Articles
<![CDATA[XGBoost Algorithm on Intrusion Detection System in Detecting Network Intrusions ]]>
<![CDATA[Mutiara Hernowo]]>;
<![CDATA[Endang Sugiharti]]>
<![CDATA[ Innovative: Journal Of Social Science Research Vol. 4 No. 1 (2024): Innovative: Journal Of Social Science Research ]]>
Publisher : <![CDATA[Universitas Pahlawan Tuanku Tambusai ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31004/innovative.v4i1.9105
<![CDATA[Saat ini, teknologi sudah menjadi kebutuhan manusia. Akibat peningkatan penggunaan internet, banyak paket data yang diteruskan ke lalu lintas jaringan tempat data berkomunikasi antara dua titik akhir (transmisi data). Aktivitas ini harus aman karena informasi pribadi pengguna bersifat rahasia. Jaringan memiliki sistem untuk menganalisis setiap data yang melewati lalu lintas dan mendeteksi data berbahaya, yang disebut Intrusion Detection System (IDS). IDS membutuhkan model deteksi untuk meningkatkan kinerjanya dalam mendeteksi intrusi. Tujuannya adalah untuk mengimplementasikan algoritma XGBoost untuk meningkatkan skor akurasi kinerja IDS menggunakan metode yang diusulkan. Dalam tulisan ini, kami mengusulkan model deteksi menggunakan algoritma XGBoost dan Sequential Feature Selection (SFS) sebagai metode pemilihan fitur. Metode-metode ini telah diuji pada dataset NSL-KDD. Melalui penelitian implementasi model yang diusulkan ini, diperoleh hasil dengan menganalisis metrik evaluasi seperti, akurasi, presisi, recall, dan f1-score. Hasilnya menunjukkan skor akurasi mencapai 99,24%. Dengan kata lain, hasilnya cukup tinggi dibandingkan penelitian sebelumnya. Dengan demikian, metode yang diusulkan dapat digunakan untuk meningkatkan kinerja IDS guna mendeteksi intrusi dan membantu jaringan menjadi lebih aman. Penelitian ini masih memerlukan pengembangan untuk penelitian selanjutnya karena teknologi terus berkembang.]]>
<![CDATA[The Effect of Augmented Reality Acceptance on E-Commerce on Cosmetic Purchase Decisions Using Combination TPB and TAM ]]>
<![CDATA[Oktaria Gina Khoirunnisa]]>;
<![CDATA[Endang Sugiharti]]>
<![CDATA[ Journal of Advances in Information Systems and Technology Vol 5 No 2 (2023): October ]]>
Publisher : <![CDATA[Department of Computer Science, Faculty of Mathematics and Natural Sciences, Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/jaist.v5i2.63743
<![CDATA[The fact that the sales of cosmetic products in Indonesia are increasing causes competition between brands to be unavoidable. One of the strategies the company prepared is to expand its marketing reach with e-commerce. But when selling cosmetic products by online new problem arises, scilicet the absence of a tester causes a lack of information about the product and how the technology is accepted. A lack of understanding about the product will affect consumer buying interest. Shopee answers this problem by providing a markerless augmented reality-based beauty cam feature. Based on this description, this study will analyze the effect of acceptance of the use of augmented reality on product purchase decisions using a combination of the Technology Acceptance Model and Theory of Planned Behavior. Data in his study was collected by distributing online questionnaires to Shopee users who have used this feature. The results of this study indicate that behavioral control variables do not affect a person's behavioral intention to use the beauty cam feature or the intention to buy cosmetic products. In addition to these correlations, all proposed correlations have a significant effect. The results of this study can stimulate future research and become a consideration for feature developers and business owners in other fields.]]>
<![CDATA[Hyperparameter Optimization Using Hyperband in Convolutional Neural Network for Image Classification of Indonesian Snacks ]]>
<![CDATA[Asyrofiyyah, Nuril]]>;
<![CDATA[Sugiharti, Endang]]>
<![CDATA[ Recursive Journal of Informatics Vol 2 No 1 (2024): March 2024 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/rji.v2i1.72720
<![CDATA[Abstract. Indonesia is known for its traditional food both domestically and abroad. Several cakes are included in favorite traditional foods. Of the many types of cakes that exist, it is visually easy to recognize by humans, but computer vision requires special techniques in identifying image objects to types of cakes. Therefore, to recognize objects in the form of images of cakes as one of Indonesian specialties, a deep learning algorithm technique, namely the Convolutional Neural Network (CNN) can be used. Purpose: This study aims to find out how the Convolutional Neural Network (CNN) works by optimizing the hyperband hyperparameter in the classification process and knowing the accuracy value when