SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Automated Printed Circuit Board Inspection System using NI Vision Builder and NI MyRio
Full text linkTo improve flaw identification in contemporary electronics manufacturing, this study introduces an automated printed circuit board (PCB) inspection system that integrates NI Vision Builder with NI MyRIO. The device effectively detects flaws like missing parts, open circuits, and over-etched traces by utilizing a high-resolution camera and sophisticated methods including color plane extraction and pattern matching. Real-time visualization, classification, and automated data recording are made possible via a LabVIEW-based interface, which makes the inspection process easy to use. A 92% accuracy rate was attained during testing on both bare PCBs and PCB assemblies, indicating better performance than conventional techniques. Although multi-layer and subsurface defect detection still presents difficulties, the system provides a scalable and affordable solution with the possibility to incorporate machine learning and sophisticated imaging in the future for increased adaptability
Sentiment analysis of youtube comments on the palestine-israel conflict: Performance comparison of SVM, KNN, and RFC
No full textThe Palestine-Israel conflict, rooted in territorial and religious identity disputes in the Middle East, notably over the sanctity of Jerusalem, is impacted by various political, economic, and social factors. This study employs text-mining techniques to analyze the sentiment of YouTube comments concerning the conflict. Utilizing data collected via the YouTube API, the study preprocesses, analyzes sentiment, and classifies comments using three machine learning algorithms: K-Nearest Neighbors (K-NN), Random Forest Classifier (RFC), and Support Vector Machine (SVM). The categorization report measures are utilized to compare how well the models performed in classifying estimation as positive or negative. Outflanking all other classifiers, the Irregular Woodland Classifier (RFC) accomplishes 78curacy with accuracy rates of 0.76 for positive and 0.79 for negative assumptions. With a precision rate of 77%, SVM illustrates an inclination in favor of negative sentiments, though K-NN, with an exactness rate of 60%, shows an imbalance favoring negative over positive estimations
Digital image based IoT intelligent fire detection with telegram notification
Full text linkDue to inadequate handling, fire disasters often result in significant losses and even loss of life. A fire detection system is essential, especially in places prone to fire. In this study, a digital image-based IoT system was built using the YOLO (You Only Look Once) algorithm to detect and provide fire warnings quickly and accurately. This research was conducted to develop a fire detection system from existing research on IoT devices by combining it with digital image processing technology with the YOLOv8 algorithm, as well as integrating the IoT system into the Telegram instant messaging application. This study also combines a fire detection system with a fire sensor, MQ-2 temperature sensor, and MQ-2 smoke sensor. The study results show that the YOLOv8 nano model with ESP32-CAM can detect small flames from candles up to a distance of 220 cm. The ESP32 fire sensor can detect small flames up to a distance of 90 cm and large flames up to a distance of 140 cm. VPS can be sent to the Telegram application, just as the LM35 temperature sensor detects temperatures above 50ºC and the MQ-2 smoke sensor detects smoke levels above 450 ppm. All data obtained can be displayed on the VPS dashboard and the Telegram application
Design and construction of website-based e-commerce applications for selling food products in the semarang region with payment gateway integration
Full text linkDigital transformation has driven a shift in transactions from traditional systems to e-commerce platforms, which have become the cornerstone of the digital economy. However, existing e-commerce platforms often fail to fully meet the needs of SMEs, particularly regarding flexible withdrawal of sales proceeds and consumer education about products. This study aims to design a website-based e-commerce application with the main features of a flexible fund withdrawal system and product education. This system is developed using the Waterfall System Development Life Cycle (SDLC) model. The implementation of the application creation uses the Laravel framework integrated with the Midtrans API for secure and flexible payment management. This application is equipped with various features, such as product catalogs, shopping carts, order tracking, and reviews, with functional testing carried out through black-box testing methods to ensure the application meets user needs. The results of the study show that web-based e-commerce applications are able to support flexible transactions, expand market reach, and strengthen the local e-commerce ecosystem. From this study, it can be concluded that website design plays an important role in answering challenges, especially increasing the security and convenience of direct fund withdrawal transactions for SMEs
Batik: souvenirs with local wisdom in tourism destinations
No full textBatik is one of Indonesia's iconic cultural heritages with great potential as a leading product in the creative economy sector and a typical souvenir of tourist destinations. However, the batik industry faces various challenges, such as low labor costs, lack of design and production technology innovation, and minimal utilization of business intelligence to support exports to global markets. This study aims to identify opportunities and challenges in developing batik as a competitive tourist destination souvenir in the international market. Using the methods of data collection and consolidation, information needs analysis, and strategy development, this research proposes a framework for mapping batik potential. Government support through regulations and marketing strategies for batik as a craft art includes market penetration, market development, product development, and diversification. A strategic approach that integrates innovation, sustainability, and community empowerment is expected to expand batik's role as a cultural symbol as well as a significant export commodity
Implementation of standard operating procedures for make up room for guest comfort at hotel grandhika pemuda semarang
