Human Error Research Articles

Robotic-assisted total knee arthroplasty is associated with the use of thinner polyethylene liners compared to navigation-guided and manual techniques.

The purpose of this study was to examine the effects of intraoperative technology use on the rate of using polyethylene liners 15 mm or greater during primary total knee arthroplasty (TKA). There were 103,295 implants from 16,386 primary unilateral TKAs performed on 14,253 patients at a single institution between 1 January2018, and 30 June2022, included in the current study. Robotic assistance and navigation guidance were used in 1274 (8%) and 8345 (51%) procedures, respectively. The remaining 6767 TKAs (41%) were performed manually. Polyethylene liners were manually identified and further subcategorised by implant thickness. Patients who underwent robotic-assisted TKA were younger (p < 0.001) and more likely to be male (p < 0.001) compared to patients who underwent navigation-guided or manual TKAs. Average polyethylene liner thickness was similar between groups (10.5 ± 1.5 mm for robotic-assisted TKAs, 10.9 ± 1.8 mm for navigation-guided TKAsand 10.8 ± 1.8 mm for manual TKAs). The proportions of polyethylene liners 15 mm or greater used were 4.9%, 3.8%and 1.9% for navigation-guided, manual and robotic-assisted procedures, respectively (p < 0.001). Multivariate regression analyses demonstrated that navigation-guided (odds ratio [OR]: 2.6, 95% confidence Interval [CI]: [1.75-4.07], p < 0.001) and manual (OR: 2.0, 95% CI: [1.34-3.20], p = 0.001) procedures were associated with an increased use of polyethylene liners 15 mm or greater. Robotic-assisted TKA was associated with a lower proportion of polyethylene liners 15 mm or greater used compared to navigation-guided and manual TKA. These findings suggest that robotic assistance can reduce human error via a more precise cutting system, limit over-resection of the tibia and flexion-extension gap mismatchand ultimately allow for more appropriately sized implants. Level III, retrospective cohort study.

Analysis of The Influence of CNC Milling Macro Programs and Sub-programs Mazak on The Effectiveness Manufacturing Cover of Pressure Cylinder Using CAM

CNC machines allow computer programming to control the movement and actions of the machine, enabling more precise and repeatable production. However, in operating a CNC machine, good and efficient programming is essential. To optimize the use of CNC machines, it is necessary to optimize the number of NC program blocks that include the concept of macros and sub-programs. An effective CNC program, along with the proper use of macros and sub-programs, can speed up the production process, reduce human error, and increase accuracy. The research method used is comparative research by comparing using macro programs and manual programming, in this case comparing the number of solid trajectories and the number of program lines in the design using the simulation method using the Autodesk Fusion 360 application. So that the optimal number of movements will be obtained through the row value in the NC program. Macros and sub- programs allow users to easily change or modify CNC programs without having to rewrite the entire program. This increases flexibility in producing various types of products. It is concluded that optimization using macro and sub-programs provides a significant reduction in the number of program blocks in the case of the machining process for manufacturing the cover of pressure cylinder. This reduction in program blocks can help improve efficiency and sustainability in the development of modified machining processes.

Enhancing Brain Tumor Classification: A CNN-Based Approach with InceptionV3 and Xception

Brain tumors are among the most aggressive and deadly diseases, with a very short life expectancy at the highest grade. To combat this, early detection and treatment are crucial.In this approach, MRI images are used to analyze brain abnormalities. The manual investigation of brain tumor classification is a time-consuming task, and there might be possibilities of human errors. Hence, accurate analysis in a short span of time is essential. This approach presents the automatic brain tumor classification algorithm using a highly accurate Convolutional Neural Network (CNN), InceptionV3 and Xception algorithm for classification of Glioma, Meningioma and No tumor. The brain part is initially segmented by a thresholding approach followed by a morphological operation. The brain MRI is classified using CNN, Inceptionv3, and Xceptionv3 algorithms. The system's performance is evaluated using precision, recall, F1 score, and accuracy parameters.

