Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
A Model of Non-ASN Employee Performance Assessment Based on the ROC and MOORA Methods
Get PDFThis study aims to assess the performance of non-ASN employees at the Human Resources Development Agency (BPSDM), East Kalimantan Province, Indonesia, to assist organizers in determining the feasibility of extending work contracts. The performance of 37 non-ASN employees has been assessed based on 12 criteria, including honesty, discipline, loyalty, responsibility, courtesy, commitment, ability and skills, neatness, communication, achievement, absence, and violations. In this study, the Rank Order Centroid (ROC) and Multi-Objective Optimization based on Ratio Analysis (MOORA) methods have been implemented to obtain rankings. Meanwhile, the confusion matrix (CM) method has also been used to measure the accuracy of both methods. Based on the experiment, the ROC method has been used to achieve the criteria weight, and the MOORA method has been utilized to rank all non-ASN employees based on the highest score. Where the CM suitability level of 81.1% has been gained so that the ranking of 37 non-ASN employees can be revealed. The study indicates that both methods can be implemented as alternative models for assessing the performance of non-ASN employees. Therefore, these methods are pretty effective, efficient, and relatively easy to use.
 
Model-Based Feature Selection for Developing Network Attack Detection and Alerting System
Get PDFIntrusion Detection Systems (IDS) still have unresolved problems, namely the lack of accuracy in attack detection, resulting in false-positive problems and many false alarms. Machine learning is one way that is often utilized to overcome challenges that arise during the implementation of IDS. We present a system that uses a machine learning approach to detect network attacks and send attack alerts in this study. The CSE-CICIDS2018 Dataset and Model-Based Feature Selection technique are used to assess the performance of eight classifier algorithms in identifying network attacks to determine the best algorithm. The resulting XGBoost Model is chosen as the model that provides the highest performance results in this comparison of machine learning models, with an accuracy rate of 99 percent for two-class classification and 98.4 percent for multi-class classification.
 
bahasa inggris
No full textClass imbalance is a serious problem that disrupts the process of semantic segmentation of satellite imagery in urban areas in Earth remote sensing. Due to the large objects dominating the segmentation process, small object are consequently limited, so solutions based on optimizing overall accuracy are often unsatisfactory. Due to the class imbalance of semantic segmentation in Earth remote sensing images in urban areas, we developed the concept of Down-Sampling Block (DownBlock) to obtain contextual information and Up-Sampling Block (UpBlock) to restore the original resolution. We proposed an end-to-end deep convolutional neural network (DenseU-Net) architecture for pixel-wise urban remote sensing image segmentation. this method to segmentation the small object in satellite imagery.The accuracy of the small object class in this study was further improved using our proposed method. This study used data from the Massachusetts Buildings dataset using Dense U-Net method and obtained an overall accuracy of 84.34%.
Class imbalance is a serious problem that disrupts the process of semantic segmentation of satellite imagery in urban areas in Earth remote sensing. Due to the large objects dominating the segmentation process, small object are consequently limited, so solutions based on optimizing overall accuracy are often unsatisfactory. Due to the class imbalance of semantic segmentation in Earth remote sensing images in urban areas, we developed the concept of Down-Sampling Block (DownBlock) to obtain contextual information and Up-Sampling Block (UpBlock) to restore the original resolution. We proposed an end-to-end deep convolutional neural network (DenseU-Net) architecture for pixel-wise urban remote sensing image segmentation. this method to segmentation the small object in satellite imagery.The accuracy of the small object class in this study was further improved using our proposed method. This study used data from the Massachusetts Buildings dataset using Dense U-Net method and obtained an overall accuracy of 84.34%
Exploring feature selection techniques on Classification Algorithms for Predicting Type 2 Diabetes at Early Stage
