Jurnal Ilmu Komputer dan Informasi
Not a member yet
247 research outputs found
Sort by
An alternative for kernel SVM when stacked with a neural network
Full text linkMany studies stack SVM and neural network by utilzing SVM as an output layer of the neural network. However, those studies use kernel before the SVM which is unnecessary. In this study, we proposed an alternative to kernel SVM and proved why kernel is unnecessary when the SVM is stacked on top of neural network. The experiments is done on Dublin City LiDAR data. In this study, we stack PointNet and SVM but instead of using kernel, we simply utilize the last hidden layer of the PointNet. As an alternative to the SVM kernel, this study performs dimension expansion by increasing the number of neurons in the last hidden layer. We proved that expanding the dimension by increasing the number of neurons in the last hidden layer can increase the F-Measure score and it performs better than RBF kernel both in term of F-Measure score and computation time
Improving Remote Sensing Change Detection Via Locality Induction on Feed-forward Vision Transformer
Full text linkThe main objective of Change Detection (CD) is to gather change information from bi-temporal remote sensing images. The recent development of the CD method makes use of the recently proposed Vision Transformer (ViT) backbone. Despite ViT being superior to Convolutional Neural Networks (CNN) at modeling long-range dependencies, ViT lacks a locality mechanism, a critical property of pixels that comprise natural images, including remote sensing images. This issue leads to segmentation artifacts such as imperfect changed region boundaries on the predicted change map. To address this problem, we propose LocalCD, a novel CD method that imposes the locality mechanism into the Transformer encoder. Particularly, it replaces the Transformer's feed-forward network using an efficient depth-wise convolution between two convolutions. LocalCD outperforms ChangeFormer by a significant margin. Specifically, it achieves an F1-score of 0.9548 and 0.9243 on CDD and LEVIR-CD datasets
Land Cover Segmentation of Multispectral Images Using U-Net and DeeplabV3+ Architecture
Full text linkThe application of Deep Learning has now extended to various fields, including land cover classification. Land cover classification is highly beneficial for urban planning. However, the current methods heavily rely on statistical-based applications, and generating land cover classifications requires advanced skills due to their manual nature. It takes several hours to produce a classification for a province-level area. Therefore, this research proposes the application of semantic segmentation using Deep Learning techniques, specifically U-Net and DeepLabV3+, to achieve fast land cover segmentation. This research utilizes two scenarios, namely scenario 1 with three land classes, including urban, vegetation, and water, and scenario 2 with five land classes, including agriculture, wetland, urban, forest, and water. Experimental results demonstrate that DeepLabV3+ outperforms U-Net in terms of both speed and accuracy. As a test case, Landsat satellite images were used for the Karawang and Bekasi Regency areas
Improving IT Assets Management with ITIL 4 Framework
Full text linkIT Asset Management (ITAM) is crucial for organizations as it enables efficient utilization of IT resources, cost reduction, and risk mitigation. Horangi, a startup company, recognizes the importance of asset optimization and aims to enhance its ITAM service. To achieve this, researcher conducts research to identify a suitable framework as a solid foundation. ITIL 4, a widely adopted IT service management framework, is chosen, along with the Continual Service Improvement and Service Value Chain models. These models provide guidelines and recommendations to identify weaknesses and improve current processes while enabling continuous improvement in response to the dynamic IT landscape. The research employs a qualitative approach, utilizing in-depth interviews, document research, and the ITIL 4 guidebook. The study aims to provide recommendations and a foundation for developing guidelines and workflows in ITAM within the company. However, a limitation of this research is not much research related to ITIL 4 in ITAM area and cannot proceed until the implementation of recommendations due to funding constraints and approval processes. To overcome this limitation, it is suggested that future research includes the implementation process to obtain more optimal evaluation results
A Dynamic-Bayesian-Network-Based Approach to Predict Immediate Future Action of an Intelligent Agent
Full text linkPredicting immediate future actions taken by an intelligent agent is considered an essential problem inhuman-autonomy teaming (HAT) in many fields, such as industries and transportation, particularly toimprove human comprehension of the agent as their non-human counterpart. Moreover, the results of suchpredictions can shorten the human response time to gain control back from their non-human counterpartwhen it is required. An example case of HAT that can be benefitted from the action predictor is partiallyautomated driving with the autopilot agent as the intelligent agent. Hence, this research aims to develop anapproach to predict the immediate future actions of an intelligent agent with partially automated drivingas the experimental case. The proposed approach relies on a machine learning method called naive Bayesto develop an action classifier, and the Dynamic Bayesian Network (DBN) as the action predictor. Theautonomous driving simulation software called Carla is used for the simulation. The results show that theproposed approach is applicable to predict an intelligent agent’s three-second time-window immediate futureaction
Implementation Genetic Algorithm for Optimization of Kotlin Software Unit Test Case Generator
