International Journal of artificial intelligence research (IJAIR)
Not a member yet
271 research outputs found
Sort by
Detection of SQL Injection Attack Using Machine Learning Based On Natural Language Processing
Get PDFThere has been a significant increase in the number of cyberattacks. This is not only happening in Indonesia, but also in many countries.  Thus, the issue of cyber attacks should receive attention and be interesting to study.  Regarding the explored security vulnerabilities, the Open Web Application Security Project has published the Top-10 website vulnerabilities. SQL Injection is still become one of the website vulnerabiliteis which is often exploited by attacker. This research has implemented and tested five algorithms. They are Naïve Bayes, Logistic Regression, Gradient Boosting, K-Nearest Neighbor, and Support Vector Machine. In addition, this study also uses natural language processing to increase the level of detection accuracy, as a part of text processing. Therefore, the main dataset was converted to corpus to make it easier to be analyzed. This process was carried out on feature enginering stage. This study used two datasets of SQL Injection. The first dataset was used to train the classifier, and the second dataset was used to test the performance of classifier. Based on the tests that have been carried out, the Support Vector Machine get the highest level of accuracy detection. The accuracy of detection is 0.9977 with 0,00100 micro seconds per query time of process. In performance testing, Support Vector Machine classifier can detect 99,37% of second dataset. Not only Support Vector Machine, the study have also revealed the detection accuracy level of further tested algorithms: K-Nearest Neighbor (0,9970), Logistic Refression (0,9960), Gradient Boosting (0,99477), and Naïve Bayes (0,9754)
Face Recognition Using Machine Learning Algorithm Based on Raspberry Pi 4b
Get PDFMachine learning is one of artificial intelligence that is used to solve various problems, one of which is classification. Classification can separate a set of objects based on certain characteristics. This study discusses the classification of objects in the form of facial images with the aim of the system being able to recognize a person's face to access a room for security reasons. The application of machine learning using the support vector machine algorithm with the support vector classifier technique is implemented on a raspberry pi-based security device. Â The results of training using this algorithm produce a model with 99% accuracy in 0.10 seconds based on testing data of 525 face images. The model evaluation got 99% precision, 99% recall, and 99% f1-score. Testing the model made from the training process using the raspberry pi model 4b is can recognize facial images in real-time. Â If the security device detects someone at the door and then recognizes the face image then room access will be granted and an alarm is activated indicating the door is open
Journal Unique Visitors Forecasting Based on Multivariate Attributes Using CNN
Get PDFForecasting is needed in various problems, one of which is forecasting electronic journals unique visitors. Although forecasting cannot produce very accurate predictions, using the proper method can reduce forecasting errors. In this research, forecasting is done using the Deep Learning method, which is often used to process two-dimensional data, namely convolutional neural network (CNN). One-dimensional CNN comes with 1D feature extraction suitable for forecasting 1D time-series problems. This study aims to determine the best architecture and increase the number of hidden layers and neurons on CNN forecasting results. In various architectural scenarios, CNN performance was measured using the root mean squared error (RMSE). Based on the study results, the best results were obtained with an RMSE value of 2.314 using an architecture of 2 hidden layers and 64 neurons in Model 1. Meanwhile, the significant effect of increasing the number of hidden layers on the RMSE value was only found in Model 1 using 64 or 256 neurons
Fuzzy subtractive clustering (FSC) with exponential membership function for heart failure disease clustering
Get PDFObjective: Fuzzy clustering algorithm is a partition method used to assign objects from a data set to a cluster by marking the average location. Furthermore, Fuzzy Subtractive Clustering (FSC) with hamming distance and exponential membership function is used to analyze the cluster center of a data point. Therefore, the purpose of this research is to determine the number of clusters with the best quality by comparing the Partition Coefficient (PC) values for each number produced. Methods: The data set which is heart failure patient data is 150 data obtained from UCI Machine Learning. The data consists of 11 variables, including age , anemia , creatinine phosphokinase , diabetes ejection fraction , high blood pressure , platelets , serum creatinine , serum sodium , gender , and smoke . It simulated and processed using Fuzzy Subtractive Clustering Algorithm, Jupyter Notebook Software with Python programming language. Result: The results showed that the most optimal number of clusters is 3, which are selected based on the largest PC value. Conclusion: Based on the results obtained, the highest P value is in cluster 3, therefore heart failure can be grouped into 3, namely low, moderate, severe
Forecasting Palawija Harvest Results In North Aceh Using Multiple Linear Regression Method
Get PDFThe agricultural sector is one sector that is very dominant in people's income in Indonesia because most Indonesians work as farmers. One of the plants that play the most crucial role is the palawija plant. An increase in the amount of production and the harvested area will also increase the amount of harvest produced; therefore, to find out which areas have the potential to become producers of productive secondary crops in North Aceh, one of them is by predicting crop yields using the multiple linear regression method. The dataset used for this research is data on the development of palawija crop intensification in North Aceh Regency from 2017 to 2021, taken from the Department of Agriculture and Food Crops, North Aceh Regency. The multiple linear regression method is implemented by entering actual data. Then the data will be calculated in various stages, starting from determining the value of constants and coefficients using a table helper. After getting the result value, then converted into matrix form A and H to find the determinants A1, A2, A3, and A4. After that, enter it into a linear regression pattern and produce a predictive value of crop yield data for the coming year. Calculations in the linear regression method are taken on soybean yields in the Tanah Jambu Aye sub-district in 2022, ranging from 61.00 tons