Get PDFPredicting early Type 2 diabetes (T2D) is critical for improved care and better T2D outcomes. An accurate and efficient T2D prediction relies on unbiased relevant features. In this study, we searched for important features to predict T2D by integrating ML-based models for feature selection and classification from 520 individuals newly diagnosed with diabetes or who will develop it. We used standard machine learning classifications, such as logistic regression (LR), Gaussian naive Bayes (NB), decision tree (DT), random forest (RF), support vector machine (SVM) with linear basis function, and k-nearest neighbors (KNN). We set out to systematically explore the viability of main feature selection representing each different technique, such as a statistical filter method (F-score), an entropy-based filter method (mutual information), an ensemble-based filter method (random forest importance), and a stochastic optimization (simultaneous perturbation feature selection and ranking (SpFSR)). We used a stratified 10-fold cross-validation technique and assessed the performance of discrimination, calibration, and clinical utility. We attained the highest accuracy of 98% using RF with the full set of features (16 features), then used RF as a classifier wrapper to select the important features. We observed a combination of SpFSR and RF as the best model with a P-value above 0.05 (P-value = 0.26), statistically attaining the same accuracy as the full features. The study's findings support the efficiency and usefulness of the suggested method for choosing the most important features of diabetic data: polyuria, gender, polydipsia, age, itching, sudden weight loss, delayed healing, and alopecia.Predicting early Type 2 diabetes (T2D) is critical for improved care and better T2D outcomes. An accurate and efficient T2D prediction relies on unbiased relevant features. In this study, we searched for important features to predict T2D by integrating ML-based models for feature selection and classification from 520 individuals newly diagnosed with diabetes or who will develop it. We used standard machine learning classifications, such as logistic regression (LR), Gaussian naive Bayes (NB), decision tree (DT), random forest (RF), support vector machine (SVM) with linear basis function, and k-nearest neighbors (KNN). We set out to systematically explore the viability of main feature selection representing each different technique, such as a statistical filter method (F-score), an entropy-based filter method (mutual information), an ensemble-based filter method (random forest importance), and a stochastic optimization (simultaneous perturbation feature selection and ranking (SpFSR)). We used a stratified 10-fold cross-validation technique and assessed the performance of discrimination, calibration, and clinical utility. We attained the highest accuracy of 98% using RF with the full set of features (16 features), then used RF as a classifier wrapper to select the important features. We observed a combination of SpFSR and RF as the best model with a P-value above 0.05 (P-value = 0.26), statistically attaining the same accuracy as the full features. The study's findings support the efficiency and usefulness of the suggested method for choosing the most important features of diabetic data: polyuria, gender, polydipsia, age, itching, sudden weight loss, delayed healing, and alopecia
Intermittent Demand Forecasting Using LSTM With Single and Multiple Aggregation
Get PDFIntermittent demand data is data with infrequent demand with varying number of demand sizes. Intermittent demand forecasting is useful for providing inventory control decisions. It is very important to produce accurate forecasts. Based on previous research, deep learning models, especially MLP and RNN-based architectures, have not been able to provide better intermittent data forecasting results compared to traditional methods. This research will focus on analyzing the results of intermittent data forecasting using deep learning with several levels of aggregation and a combination of several levels of aggregation. In this research, the LSTM model is implemented into two traditional models that use aggregation techniques and are specifically used for intermittent data forecasting, namely ADIDA and MAPA. The result, based on tests on the six predetermined data, the LSTM model with aggregation and disaggregation is able to provide better test results than the LSTM model without aggregation and disaggregation.Intermittent demand data is data with infrequent demand with varying number of demand sizes. Intermittent demand forecasting is useful for providing inventory control decisions. It is very important to produce accurate forecasts. Based on previous research, deep learning models, especially MLP and RNN-based architectures, have not been able to provide better intermittent data forecasting results compared to traditional methods. This research will focus on analyzing the results of intermittent data forecasting using deep learning with several levels of aggregation and a combination of several levels of aggregation. In this research, the LSTM model is implemented into two traditional models that use aggregation techniques and are specifically used for intermittent data forecasting, namely ADIDA and MAPA. The result, based on tests on the six predetermined data, the LSTM model with aggregation and disaggregation is able to provide better test results than the LSTM model without aggregation and disaggregation
Application of The NaΓ―ve Bayes Classifier Algorithm to Classify Community Complaints
