Jurnal Teknologi dan Sistem Komputer
ISSN / EISSN : 2620-4002 / 2338-0403
Current Publisher: Diponegoro University (10.14710)
Total articles ≅ 240
Latest articles in this journal
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 255-262; doi:10.14710/jtsiskom.2020.13591
This study examines the application of a landslide disaster monitoring system based on soil activity information that utilizes humidity, temperature, and accelerometer sensors. An artificial highland was built as the research object, and the landslide process was triggered by supplying the system with continuous artificial rainfall. The soil activities were observed through its slope movement, temperature, and moisture content, utilizing an accelerometer, temperature, and humidity sensors both in dry and wet conditions. The system could well observe the soil activities, and the obtained data could be accessed in real-time and online mode on a website. The time delay in sending the data to the server was 2 seconds. Moreover, the characteristics of soil porosity and its relevance to soil saturation level due to water pressure were studied as well. Kinetic study showed that the water adsorption to soil followed the intraparticle diffusion model with a coefficient of determination R2 0.99043. The system prototype should be used to build the information center of disaster mitigation, particularly in Indonesia.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 228-233; doi:10.14710/jtsiskom.2020.13733
Cacao pod's ideal harvesting time is when it is about to be ripe. Immature harvest would result in hard cacao beans not suitable for fermentation, while overripe cacao pods lead to fungal-infected, defective, and poor-quality yields. The demand for high-quality cacao products is expected to rise due to advancing technology in the present. Pre-harvesting needs to provide optimal identification of which amongst the pods are ripened enough and ready for the next stage of the cacao process. This paper recommends a technique to determine the ripeness of cacao. Nine hundred thirty-three cacao samples were used to collect thumping audio data at five different pod's exocarp locations. Each sound file is 1 second long, creating 4665 cacao sound file datasets at 16kHz sample rate and 16-bit audio bit depth. The process of the Mel-Frequency Cepstral Coefficient Spectogram was then applied to extract recognizable features for the training process. The deep learning method integrated was a convolutional neural network (CNN) to classify the cacao sound successfully. The experimental design model's output exhibits an accuracy of 97.50 % for the training data and 97.13 % for the validation data. While the overall accuracy mean of the classification system is 97.46 %, whether the cacao is unripe or ripe.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 239-245; doi:10.14710/jtsiskom.2020.13734
Civet coffee is considered as highly marketable and rare. This specialty coffee has a special flavor and higher price relative to regular coffee, and it is restricted in supply. Establishing a straightforward and efficient approach to distinguish Civet coffee for quality; likewise, consumer protection is fundamental. This study utilized visible spectroscopy as a non-destructive and quick technique to obtain the absorbance, ranging from 450 nm to 650 nm, of the civet coffee and non-civet coffee samples. Overall, 160 samples were analyzed, and the total spectra accumulated was 960. The data gathered from the first 120 samples were fed to the classification learner application and were used as a training data set. The remaining samples were used for testing the classification algorithm. The study shows that civet coffee bean samples have lower absorbance values in visible spectra than non-civet coffee bean samples. The process yields 96.7 % to 100 % classification scores for quadratic discriminant analysis and logistic regression. Among the two classification algorithms, logistic regression generated the fastest training time of 14.050 seconds. The application of visible spectroscopy combined with data mining algorithms is effective in discriminating civet coffee from non-civet coffee.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 222-227; doi:10.14710/jtsiskom.2020.13660
CCTV cameras have an important function in the field of public service, especially for convenience. The objects recorded through CCTV cameras are processed into information to support service satisfaction in the community. This study uses the function of CCTV for people counting from objects recorded by a camera. Currently, the process of detecting and tracking people takes a long time to detect all frames. In this study, the frame selection into keyframes uses the mutual information entropy method. The keyframes processing uses the Histogram of Oriented Gradient (HOG) and Kalman filter methods. The proposed method results F1 value of 0.85, recall of 76 %, and precision of 97 % with winStride parameter (12,12), scale 1.05, and the distance of the human object to CCTV 4 meters.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 210-216; doi:10.14710/jtsiskom.2020.13590
