JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Investigation of Mobile Cloud Storage Adoption Factors in Higher Education
Get PDFMobile cloud storage provides benefits for educational institutions. Several researchers have researched cloud computing adoption, but only a few studies related to how users experience using Personal Cloud Storage Services. This research aims to investigate the adoption of the mobile cloud storage factors following the theory, as well as research that has been previously proven related to user interest in using mobile cloud storage among higher education students. This quantitative research uses data analysis techniques using GSCA to prove the theory and achieve the research goals. The research methodology consists of five main stages, namely the stage of model development and research design, the stage of preparing the instrument and its measurement, the stage of testing the instrument, the stage of survey and results, as well as the stages of analysis and discussion as well as conclusions. Five variables are investigated in this research: knowledge sharing, perceived usefulness, attitude toward using a system, trust, and intention to use. The results of hypothesis testing were conducted using GSCA; three proposed hypotheses were accepted, and one was rejected. The variables the research model can explain are 68%, and the remaining 32% are other variables not used in this study. The characteristics of respondents can provide several ways to increase the adoption of mobile cloud computing by linking research results from inferential analysis and descriptive analysis. Future research can focus on extracting these variables through user interviews regarding students' intentions to use mobile cloud computing
Introversion-Extraversion Prediction using Machine Learning
Get PDFIntroversion and extroversion are personality traits that assess the type of interaction between people and others. Introversion and extraversion have their advantages and disadvantages. Knowing their personality, people can utilize these advantages and disadvantages for their benefit. This study compares and evaluates several machine learning models and dataset balancing methods to predict the introversion-extraversion personality based on the survey result conducted by Open-Source Psychometrics Project. The dataset was balanced using three balancing methods, and fifteen questions were chosen as the features based on their correlations with the personality self-identification result. The dataset was used to train several supervised machine-learning models. The best model for the Synthetic Minority Oversampling (SMOTE), Adaptive Synthesis Sampling (ADASYN), and Synthetic Minority Oversampling-Edited Nearest Neighbor (SMOTE-ENN) datasets was the Random Forest with the 10-fold cross-validation accuracy of 95.5%, 95.3%, and 71.0%. On the original dataset, the best model was Support Vector Machine, with a 10-fold cross-validation accuracy of 73.5%. Based on the results, the best balancing methods to increase the models’ performance were oversampling. Conversely, the hybrid method of oversampling-undersampling did not significantly increase performance. Furthermore, the tree-like models, like Random Forest and Decision Tree, improved performance substantially from the data balancing. In contrast, the other models, excluding the SVM, did not show a significant rise in performance. This research implies that further study is needed on the hybrid balancing method and another classification model to improve personality classification performance
Breed Lineage Prediction of Small Ruminants Using Deep Learning
Get PDFSheep are a significant food source for humans, besides cattle and poultry. Despite its significance to Malaysian Muslims, who make up approximately 60% of the local population, the sheep supply is limited by the high mortality rate caused by fatal diseases such as foot and mouth disease (FMD) and tetanus. Infected sheep can spread food-borne bacteria, such as Escherichia coli, at various preparation phases, contaminating the meat. The objectives of this study are to identify internal and external factors that influence sheep breed lineage continuity, investigate current practices for collecting and managing data knowledge on sheep breed and hereditary diseases, and propose a sheep breed and disease data knowledge model based on the feedforward artificial neural network (FANN) deep learning method. This study utilized qualitative and quantitative data to obtain in-depth answers to the research questions, which involves collecting all the information required for the system development using the FANN deep learning method. This study found that breeding is the leading data group for tracking each sheep's ADG and BCS. Feed type, sanitization, and medication influence sheep’s daily increase and health. Collaboration, worker knowledge, and climate are recognized as external factors that potentially influence sheep's daily increase. The interview analysis also suggested attributes that could contribute to detecting breed lineage, including breed, category, ADG, and BCS. Therefore, it is recommended that future research adopt this method for other farmed animals
A Review of Neural Network Approach on Engineering Drawing Recognition and Future Directions
