Testing Processes Research Articles

Detection of new oil palm fruit bunches based on deep learning

Abstract The Indonesian oil palm plantation experiences a production rate of fresh fruit bunches and crude palm oil (CPO) influenced by the quality of fruits with excellent and uniform maturity accepted by the palm oil processing factory. The uniformity of fruit quality produced from the harvesting process through fruit maturity criteria, namely fractions 00, fraction 1, fraction 3, and fraction 4, necessitates the need for maturity detection based on deep learning with a pre-trained YOLOv5 model capable of detecting the maturity of new oil palm fruit bunches. The aim is to develop a deep learning-based maturity detection model based on visual images and analyse the deep learning algorithm’s performance by classifying the maturity level of new oil palm fruit bunches. The method collects a dataset of new oil palm fruit bunches with 4180 images. The collected dataset will be annotated with Roboflow, so the annotation results will undergo training, validation, and testing processes using the deep learning script. The result obtained for the data found to detect the ripeness levels of Fresh Fruit Bunches (FFB), shows that the YOLOv5 model demonstrates strong performance with an accuracy reaching 72.5% in testing, which falls into the category of fair annotation. These results indicate that the system created and used is functioning well.

Web accessibility and CMS. Moodle as case study

<p>The advance of ICT can be appreciated in a range of synchronous and asynchronous tools for communication that facilitate the interaction without spatio-temporal restrictions. The Web Accessibility Initiative defines guidelines to let people with disabilities access ICT. The article presents the method and the results obtained from web accessibility evaluation applied to Moodle CMS, using guidelines WCAG 2.0. The results of this study provided data to guide further research and development focused on test processes on web accessibility using specific tools, in order to improved user´s experience.</p>

RESEARCH ON ARTIFICIAL INTELLIGENCE TOOLS FOR AUTOMATING THE SOFTWARE TESTING PROCESS

The subject matter of the article is artificial intelligence (AI) tools for automating the software testing process. The rapid development of the software development industry in recent decades has led to a significant increase in competition in the IT technology market and, as a result, stricter requirements for corresponding products and services. AI-driven test automation is becoming increasingly relevant due to its ability to solve complex tasks that previously required significant human resources. The goal of the work is to investigate the possibilities of using AI technologies to automate manual testing processes, which will increase testing efficiency, reduce costs, and improve software quality. The following tasks were solved in the article: analysis of existing tools and approaches to test automation using AI; development of a conceptual model of a system that integrates AI into the testing process; exploring the potential of AI to automate various aspects of software testing, such as generating test scenarios, detecting defects, predicting errors, and automatically analyzing test results. The following methods are used: theoretical analysis of the literature and existing solutions in the field of test automation, experimental study of the effectiveness of the proposed test automation methods. The following results were obtained: the concept of a system that integrates AI technologies for automating software testing is presented. It has been found that the use of AI allows automating routine testing tasks, significantly reducing the number of human errors, and improving the quality of software products and the effectiveness of verification and validation processes. Conclusions: The development and implementation of AI-based testing automation systems are extremely relevant and promising. The use of AI technologies makes it possible to significantly increase the efficiency of testing, reduce the costs of its implementation, and improve the quality of software. The proposed approach to the development of an AI-based test automation system can be used as a basis for further research and development in this field.

Design of stochastic computational Levenberg Marquardt backpropagation-based technique to investigate temperature distribution of longitudinal moving porous fin

The improvement of thermal exchange is of utmost interest in a wide range of engineering areas. The current study focuses on thermal evaluation involving natural radiation and convection in a fractionally arranged moving longitudinal fin model placed under a magnetic field. We implement the Levenberg Marquardt backpropagation (LMB) algorithm for investigating an innovative use of stochastic numerical computation for analyzing the efficiency of the temperature distribution in a porous moving longitudinal fin. The datasets for LMB have been created using a shooting approach for dynamic systems with varying ranges of different parameters. The validation, testing, and training processes are used to simulate networks using the LMB approach for diverse scenarios of moving porous fin models. The reliability of results is assessed based on the regression measures, absolute error, error histograms, mean square error, and other metrics for fuller numerical modeling of the suggested LMB to investigate the thermal efficiency and effectiveness of porous moving fin.