Hybrid Data Mining with the Combination of K-Means Algorithm and C4.5 to Predict Student Achievement
No full textGetting academic achievement is the dream of every student who studies at higher education, especially undergraduate level. Undergraduate students aspire to the highest achievement (champion) at the last achievement of their studies. However, students cannot predict whether these students with the habits that have been done and the current conditions will make them excel or not. Apart from that, of course, students also want to know what factors and conditions influence the achievement the most. The objective to be achieved in this research is how to predict which number of students among them are predicted to excel (champion) at the end of the semester with a combination of the K-Means and C4.5 methods. Besides, the purpose of this study reveals how the K-Means algorithm performs data clustering of student data who will excel or not and how the C4.5 algorithm predicts students who have been grouped. Data processing in this study uses the Rapid Miner software version 9.7.002. The result of this research is that it is easier to group data in numerical form than data in polynomial form. Other results in this study were that out of 100 students, 27 students (27%) were predicted to excel (champions) and 73 (73%) did not achieve (not champions)
Covid-19: Implementation e-voting Blockchain Concept
Get PDFThe current situation of the Covid-19 pandemic is currently increasing public concern about the community. The government has especially recommended Stay at Home and the implementation of PSBB in various regions. One of the concerns is when the election of regional leaders to the general chairman. Even though there is already a safeguard regulation, this is not considered safe in the current Covid-19 pandemic. The solution in this research is the use of a blockchain-based E-voting system to help tackle election unrest during Covid-19. Where e-voting with blockchain technology can be carried out anywhere through the device without the need to be present in the voting booth, reducing data fraud, accurate and decentralized voting results that can be accessed by the public in real-time. The use of cryptographic protocols is applied for data transfer between system components as well as valid system security. This research method uses SUS trial analysis in a significant system of the Covid-19 pandemic situation. The implication that the SUS Score analysis shows 90 shows an acceptable E-voting system, meaning that the community can accept it because it brings positive and significant impacts such as effectiveness and efficiency
Stochastic Perturbations on Low-Rank Hyperspectral Data for Image Classification
Get PDFHyperspectral imagery (HSI) contains hundreds of narrow contiguous bands of spectral signals. These signals, which form spectral signatures, provide a wealth of information that can be used to characterize material substances. In recent years machine learning has been used extensively to classify HSI data. While many excellent HSI classifiers have been proposed and deployed, the focus has been more on the design of the algorithms. This paper presents a novel data preprocessing method (LRSP) to improve classification accuracy by applying stochastic perturbations to the low-rank constituent of the dataset. The proposed architecture is composed of a low-rank and sparse decomposition, a degradation function and a constraint least squares filter. Experimental results confirm that popular state-of-the-art HSI classifiers can produce better classification results if supplied by LRSP-altered datasets rather than the original HSI datasets.Â
Causal Relations of Factors Representing the Elderly Independence in Doing Activities of Daily Livings Using S3C-Latent Algorithm
Get PDFThe growth of the elderly population in Indonesia from year to year has always increased, followed by the problem of decreasing physical strength and psychological health of the elderly. These problems can affect the increase in dependence and decrease the independence of the elderly in ADL. In previous studies, various factors affect independence in ADLs such as cognitive, psychological, economic, nutrition, and health. However, In general, these studies only focus on predictive analysis or correlation of variables, and no research has attempted to identify the casual relationship of the elderly independence factors. Therefore, this study aimed to determine the mechanism of the causal relationship of the factors that influence the independence of the elderly in ADLs using a casual method called the Stable Specification Search for Cross-Sectional Data With Latent Variables (S3C-Latent). In this research we found strong causal and associative relationships between factors.The causal relationship of elderly independence in ADLs was influenced by cognitive, psychological, nutritional and health factors and gender with α values respectively (0.61; 0.61;1.00, 0.65;0.70). Cognitive factors associated with psychological, economic, nutrition, and health with a value of α (0.77; 1.00; 1.00; 0.64). Furthermore, psychological factors associated with economy, nutrition, and health with a value of α (0.77; 0.95; 0.63). Bisides, economic factors are associated with nutrition and health with α values of ( 0.86; 0.75) and nutrition with health with α values of 0.64. The last association was found between nutritional factors and gender with a value of α 0.76. This research is expected to increase the independence of the elderly in carrying out daily activities
The Development of ITSM Research in Indonesia: A Systematic Literature Review
Get PDFIT Service Management (ITSM) is a framework used to support businesses by increasing IT service quality. Several studies have tried to examine the development of ITSM based on their respective interests. However, the development of ITSM in Indonesia has not been widely studied, such as the types of research that are most often investigated, what domains are often researched, the areas and types of companies being studied. The things above are the main objectives of this research. The method used in capturing data, screening, and analysis is the systematic literature review method. There are many findings obtained from this research. One of them is the domination of the service operation research area (45%) among other areas. Meanwhile, applied research had been researched quite consistently over the last five years. From these results, it can be noticed that a deeper understanding of the synchronization between business and IT is needed. This is in accordance with the objectives of ITSM implementation so that future research is expected to provide balance in other areas, such as service strategy, design, transition, operation, and continuous service improvement