Get PDFEngineering Drawing (ED) digitization is a crucial aspect of modern industrial processes, enabling efficient data management and facilitating automation. However, the accurate detection and recognition of ED elements pose significant challenges. This paper presents a comprehensive review of existing research on ED element detection and recognition, focusing on the role of neural networks in improving the analysis process. The study evaluates the performance of the YOLOv7 model in detecting ED elements through rigorous experimentation. The results indicate promising precision and recall rates of up to 87.6% and 74.4%, respectively, with a mean average precision (mAP) of 61.1% at IoU threshold 0.5. Despite these advancements, achieving 100% accuracy remains elusive due to factors such as symbol and text overlapping, limited dataset sizes, and variations in ED formats. Overcoming these challenges is vital to ensuring the reliability and practical applicability of ED digitization solutions. By comparing the YOLOv7 results with previous research, the study underscores the efficacy of neural network-based approaches in handling ED element detection tasks. However, further investigation is necessary to address the challenges above effectively. Future research directions include exploring ensemble methods to improve detection accuracy, fine-tuning model parameters to enhance performance, and incorporating domain adaptation techniques to adapt models to specific ED formats and domains. To enhance the real-world viability of ED digitization solutions, this work highlights the importance of conducting testing on diverse datasets representing different industries and applications. Additionally, fostering collaborations between academia and industry will enable the development of tailored solutions that meet specific industrial needs. Overall, this research contributes to understanding the challenges in ED digitization and paves the way for future advancements in this critical field
Smart Room System for Paralysis Patients with Mindwave EEG Sensor Control
Get PDFPersons with disabilities experience physical, intellectual, mental, or sensory difficulties. One type of disability is paralysis. Paralysis is a condition where there is interference with the nerves that control body movement, causing the limbs to be unable to move. Paralyzed people will find it difficult to move without the help of others. Therefore, research was carried out by creating an intelligent room system to help persons with disabilities manage their own rooms so that they do not always have to be accompanied by a nurse. Paralyzed people can turn lights or fans on and off, and send help messages to their carers via the Telegram bot. This study used the NeuroSky Mindwave EEG headset which detects the user's brain signals with outputs in the form of attention level, relaxation level (meditation), and blink strength level. The resulting signal is processed via a PC and sent via NodeMCU to give commands in the form of turning lights and fans on or off, as well as sending messages to nurses. From this research a system was produced that could turn on the lights based on the value of Attention ≥ 70, turn on the fan based on the Meditation value ≥ 74, then the value of BlinkStrength ≥ 81 which was counted 2 times to turn off the lights, 3 times to turn off the fan, 4 times to turn off the lights and fan, and more than 4 times sending help message
Application of IoT Technologies in Seaport Management
Get PDFSeaports have a very important role in connecting freight by sea. Goods transported through seaports in the world are increasing day by day to meet human needs. This increases the pressure to apply more technologies for better port management. The world's seaports in the 4th generation, the generation in which seaports enhance connectivity to form a large network, have shown high efficiency when applying technology to port management. This optimizes port operations and connects port information into a network that improves productivity and reduces loading and unloading times. Today, the Internet of Things is the foundation for technologies to manage and optimize operations in various fields. It is considered by scientists to be a highly influential technology in the “4.0†era. The Internet of Things (IoT) technology directly affects the activities and processes of loading and unloading goods at seaports. Modern IoT-based port management technologies such as Radio Frequency Identification (RFID) and Dedicated Short Range Communications (DSRC) are contributing to the increased speed and safe movement of goods through seaports. The application of IoT in port management has become an inevitable trend and will be presented in this article. In the next generation, seaports tend to develop into smart ports based on rapidly developing technology platforms such as IoT, blockchain, and cloud computing. Smart port development also poses many issues to be resolved, including environmental issues. In this paper, the authors present some solutions to develop smart ports in an environmentally friendly manner
Optimization of Vehicle Object Detection Based on UAV Dataset: CNN Model and Darknet Algorithm
Get PDFThis study was conducted to identify several types of vehicles taken using drone technology or Unmanned Aerial Vehicles (UAV). The introduction of vehicles from above an altitude of more than 300-400 meters that pass the highway above ground level becomes a problem that needs optimum investigation so that there are no errors in determining the type of vehicle. This study was conducted at mining sites to identify the class of vehicles that pass through the highway and how many types of vehicles pass through the road for vehicle recognition using a deep learning algorithm using several CNN models such as Yolo V4, Yolo V3, Densenet 201, CsResNext –Panet 50 and supported by the Darknet algorithm to support the training process. In this study, several experiments were carried out with other CNN models, but with peripherals and hardware devices, only 4 CNN models resulted in optimal accuracy. Based on the experimental results, the CSResNext-Panet 50 model has the highest accuracy and can detect 100% of the captured UAV video data, including the number of detected vehicle volumes, then Densenet and Yolo V4, which can detect up to 98% - 99%. This research needs to continue to be developed by knowing all classes affordable by UAV technology but must be supported by hardware and peripheral technology to support the training process