Experimental and FEA Simulations Using ANSYS on the Mechanical Properties of Laminated Object Manufacturing (LOM) 3D-Printed Woven Jute Fiber-Reinforced PLA Laminates

The mechanical properties of woven jute fiber-reinforced PLA polymer laminates additively manufactured through Laminated Object Manufacturing (LOM) technology are simulated using the finite element method in this work. Woven jute fiber reinforcements are used to strengthen bio-thermoplastic PLA polymers in creating highly biodegradable composite structures that can serve as one of the environmentally friendly alternatives for synthetic composites. A LOM 3D printer prototype was designed and built by the authors. All woven jute/PLA biocomposite laminated specimens made using the built prototype in this study had their tensile and flexural properties measured using ASTM test standards. These laminated structures were modeled using the ANSYS Mechanical Composite PrepPost (ACP) module, and then both testing processes were simulated using the experimentally measured input values. The FEA simulation results indicated a close match with experimental results, with a maximum difference of 9.18%. This study served as an exemplary case study using the FEA method to predict the mechanical behaviors of biocomposite laminate materials made through a novel manufacturing process.

Tribological behaviors and wettability evolution of phenolic resin-impregnated graphite materials under water immersion condition

This study investigated the tribological behaviors of two phenolic resin-impregnated graphite samples and one non-impregnated sample under dry and water immersion using a reciprocating testing device. The frictional configuration involved a steel hemisphere sliding against the surface of the graphite samples. The influence of water immersion time before each formal test on friction coefficients was discussed. The wettability evolution during the test processes and the difference in porosity, which could significantly affect water infiltrating into the sample matrix and frictional interfaces, were associated with the variation in tribological behaviors. The worn surface morphology and element analysis results indicated that the shallow valleys and pores on the surface of graphite were gradually filled by wear debris from both the graphite samples and the harder counterpart. Based on these experimental results, a tribological mechanism of the phenolic resin-impregnated graphite materials under water immersion was developed.

Mathematical Model of Logistic Regression for Binary Classification. Part 2. Data Preparation, Learning and Testing Processes

This article reviews the theoretical aspects of logistic regression for binary data classification, including data preparation processes, training, testing, and model evaluation metrics. Requirements for input data sets are formulated, methods of coding categorical data are described, methods of scaling input features are defined and substantiated. A scheme for learning logistic regression using the gradient descent method has been developed to minimize the loss function by the appropriate adjustment of the weights of the features of the sample of objects intended for classification. Features of the construction of recurrent methods of classical and stochastic gradient descent are determined. The requirements for the organization of the data sample for the multi-stage learning model in order to avoid overtraining or undertraining of logistic regression are described. The scheme of testing the trained logistic regression is given and the main quality metrics of binary classification are described. The influence of the height of the classification threshold on the efficiency of logistic regression was noted. According to the results of the work, the directions of perspective research of logistic regression are outlined.

Dampak Pemahaman Kode Etik Profesi Akuntan Dan Idealisme Terhadap Persepsi Etika Mahasiswa Akuntansi : Peran Jender Sebagai Variabel Moderasi

Students as the nation's successors who are expected to contribute greatly in upholding the name of the country have a role to do the best, especially accounting students in disclosing the accountability of state financial reporting, starting from simulating the understanding of several ethics courses that have been given in college. The purpose of this study is to examine the effect of understanding the accountant's professional code of ethics and idealism on the ethical perceptions of accounting students with gender roles as moderating variables. In analyzing this research using quantitative methods with purposive sampling techniques to evaluate the population of accounting students in Gresik Regency and data collection was carried out through distributing online questionnaires using a Likert scale and tested using SEM PLS MGA techniques. From going through various test processes, the results showed that Gender managed to moderate the Accountant Professional Code of Ethics strongly on the Ethical Perceptions of Accountant Students. And the Accounting Professional Code of Ethics and Idealism have a positive effect on the Ethical Perceptions of Accounting Students. However, Gender did not succeed in moderating Idealism on the Ethical Perceptions of Accounting Students.