Get PDFUnsatisfactory public services encourage the public to submit complaints/ reports to public service providers to improve their services. However, each complaint/ report submitted varies. Therefore, the first step of the community complaint resolution process is to classify every incoming community complaint. The Ombudsman of The Republic of Indonesia annually receives a minimum of 10,000 complaints with an average of 300-500 reports per province per year, classifies complaints/ community reports to divide them into three classes, namely simple reports, medium reports, and heavy reports. The classification process is carried out using a weight assessment of each complaint/ report using 5 (five) attributes. It becomes a big job if done manually. This impacts the inefficiency of the performance time of complaint management officers. As an alternative solution, in this study, a machine learning method with the NaΓ―ve Bayes Classifier algorithm was applied to facilitate the process of automatically classifying complaints/ community reports to be more effective and efficient. The results showed that the classification of complaints/ community reports by applying the NaΓ―ve Bayes Classifier algorithm gives a high accuracy value of 92%. In addition, the average precision, recall, and f1-score values, respectively, are 91%, 93%, and 92%.Unsatisfactory public services encourage the public to submit complaints/ reports to public service providers to improve their services. However, each complaint/ report submitted varies. Therefore, the first step of the community complaint resolution process is to classify every incoming community complaint. The Ombudsman of The Republic of Indonesia annually receives a minimum of 10,000 complaints with an average of 300-500 reports per province per year, classifies complaints/ community reports to divide them into three classes, namely simple reports, medium reports, and heavy reports. The classification process is carried out using a weight assessment of each complaint/ report using 5 (five) attributes. It becomes a big job if done manually. This impacts the inefficiency of the performance time of complaint management officers. As an alternative solution, in this study, a machine learning method with the NaΓ―ve Bayes Classifier algorithm was applied to facilitate the process of automatically classifying complaints/ community reports to be more effective and efficient. The results showed that the classification of complaints/ community reports by applying the NaΓ―ve Bayes Classifier algorithm gives a high accuracy value of 92%. In addition, the average precision, recall, and f1-score values, respectively, are 91%, 93%, and 92%
Sistem Pengukuran Suhu Tubuh Menggunakan AMG8833 Dan Kinect Sebagai Pencegahan Penularan Covid-19
No full textThe purpose of this study is to create an effective and safe body temperature measurement system to prevent the transmission of covid-19 using the AMG8833 and Kinect. The method of sending data uses the Internet of Thing (IoT) and face tracking with 3D form as face identification using a kinect type xbox 360 using an arduino uno and a buzzer connected to the AMG8833. AMG8833 has an infrared detector which is arranged in an 8x8 array and reads body temperature non-contact by detecting infrared energy from the body. kinect recognizes facial features based on the distance of the kinect position coordinates on the face. AMG8833 and kinect as input, Arduino uno as AMG8833 data processing and buzzer gives a sound signal if the temperature is above 37.10 0C. Body temperature measurement data was carried out 3 times, namely at a distance of 5,10 and 15cm. Measurement data from this body temperature measuring instrument are compared with a thermogun average error value of 0.11% with a difference between the maximum and minimum average body temperatures of 0.04%. It is hoped that body temperature measurements can be as a precaution against the spread of covid-19.
Pada masa pandemi covid-19, pemerintahan indonesia menetapkan kebijakan tentang protokol kesehatan (prokes) bagi masyarakat untuk mencegah semakin meluasnya penularan covid-19. Salah satu prokes yang harus dilakukan adalah mengukur suhu tubuh. Tujuan penelitian ini membuat sistem pengukuran suhu tubuh secara efektif dan aman dilakukan sebagai pencegahan penularan covid-19 menggunakan sensor AMG8833 dan kinect. Metode pengiriman data menggunakan Internet Of Thing (IoT) dan face tracking bentuk 3D sebagai identifikasi wajah pada kinect tipe xbox 360. AMG8833 memiliki inframerah detektor yang disusun secara array 8x8 dari sebuah sensor thermopile dengan menggunakan teknologi MEMS (Micro Electro Mechanical System) dan membaca suhu tubuh secara non-kontak dengan mendeteksi energi inframerah dari tubuh. Kinect sebagai input mengenali fitur wajah pada objek berdasarkan titik-titik wajah melalui sistem koordinat jarak kinect dengan wajah sebagai memasukan data pengguna secara otomatis. Hasil deteksi wajah melalui titik tersebut antara lain terletak di dahi, sisi wajah sebelah kanan dan kiri, dagu, serta titik tengah hidung. AMG8833 sebagai input pengukuran suhu tubuh, arduino uno sebagai pemprosesan data AMG8833 dan buzzer memberikan tanda bunyi jika suhu diatas 37.100C. Pengukuran suhu tubuh menggunakan AMG8833 dilakukan sebanyak 3 kali pengukuran yaitu pada jarak 5,10, dan 15Cm. Hasil pengukuran suhu tubuh menggunakan AMG8833 dibandingkan dengan pengukuran menggunakan thermogun dan didapatkan nilai rata-rata error sebesar 0,11% dengan selisih rata-rata suhu tubuh maksimal dan minimum sebesar 0,04%. Pengukuran suhu tubuh ini diharapkan dapat dilakukan sebagai pencegahan penularan covid-19