Maritime accident analysis and reduction technique for analysing maritime collision accidents

ABSTRACT The Human Error and Reduction Technique (HEART) is a robust method consisted of both qualitative and quantitative steps. The HEART method has been utilized to analysed the human reliability in various industries. In maritime safety research, understanding human error's role in accidents is crucial. This study introduces a novel methodology integrating the HEART method with the 4M framework and TOPSIS analysis to comprehensively assess human error's interplay with other accident factors. By categorizing generic tasks and error-producing conditions (EPC) into man, machine, media, and management domains, the methodology reveals intricate relationships among accident factors. Additionally, TOPSIS analysis facilitates quantitative evaluation, enhancing decision-making by assigning weights to identified factors. The methodology offers a systematic approach to identify critical areas for intervention, such as improving lookout tasks and communication. Application of this methodology can enhance maritime safety practices by providing actionable insights into accident prevention strategies. Through its holistic and quantitative approach, this study contributes to advancing maritime safety research and fostering a safer operational environment.

Automated Code Review Tool

As software development undergoes continual evolution, the assurance of code quality remains paramount in the development lifecycle. This research paper introduces an innovative Automated Code Review Tool engineered to augment and streamline the code review process. The tool capitalizes on advanced static code analysis, machine learning algorithms, and industry best practices to automate the detection of code quality issues, security vulnerabilities, and compliance with coding standards. The Automated Code Review Tool addresses the inherent challenges of manual code reviews, including human error, time constraints, and inconsistencies. Through automation, developers can expedite the identification and resolution of potential issues, thereby enhancing overall code quality and software reliability. Key features of the tool encompass intelligent pattern recognition, real-time feedback, and customizable rule sets, enabling development teams to tailor the tool to their project-specific requirements. Leveraging machine learning algorithms facilitates the tool's continuous learning from past reviews, thereby adapting to evolving coding practices and emerging security threats. This paper presents the architectural framework and design principles underpinning the Automated Code Review Tool, emphasizing its capacity to foster collaboration among development teams, reduce time-to-market, and ultimately contribute to the development of more robust and secure software. A comprehensive evaluation of the tool's efficacy across diverse development environments is conducted, offering insights into the practical implications of embracing automated solutions in real-world contexts. Keywords: Automated Code Review Tool, Code quality, Static code analysis, Machine learning algorithms, Coding standards, Manual code reviews, Human error, Time constraints, etc.

Automatic classification and segmentation of blast cells using deep transfer learning and active contours.

Acute lymphoblastic leukemia (ALL) presents a formidable challenge in hematological malignancies, necessitating swift and precise diagnostic techniques for effective intervention. The conventional manual microscopy of blood smears, although widely practiced, suffers from significant limitations including labor-intensity and susceptibility to human error, particularly in distinguishing the subtle differences between normal and leukemic cells. To overcome these limitations, our research introduces the ALLDet classifier, an innovative tool employing deep transfer learning for the automated analysis and categorization of ALL from White Blood Cell (WBC) nuclei images. Our investigation encompassed the evaluation of nine state-of-the-art pre-trained convolutional neural network (CNN) models, namely VGG16, VGG19, ResNet50, ResNet101, DenseNet121, DenseNet201, Xception, MobileNet, and EfficientNetB3. We augmented this approach by incorporating a sophisticated contour-based segmentation technique, derived from the Chan-Vese model, aimed at the meticulous segmentation of blast cell nuclei in blood smear images, thereby enhancing the accuracy of our analysis. The empirical assessment of these methodologies underscored the superior performance of the EfficientNetB3 model, which demonstrated exceptional metrics: a recall specificity of 98.5%, precision of 95.86%, F1-score of 97.16%, and an overall accuracy rate of 97.13%. The Chan-Vese model's adaptability to the irregular shapes of blast cells and its noise-resistant segmentation capability were key to capturing the complex morphological changes essential for accurate segmentation. The combined application of the ALLDet classifier, powered by EfficientNetB3, with our advanced segmentation approach, emerges as a formidable advancement in the early detection and accurate diagnosis of ALL. This breakthrough not only signifies a pivotal leap in leukemia diagnostic methodologies but also holds the promise of significantly elevating the standards of patient care through the provision of timely and precise diagnoses. The implications of this study extend beyond immediate clinical utility, paving the way for future research to further refine and enhance the capabilities of artificial intelligence in medical diagnostics.

