Articles
<![CDATA[Design of Simulation Definite Integral Application learning Using Trapezoid Method based on VB.Net ]]>
<![CDATA[N. PRIYA DHARSHINNI]]>;
<![CDATA[Amir Saleh]]>;
<![CDATA[Fadhillah Azmi]]>;
<![CDATA[I Fawwaz]]>
<![CDATA[ JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 4, No 1 (2020): ---> EDISI JULI ]]>
Publisher : <![CDATA[Universitas Medan Area ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (365.427 KB)
|
DOI: 10.31289/jite.v4i1.3880
<![CDATA[The definite integral is one of the subjects that is difficult for students to understand because the process of calculating definite integral of functions is quite complicated and long because it requires mastery of some integrating rules so an interactive learning simulation application is needed to make it easier for students to calculate definite integral of functions and the depiction of the area the curve. One method for calculating definite integrals is the trapezoid method. The trapezoid method works by dividing the boundary into 2 intervals namely x = x0 to x = x1. Simulation media application learning will be designed with the VB.Net programming language. This simulation media learning starts with reading and checking data input. The process is continued by displaying the depiction of the input curve and ending with calculating the area of the curve. Simulation media learning provides a facility to store the input data, the results of the calculation of the area and the image of the curve function in the image format of * .bmp. In this media, the media and material expert’s the results of the average are produced by 88.68% included into media category is very valid media and the results of pre-test and post-test trials showed an increase with an average value of 48.3 for pre-test and 87 for the post-test of the passing grade requirement of 70.Keywords: Definite Integral, Trapezoid Method,VB.Net, Media Validation.]]>
<![CDATA[Face Identification on Login Security Using Algorithm Combination of Viola-Jones and Cosine Similarity ]]>
<![CDATA[FADHILLAH AZMI]]>;
<![CDATA[Amir Saleh]]>;
<![CDATA[N P Dharshinni]]>
<![CDATA[ JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 4, No 1 (2020): ---> EDISI JULI ]]>
Publisher : <![CDATA[Universitas Medan Area ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (328.953 KB)
|
DOI: 10.31289/jite.v4i1.3885
<![CDATA[Data security by using an alphanumeric combination password is no longer used, so it needs to be added security that is difficult to be manipulated by certain people. One type of security is the type of biometrics technology using face recognition which has different characteristics by combining the Viola-Jones algorithm to detect facial features, GLCM (Gray Level Co-occurrence Matrix) for extracting the texture characteristics of an image, and Cosine Similarity for the measurement of the proximity of the data (image matching). The image will be detected using the Viola-Jones algorithm to get face, eyes, nose, and mouth. The image detection results will be calculated the value of the texture characteristics with the GLCM (Gray Level Cooccurrence Matrix) algorithm. Image matching using cosine similarity will determine or match the data stored in the database with new image input until identification results are obtained. The results obtained in this study get the level of accuracy of the identification of the three algorithms by 77.20% with the amount of data that was correctly identified as many as 386 out of 500 images.Keywords: Security, face recognition, Viola-Jones, Cosine Similarity.]]>
<![CDATA[Identifikasi Tanaman Herbal Berdasarkan Citra Daun Menggunakan Cosine Similarity dan Features Extraction ]]>
<![CDATA[Alexander F K Sibero]]>;
<![CDATA[Amir Saleh]]>
<![CDATA[ JURNAL MAHAJANA INFORMASI Vol 5 No 1 (2020): JURNAL MAHAJANA INFORMASI ]]>
Publisher : <![CDATA[Universitas Sari Mutiara Indonesia Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Tanaman herbal merupakan tanaman yang dimanfaatkan sebagai obat-obatan untuk berbagai jenis penyakit. Tanaman ini banyak terdapat di daerah hutan atau lingkungan hijau yang keberadaannya tak jarang luput dari manusia. Bahkan beberapa orang sulit untuk membedakan mana tumbuhan herbal dan mana yang bukan. Langkah yang terbaik sebelum menggunakan tumbuhan tersebut adalah dengan melakukan identifikasi terhadap daun tanaman herbal, karena terdapat juga tumbuhan yang hampir mirip dengan tanaman herbal ternyata adalah tanaman yang mengandung racun. Identifikasi yang dilakukan dengan cara mengambil citra dari daun tersebut dan diolah menggunakan komputer dengan metode identifikasi seperti, cosine similarity. Sebelum diklasifikasi dengan metode cosine similarity, terlebih dahulu citra akan diolah dan diektraksi ciri menggunakan ciri tekstur dengan GLCM dan ciri morfologi dengan moment invariant. Hal ini dilakukan untuk mengetahui ciri-ciri dari masing-masing citra daun untuk proses identifikasi. Berdasarkan pengujian yang dilakukan menggunakan metode yang diusulkan tersebut diperoleh akurasi rata-rata identifikasi dengan ketepatan sebesar 89,57%.]]>
<![CDATA[FACE IMAGE RETRIEVAL SYSTEM USING COMBINATION METHOD OF SELF ORGANIZING MAP AND NORMALIZED CROSS CORRELATION ]]>
<![CDATA[Amir Saleh]]>;
<![CDATA[Diky Suryandy]]>;
<![CDATA[Jesron Nainggolan]]>
<![CDATA[ INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence ]]>
Publisher : <![CDATA[Sean Institute ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (438.05 KB)