Speaker Identification Using a Convolutional Neural Network
No full textSpeech, a mode of communication between humans and machines, has various applications, including biometric systems for identifying people have access to secure systems. Feature extraction is an important factor in speech recognition with high accuracy. Therefore, we implemented a spectrogram, which is a pictorial representation of speech in terms of raw features, to identify speakers. These features were inputted into a convolutional neural network (CNN), and a CNN-visual geometry group (CNN-VGG) architecture was used to recognize the speakers. We used 780 primary data from 78 speakers, and each speaker uttered a number in Bahasa Indonesia. The proposed architecture, CNN-VGG-f, has a learning rate of 0.001, batch size of 256, and epoch of 100. The results indicate that this architecture can generate a suitable model for speaker identification. A spectrogram was used to determine the best features for identifying the speakers. The proposed method exhibited an accuracy of 98.78%, which is significantly higher than the accuracies of the method involving Mel-frequency cepstral coefficients (MFCCs; 34.62%) and the combination of MFCCs and deltas (26.92%). Overall, CNN-VGG-f with the spectrogram can identify 77 speakers from the samples, validating the usefulness of the combination of spectrograms and CNN in speech recognition applications
Klasifikasi Kematangan Tanaman Hidroponik Pakcoy Menggunakan Metode SVM
No full textPakcoy is a type of vegetable plant belonging to the Brassica family. Pakcoy plants can be cultivated using hydroponic techniques, namely plant cultivation techniques without soil media. The advantage of cultivating Pakcoy plants using hydroponic techniques is that it does not require a large area of ββland, so it is easy to apply in the yard. However, cultivation with hydroponic techniques has drawbacks such as farmers need to make regular observations to determine the harvest readiness of each plant. This causes a lack of effectiveness of farmers in cultivating Pakcoy plants. With the development of Machine Learning technology, a model can classify the maturity of Pakcoy plants based on digital image data. By applying the Support Vector Machine (SVM) Algorithm, the Machine Learning model can learn to classify a digital image of Pakcoy plants with the category "Small" to represent immature Pakcoy plants and "Large" to represent mature Pakcoy plants which results in an accuracy level of above 79%. It can be concluded that Machine Learning can be implemented in Pakcoy cultivation activities to support hydroponic farmers.
Tanaman Pakcoy merupakan tanaman jenis tanaman sayur yang tergolong dalam keluarga sawi. Tanaman Pakcoy dapat dibudidayakan dengan teknik hidroponik, yaitu teknik budidaya tanaman tanpa media tanah. Keunggulan budidaya tanaman Pakcoy menggunakan teknik hidroponik adalah tidak memerlukan lahan yang luas sehingga, mudah diterapkan di halaman rumah. Namun budidaya dengan teknik hidroponik memiliki kekurangan diantaranya petani perlu melakukan pengamatan secara rutin untuk menentukan kesiapan panen setiap tanaman. Hal ini menimbulkan kurangnya efektifitas petani dalam membudidayakan tanaman Pakcoy. Adanya perkembangan teknologi Machine Learning, sebuah model dapat mengklasifikasi kematangan tanaman Pakcoy berdasarkan data citra digital. Dengan menerapkan Algoritma Support Vector Machine (SVM), model Machine Learning dapat belajar mengklasifikasi sebuah citra digital tanaman Pakcoy dengan kategori βKecilβ untuk mewakili tanaman Pakcoy belum matang dan βBesarβ untuk mewakili tanaman Pakcoy sudah matang yang menghasilkan tingkat akurasi mencapai di atas 79%. Dapat disimpulkan bahwa Machine Learning dapat diimplementasikan pada kegiatan budidaya tanaman Pakcoy untuk mendukung petani hidroponik
The Clustering Rice Plant Diseases Using Fuzzy C-Means and Genetic Algorithm
No full textRice is an agricultural sector that is very important for Indonesia's economy. The main problem with rice plants is pest and disease control which has a hazardous impact and economic losses for farmers. The apparent characteristics of rice leaves have a greater area than other plant structures; rice leaves can be applied for the early diagnosis of rice plant diseases. The approaches employed are fuzzy C-Means (FCM) and Genetic Algorithm-Fuzzy C-Means (GA-FCM). The center of the cluster is obtained while adopting genetic algorithms for optimization. The primary dataset used in this research is Teaching Sawah Farm IPB, and the second dataset is UCI Rice Leaf Diseases. According to the comparison results, the GA-FCM optimization results in a higher level of clustering precision with a 65% optimal cluster center point on the silhouette coefficient value compared to just 60% for FCM. This research shows that the proposed method can add 5% accuracy to the clustering results in correctly identifying rice plant diseases.