ANALYSIS OF ACCIDENT DATA AT PT X FOR THE 2018-2022 PERIOD USING THE HFACS-MINING INDUSTRY FRAMEWORK METHOD

The mining industry is a high-risk industrial activity. Human factors have been identified as the most common cause of major accidents in the mining industry. The Incident Management System of PT X, which is a company in exploration, mining, processing, and marketing sector of copper, gold and silver concentrate, part of the state-owned mining holding enterprise Mining Industry Indonesia, documented 322 cases of accidents within the 2018-2022 period. This research aims to analyze accident data at PT X using the Human Factor Analysis and Classification System-Mining Industry (HFACS-MI) framework. Methods. This research collected qualitative data for 322 accident cases at PT X in 2018-2022 from the incident management system database categorized as recordable injuries. Factors causing the accident were coded using the HFACS-MI framework. Accident data analysis used descriptive statistics. Results. The study findings revealed that 84% of all accidents involved contractor workers and 16% involved permanent workers at PT X. The results of the analysis using the HFACS-MI framework showed that each layer or level contributes to accidents, namely external factors by 44%, organizational influence by 68%, unsafe leadership by 90%, preconditions for unsafe acts by 99%, and unsafe acts by 99.7%. Conclusion. These findings emphasize the need to reduce the number of human errors during mining operations to reduce the current accident trend. The HFACS-MI framework has proven to be a valuable tool for robust accident analysis of human factors in mining.

Lightweight Convolutional Network with Integrated Attention Mechanism for Missing Bolt Detection in Railways

Railway infrastructure safety is a paramount concern, with bolt integrity being a critical component. In the realm of railway maintenance, the detection of missing bolts is a vital task that ensures the stability and safety of tracks. Traditionally, this task has been approached through manual inspections or conventional automated methods, which are often time-consuming, costly, and prone to human error. Addressing these challenges, this paper presents a state-of-the-art solution with the development of a lightweight convolutional neural network (CNN) featuring an integrated attention mechanism. This novel model is engineered to be computationally efficient while maintaining high accuracy, making it particularly suitable for real-time analysis in resource-constrained environments commonly found in railway inspections. The proposed CNN utilises a distinctive architecture that synergises the speed of lightweight networks with the precision of attention-based mechanisms. By integrating an attention mechanism, the network selectively concentrates on regions of interest within the image, effectively enhancing the model’s capability to identify missing bolts with remarkable accuracy. Comprehensive testing showcases a remarkable 96.43% accuracy and an impressive 96 F1-score, substantially outperforming existing deep learning frameworks in the context of missing bolt detection. Key contributions of this research include the model’s innovative attention-integrated approach, which significantly reduces the model complexity without compromising detection performance. Additionally, the model offers scalability and adaptability to various railway settings, proving its efficacy not just in controlled environments but also in diverse real-world scenarios. Extensive experiments, rigorous evaluations, and real-time deployment results collectively underscore the transformative potential of the presented CNN model in advancing the domain of railway safety maintenance.