End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study
Get PDFIdentifying writers using their handwriting is particularly challenging for a machine, given that a person’s writing can serve as their distinguishing characteristic. The process of identification using handcrafted features has shown promising results, but the intra-class variability between authors still needs further development. Almost all computer vision-related tasks use Deep learning (DL) nowadays, and as a result, researchers are developing many DL architectures with their respective methods. In addition, feature extraction, usually accomplished using handcrafted algorithms, can now be automatically conducted using convolutional neural networks. With the various developments of the DL method, it is necessary to evaluate the suitable DL for the problem we are aiming at, namely the classification of writer identification. This comparative study evaluated several DL architectures such as VGG16, ResNet50, MobileNet, Xception, and EfficientNet end-to-end to examine their advantages to offline handwriting for writer identification problems with IAM and CVL databases. Each architecture compared its respective process to the training and validation metrics accuracy, demonstrating that ResNet50 DL had the highest train accuracy of 98.86%. However, Xception DL performed slightly better due to the convergence gap for validation accuracy compared to all the other architectures, which were 21.79% and 15.12% for IAM and CVL. Also, the smallest gap of convergence between training and validation accuracy for the IAM and CVL datasets were 19.13% and 16.49%, respectively. The results of these findings serve as the basis for DL architecture selection and open up overfitting problems for future work
Inversed Control Parameter in Whale Optimization Algorithm and Grey Wolf Optimizer for Wrapper-based Feature Selection: A comparative study
Get PDFWhale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO) are well-perform metaheuristic algorithms used by various researchers in solving feature selection problems. Yet, the slow convergence speed issue in Whale Optimization Algorithm and Grey Wolf Optimizer could demote the performance of feature selection and classification accuracy. Therefore, to overcome this issue, a modified WOA (mWOA) and modified GWO (mGWO) for wrapper-based feature selection were proposed in this study. The proposed mWOA and mGWO were given a new inversed control parameter which was expected to enable more search area for the search agents in the early phase of the algorithms and resulted in a faster convergence speed. The objective of this comparative study is to investigate and compare the effectiveness of the inversed control parameter in the proposed methods against the original algorithms in terms of the number of selected features and the classification accuracy. The proposed methods were implemented in MATLAB where 12 datasets with different dimensionality from the UCI repository were used. kNN was chosen as the classifier to evaluate the classification accuracy of the selected features. Based on the experimental results, mGWO did not show significant improvements in feature reduction and maintained similar accuracy as the original GWO. On the contrary, mWOA outperformed the original WOA in terms of the two criteria mentioned even on high-dimensional datasets. Evaluating the execution time of the proposed methods, utilizing different classifiers, and hybridizing proposed methods with other metaheuristic algorithms to solve feature selection problems would be future works worth exploring
Comparison of K-Medoids Method and Analytical Hierarchy Clustering on Students' Data Grouping
Get PDFOne sign of how successfully the educational process is carried out on campus in a university is the timely graduation of students. This study compares the Analytic Hierarchy Clustering (AHC) approach with the K-Medoids method, a data mining technique for categorizing student data based on school origin, region of origin, average math score, TOEFL, GPA, and length study. This study was carried out at University X, which contains a variety of architectural styles. The R department, the S department, the T department, and the U department make up one of them. K-Medoids and AHC techniques Utilize the number of clusters 2, 3, and 4 and the silhouette coefficient approach. The evaluation's findings indicate a value. Although there is a linear silhouette between the AHC and K-Medoids methods, the AHC approach (departments R: 0.88, S: 0.87, T: 0.88, and U: 0.88) has a more excellent Silhouette value than K-Medoids (department R: 0.35, department S: 0.65 number of cluster 2, department T: 0.67 number of cluster 2 and program Study U: 0,52). The results of the second approach, which includes the K-Medoids and AHC procedures, are determined by the data distribution to be clustered rather than by the quantity of data or clusters. Based on this methodology, University X can refer to the grouping outcomes for the four departments with two achievements to receive results on schedule