Search

Seiring dengan perkembangan jumlah penggunaan Internet of Things yang terus meningkat dan meluas. Ancaman keamanan pada jaringan IoT juga meningkat. Terdapat beberapa teknik yang diterapkan untuk mengatasi ancaman keamanan ini. Salah satunya adalah teknik untuk mengklasifikasi suatu aktivitas yang termasuk dalam serangan atau bukan beserta jenis serangannya. Machine learning dapat dimanfaatkan untuk proses pengklasifikasian ini. Diantara algoritma machine learning yang dapat digunakan untuk penelitian ini adalah pendekatan algoritma Decision Tree dan K-Nearest Neighbor. Penelitian ini bertujuan untuk mendapatkan hasil klasifikasi terbaik untuk mendeteksi jenis serangan jaringan IoT baik dalam klasifikasi biner maupun klasifikasi multikleas. Dalam penelitian ini memanfaatkan Dataset Edge-IIoTset Cyber Security Dataset of IoT & IIoT. Hasil nilai evaluasi yang didapatkan menunjukkan bahwa performa algoritma Decision Tree lebih baik dibandingkan dengan Algoritma KNN. Dengan selisih nilai presisi, recall, F1-score, dan akurasi secara berurutan adalah 0.15, 0.18, 0.17 dan 0.08 dalam klasifikasi biner. Sedangkan dalam klasifikasi multikelas mendapatkan nilai selisih antar kedua algoritma sebesar 0.26, 0.20, 0.22, dan 0.23 secara berurutan untuk presisi, recall, F1-score, dan akurasi.

River water quality could be determined by understanding the capacity of pollutants in a water body. Fuzzy C-Means (FCM) is one of the fuzzy clustering methods for determining river water quality by measuring water quality parameters, that is, dissolved oxygen (DO) and total dissolved solids (TDS). The FCM algorithm is an effective fuzzy clustering algorithm for grouping data but often produces local and inconsistent optimal solutions due to the partition matrix's random initialisation process. Therefore, this study proposes to modify the FCM algorithm to be precise in the partition matrix initialisation process using several distance concepts. The purpose of the proposed algorithm modification is to get more consistent FCM clustering results and minimise stop iterations. The validation process for the clustering results uses the FCM algorithm, and the FCM modification algorithm uses three parameters, namely the Partition Coefficient Index (PCI), Partition Entropy Index (PEI) and Silhouette Score (SS). The experiments were conducted with three replications and using various distance concepts. The results showed that the number of iterations stopped in the FCM algorithm has different values for PCI, PEI, SS, and stop iterations and objective functions in each trial. On the contrary, the FCM modification algorithm has consistent PCI, PEI, and SS values, and the number of iterations stops with fewer iterations. Therefore, the modified algorithm for initialising the partition matrix can be used in the fuzzy C-means clustering algorithm. [ABSTRACT FROM AUTHOR]

SD Muhammadiyah Sangonan 1 has implemented fingerprint attendance, where teachers and staff record their attendance when they arrive and leave. Attendance records are still manually recorded by administrative personnel, and attendance reporting is limited to attendance recapitulation. In short, the efficiency of managing teacher and staff attendance administration is still low. Therefore, this research aims to improve the efficiency of teacher and staff administration through the implementation of image processing technology for fingerprint attendance. The planned stages of the research are planning, fingerprint attendance system development, administration system training, and program evaluation. In its implementation, this program has proven to be effective in improving the effectiveness of SD Muhammadiyah Sangonan 1 Godean’s school administration in terms of easier and faster attendance data processing. The outputs achieved include mass media news and videos.

The very dense breast of mammogram image makes the Radiologists often have difficulties in interpreting the mammography objectively and accurately. One of the key success factors of computer-aided diagnosis (CADx) system is the use of the right features. Therefore, this research emphasizes on the feature selection process by performing the data mining on the results of mammogram image feature extraction. There are two algorithms used to perform the mining, the decision tree and the rule induction. Furthermore, the selected features produced by the algorithms are tested using classification algorithms: k-nearest neighbors, decision tree, and naive bayesian with the scheme of 10-fold cross validation using stratified sampling way. There are five descriptors that are the best features and have contributed in determining the classification of benign and malignant lesions as follows: slice, integrated density, area fraction, model gray value, and center of mass. The best classification results based on the five features are generated by the decision tree algorithm with accuracy, sensitivity, specificity, FPR, and TPR of 93.18%; 87.5%; 3.89%; 6.33% and 92.11% respectively. [ABSTRACT FROM AUTHOR]