SISTEM PELAPORAN PENCATATAN AKUNTANSI ATAS PENDAPATAN PAJAK KENDARAAN BERMOTOR DENGAN MENGGUNAKAN METODE CASH BASIS PADA LAYANAN SAMSAT KELILING

AbstractRegional Revenue Management Center for Kab. Cirebon 1 Sumber is the center of an organization or agency that is under the local government which has responsibility for receiving regional revenues through coordinating and collecting taxes, levies, tax sharing, balancing funds and others. This study aims to design, implement, analyze, and implement.The data collection methodology used in a study is observation. The system used in this application program is PHP (Hypertext Preprocessor) as the web, MySQL as the database design, using the Google Chrome browser and using a cash-based method (cash basis). In reporting daily receipts at the central office for regional revenue management in the Cirebon Regency, 1 source is still using the manual, namely using HVS paper, there is accumulation of files, data recording errors, and in making reports less efficient and effective. cirebon 1 source is illustrated by using a running flowchart accompanied by explanatory narration, then made computerized into a flowmap to be applied to the system so as to minimize the occurrence of human errors, file stacking, lost data, to be more efficient and effective. Keywords: Income, Motor Vehicle Tax, Cash Basis, Mobile Samsat

Transforming the University HR on Boarding Process with RPA

The HR Onboarding Assistant project employs Robotic Process Automation (RPA) to enhance the efficiency of on boarding in education institutions. This initiative utilizes a well-structured RPA system with bots, data integration, security measures, and user-friendly interfaces to automate tasks, reduce errors, and improve the onboarding experience. It also supports ongoing optimization and data-driven decision-making for colleges and universities. This initiative addresses these challenges by introducing a meticulously designed RPA architecture. The architecture encompasses a suite of RPA bots, an orchestration layer, and compliance measures. Each component collaborates to automate specific tasks, thereby reducing manual workload, eliminating human errors, and accelerating the onboarding timeline. The project offers a comprehensive solution that includes a user-friendly interface for HR professionals, real-time notifications. Furthermore, the architecture accommodates ongoing optimization, and continuous monitoring. It is designed to foster a culture of data-driven decision - making, ensuring that the onboarding process evolves and adapts to the institution's needs.

Classification model for chlorophyll content using CNN and aerial images

Chlorophyll content is usually used as a quantitative measurement of plant health. The chlorophyll content is also a continuous number of data type, leading to a regression approach when developing the deep learning model. The regression model will predict the chlorophyll content in number format, which requires experts to analyse the outcome. Nevertheless, the analysis of the outcome could possibly lead to human error in diagnosing the plant’s health condition. Therefore, this study proposed a classification approach in developing a deep learning model to analyse the plant’s health condition without human intervention. The classification approach requires a discrete group for dependent variables instead of continuous numbers. When forming the chlorophyll content index groups in this study, which are low, optimum and high levels, two research studies were combined to form the groups, which were (1) the product of the standard range of nitrogen value in mango plant and (2) the correlation analysis between nitrogen value and chlorophyll content index. The classification model in this study used transfer learning algorithms, which were InceptionV3, DenseNet121 and ResNet50, with the canopy-scale level of mango plant RGB images with complex leaf structures in an uncontrolled and open area. Based on the findings, the classification model could classify the chlorophyll content index levels on both mango plant images, which were infected and not infected with black sooty mould. The finding also shows that a clearer distribution pattern of spectral information extracted from the mango plant images can influence the performance result of the classification model. Besides that, the starting point of the Digitization Footprint for this study site across the development stages of the classification model was 308.5756 MB/ha. Finally, the overall accuracy performances for the classification models that used the transfer learning algorithms, which were InceptionV3, DenseNet121, and ResNet50, and trained using the images of the mango plant infected with pest were 96.49 %, 92.98 %, and 89.47 %, respectively, and for using the images of the mango plant not infected with pest were 88.10 %, 78.57 %, and 69.05 %, respectively.