Flood Susceptibility Mapping Using Information Fusion Paradigm Integrated with Decision Trees

Accurate estimation of flood-damaged zones in a watershed is prominent in guiding a framework for developing sustainable strategies. For these purposes, several flood conditioning factor values at flooded and non-flooded points are extracted, and those points are analyzed using decision tree algorithms and eight novel information fusion techniques to get more reliable flood susceptibility mapping. The belief function values of flood susceptibility values at leaf nodes of the tree are fused by several techniques named Dempster-Shafer (DS), Fuzzy Gamma Overlay (FGO), Hesitant Fuzzy Weighted Averaging (HFWA), Hesitant Fuzzy Weighted Geometric (HFWG), Hesitant Fuzzy Weighted Ordered Averaging (HFWOA), HFWOG, Closeness coefficient (Cc) using Euclidean and Manhattan distances. The flood susceptibility values are extracted from the generated maps and are validated by receiver operating characteristics (ROC) curve parameters, and the seed cell area index (SCAI) of classified flood levels. The area under ROC (AUROC) values of training process are 0.997 for DS, HFWA, HFWOA, and Cc-Euclidean, 0.996 for Cc-Manhattan, 0.995 for FGO and 0.994 for HFWG and HFWOG. The AUROC values of the testing process are 0.951 for DS, HFWA, HFWOA, Cc-Euclidean, and Cc-Manhattan, 0.945 for FGO, 0.943 for HFWG, and 0.941 for HFWOG. True Skill Statistics values are 0.962 and 0.870 for training and testing processes. Although these techniques present excellent performance, the SCAI values versus flood susceptibility classes are fitted to assess the prediction capabilities of the techniques further. HFWA and HFWOG have the first- and second-best performances on the estimations. Hence, information fusion paradigm can be employed to combine flood conditioning factors based on a robust classification method to get reliable predictions of flood potential levels and utilize them for land use and construction planning and management.

An Investigation of Molecular Property Prediction and Classification Based on Machine Learning Algorithms

With the rapid advancement of science and technology, chemical and physical research has entered an era of complexity and high dimensionality, where traditional research paradigms struggle to optimize vast chemical parameter searches. The Machine Chemist platform was developed in this context, leveraging big data and intelligent models to automate chemical synthesis, characterization, and testing processes. This study aims to predict the y1, y2 and y3 properties and classes of 2,580 molecules based on their physicochemical properties and improve model accuracy through data analysis and modeling. Data preprocessing involved removing missing values, duplicates, and outliers using the quartile method, resulting in an analyzable dataset. A scatter plot of y2 and id suggested a univariate polynomial function relationship, leading to the construction of a univariate nonlinear regression model. The model achieved a high prediction accuracy, with a low root mean square error and a high coefficient of determination. Additionally, the relationship between class and y1~y3 , x1~x100 indicators was examined, revealing mostly nonlinear relationships. A random forest model was established to classify 2,580 molecules into 1 to 4 classes based on the properties of 200,000 chemical molecules. The model's performance was evaluated using decision trees, confusion matrices, precision, and recall metrics. Finally, the SHAP method assessed the impact of feature indicators on classification outcomes, contributing to the development of a reliable molecular category prediction model.

