cover
Contact Name
Mega Novita
Contact Email
novita@upgris.ac.id
Phone
+6285867312111
Journal Mail Official
asset@upgris.ac.id
Editorial Address
Jl. Sidodadi Timur No.24, Karangtempel, Kec. Semarang Tim., Kota Semarang, Jawa Tengah 50232
Location
Kota semarang,
Jawa tengah
INDONESIA
Advance Sustainable Science, Engineering and Technology (ASSET)
ISSN : -     EISSN : 27154211     DOI : https://doi.org/10.26877/asset
This journal aims to provide a platform for scientists and academicians all over the world to promote, share, and discuss various new issues and developments in different areas of science, engineering, and technology
Articles 141 Documents
The Effect of LAB Color Space with NASNetMobile Fine-tuning on Model Performance for Crowd Detection Rafid, Muhammad; Luthfiarta, Ardytha; Naufal, Muhammad; Al Fahreza, Muhammad Daffa; Indrawan, Michael
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17821

Abstract

In the COVID-19 pandemic, computer vision plays a crucial role in crowd detection, supporting crowd restriction policies to mitigate virus spread. This research focuses on analyzing the impact of using the RGB LAB color space on the performance of NASNetMobile for crowd detection. The fine-tuning process, involving freezing layers in various NASNetMobile base model variations, is considered. Results reveal that the model with LAB color space outperforms model with RGB color space, with an average accuracy of 94.68% compared to 94.15%. From all the test iterations, it was found that the highest performance for the NASNetMobile model occurred when freezing 10% of the layers from the back for both model LAB and RGB color spaces, with the LAB color space achieving an accuracy of 95.4% and the RGB color space achieving an accuracy of 95.1%.
Overcoming The Buildup of Queues By Carrying Out the Concept of Self-Service Using Responsive Web-Based Applications Permatasari, Putri Wahyu; Aryanto, Joko
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17440

Abstract

With today's technological advances, all things can be done with the internet, one of which is a web-based food and beverage menu self-order system. This system was created to make it easier for waiters and customers in the ordering process. Because of the problems that occur today, namely the queue in the ordering process and busy waiters who make customers neglected. Therefore, this system was designed to facilitate service, and waiters no longer need to record food menus manually, customers can also order menus directly through the system without having to queue. Before designing the system, an analysis is carried out first, in the design of the system is designed with a quantitative method where researchers take the necessary data and information by conducting direct interviews with related parties. This system will be designed in the form of a responsive website and designed using the PHP programming language and MySQL which is used as a database storage. With the final result, this system can help and facilitate the ordering process and data collection of incoming orders. And the system can run according to the needs of restaurants and customers who use this system
Supplier Selection Modeling and Analysis in the Metal Casting Industry Using Analytical Hierarchy Process Firdantara, Zahra Nasywari; Qurtubi, Qurtubi; Setiawan, Danang
Advance Sustainable Science, Engineering and Technology Vol 6, No 2 (2024): February - April
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i2.18323

Abstract

This study presents a supplier selection problem of a raw material using an analytical hierarchy process. In the existing process, the delivery of raw materials experienced delays and impacted the production process. Therefore, this paper aims to determine the criteria for supplier selection and provide recommendations for the best vendor to be selected from the last request for quotation document. Analytical Hierarchy Process (AHP), as a multi-criteria approach, was utilized in this research, starting from determining criteria, the weight of criteria, and the final score for each supplier. Through discussions with the company’s expert, procurement department, and users, as well as a review of the previous studies, this research defined three criteria, each consisting of three sub-criteria. The AHP approach was utilized to evaluate and determine the weights for the three criteria, yielding the following results: quality (62%), price (28%), and delivery (10%). The identified criteria, sub-criteria, and respective weights are subsequently utilized in a supplier selection scenario. Three suppliers of mild steel raw materials were evaluated using the weights of the criteria and sub-criteria obtained. Supplier 1 was selected because of having the higher alternative value of 0.602. The use of AHP in supplier selection is often impractical and contains subjectivity. Therefore, further research can be performed by integrating AHP with other methods, such as weighted scoring, to facilitate further the vendor selection process and integration with other methods, such as fuzzy logic, to reduce subjectivity.
Implementation of Data Layer In Blockchain Network Using SHA256 Hashing Algorithm Sondakh, Clivent Gerhard; Ardiansyah, Rizka; Joefrie, Yuri Yudhaswana; Angreni, Dwi Shinta; Pusadan, Mohammad Yazdi
Advance Sustainable Science, Engineering and Technology Vol 6, No 2 (2024): February - April
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i2.18103