Enhancing the automatic facies classification of Brazilian presalt acoustic image logs with SwinV2-Unet: Leveraging transfer learning and confident learning

Facies classification of image logs plays a vital role in reservoir characterization, especially in the heterogeneous and anisotropic carbonate formations of the Brazilian presalt region. Although manual classification remains the industry standard for handling the complexity and diversity of image logs, it has the notable disadvantages of being time consuming, labor intensive, subjective, and nonrepeatable. Recent advancements in machine learning offer promising solutions for automation and acceleration. However, previous attempts to train deep neural networks for facies identification have struggled to generalize to new data due to insufficient labeled data and the inherent intricacy of image logs. In addition, human errors in manual labels further hinder the performance of trained models. To overcome these challenges, we develop adopting the state-of-the-art SwinV2-Unet to provide depthwise facies classification for Brazilian presalt acoustic image logs. The training process incorporates transfer learning to mitigate overfitting and confident learning to address label errors. Through a k-fold cross-validation experiment, with each fold spanning more than 350 m, we achieve an impressive macro F1 score of 0.90 for out-of-sample predictions. This significantly surpasses the previous model modified from the widely recognized U-Net, which provides a macro F1 score of 0.68. These findings highlight the effectiveness of the used enhancements, including the adoption of an improved neural network and an enhanced training strategy. Moreover, our SwinV2-Unet enables a highly efficient and accurate facies analysis of the complex yet informative image logs, significantly advancing our understanding of hydrocarbon reservoirs, saving human effort, and improving productivity.

Ensuring Sustainable Hospitality: A Case Study on Occupational Health and Safety Governance at Ros-In Hotel

Workplace accidents often stem from worker negligence, human error, and insufficient management, including substandard occupational health and safety measures. Case studies, a common qualitative research method, utilize interviews and observations for primary data collection. In a specific case study at Hotel Ros-In, Yogyakarta, the Human Resources Manager was the key informant, participating in a 60-minute interview with three sub-themes: Covid-19 Post-Pandemic Regulation, Occupational Health and Safety, and Environmental Health. During the interview, Ros-In Hotel exhibited a robust commitment to complying with Ministry of Tourism and Creative Economy guidelines on hygiene, health, safety, and environmental sustainability. In the industrial sector, effective health and safety governance is crucial for maintaining consumer confidence and ensuring facilities meet stringent standards, protecting both consumers and workers. Strong safety protocols actively reduce workplace accidents and occupational diseases, fostering a safer work environment. This commitment not only benefits employees' well-being but enhances the company's overall reputation. Companies like Ros-In Hotel, through adherence to regulatory guidelines and robust safety measures, play a vital role in establishing a secure working atmosphere, instilling confidence in consumers and the broader community.

Socio-economic Challenges in COVID Detection using Transfer Learning-Based Methods

Healthcare systems are at risk of collapsing unless significant structural and transformative measures are taken. Despite the global economy generating an additional 40 million jobs in the health sector by 2030, the World Health Organization projects a shortage of 9.9 million physicians, nurses, and midwives during the same period (WHO, 2016). The core of innovation in the healthcare industry lies in automation systems, particularly in the realm of image detection. As the ratio of healthcare workers to patients decreases, the integration of robotics and artificial intelligence plays a crucial role in bridging the gap. These technologies not only compensate for the declining workforce but also bring a level of accuracy and precision that eliminates the potential for human error in image detection processes. In this paper we focus on the COVID-19 pandemic that presents significant socio-economic challenges, impacting various aspects of daily life, including health, the economy, and social development. The need for chest X-ray (CXR) scans is rising due to pneumonia being a critical and common complication of COVID-19. Early detection and diagnosis are pivotal in curbing the spread of the virus, prompting the utilization of the reverse transcription polymerase chain reaction (RT-PCR) as the predominant screening technology. Nevertheless, the task's complexity, time-consuming nature, and reported insensitivity in this research emphasize the need for alternative approaches. CXR is a widely employed screening tool for lung-related diseases due to its straightforward and cost-effective application. In this paper, we have deployed different transfer learning methods to detect COVID-19 using chest X-ray images such as VGG19, ResNet-50, and InceptionResnetV2. The findings of our results indicate that the fine-tuned model utilizing the transfer learning and data augmentation techniques enhances the efficiency of COVID-19 detection. We performed a comparison of pre-trained networks and identified the InceptionResNetV2 model as having the highest classification performance with an accuracy of 97.33%.