Full text linkUnit testing has a significant role in software development and its impacts depend on the quality of test cases and test data used. To reduce time and effort, unit test generator systems can help automatically generate test cases and test data. However, there is currently no unit test generator for Kotlin programming language even though this language is popularly used for android application developments. In this study, we propose and develop a test generator system that utilizes genetic algorithm (GA) and ANTLR4 parser. GA is used to obtain the most optimal test cases and data for a given Kotlin code. ANTLR4 parser is used to optimize the mutation process in GA so that the mutation process is not totally random. Our model results showed that the average value of code coverage in generated unit tests against instruction coverage is 95.64%, with branch coverage of 76.19% and line coverage of 96.87%. In addition, only two out of eight generated classes produced duplicate test cases with a maximum of one duplication in each class. Therefore, it can be concluded that our optimization with GA on the unit test generator is able to produce unit tests with high code coverage and low duplication
Classification of Clove Leaf Blister Blight Disease Severity Using Pre-trained Model VGG16, InceptionV3, and ResNet
Full text linkClove is one of the precious plants produced in Indonesia. Clove has many benefits for humans, but clove cultivation often experiences problems due to disease attacks, including Leaf Blister Blight Disease(CDC). The handling of CDC disease is carried out based on the severity of the symptoms that can be seen on the affected leaves. This research was conducted to obtain a CDC disease classification model, so appropriate treatment can be carried out. This study used the pre-trained VGG16, InceptionV3, and ResNet models for classification. VGG16 got the highest average accuracy of 96.7%. Aside from that, k-fold cross validation improved the model's accuracy
Temporal Action Segmentation in Sign Language System for Bahasa Indonesia (SIBI) Videos Using Optical Flow-Based Approach
Full text linkSign language (SL) is vital in fostering communication for the deaf and hard-of-hearing communities. Continuous Sign Language Translation (CSLT) is a work that translates sign language into spoken language. CSLT translation is done by changing continuous forms into isolated signs. Segmenting morpheme signs from phrase signs has several challenges, such as the availability of annotated datasets and the complexity of continuous gesture movements. The Indonesian Sign Language (SIBI) system follows Indonesian grammatical norms, including word formation, in contrast to other sign languages with rules derived from their spoken language. In SIBI, a word can consist of a root word and an affix word. Therefore, temporal action segmentation in SIBI is important to reconstruct the results of translating each sign into spoken Indonesian sentences. This research uses an optical flow approach to segment temporal actions in SIBI videos. Optical flow methods that calculate changes in intensity between adjacent frames can be used to determine the occurrence of sign movement or vice versa to determine the delay between sign movements. The absence of intensity differences between the two frames indicates the boundary between sign gestures. This study tested the use of dense optical flow on videos containing SIBI sentences taken from 3 signers. Evaluation is done on several parameters in the dense optical flow algorithm, such as threshold size, PyrScale, and WinSize, to obtain the best accuracy. This paper shows that the optical flow algorithm successfully performs segmentation, as measured by Perf and F1r. The experimental results showed that the highest Perf and F1r yields were 0.8298 and 0.8524, respectively
Rethinking Smart Keyboard Layout to Aid Strong Password Creation
Full text linkIn an era marked by increasing digitization and the omnipresence of smartphones, the importance of robustpassword security cannot be overstated. With the ever-growing threat of cyberattacks, there is a pressing needfor user-friendly tools that facilitate the creation of strong and unique passwords. Traditional alphanumerickeyboard layouts (physical or virtual) have remained largely unchanged for decades, relying on the sameQWERTY layout initially designed for typewriters. However, these layouts may not be optimal for generatingstrong passwords. This paper focuses on tailoring virtual keyboard layouts on smartphones specifically forstrong password creation. For this, we have performed extensive user surveys to see if the presence ofdedicated rows for digits and special characters (essential in any strong password) allows users to createstronger passwords compared to regular smartphone keyboard layout. Apart from that, we also investigatedthe optimal assignment of characters, digits, and special characters and their groupings in a single soft key.The findings from the detailed user experiment suggested optimal settings for a smartphone virtual keyboard(for Android) like- diagonal length for good typing speed (approximately between 8.38 and 9.41 cm), andkey density (0.88 to 1.21 keys/cm2) which produces the least error without sacrificing the strength ofpasswords created using those layouts. We hope the outcome of this paper will help designers to aid virtualkeyboard layouts for smartphones that can motivate and create strong passwords without sacrificing usability
Automated Ultrasound Object Segmentation Using Combinatorial Active Contour Method
Full text linkActive Contour (AC) is an algorithm widely used in segmentation for developing Computer-Aided Diagnosis (CAD) systems in ultrasound imaging. Existing AC models still retain an interactive nature. This is due to the large number of parameters and coefficients that require manual tuning to achieve stability. Which can result in human error and various issues caused by the inhomogeneity of ultrasound images, such as leakage, false areas, and local minima. In this study, an automatic object segmentation method was developed to assist radiologists in an efficient diagnosis process. The proposed method is called Automatic Combinatorial Active Contour (ACAC), which combines the simplification of the global region-based CV (Chan-Vese) model and improved-GAC (Geodesic Active Contour) for local segmentation. The results of testing with 50 datasets showed an accuracy value of 98.83%, precision of 95.26%, sensitivity of 86.58%, specificity of 99.63%, similarity of 90.58%, and IoU (Intersection over Union) of 82.87%. These quantitative performance metrics demonstrate that the ACAC method is suitable for implementation in a more efficient and accurate CAD system