No full textThis study aims to explain the implementation of Standard Operating Procedures (SOP) for making up rooms at Hotel Grandhika Pemuda Semarang with a focus on guest comfort. SOP for making up rooms is a work guideline that ensures that the cleaning and arranging of rooms are carried out according to the standards set by the hotel, thus providing a comfortable stay experience for guests. The research method uses a qualitative descriptive approach with data collection techniques through direct observation, interviews with supervisors, and documentation studies. The results of the study indicate that the implementation of SOP for making up rooms is consistently able to improve the cleanliness, tidiness, and comfort of hotel rooms. However, there are several obstacles, such as the lack of ongoing training for staff and time constraints in the cleaning process when the occupancy rate is high. The conclusion that can be drawn is that with optimization efforts through routine training, stricter supervision, and effective work time management. Implementation of good make up room SOP can increase guest comfort and the reputation of Hotel Grandhika Pemuda Semarang as a hotel that prioritizes service quality
Guava Disease Classification Using EfficientNet and Genetic Algorithm-Optimized XGBoost
Full text linkGuava is an evergreen plant in the Myrtaceae family, is renowned for its adaptability and noteworthy nutritional benefits. However, guava production has experienced a substantial decline in recent years due to various diseases affecting the fruit. Farmers typically employ manual inspection to identify these diseases, a method that is time-consuming, labor-intensive, and susceptible to errors. This underscores the necessity for an automated classification model capable of accurately diagnosing guava fruit diseases. While numerous machine learning and deep learning models have been developed for agricultural disease detection, research on combining deep transfer learning as a feature extractor with machine learning classifiers remains relatively limited. Addressing this research gap, the proposed model integrates the strengths of both approaches, achieving an impressive accuracy of 98.62%, surpassing the performance reported in previous studies. This encouraging outcome underscores the potential of hybrid models in enhancing guava fruit disease classification, paving the way for more efficient and scalable agricultural management solutions
Melanoma detection on skin images using deep learning based on convolutional neural network (CNN)
Full text linkMelanoma is a life-threatening skin cancer that poses challenges in regions with limited access to specialized medical personnel, such as Papua, Indonesia. Early diagnosis is essential, but accurate detection is hindered by the scarcity of dermatologists. This study develops a melanoma detection system using computer vision, utilizing the VGG16 architecture enhanced with the Convolutional Block Attention Module (CBAM) and fine-tuning via transfer learning. The model was trained on a dataset comprising melanoma and non-melanoma images, with data augmentation to address class imbalance. The model achieved an accuracy of 91.25%, precision of 92.31%, recall of 90%, and an F1-score of 91.13%, demonstrating reliable performance in melanoma classification. High specificity (92.5%) indicates a low false positive rate, while sensitivity (90%) shows effective melanoma detection, though the 10% false negative rate requires improvement. Future enhancements include increasing sensitivity through weighted loss functions, optimizing classification thresholds, and performing external validation. Additionally, Grad-CAM is used for interpretability, and a web-based application is proposed to support healthcare practitioners, offering an accessible diagnostic tool for melanoma screening in resource-limited settings
Decision support system for selecting outstanding students using simple addictive weighting (SAW) and rank order centroid (ROC) methods
Full text linkSelecting outstanding students is essential in fostering appreciation and motivation within the school environment. Nevertheless, many educational institutions continue to use manual assessment methods, which are often subjective and inefficient. This research focuses on the development of a web-based decision support system designed to assist in the selection process at a in Indonesia. The system integrates the Simple Additive Weighting (SAW) technique to generate student rankings based on preference scores, while the Rank Order Centroid (ROC) method is applied to assign weight values to the evaluation criteria, including academic performance, attendance, behavior, and extracurricular involvement. Data for this study were collected through interviews, direct observation, and student records. The application was developed using PHP for the backend, MySQL for database handling, and Bootstrap for the user interface design. The system’s functionality was verified using black box testing, which confirmed that all features operated correctly. Additionally, the system was evaluated against the manual selection process conducted by the school, and the results showed an accuracy level of 80% in matching student rankings. This system proves to be a practical and structured solution for enhancing the transparency and objectivity of student achievement evaluations
Preliminary identification of N-Acetyltransferase 2 (NAT2) gene polymorphisms in the dayak population
No full textPolymorphism is a change or mutation in a gene that does not cause a change in the protein structure. The N-Acetyltransferase NAT enzyme is encoded by the N-Acetyltransferase 2 (NAT2) gene, the N-Acetyltransferase 2 (NAT2) gene, several variations of DNA known as single nucleotide polymorphisms (SNPs) that alter the genotype, haplotype, and phenotype. The NAcetyltransferase 2 (NAT2) genotype was classified into three phenotypes, namely fast acetylators, intermediate acetylators, and slow acetylators. The purpose of this study was to determine the type of polymorphism and the type of polymorphism of the NAT2 gene of the Dayak tribe. In this study, blood samples from the Dayak tribe were isolated from the Wizard Genomic DNA Purification kit and then identified Polymerase Chain Reaction-Restriction Fragment Length Polymorphism (PCR-RFLP). With stages 1. Denaturation 2. Anneling and 3. Extension using NAT2 N4 and N5 primers then RFLP with restriction enzymes KpnI, TaqI and BamHI then electrophoresed with 2% agarose gel. The results of the initial identification of the N-Acetyltransferase 2 (NAT2) gene polymorphism in the Dayak tribe obtained 5 types of genotypes NAT2*4/*5B (20%), NAT2*4/*6A (33.3%), NAT2*4/*7B (20%), NAT2*5B/5B (13.3%) and NAT2*7B/7B (13.3%). From the phenotype of the Dayak tribe, there are two medium acetylators (73.3%) and slow acetylators (26.3%)