<![CDATA[Content based image retrieval (CBIR) is one method in computer vision that is widely applied in various fields of life. In this study, two algorithms will be combined, namely self organizing map (SOM) and normalized cross correlation (NCC) to test the method in the face image retrieval system. The SOM algorithm is used to perform learning on the system created and the NCC method is used to calculate the proximity value between the input image and the image contained in the database to be displayed as the result of image retrieval. The test results in the proposed research show good results with an accuracy rate of face image retrieval of 93.62%. This percentage is higher than using the usual SOM method with an accuracy rate of face image retrieval of 91.62%.]]>
<![CDATA[Iris Recognition Using Hybrid Self-Organizing Map Classifier and Daugman’s Algorithm ]]>
<![CDATA[Amir Saleh]]>;
<![CDATA[Yusuf Roni Laia]]>;
<![CDATA[Fransiskus Gowasa]]>;
<![CDATA[Victor Daniel Sihombing]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 1 (2023): February 2023 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29207/resti.v7i1.4441
<![CDATA[One of the neural network algorithms that can be used in iris recognition is self-organizing map (SOM). This algorithm has a weakness in determining the initial weight of the network, which is generally carried out randomly, which can result in a decrease in accuracy when an incorrect determination is made. The solution that is often used is to apply a hybrid process in determining the initial weight of the SOM network. This study takes an approach using the cosine similarity equation to determine the initial weight of the network SOM in order to increase recognition accuracy. In addition, the localization process needs to be carried out to limit the area of the iris image being studied so that it is easy for the recognition process to be carried out. The method proposed in this study for iris recognition, namely hybrid SOM and Daugman’s algorithm, has been tested on several people by capturing the iris of the eye using a digital camera. The captured eyes have been localized first using the Daugman’s algorithm, and then the image features were extracted using the GLCM and LBP methods. In the final stage of the study, an iris recognition comparison test was performed, and the results obtained an accuracy of 85.50% using the proposed method and an accuracy of 73.50% without performing a hybrid process on the SOM network.]]>
<![CDATA[Implementation of Recommendation Systems in Determining Learning Strategies Using the Naïve Bayes Classifier Algorithm ]]>
<![CDATA[Saleh, Amir]]>;
<![CDATA[Dharshinni, NP]]>;
<![CDATA[Perangin-Angin, Despaleri]]>;
<![CDATA[Azmi, Fadhillah]]>;
<![CDATA[Sarif, Muhammad Irfan]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 1 (2023): Articles Research Volume 7 Issue 1, 2023 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v8i1.11954
<![CDATA[Recommendation systems are widely used in various fields of life to provide suggestions for a product, service, or piece of information to someone where there is an object to choose from. The recommendation system can also be applied in the field of education, especially in improving the quality of learning that occurs in schools. In this study, developing and implementing a recommendation system was used to determine the learning strategy applied in class. The system is very necessary in order to obtain effective and efficient learning in accordance with the desired learning style of students. In addition, learning that leads to students' desire to learn can make it easier for teachers to achieve predetermined learning goals. In this study, collaborative filtering techniques based on the Naive Bayes algorithm were used to determine the learning strategy. Before carrying out the recommendation process, datasets will be collected first, which are obtained from student responses through the questionnaires provided. This data will be used as training data to obtain recommendations on learning strategies that will be applied by the teacher in the classroom. After the training data is collected, the teacher will provide a response, and the results obtained will be used as testing data. From the results of implementing a recommendation system that has been built using the Naïve Bayes algorithm, the accuracy obtained is 90.91% in determining learning strategies that are appropriate to student learning styles.]]>
<![CDATA[Herbal Plant Classification Using Multi-Feature Extraction and Multilayer Perceptron ]]>
<![CDATA[Simanjuntak, Englis Franata]]>;
<![CDATA[Sipahutar, Yohannes Saputra]]>;
<![CDATA[Pasaribu, Martin Josua]]>;
<![CDATA[Saleh, Amir]]>
<![CDATA[ Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 5, No 2 (2024) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Sumatera Utara, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30596/jcositte.v5i2.20835
<![CDATA[Herbal plants used for medicine have prompted many researchers in the field of computer science to develop an efficient way to identify these plants through their leaves. This study will propose artificial neural networks, such as Multilayer Perceptron (MLP), to classify herbal plants. This method is used with feature extraction methods like the Gray Level Co-occurrence Matrix (GLCM), Hue Saturation Value (HSV), and Histogram of Oriented Gradients (HOG) to find out about the leaves' texture, color, and histogram. The dataset used was taken directly with a digital camera from various types of herbal plants that people usually see in everyday life. The dataset, which consisted of 450 images, was classified into nine classes. The entire dataset will be processed using a combined feature extraction method before the MLP method is used for clustering. This method is used to better understand the diversity of herbal plants and improve classification accuracy. The experimental results show that the combination of the feature extraction method and the MLP algorithm can achieve the highest accuracy of 95.56% in identifying various types of plants. This research provides significant benefits and contributes to the development of an herbal plant recognition system capable of accurate classification.]]>