Abstract

The escalating demand for secure data management in blockchain systems has prompted the exploration of advanced cryptographic techniques. Leveraging the SHA256 hashing algorithm, this implementation aims to fortify data integrity, confidentiality, and authentication within the blockchain network. By meticulously examining the algorithm's application, the research demonstrates its efficacy in ensuring tamper-resistant data storage and retrieval, quantifying improvements in security percentages and specific metrics. The integration of SHA256 within the data layer is explored in technical detail, highlighting the concrete benefits of heightened security and immutability. The analysis discusses practical implications and delves into potential advancements in blockchain technology, offering valuable insights for researchers, developers, and practitioners seeking to bolster the robustness of data layers in blockchain networks.
Yogyakarta Batik Image Classification Based on Convolutional Neural Network Susanti, Indah Dwi
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.18002

Abstract

This paper studies the efficiency of identifying motifs and patterns in Yogyakarta batik using the Convolutional Neural Network (CNN) algorithm. This research uses the AlexNet architecture on CNN to increase the accuracy of batik image classification. Apart from that, it also involves the use of Canny edge detection techniques and feature extraction using the Gray Level Co-occurrence Matrix (GLCM) to improve the feature extraction process in batik images. There are 6 folders representing 6 types of motifs containing -+20 to 25 data that have been prepared for the training session. Next, the data is processed with 20% of the data used for training and 80% for testing. The accuracy of this research using the SGDM optimizer reached 100%. The evaluation results provide insight into the extent to which edge emphasis can improve the model's ability to recognize and classify batik patterns. It also presents classification test results and evaluation metrics such as precision, recall, and F1 score.
Protein Concentrate From Tuna Head Waste Using Methanol-Acetone Solvent Extraction Ardiansyah, Feri; Rahmasari, Shofia Dwi Fitri; Wahyusi, Kindriari Nurma
Advance Sustainable Science, Engineering and Technology Vol 6, No 2 (2024): February - April
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i2.18701

Abstract

The frigate tuna (Euthynnus affinis) is known for its high protein content in the head, making it suitable for the production of protein concentrate used in animal feed. This research aims to investigate the influence of adding a methanol-acetone mixture solvent, the duration of the extraction process, and the protein content in the resulting concentrate using the Kjeldahl method. The protein concentrate is produced through the maceration extraction method, where 30 grams of the frigate tuna head sample is mixed with a methanol-acetone solvent in various ratios (1:9; 3:7; 5:5; 7:3; 9:1) at a temperature of 50 °C and a stirring speed of 500 rpm, with extraction times ranging from 2 to 6 hours. Subsequently, filtration is performed, and the precipitate is dried using an oven at 100 °C for 30 minutes. The dried sample is then subjected to protein content testing using the Kjeldahl method. Research results indicate that both protein content and extraction yield values increase with the duration of the extraction process, while the water content decreases. The optimal result in maceration extraction is achieved with the methanol-acetone mixture (9:1) treatment and a 6-hour extraction time, yielding a protein content of 89.15 %, water content of 5.57 %, and an extraction yield of 23.86 %.Protein concentrate can be used as animal feed to increase protein needs. Animals that are given sufficient protein will fatten and make the animal healthy
Zonation Method for Efficient Training of Collaborative Multi-Agent Reinforcement Learning in Double Snake Game Hadiyanto, Marvin Yonathan; Harsono, Budi; Karnadi, Indra
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17562