IoT traffic classification and anomaly detection method based on deep autoencoders

This study investigates anomaly detection of IoT device traffic using Convolutional Neural Networks (CNN) and Variational Autoencoders (VAE) to enhance the detection capability of security threats in IoT environments. A series of hardware configurations, software environments, and hyperparameters were utilized to optimize the training and testing processes of the models. The CNN model demonstrates robust classification performance, achieving an accuracy rate of 95.85% on the test dataset, effectively distinguishing between different types of IoT device traffic. Meanwhile, the VAE model exhibits proficient anomaly detection capabilities by effectively capturing abnormal patterns in the data using reconstruction loss and KL divergence. The combined use of CNN and VAE models offers a comprehensive solution to cybersecurity challenges in IoT environments. Future research directions include exploring diverse IoT traffic data, practical deployment for validation, and further optimization of model structures and parameters to improve performance and applicability.

Gene Therapies in Clinical Development to Treat Retinal Disorders.

Gene therapies have emerged as promising treatments in clinical development for various retinal disorders, offering hope to patients with inherited degenerative eye conditions. Several gene therapies have already shown remarkable success in clinical trials, with significant improvements observed in visual acuity and the preservation of retinal function.A multitude of gene therapies have now been delivered safely in human clinical trials for a wide range of inherited retinal disorders but there are some gaps in the reported trial data. Some of the most exciting treatment options are not under peer review and information is only available in press release form. Whilst many trials appear to have delivered good outcomes of safety, others have failed to meet primary endpoints and therefore not proceeded to phase III. Despite this, such trials have enabled researchers to learn how best to assess and monitor patient outcomes, which will guide future trials to greater success. In this review, we consider recent and ongoing clinical trials for a variety of potential retinal gene therapy treatments and discuss the positive and negative issues related to these trials. We discuss the treatment potential following clinical trials as well as the potential risks of some treatments under investigation. As these therapies continue to advance through rigorous testing and regulatory approval processes, they hold the potential to revolutionise the landscape of retinal disorder treatments, providing renewed vision and enhancing the quality of life for countless individuals worldwide.

Students’ understanding of vector operations: With and without physics education technology simulation

This study aims to investigate the influence of technology integration (physics education technology simulation) in physics learning. A quantitative method with a quasi-experimental post-test-only design was applied to reveal the differences in students’ abilities to operate vectors between the group that learned and tested using simulation and the group that learned using graphics only. The test consisted of 16 questions on the addition and subtraction of two vectors divided into one and two dimensions. Student response data were analyzed using descriptive statistics and Kruskal-Wallis test. The analysis results show that the vector operation score for experimental group 1, which learned vector operations through graphic learning using simulation and tested with the same simulation (86.15), is higher than experimental group 2, which learned vector operations through graphic learning using simulation (76.59), and the control group, which learned vector operations through graphic learning without simulation assistance (71.81). All three groups have higher average scores for one-dimensional than two-dimensional vector operations. They also have higher average scores for vector addition compared to vector subtraction operations. Kruskal-Wallis test results indicate a significant difference in the average vector operation scores for the three groups (ρ=0.021). This suggests that integrating technology in the learning and testing processes leads to a significant difference. Moreover, the difference is significant for one-dimensional vector operations (ρ=0.004) and not significant for two-dimensional vector operations (ρ=0.107). These findings could support the implementation of similar approaches at the university and high school levels, especially for vector-related topics, in both learning and testing processes.

Design and performance analysis of asynchronous network on chip for streaming data transmission on FPGA

The majority of the system on chip (SoC) uses the network on chip (NoC) as routing ports for data transfer from node-to-node with minimal power consumption and low latency and high throughput. This paper concentrates on the ability to model the asynchronous NoCs on the asynchronous circuits on field programmable gate arrays (FPGAs). A 3×3 NoC and its universal asynchronous receiver transmitter (UART) protocol is designed and its simulation of the Verilog hardware description language (VHDL) code is done and tested on the Artix-7 FPGA kit, the testing processes in done using the Chipscope tool. In order to meet target requirements in terms of power consumption and latency, the label switching (LS) technique is used as routing. The proposed LS-NoC with level-encoded dual-rail (LEDR) encoding technique provides throughput by registering the packet between the different routers and it helps to improve throughput and speed. The effectiveness of the data transfer is measured and analyzed through a synthesis summary in terms of lookup table’s (LUT’s), slice registers, flip flops’s (FF’s), latency, and packet delivery ratio (PDR) for the traffic pattern generator. The proposed NoC is designed for 8×8 and each port size is 21 bits including ID’s of source and destination routers. The results can be justified by following results: improvement of LUTs is about 12%, flip-flops are 7%, improvement of throughput is 23% and delay is reduced by 26%.