Dynamic reliability analysis of angular contact ball bearing based on maximum entropy quadratic fourth moment method*

ABSTRACT Bearing failure occurs when the dynamic contact stress exceeds the yield strength of the bearing material during operation. To minimise the risk of bearing failure, a new reliability theory method is proposed based on the stress-strength model of bearings, incorporating random input variables to analyse the reliability of angular contact ball bearings (ACBBs) and quantify their dynamic performance. The maximum entropy quadratic fourth moment method is used to calculate the probability distribution of maximum orthogonal shear stress-strength of bearing, and the maximum entropy principle is used to obtain the approximation of the minimum human error factors. Additionally, reliability-based sensitivity indices are derived to investigate the parametric significance of random input variables. Using B218 bearing as an example, the engineering application of this method in dynamic reliability and reliability-based sensitivity analysis is illustrated. Monte Carlo simulation is performed to verify the accuracy and effectiveness of the method to provide benchmark results. The results show that the Poisson’s ratio have a greater influence on the dynamic reliability of ACBBs than other parameters. Improving parameters such as ball diameter, raceway groove curvature radius and contact angle can also improve the reliability of bearings to some extent.

Implicit communication in cyclist-vehicle interaction: Examining the influence of driving dynamics in interactions with turning (automated) vehicles on cyclists' perceived safety, behavioral intention, and risk anticipation

Successful and safe management of interactions between cyclists and motorized vehicles often includes implicit communication, such as vehicle motion signals. While the introduction of automated vehicles (AVs) is anticipated to increase safety for cyclists by eliminating human error, it is still unclear how they should communicate implicitly in complex traffic scenarios. The turning maneuver constitutes a complex and ambiguous scenario, as it involves vehicle deceleration even when there is no intention to halt for the cyclist, proceeding straight ahead. A video-based laboratory study incorporating a bicycle setup examined the influence of four driving dynamics and automation status on cyclists' risk anticipation, perceived safety, and intention to continue to cycle through an intersection. Forty-two participants viewed videos of an oncoming vehicle making a left turn at an intersection from the perspective of a cyclist traveling straight through the intersection. The results indicated that participants perceived early and continuous braking of the vehicle ("passive yield") as the most favorable approach (reduced risk anticipation, higher perceived safety, and greater intention to continue to cycle through the intersection), even when compared to later but stronger braking ("active yield"). The objectively riskiest maneuver that would result in a collision ("collision") was evaluated as the least desirable. A rule-violating yet objectively safe maneuver (accelerating to exit the conflict area before the cyclist; "no yield") led to increased risk anticipation but not to lower perceived safety or reduced intention to continue to cycle through the intersection compared to active yield. The displayed automation status had minimal influence overall, although participants in the passive yield condition expressed greater uncertainty regarding their intention to continue to cycle through the intersection in interactions with AVs compared to MVs. It appears that natural driving dynamics exhibited by "good" human drivers could represent a promising approach to ensuring the safety and comfort of cyclists in interactions with AVs. Here, early and continuous braking is preferable to later and stronger braking.

Unsafe-Net: YOLO v4 and ConvLSTM based computer vision system for real-time detection of unsafe behaviours in workplace

AbstractUnsafe behaviour is a leading cause of death or injury in the workplace, including many accidents. Despite regular safety inspections in workplaces, many accidents occur as a result of breaches of occupational health and safety protocols. In these environments, despite efforts to prevent accidents and losses in hazardous environments, human error cannot be completely eliminated. In particular, in computer-based solutions, automated behaviour detection has low accuracy, is very costly, not real-time and requires a lot of time. In this study, we propose Unsafe-Net, a hybrid computer vision approach using deep learning models for real-time classification of unsafe behaviours in workplace. For the Unsafe-Net, a dataset is first specifically created by capturing 39 days of video footage from a factory. Using this dataset, YOLO v4 and ConvLSTM methods are combined for object detection and video understanding to achieve fast and accurate results. In the experimental studies, the classification accuracy of unsafe behaviours using the proposed Unsafe-Net method is 95.81% and the average time for action recognition from videos is 0.14 s. In addition, the Unsafe-Net has increased the real-time detection speed by reducing the average video duration to 1.87 s. In addition, the system is installed in a real-time working environment in the factory and employees are immediately alerted by the system, both audibly and visually, when unsafe behaviour occurs. As a result of the installation of the system in the factory environment, it has been determined that the recurrence rate of unsafe behaviour has been reduced by approximately 75%.