Genetic algorithm (GA) can improve the classification of the face recognition process in the principal component analysis (PCA). However, the accuracy of this algorithm for the smart home security system has not been further analyzed. This paper presents the accuracy of face recognition using PCA-GA for the smart home security system on Raspberry Pi. PCA was used as the face recognition algorithm, while GA to improve the classification performance of face image search. The PCA-GA algorithm was implemented on the Raspberry Pi. If an authorized person accesses the door of the house, the relay circuit will unlock the door. The accuracy of the system was compared to other face recognition algorithms, namely LBPH-GA and PCA. The results show that PCA-GA face recognition has an accuracy of 90 %, while PCA and LBPH-GA have 80 % and 90 %, respectively.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 234-238; doi:10.14710/jtsiskom.2020.13407
An open challenge in bioinformatics is the analysis of the sequenced metagenomes from the various environments. Several studies demonstrated bacteria classification at the genus level using k-mers as feature extraction where the highest value of k gives better accuracy but it is costly in terms of computational resources and computational time. Spaced k-mers method was used to extract the feature of the sequence using 111 1111 10001 where 1 was a match and 0 was the condition that could be a match or did not match. Currently, deep learning provides the best solutions to many problems in image recognition, speech recognition, and natural language processing. In this research, two different deep learning architectures, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), trained to approach the taxonomic classification of metagenome data and spaced k-mers method for feature extraction. The result showed the DNN classifier reached 90.89 % and the CNN classifier reached 88.89 % accuracy at the genus level taxonomy.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 201-209; doi:10.14710/jtsiskom.2020.13476
Information that can be in the form of text, image, audio, and video, is a valuable asset that needs to be secured from unauthorized parties. This research aims to study the implementation of Vigenere cipher 128 (VC-128) and square rotation to secure text information. The square rotation is applied to increase the security of the encryption results obtained from VC-128. The randomness of the rotation results was measured using Shannon entropy based on the distance between characters, and the Avalanche Effect measured changes in the encryption results compared to the original text. The square rotation can increase the randomness of the VC-128 encryption results, as indicated by an increase in entropy values. The highest increase in entropy of 34.8 % occurs in repetitive texts with the square size that produces optimal entropy was a 9x9 medium-size square. The Avalanche effect for each test data shows inconsistent results ranging from 44.5 % to 49 %.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 246-254; doi:10.14710/jtsiskom.2020.13648
Hotel occupancy rates are the most important factor in hotel business management. Prediction of the rates for the next few months determines the manager's decision to arrange and provide all the needed facilities. This study performs the optimization of lag parameters and k values of the k-Nearest Neighbor algorithm on hotel occupancy history data. Historical data were arranged in the form of supervised training data, with the number of columns per row according to the lag parameter and the number of prediction targets. The kNN algorithm was applied using 10-fold cross-validation and k-value variations from 1-30. The optimal lag was obtained at intervals of 14-17 and the optimal k at intervals of 5-13 to predict occupancy rates of 1, 3, 6, 9, and 12 months later. The obtained k-value does not follow the rule at the square root of the number of sample data.
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 192-200; doi:10.14710/jtsiskom.2020.13657
Land suitability evaluation has a vital role in land use planning aimed to increase food production effectiveness. Palm oil is a leading and strategic commodity for Indonesian people, which is predicted consumption will exceed production in the future. This study aims to evaluate palm oil land suitability using a spatial decision tree algorithm that is conventional decision tree modification for spatial data classification with adding spatial join relation. The spatial dataset consists of eight explanatory layers (soil nature and characteristics), and a target layer (palm oil land suitability) in Bogor District, Indonesia. This study produced three models, where the best model was obtained based on optimizing accuracy (98.18 %) and modeling time (1.291 seconds). The best model has 23 rules, soil texture as the root node, two variables (drainage and cation exchange capacity) are uninvolved, with land suitability visualization obtains percentage S2 (29.94 %), S3 (53.16 %), N (16.57 %), and water body (0.33 %).
Jurnal Teknologi dan Sistem Komputer, Volume 8, pp 217-221; doi:10.14710/jtsiskom.2020.13619
Blood donation is the process of taking blood from someone used for blood transfusions. Blood type, sex, age, blood pressure, and hemoglobin are blood donor criteria that must be met and processed manually to classify blood donor eligibility. The manual process resulted in an irregular blood supply because blood donor candidates did not meet the criteria. This study implements machine learning algorithms includes kNN, naïve Bayes, and neural network methods to determine the eligibility of blood donors. This study used 600 training data divided into two classes, namely potential and non-potential donors. The test results show that the accuracy of the neural network is 84.3 %, higher than kNN and naïve Bayes, respectively of 75 % and 84.17 %. It indicates that the neural network method outperforms comparing with kNN and naïve Bayes.