Enabling FuSE Security Objectives by Leveraging Cyber Survivability Methods

AbstractThe importance of system security continues to grow as systems become more complex, more connected, and more vulnerable. The INCOSE Vision 2035 sets goals for systems engineering (SE) as a discipline in enabling engineering solutions for a better world: “By 2035, cybersecurity will be as foundational a perspective in systems design as system performance and safety are today” (INCOSE, 2024). A key objective of the INCOSE Future of Systems Engineering (FuSE) Security Foundations Roadmap is to recognize system security as a fundamental part of the mission, integrated into the system architecture, and not “bolted‐on” as a separate subsystem or set of features in the detailed design. To achieve this, systems engineering must address system security early in the system lifecycle, during the mission analysis and concept development phase and ensure it is addressed as a functional requirement throughout the systems engineering lifecycle. System security needs must be treated as fundamental system capability.The INCOSE FuSE Security foundations roadmap identifies six (6) objectives and eleven (11) foundational concepts necessary to achieve the FuSE vision for system security (Dove, et al., 2021). Five of the objectives and five of the foundational concepts are directly related to systems acquisition and engineering lifecycle processes. The five key foundational concepts are: Stakeholder Alignment, Security as a Capability, Security as a Functional Requirement, Loss Driven Engineering and Modeled Trustworthiness.The Operational Test and Evaluation (OT&E) community has extensive cyber assessment and execution processes mandated through numerous Department of Defense (DoD) and individual service policies, directives and guidebooks. This paper studies several of the cybersecurity assessment and process guidebooks, analyzing the processes and methods to identify areas where systems engineering should be responsible, and which SE activities and outputs are needed to enable the requirements of each guidebook.This paper examines six OT&E cyber security guidebooks, and the methods and processes they describe to achieve system security in relation to the five foundation concepts. In addition to their test and evaluation processes, each describes systems engineering processes, activities and outputs that could be used to form the initial foundation of a system security technical process.While the original INCOSE vision statement uses the term “cybersecurity,” the FuSE Security initiative is adopting the term “system security” to emphasize that this is a system engineering responsibility as opposed to software engineering or information technology task. As a result, the analysis of the cybersecurity guidebooks will be in the context of “system security.”

PP01.77 Biomarker testing in lung cancer: perspectives and challenges concerning internal, external and reflexive testing processes in an academic medical center

PP01.77 Biomarker testing in lung cancer: perspectives and challenges concerning internal, external and reflexive testing processes in an academic medical center

Modifikasi Kereb dengan Inovasi Fitur Self-Glow Melalui Penambahan Fosforence dan Glass Bead

The increase in population in Indonesia occurs rapidly as the years go by, which is directly proportional to the need for adequate facilities and infrastructure for carrying out activities and mobilizing from one place to another. Fulfillment of multi-story parking facilities is often found in the basement. It can be supported by additional facilities that help vehicle drivers take advantage of limited land. This section is quite dark and can potentially harm drivers because it causes high installation and maintenance costs for electrical installations and lighting. In overcoming this problem, one alternative research effort is to innovate the addition of a self-glow feature by adding phosphorescence powder and glass beads to modifications to conventional carriages' road dividers. Using a layer variation of 30%P1 20%P2; (15%F1;60%T1); (20%F2;80%T2); (25%F3;100%); top coat 100:50 tested for drying time, adhesion test, low-temperature test, softening point test, shelf life test, gradation test, and reflectivity test according to SNI 03-6450-2000. Glass waste was chosen as an additional material because it has the same properties as glass beads in reflecting light. Phosphorescence powder can glow in the dark, while glass beads can reflect light. Then it went through various testing processes (30%P1; 25%; 100%F3), which is an efficient variation and has the quality of the results of the luminescence test and reflectivity test, namely Qd 417, and it can be seen that the water-based phosphorescence coating can light up to 50 minutes at exposure 46.2 lux.

