INTERNATIONAL SCIENTIFIC JOURNAL OF ENGINEERING AND TECHNOLOGY (ISJET)

Alternative Design of a Stacking-Bag Assistive Device for Facilitating Loading and Unloading of Objects – A Case Study on Sago Bags

2024-02-09T10:42:23+07:00

This study presents an alternative design for handling sago bags, focusing on creating a user-friendly platform for loading and unloading. Sago is packed in canvas bags of varying loads (15 kg, 25 kg, and 30 kg), which poses challenges due to its non-uniform distribution and can lead to stability issues during transport. The study proposes an assistive device made of durable, tough, and resistant materials such as HDPE, PP, ABS, and Polyester, offering a balance between hardness and solidity. The device’s standardized size allows for easy connection and application with the forklift lever, with a simple design for easy maintenance and part replacement. The elastic properties of polymer materials enable deformation during heavy load handling, crucial for shock absorption in a stackinglike building style. Rubberized shoulder straps enhance grip and durability. The device can be folded into a compact size (109 cm Î 30 cm Î 10 cm) for easy stacking and storage. The handle features a rubber grip for comfort, and the side belt is made of 1.5 mm thick polyester, designed to accommodate 50% and 100% capacity. The base, 1 mm thick, is constructed from polypropylene (PP) and measures 109 Î 120 cm, ensuring a robust and efficient solution.

Credit Risk Prediction Model Using Feature Engineering and Machine Learning Techniques

2023-07-05T11:47:23+07:00

Credit scoring is a crucial step in the risk management process of the financial industry and commercial banks. The objective of this research is the development of a credit risk prediction model using feature engineering and machine learning techniques. This research was used to test the algorithm with a peer-to-peer (P2P) lending dataset and measure performance with classification accuracy. The experiment in this research found the XGB algorithm provided the most effective classification accuracy of 88.94%, which is better than other classifiers. Therefore, the proposed
research framework of this research, working with feature engineering, feature selection, and machine learning techniques, is suitable and effective for credit scoring problem analysis.

Development of Crispy Spicy Snack from Bhutan Oyster Mushroom by-Product with Narok Chili Paste

2023-08-24T10:27:55+07:00

The aim of this study is to develop a crispy spicy snack from Bhutan oyster mushroom by-product and Narok chili paste. It was rejected
from the mushroom house with an evaporation system at Wat Jampee school, Suphan Buri province. The methodology of this study is the preparation of three different sizes of oyster mushroom by-products; shreded, medium, and whole mushrooms. They were then blanched in hot water, cooled in cold water, soaked in 1% Calcium Chloride (CaCl2) for 15 min., drained and dipped in batter, and deep fried at 160 °C in vegetable oil. The shred and medium size of mushrooms took 8 min. and 10 min. for the whole mushroom. It was then, baked at 90°C for 50 min. It was found that the shred and medium-sized oyster mushroom by-products had the exact overall liking at 6.90 at a slightly liking level. To select the standard recipe for Narok chili paste and the most appropriate size of mushroom by target customer for further product development. The experiment found that shredded mushrooms with Narok chili paste recipe
1 (T1S1) from six samples received the highest overall preference score of 6.10. As for the sensory evaluation with a 9-point Hedonic Scale found that the shredded mushroom with the first recipe chili paste got moderate overall liking (7.06), the color of the mushroom (7.09), crispiness (7.04) chili paste color (7.49), spiciness (6.90), saltiness (6.52). The consumer acceptance was 77%. Hence, the study of the development of a crispy spicy Bhutan Oyster Mushroom by-product snack from the mushroom house with an evaporation system at Wat Jampee School, Suphan Buri province, add value to the by-product until the country’s economic sustainability in the future.

Enhanced Autonomous Driving: PrediNet20 with AHLR for Improved Performance

2024-01-04T10:54:57+07:00

In the continually evolving field of autonomous driving, enhancing model prediction accuracy and addressing noisy data remain pivotal challenges. This study introduces PrediNet20, a customized end-to-end Convolutional Neural Network (CNN) designed for the Donkey Car platform. PrediNet20 aims to alleviate the limitations of current deep learning models by improving accuracy in predicting throttle and steering angles, crucial components in autonomous driving systems. At the core of this enhancement is the introduction of AHLR, a novel adaptive loss function that enhances model training and generalization. It dynamically adjusts the loss based on the prediction error, facilitating a smooth transition from quadratic to linear loss. Coupled with the application of L1 regularization, it aids in reducing overfitting, potentially enhancing the model’s resistance to data noise and outliers. Preliminary experiments using real driving data indicate that compared to existing models, PrediNet20 demonstrates approximately a 33.3% improvement in convergence speed, a 37.5% improvement in stability, a 10% improvement in robustness, and a 50% improvement in generalization. PrediNet20 oﬀers higher accuracy and faster convergence, marking a significant step forward
in the development of more reliable autonomous driving systems.

The Design and Implementation of Material Requirement Planning: A Case Study of the Plastic Company

2023-04-12T23:07:38+07:00

The Company has a problem with inventory shortages caused by insufficient materials to meet customer needs and a lack of spare components for constructing finished goods due to the shared use of spare parts. To improve inventory management, this research employs engineering principles to create a new Material Requirement Planning (MRP). It also oﬀers planners an option that would
provide an inventory that is more efficient than the current approach. The problem was analyzed with Cause and Eﬀect (Fishbone Diagram), presented the structure of the Bill of Material (BOM), and used a spreadsheet program on the cloud (realtime) for material management Order Notification Program can be compatible with Microsoft Excel. This research uses ABC analysis of the high-order
Type A products of four departments. The reduction in raw material shortages from November to December 2022 resulted in a 100% reduction in delivery delays across all departments and a 66.67% reduction in the cost of warehouse management compared to the average ratio in the year 2022, leading to a cost savings of 64,180 baht
per year for warehouse management

Strawberry History, Cultivation and Problems in the Northern Area of Thailand: A review

2024-04-25T16:30:41+07:00

In Thailand, strawberries have been brought into cultivation since 1960 by His Majesty King Rama IX with the objective to replace opium cultivation and develop the living standards of hill tribe in the northern area. First strawberry was successfully growth by 1972 and introduced to local growers as a replacement crop. After that, the Royal Project and Kasetsart University have brought in newer cultivars; Number 329 (yael), Pharachatan number 50 (B5), 60 (Rosa Linda × Tochiotome), 70 (Toyonoka), 72 (Tochiotome), and 80 (hybrid) to replace the older due to their many advantages. Currently, strawberries are considered as a high-value crop with the highest unit price among Thai economic crops.