hyperband is applied to the optimal hyperparameter selection process for classifying Indonesian snack images. Methods/Study design/approach: This study optimizes the hyperparameter Convolutional Neural Network (CNN) using Hyperband on the Indonesian cake dataset. The dataset is 1845 images of Indonesian snacks which consists of 1523 training data, 162 validation data and 160 testing data with 8 classes. In training data, the dataset is divided by 82% on training data, 9% validation, and 9% testing. Result/Findings: The best hyperparameter value produced is 480 for the number of dense neurons 2 and 0.0001 for the learning rate. The proposed method succeeded in achieving a training value of 87.53%, for the validation process it was obtained 66.8%, the testing process was obtained 79.37%. Results obtained from model training of 50 epochs. Novelty/Originality/Value: Previous research focused on the application and development of algorithms for the classification of Indonesian snacks. Therefore, optimizing hyperparameters in a Convolutional Neural Network (CNN) using Hyperband can be an alternative in selecting the optimal architecture and hyperparameters.]]>
<![CDATA[Implementation of Random Forest with Synthetic Minority Oversampling Technique and Particle Swarm Optimization for Predicting Survival of Heart Failure Patients ]]>
<![CDATA[Zaaidatunni'mah, Untsa]]>;
<![CDATA[Sugiharti, Endang]]>
<![CDATA[ Recursive Journal of Informatics Vol 2 No 2 (2024): September 2024 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/rji.v2i2.76142
<![CDATA[Abstract. Heart failure is caused by a disruption in the heart’s muscle wall, which results in the heart’s inability to pump blood in sufficient quantities to meet the body’s demand for blood. The increasing prevalence and mortality rates of heart failure can be reduced through early disease detection using data mining processes. Data mining is believed to aid in discovering and interpreting specific patterns in decision-making based on processed information. Data mining has also been applied in various fields, one of which is the healthcare sector. One of the data mining techniques used to predict a decision is the classification technique. Purpose: This research aims to apply SMOTE and PSO to the Random Forest classification algorithm in predicting the survival of heart failure patients and to determine its accuracy results. Methods/Study design/approach: To predict the survival of heart failure patients, we utilize the Random Forest classification algorithm and incorporate data imbalance handling with SMOTE and feature selection techniques with PSO on the Heart Failure Clinical Records Dataset. The data mining process consists of three distinct phases. Result/Findings: The application of SMOTE and PSO on the Heart Failure Clinical Records Dataset in the Random Forest classification process resulted in an accuracy rate of 93.9%. In contrast, the Random Forest classification process without SMOTE and PSO resulted in an accuracy rate of only 88.33%. This indicates that the proposed method combination can optimize the performance of the classification algorithm, achieving a higher accuracy compared to previous research. Novelty/Originality/Value: Data imbalance and irrelevant features in the Heart Failure Clinical Records Dataset significantly impact the classification process. Therefore, this research utilizes SMOTE as a data balancing method and PSO as a feature selection technique in the Heart Failure Clinical Records Dataset before the classification process of the Random Forest algorithm.]]>
<![CDATA[Efektifitas Pengelolaan Manajemen Pergudangan Terhadap Sistem Distribusi Beras pada Pemerintah Daerah DKI Jakarta ]]>
<![CDATA[Heryadi, Muhammad Heri]]>;
<![CDATA[Nofrisel, Nofrisel]]>;
<![CDATA[Sugiharti, Endang]]>;
<![CDATA[Simarmata, Juliater]]>;
<![CDATA[Anggara, Dian Christopher]]>
<![CDATA[ Jurnal Manajemen Transportasi & Logistik (JMTRANSLOG) Vol 11, No 1 (2024): Maret ]]>
Publisher : <![CDATA[Institut Transportasi dan Logistik Trisakti ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.54324/j.mtl.v1i1.1368