An Implementation of Blockchain Technology in Forensic Evidence Management

The importance of crime forensic data in the criminal justice system is paramount. However, traditional methods of storing this sensitive information have been plagued by issues such as the risk of tampering, human error, and cyber-attacks. This paper proposes a ground breaking solution that leverages Block chain technology to create a tamper-sproof, decentralized repository for crime forensic data. Unlike existing techniques, which often rely on manual documentation or centralized servers, the proposed block chain-based system offers inherent data integrity, auditability, and security features. By shifting to a decentralized model, we not only reduce the risk of unauthorized alterations but also facilitate a more transparent and trustworthy environment for all stakeholders involved in the judicial process. The paper delves into the architectural considerations, security features, and potential challenges associated with implementing this blockchain-based system. Preliminary results indicate that this approach could significantly enhance the credibility and reliability of crime forensic data, thereby contributing to a more just and effective criminal justice system

A comparative study of pre-processing methods to improve glioma segmentation performance in brain MRI using deep learning

Background: Glioma is the most common brain tumor in adult patients and requires accurate treatment. The delineation of tumor boundaries must be accurate and precise, which is crucial for treatment planning. Currently, delineating boundaries for tumors is a tedious, time-consuming task and may be prone to human error among oncologists. Therefore, artificial intelligence plays a vital role in reducing these problems. Objective: This study aims to find a relationship between improving image enhancement and evaluating the performance of deep learning models for segmenting glioma image data on brain MRI images. Materials and methods: The BraTs2023 dataset was used in this study. The image dataset was converted from three dimensions to two dimensions and then subjected to pre-processing via four image enhancement techniques, including contrast-limited adaptive histogram equalization (CLAHE), gamma correction (GC), non-local mean filter (NLMF), and median and Wiener filter (MWF). Subsequently, it was evaluated for structural similarity index (SSIM) and mean squared error. The deep learning segmentation model was created using the U-Net architecture and assessed for dice similarity coefficient (DSC), accuracy, precision, recall, F1-score, and Jaccard index for tumor segmentation. Results: The performance of enhanced image results for CLAHE, GC, NLMF, and MWF techniques shows SSIM values of 0.912, 0.905, 0.999, and 0.911, respectively. The dice similarity coefficient (DSC) for segmentation without image enhancement was 0.817. The DSC of segmentation for CLAHE, GC, NLMF, and MWF techniques were 0.818, 0.812, 0.820, and 0.797, respectively. Conclusion: The enhanced image technique could affect the performance of tumor segmentation. by the enhanced image for use in a trained model may increase or decrease performance depending on the chosen image enhancement technique and the parameters determined by each method.

THE DESIGN OF THE SUTI (STUDENT PROJECTION) APPLICATION WITH THE PHP PROGRAM FOR EDUCATION PLANNING

Objective: The research objective is to design a student projection application that is needed in educational planning.   Theoretical reference: Student projection is a process of predicting the number of students in the future which is necessary to make plans for the future.   Methods: The research methodology is to design the application using PHP (Hypertext Preprocessing) programme. After that, a trial was conducted to see the effectiveness of the application. The results were compared with data processing manually and through the application.   Results and Conclusion: The PHP application produces a student projection application in education planning called SUTI (Student Projection) application. This application can provide efficiency in the calculation process and also minimise errors or human error.   Research implications: Planning requires the prediction of future data. To get the future data, projections are made. With this projection application, it can help calculate data projections needed in education planning.   Originality/value: This SUTI application is a new thing that can help in the process of efficient calculation of data projections needed in education planning.