PDFClassification of economic journal articles has been done using the VSM (Vector Space Model) approach and the Cosine Similarity method. The results of previous studies are considered to be less optimal because Stopword Removal was carried out by using a dictionary of basic words (tuning). Therefore, the omitted words limited to only basic words. This study shows the improved performance accuracy of the Cosine Similarity method using frequency-based Stopword Removal. The reason is because the term with a certain frequency is assumed to be an insignificant word and will give less relevant results. Performance testing of the Cosine Similarity method that had been added to frequency-based Stopword Removal was done by using K-fold Cross Validation. The method performance produced accuracy value for 64.28%, precision for 64.76 %, and recall for 65.26%. The execution time after pre-processing was 0, 05033 second
Design of a-based smart meters to monitor electricity usage in the household sector using hybrid particle swarm optimization - neural network
Get PDFThe procedure is training and testing the nerves that will be made. Matlab software has a Neural Network tool, which in this study will be used. Load sampling data is used as input data for neural network training. As output / target load classification is used. Load classification method, which is 1 for TV load classification, 2 for fan load, 3 for iron load, 4 for water pump load, 5 for lamp load, 6 for dispenser load, and 7 for fan iron load combination. The total load is 6 single loads and 1 combination load. One load combination was chosen because, on the combination load characteristics after the fan has characteristics that are not the same as the others. Data sampling of the current of each load will be used as neural network training. Load data used is 30 samples or for 30 seconds, with every minute the data is taken. From the results of the training, it can be seen that the biggest training error is in the seventh data, namely the identification of the load on the classification of the fan-iron load. This is because the current pattern on the iron and fan with the iron or fan itself has almost the same characteristics. However, for this process networks will be used and then the PSO optimization method is used to reduce the error, in the next study. From the test results, it is shown that by varying the input current data of each load, the network has been able to identify well, even though in the data classification load 7, the load of the iron-fan combination still has a large error. This will be corrected in subsequent studies with Particle Swarm Optimization (PSO) algorithm optimization
Application Of Backpropagation Neural Networks In Predicting Rainfall Data In Ambon City
Get PDFThe Artificial Neural Networks is a process of information system on certain traits which as representatives of the human neural networks. The Artificial Neural Networks can be applied in every area of human life, one of them is environment especially about prediction of climate or weather. In this research, the artificial neural network is used to predict the rainfall with Backpropagation method and using MATLAB software. The other meteorology parameters used to predict the rainfall are air temperature, air velocity and air pressure. The result showed less accuracy level is 80% by using alpha 0,7, iteration number (epoch) 10000 and MSE value = 0,0218. Therefore, the result of rainfall prediction system is accurate
Comparative Analysis Of Dempster Shafer Method With Certainty Factor Method For Diagnose Stroke Diseases
Get PDFThe development of artificial intelligence technology that has occurred has allowed expert systems to be applied in detecting disease using programming languages. One in terms of providing information about a variety of disease problems that have recently been feared by Indonesian society, namely stroke. Expert system method used is dempster shafer and certainty factor method is used to analyze the comparison of both methods in stroke.Based on the analysis result, it is found that certainty factor is better than demster shafer and more accurate in handling the knowledge representation of stoke disease according to the symptoms of disease obtained from one hospital in medan city, uniqueness of algorithm that exist in both methods
The Implementation of AHP for Determining Dominant Criteria in Higher Education Competitiveness Development Strategy Based on Information Technology
Get PDFThe existence of Higher Education has a huge role in nation and state’s life through tri dharma of Higher Education named education, research and community service. Higher Education can produce economic innovations based on knowledge so that, it will increase productivity and nation competitiveness. Higher Education must have strategies that will be carried out, therefore they are able to compete with other higher education according to stakeholder needs. The purposes of this research are to analyze 2 (two) models of information technology relations in the higher education competitiveness development strategy determining the most dominant criteria according to the higher education development direction (Relevance, Academic Atmosphere, Internal Management, Sustainability, Efficiency and Productivity, Access and Equit and Leadership). The method of this reserach is AHP method in wich the data are collected through questionnaires to respondents in collage. The criteria of this research are internal management & organization, academic atmosphere and university competitive sustainability. The results of this research are the information technology relations model with internal management, and the relation model between internal management and efficiency & productivities, and also the most dominant criteria in the higher education competitiveness development strategy are the criteria of Academic Atmosphere, Efficiency and Productivity
Machine Learning Based Prediction versus Human-as-a-Security-Sensor
Get PDFPhishing is one of the most common cyber threats in the world today. It is a type of social engineering attack where the attacker lures unsuspecting victims into carrying out certain tasks mostly to steal personal and sensitive information. These stolen information are exploited to commit further crimes e.g. blackmails, data theft, financial theft, malware installation etc. This study was carried out to tackle this problem by designing an anti-phishing learning algorithm to detect phishing emails and also to study the accuracies of human phishing prediction to machine prediction. A graphical user interface was designed to emulate an email-client system that popped-up a warning on detecting a phishing mail successfully and collection of predictions made by expert and non-expert users on anti-phishing techniques. These predictions were compared to the predictions made by the machine learning algorithm to compare the efficiencies of all predictions considered in this research. The performance of the classifier used was measured with metrics such as confusion matrix, accuracy, receiver operating characteristic curve and area under grap
A modeling approach for short-term load forcasting using fuzzy logic type-2 in sulselrabar system
No full textThis research proposed a modeling approach for 24-hour short-term load forcasting based on fuzzy logic type-2. In this research we get an approach in designing load forecasting model, where previously still using conventional fuzzy logic. Implementation of load forecasting in this research is done on electrical system 150 kV Sulselrabar. Sulselrabar electrical system in its development has grown rapidly, therefore needed a study that to improve system performance, one of which is the study of short-term load forcasting. As the input data used load data from 2010 to 2016 on the same day that is January 8th. To see the accuracy of the results, two approaches are performed, ie fuzzy logic type-1 modeled using Simulink and fuzzy logic type-2 modeled using m-file Matlab. From the analysis results obtained, Mean Percentage Error (MAPE) is the smallest by using Fuzzy Logic Type-2 method, compared with Fuzzy Logic Type-1 method.. Where, MAPE for fuzzy logic type-1 method is 2.133371219%, and by using fuzzy logic type-2 method, MAPE is 1.729778866%