<![CDATA[DKI Jakarta experienced the rice production deficit of 99.61% in 2020. The problem arised because DKI Jakarta could fulfill its rice necessity from other cities and the poor management of the warehouse and distribution system. The aim of the study is to propose a warehouse management to improve the effective distribution system. The study used qualitative descriptive research method. There were 16 officials of the warehouse management and distribution system in PT. Tjipinang Jaya Food Station as the participants. The data was processed using the credibility, transferability, dependability and confirmability tests approaches. The results of the study indicate that the warehouse management and distribution system in PT. Tjipinang Jaya Food Station is considered ineffective and inefficient in improving food security operation in DKI Jakarta. The evidence found is the absorption or the less than demand purchase of the product, which is 2,665 tons with a total demand of 688,226 tons. The problem with inequality distribution, decreased quantity in the distribution process, raw materials received delay, unfulfilled delivery of finished material to consumers and uncertainty of the warehouse utilization planning are factors needed to be restored continuously in the future.]]>
<![CDATA[Implementation Data Mining with Naive Bayes Classifier Method and Laplace Smoothing to Predict Students Learning Results ]]>
<![CDATA[Pradana, Dany]]>;
<![CDATA[Sugiharti, Endang]]>
<![CDATA[ Recursive Journal of Informatics Vol 1 No 1 (2023): March 2023 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/rji.v1i1.63964
<![CDATA[Abstract. The application of information technology in the field of education produces big data. It retains information that can be treated as useful. Having data mining, can be used to model highly useful student performance for educators performing corrective actions against weak students. Purpose: The study was to identify the application and accuracy algorithm Naive Bayes Classifier to predict students' study results. Methods: The prediction system for student learning outcomes was built using the Naive Bayes Classifier and Laplace Smoothing methods using a combination of two Information Gain and Chi Square feature selections. The experiment was carried out 2 times using different dataset comparisons. Result: In the first experiment using a dataset of 80:20, the accuracy Naive Bayes Classifier method with Laplace Smoothing and without Laplace Smoothing showed the same results as 94.937%. On the second experiment to equate dataset 60:40 results of the Naive Bayes Classifier accurate method without Laplace Smoothing only 86.076%, then score a 91.772% accuracy using the Laplace Smoothing. The improvement is caused by a probability of zero that can be worked out with Laplace Smoothing. Novelty: The selection feature process is very important in the classification process. Thus, in this study, information gain and chi square double selections of such features as information gain and so promote accuracy.]]>
<![CDATA[Optimization of support vector machine using information gain and adaboost to improve accuracy of chronic kidney disease diagnosis ]]>
<![CDATA[Listiana, Eka]]>;
<![CDATA[Muzayanah, Rini]]>;
<![CDATA[Muslim, Much Aziz]]>;
<![CDATA[Sugiharti, Endang]]>
<![CDATA[ Journal of Soft Computing Exploration Vol. 4 No. 3 (2023): September 2023 ]]>
Publisher : <![CDATA[SHM Publisher ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52465/joscex.v4i3.218
<![CDATA[Today's database is growing very rapidly, especially in the field of health. The data if not processed properly then it will be a pile of data that is not useful, so the need for data mining process to process the data. One method of data mining used to predict a decision in any case is classification, where in the classification method there is a support vector machine algorithm that can be used to diagnose chronic kidney disease. The purpose of this study is to determine the level of accuracy of the application of information gain and AdaBoost on the support vector machine algorithm in diagnosing chronic kidney disease. The use of information gain is to select the attributes that are not relevant while AdaBoost is used as an ensemble method commonly known as the method of classifier combination. In this study the data used are chronic kidney disease (CKD) dataset obtained from UCI repository of machine learning. The result of experiment using MATLAB applying information gain and AdaBoost on vector machine support algorithm with k-fold cross validation default k = 10 shows an accuracy increase of 0.50% with the exposure of the result as follows, the support vector machine algorithm has accuracy of 99.25 %, if by applying AdaBoost on the support vector machine has an accuracy of 99.50%, whereas if applying AdaBoost and information gain on the support vector machine has an accuracy of 99.75%.]]>
<![CDATA[Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures ]]>
<![CDATA[Auni, Ahmad Ramadhan]]>;
<![CDATA[Sugiharti, Endang]]>
<![CDATA[ Scientific Journal of Informatics Vol. 11 No. 4: November 2024 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/sji.v11i4.15169