Abstract

This paper proposes a zonation method for training the two reinforcement learning agents. We demonstrate the method's effectiveness in the double snake game. The game consists of two snakes operating in a fully cooperative setting to maximize the score. The problem in this game can be related to real-world problems, namely, coordination in autonomous driving cars and the operation of collaborative mobile robots in warehouse applications. Here, we use a deep Q-network algorithm to train the two agents to play the double snake game collaboratively through a decentralized approach, where distinct state and reward functions are assigned to each agent. To improve training efficiency, we utilize the snake sensory data of the surrounding objects as the input state to reduce the neural network complexity. The obtained result show that the proposed approaches can be used to train collaborative multi-agent efficiently, especially in the limited computing resources and training time environment
A Good Evaluation Based on Confusion Matrix for Lung Diseases Classification using Convolutional Neural Networks Kamila, Izza Putri; Sari, Christy Atika; Rachmawanto, Eko Hari; Cahyo, Nur Ryan Dwi
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.17330

Abstract

CNN has been widely used to detect a pattern with image classification. This study used CNN to perform a classification analysis of lung abnormality detection on chest X-ray images. The dataset consists of 5,732 2D images with dimensions of 200 x 200 x 1 divided into training data (85%) and testing data (15%). The preprocessing process includes image resizing, enhancement to increase contrast and reduce image complexity, and filtering to improve visibility and reduce noise. CNN is used to classify imagery into three categories, Normal (no abnormalities), Pneumonia, and Tuberculosis. The results showed a good level of accuracy, with an average accuracy of 97.24% in 3 trainings, and a 100% success rate in 6 classification experiments. This research provides insights into the detection of lung disorders and encourages further exploration in medical diagnosis.
Enhancing Web Server Security against Layered Cyber Threats in Healthcare Rifai, Muhammad Fajar; Hendra, Syaiful; Ngemba, Hajra Rasmita; Azhar, Ryfial; Laila, Rahmah
Advance Sustainable Science, Engineering and Technology Vol 6, No 2 (2024): February - April
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i2.18307

Abstract

Information technology plays an important role in improving operational efficiency at Torabelo Hospital. The server system in use today faces security and optimization challenges. This research analyzes the impact and recommends solutions to improve server security and optimization. The findings show that the server system is vulnerable to various types of attacks and performance degradation. This can negatively impact hospital operations and put patients at risk. The recommended solution is to implement Squid as reverse proxy, WAF (Web Application Firewall), and Snort as IDS (Intrusion Detection System). System testing showed that this solution successfully detected and prevented various common attacks. This research provides insights to health IT professionals to improve the security and performance of their server systems and improve healthcare services to patients at Torabelo Hospital.
XGBoost and Random Forest Optimization using SMOTE to Classify Air Quality Arifianti, Fidela Putri; Salam, Abu
Advance Sustainable Science, Engineering and Technology Vol 6, No 1 (2024): November-January
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v6i1.18136

Abstract

Air pollution due to the growth of industry and motorized vehicles seriously threatens human health. Clean air is essential, but pollutant contamination can cause acute respiratory illnesses and other illnesses. Several studies have been carried out to anticipate this air pollution. Various algorithms, methods, and data balancing techniques have been implemented, but still need to be done to obtain better accuracy results. Therefore, this study aims to classify heart disease using the XGBoost and Random Forest algorithms and implement the SMOTE technique to overcome data imbalance. This research produces a Random Forest algorithm with SMOTE implementation with splitting 80:20, which has the best accuracy with an accuracy of 92.4%, an average AUC of 0.98, and a log loss of 0.2366, which shows that SMOTE has succeeded in improving model performance in classifying minority classes. Based on the results obtained, the XGBoost and Random Forest algorithms after SMOTE are superior to the model with SMOTE, with accuracy above 90%.