<![CDATA[Image Segmentation Using Hybrid Clustering Algorithms for Machine Learning-Based Skin Cancer Identification ]]>
<![CDATA[Maulana, Riza]]>;
<![CDATA[Interiesta, Diva Cahaya]]>;
<![CDATA[Sofy, Annisa Kurnia]]>;
<![CDATA[Maulana, Ilham Habib]]>;
<![CDATA[Saleh, Amir]]>
<![CDATA[ Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 5, No 2 (2024) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Sumatera Utara, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30596/jcositte.v5i2.21016
<![CDATA[Early identification of skin cancer is crucial to increasing the chances of a cure and reducing mortality rates. This research aims to develop a method for identifying skin cancer using image processing techniques, specifically the hybrid clustering method. This method integrates machine learning with fuzzy c-means clustering (FCM) and hierarchical clustering (HC) segmentation techniques to segment skin cancer more accurately. Hybrid clustering is used to separate suspicious areas in skin images, resulting in more precise segmentation compared to conventional methods. The segmentation results are then used as input for various machine learning methods that are trained to recognize patterns in identifying types of skin cancer. Tests were carried out using data obtained from the Kaggle Dataset, and the results showed that the proposed method was able to achieve a high level of accuracy in identifying skin cancer. After segmentation, the ensemble learning method yielded the best identification results. The Random Forest algorithm, which is applied to process and analyze features from skin images, shows higher performance compared to other machine learning methods. Tests show that the Random Forest method with the proposed segmentation achieves an accuracy level of up to 89%, while other machine learning methods such as K-Nearest Neighbor only achieve an accuracy level of around 86%. This research makes an important contribution to the development of efficient and reliable diagnostic tools for skin cancer identification, with appropriate segmentation methods proven to increase accuracy.]]>
<![CDATA[Improving the Major Recommendation Systems: Analysis of Hybrid Naïve Bayes-based Collaborative Filtering and Fuzzy Logic ]]>
<![CDATA[Amir Saleh]]>;
<![CDATA[Sitompul, Boy Arnol]]>;
<![CDATA[Wijaya Laia, Laksana Febri]]>;
<![CDATA[Sinaga, Nicholas Ferdinan]]>
<![CDATA[ Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 8, No. 4, November 2023 ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Malang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.22219/kinetik.v8i4`.1797
<![CDATA[Major recommendation systems have been widely used to assist prospective students in choosing major that matches their interests and potential. In an effort to improve the performance of the recommendation system, this study proposed to use collaborative filtering techniques with naïve Bayes approach. In addition, this study improved the input parameters using fuzzy logic in determining the recommended majors. The methodology used started from collecting user data, including gender, academic history, interests, and other relevant attributes. The data were used to train the naïve Bayes technique by estimating the probability of feature conformity between users and students in the recommended majors. However, there were problems such as uncertainty and ambiguity in user preferences for input data. The fuzzy logic method aimed to improve the input parameters to more accurately reflect the user preferences. The results of improving the input parameters by using fuzzy logic were then used in the naïve Bayes technique to obtain recommendations for the direction that best suits the user’s preferences. The final stage of this study used evaluation metrics such as precision, recall, and f1-score to measure the performance of the recommendation system in providing accurate recommendations. The use of a hybrid of naïve Bayes and fuzzy logic algorithms obtains an accuracy value of 87.27%, a precision value of 87.33%, a recall value of 87.24%, and an f1-score value of 87.26%. These results are higher than the usual naïve Bayes model applied in major recommendation systems.]]>
<![CDATA[An Approach for Early Heart Attack Prediction Systems Using K-Means Clustering and Cosine Similarity ]]>
<![CDATA[Novita, Nanda]]>;
<![CDATA[Saleh, Amir]]>;
<![CDATA[Azmi, Fadhillah]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3324
<![CDATA[In this study, we used cosine similarity and k-means clustering to construct a system to predict heart attacks. In order to divide patient data into groups with distinct clinical profiles based on their clinical characteristics, the k-means clustering approach is used. The new patient profiles were also contrasted with predetermined risk group profiles using the cosine similarity method. Heart attack high-risk patients are those with a profile that resembles that of the high-risk category. This suggested prediction system offers numerous benefits and contributions. First, the technique helps identify individuals who are at high risk of having a heart attack, allowing for prompt intervention and treatment. Second, the technology aids in lowering the mortality and effects of a heart attack by foreseeing the possibility of one in high-risk patients. Combining the k-means clustering method and cosine similarity, this system can predict heart attacks with an accuracy and dependability of 93.71%. In order to aid medical practitioners in making wise decisions and enhancing patient care, this research offers fresh perspectives on how to understand and manage heart attacks.]]>