Effective Automation of End-to-End Testing for OTT Platforms

The rapid evolution of Over-the-Top (OTT) platforms has reshaped the digital media landscape, necessitating robust testing strategies to ensure seamless user experiences and service reliability. Effective automation of end-to-end testing for OTT platforms emerges as a crucial strategy to address the complexities associated with diverse content delivery, user interactions, and varying device compatibilities. This paper explores the challenges and best practices in automating end-to-end testing processes for OTT platforms, focusing on integrating various testing tools, frameworks, and methodologies to achieve comprehensive coverage and efficiency. OTT platforms deliver content directly over the internet, bypassing traditional broadcast and cable channels. This direct-to-consumer approach introduces unique challenges in testing, such as ensuring consistent performance across different devices, network conditions, and content types. Additionally, the dynamic nature of content libraries and frequent updates necessitate rigorous testing to identify and rectify potential issues proactively. Automation, with its capacity to simulate real-world usage scenarios, streamline repetitive tasks, and enhance testing accuracy, plays a pivotal role in addressing these challenges. The paper first outlines the primary challenges in end-to-end testing for OTT platforms. These challenges include the need for cross-platform compatibility, performance under varying network conditions, and the ability to handle diverse content formats and streaming protocols. The complexities are compounded by the requirement for real-time performance metrics and user experience evaluations, which demand a sophisticated testing infrastructure.

Web-based Educational Game Application to Improve the Ability to Identifying the Main Idea in Indonesian Language Learning

The limited provision of innovative, interesting, and technology-based learning media can affect the running of teaching and learning activities in schools to be less than optimal, especially in Indonesian subjects. The purpose of this research is to create a web-based educational game media application to improve the ability to identify the main idea in Indonesian language subjects on learning entrepreneurship material for grade V elementary school students. This study uses a type of Research and Development research with the ADDIE research and development model. Techniques applied in data collection are test techniques through pretests and posttests, as well as non-test techniques through observation activities, interviews, data in the form of documents, and questionnaires or questionnaires. The questionnaire instrument in data collection is in the form of a rating scale that has passed testing from media experts, material experts, practitioners, and students. The sample for this research was 24 fifth-grade elementary school students. Quantitative descriptive analysis techniques and qualitative descriptive analysis are the two techniques used in this study. The data analysis process in this study uses the SPSS 29 application which includes several test processes including the normality test, homogeneity test, t-test, and N-Gain test. The results of the study obtained that the web-based educational game learning media developed is very feasible and effective to be applied to the Indonesian language learning process to improve the understanding and learning outcomes of fifth-grade elementary school.

Fake News Detection and Classification with Recurrent Neural Network Based Deep Learning Approaches

Events happening in the world are transmitted to the end user through the news channel. The information transmitted from the news is generally considered to be accurate. However, there may be errors or lies in the information that circulates on the news channels. At the same time, this news has an impact on serious environments, such as the economy. In social networks where data sharing is increasing, news data is piling up uncontrollably. In these data piles, there is real information as well as different information that is not real commercial, political, or sales-orientated. False information and data expand faster as a result of sharing false information by users. This news directly affects users, causing erroneous transactions, misinformation, or financial loss. For the stated reasons, automatic fake news classification systems are proposed in this article by combining natural language processing with Recurrent Neural Network (RNN) based deep learning methods. The proposed systems were tested on a dataset containing 23,481 fake news and 21,417 real news using general performance metrics. As a result of the test processes, the proposed BiLSTM method provided 99,72% accuracy, while the proposed GRU method accessed 97,50% accuracy.