<![CDATA[Purpose: Mango production can be severely impacted by diseases affecting mango plants. By leveraging artificial intelligence, the agricultural sector can automate the analysis of mango leaves to monitor plant health. The goal of this research is to improve the early detection of diseases in mango leaves to allow early treatment to minimize damage to the crops. Methods: This study employs an approach of combining two pre-trained CNN architectures, namely MobileNetV2 and DenseNet201 through concatenation method. To enhance the model’s generalization ability, various image augmentation techniques were applied during the training phase. Result: The model developed in this study achieved great performance in classifying mango leaf diseases with a testing accuracy of 99.25%. This result indicates the effectiveness of the concatenation method by outperforming the accuracy of either MobileNetV2 or DenseNet201 when implemented separately. Novelty: This research introduces a novel strategy by concatenating two pre-trained CNN architectures for mango leaf disease classification, a method not previously explored in this context. The model developed from this study has the potential to serve as a tool for the early detection and treatment of mango leaf diseases.]]>
<![CDATA[Soft voting ensemble model to improve Parkinson’s disease prediction with SMOTE ]]>
<![CDATA[Unjung, Jumanto]]>;
<![CDATA[Rofik, Rofik]]>;
<![CDATA[Sugiharti, Endang]]>;
<![CDATA[Alamsyah, Alamsyah]]>;
<![CDATA[Arifudin, Riza]]>;
<![CDATA[Prasetiyo, Budi]]>;
<![CDATA[Muslim, Much Aziz]]>
<![CDATA[ International Journal of Advances in Intelligent Informatics Vol 11, No 1 (2025): February 2025 ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/ijain.v11i1.1627
<![CDATA[Parkinson's disease is one of the major neurodegenerative diseases that affect the central nervous system, often leading to motor and cognitive impairments in affected individuals. A precise diagnosis is currently unreliable, plus there are no specific tests such as electroencephalography or blood tests to diagnose the disease. Several studies have focused on the voice-based classification of Parkinson's disease. These studies attempt to enhance the accuracy of classification models. However, a major issue in predictive analysis is the imbalance in data distribution and the low performance of classification algorithms. This research aims to improve the accuracy of speech-based Parkinson's disease prediction by addressing class imbalance in the data and building an appropriate model. The proposed new model is to perform class balancing using SMOTE and build an ensemble voting model. The research process is systematically structured into multiple phases: data preprocessing, sampling, model development utilizing a voting ensemble approach, and performance evaluation. The model was tested using voice recording data from 31 people, where the data was taken from OpenML. The evaluation results were carried out using stratified cross-validation and showed good model performance. From the measurements taken, this study obtained an accuracy of 97.44%, with a precision of 97.95%, recall of 97.44%, and F1-Score of 97.56%. This study demonstrates that implementing the soft-voting ensemble-SMOTE method can enhance the model's predictive accuracy.]]>
<![CDATA[Peran Kecerdasan Buatan Generatif Bagi Peningkatan Kompetensi Guru di SMA Muhammadiyah 2 Semarang ]]>
<![CDATA[Setiawan, Abas]]>;
<![CDATA[Arifudin, Riza]]>;
<![CDATA[Sugiharti, Endang]]>;
<![CDATA[Abidin, Zaenal]]>;
<![CDATA[Al Hakim, M. Faris]]>;
<![CDATA[Choirunnisa, Rizkiyanti]]>;
<![CDATA[Subarkah, Agus]]>
<![CDATA[ ABDIMASKU : JURNAL PENGABDIAN MASYARAKAT Vol 8, No 2 (2025): MEI 2025 ]]>
Publisher : <![CDATA[LPPM UNIVERSITAS DIAN NUSWANTORO ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.62411/ja.v8i2.2952
<![CDATA[Tantangan yang saat ini dibutuhkan oleh guru SMA adalah menciptakan inovasi pembelajaran berbasis teknologi. Saat ini kecerdasan buatan (AI) telah muncul sebagai solusi potensial untuk meningkatkan kualitas pembelajaran di tengah pesatnya kemajuan teknologi. Namun, geografi Indonesia yang luas membuat fasilitas teknologi pendidikan belum merata. Oleh karena itu, guru di SMA Muhammadiyah 2 Semarang perlu meningkatkan kompetensi literasi digitalnya, terutama untuk teknologi terkini. Program ini telah berhasil membuka wawasan guru terhadap teknologi baru dan memberikan keterampilan praktis dalam mengintegrasikan teknologi Kecerdasan Buatan Generatif ke dalam proses pembelajaran. Para guru diberikan pembekalan penggunaan teknologi ChatGPT dan Gemini untuk mempersiapkan bahan ajar. Hasil evaluasi menunjukkan bahwa guru mampu memahami dan mulai menerapkan teknologi AI dalam pembuatan materi ajar, serta merasa termotivasi untuk terus menggunakannya secara berkelanjutan dalam pembelajaran.]]>
