Journal of Engineering and Digital Technology (JEDT)

Adaptive Pseudocoloring Method based on Color Image Scale for Emotional Art Image

2021-12-28T16:21:57+07:00

Color can dramatically affect and arouse the emotions. In this paper, we propose a pseudocoloring method by applying the color psychology of color image scale to create an emotional art image. The proposed technique utilizes two key color groups, image segmentation, shape-preserving piecewise cubic Hermite interpolation with uniform lightness difference, Gaussian filter and morphological gradient to develop an adaptive color mapping of grayscale image. The key color groups of the desired emotion are extracted from the color image scale and the color map is generated from the interpolation results in CIELAB color space for each key color group to the segmented area. The simulation results show that the smooth gradient of key colors impressively transfers an implicative emotion of the image. In addition, soft transition between key color groups by smoothing at the edge of segmented area makes the image more artistic appeal. The emotional art image of the proposed pseudocoloring method could enrich the digital decoration and color therapy in both artifactual and natural images.

An Improvement of Product Locations in the Warehouse: A Case Study of Srithai Superware Korat Company Limited

2021-12-28T15:49:15+07:00

The objectives of this research are gaining knowledge and improving the layout of the product in Srithai Superware Korat exhibition warehouse. The current improper layout of the product in this warehouse leads to the problem of not achieving 100% on time delivery. This research will use both the ABC Classification system and the line programming module to rearrange the product priority and products that move frequently should be considered to be placed nearest to the door. The expected result for this implementation of this exhibition product layout is a decreasing distance of picking products in the warehouse for each order every month. The result of this research is firstly, the distance of picking the product in the warehouse decreased by 22.54%. Secondly, the electricity bill for the forklift decreased by 22.54%. Lastly, the total cost of the picking product process decreased by 2.22% per month.

A Plant Layout Improvement to Increasing Productivity: A Case Study Downlight Manufacturer

2021-12-28T15:07:25+07:00

The purpose of the study is to improve factory’s layout and production process, leading to the more effective processes of downlight lamp and to reduce cost. Because of the long distance and duration of transferring materials, the bottleneck process caused the delay. The study covers the analysis of the sample factory’s need and problems, using systematic layout planning, collecting fundamental information of each department such as duration and distance for transferring materials, cycle of customers’ needs for balancing assembly line, designing and setting out the factory, and adjusting the process and balance of assembly lines. The consequences of improving the factory reveal the reduced distance in transferring materials by 33 meters or 27.04% and the reduced duration by 43 minutes or 24.57% accordingly. Moreover, the results of improvement in balancing assembly line by using ECRS show the reduction of cycle time in assembly lines by 64.08 seconds to 61.36 seconds, total of reduced cycle time is 2.7 seconds or 4.24%. The productivity has been increased from 2,234 to 3,037 per day. The total increased output is 803 pieces or 35.94% per day and reduce 2 from 10 workers or 25%. These lead to the ability of the factory to support the increasing purchased orders from customers in the future properly.

A Study of Air Quality Effect by Creating a Device Detect PM2.5, TVOC and CO2-eq

2021-12-28T14:03:14+07:00

This paper presents the study of air quality effect from particulate matter with diameter of less than 2.5 microns (PM2.5), total volatile organic compound (TVOC) and carbon dioxide equivalent (CO₂-eq) for indoor and outdoor Department of Electronics Technology, Ramkhamhaeng University, Bangkok. By creating a device detect air quality for the period from November 2020 to March 2021. From the results, It was found that the average PM2.5 of 24-hour continuous is 31.50 for the inside office (good level), 38.24 for the inside building (moderate level) and 44.80 for the outside building (moderate level). The average TVOC of 8-hour continuous is 0.58 for the inside office (good level), 0.32 for the inside building (good level) and 0.41 for the outside building (good level). The average CO₂-eq of 24-hour continuous is 1122.73 for the inside office, 983.97 for the inside building and 922.88 for the outside building.

Human and Luggage Analysis for Abandoned Object Detection

2021-12-28T13:30:13+07:00

This paper presents a method to analyze videos for Abandoned Object Detection (AOD) and ownership identification. Abandoned luggage is a risky event that can actually occur in many public areas such as train stations, airports, or other important places in the building. Deep learning is used for person and luggage detection. The dataset is trained for both people and luggage images including backpacks, handbags and suitcases for more than 12,000 images. In this work, we use the YOLOv3 model that can be processed in real time with 98% accuracy. For ownership identification and abandoned detection, we propose a method that evaluates the spatial relationships and trajectories of each person and luggage. Ownership identification yields 65.1% accuracy while abandoned detection provides 66.6% accuracy.

Performance Evaluation of Consecutive Collision Avoidance Technique for Binary Tree Algorithm

2021-12-28T16:10:40+07:00

Nowadays, RFID technology is very popular in tracking goods or users. But when there are more users in the system collision may occur. RFID technology has adopted Binary tree algorithm to solve the collision problem. The Binary tree algorithm is designed to resolve data collisions. When a collision occurs, the Binary tree algorithm divides the users involved in the collision into two groups. The users in the first group access the first slot and the users in the second group access the second slot. If the number of users in the system is relatively larger than the number of slots. For example, in the case of 50 users and 2 slots this can cause consecutive collisions, resulting in inefficient access to the channel. Therefore, this paper presents consecutive collisio n avoidance techniques for Binary tree algorithms. In the second consecutive collision, this technique proposes to increase the number of slots from 2 to 3 slots to reduce the chances of consecutive collisions. From the results, we found that the proposed technique can improve the performance of Binary tree algorithm, especially in cases where the number of users in the system is relatively greater than the number of slots.

Potential of Biogas Production by Co-Digestion between Physical Pretreatment Sugar Cane Leaf and Cow Dung

2021-12-28T11:58:02+07:00

This research studied the potential of biogas production by co-digestion between physically pretreated sugarcane leaf and cow dung. The biogas production system was operated until optimum for operation. The optimum ratio of sugarcane leaf and cow dung was 1:1. Sugarcane leaf was physically pretreated to small sizes and 16 g L^-¹ CaCO₃ maintained the optimum pH and alkalinity in system. The alkalinity can be maintained between 1,480–4,640 mg L^-1 CaCO₃; pH was 6.95–7.15. This is optimum pH for microbial mechanisms in the system. However, before biogas production sugarcane leaf component analysis, cellulose 39.096 ± 0.559%, hemicellulose 25.291 ± 0.937%, and lignin 18.556 ± 1.399%. The potential of the biogas production test by co-digestion between sugarcane leaf and cow dung was found to have the highest percentage of methane production 65.11 ± 0.30%, highest cumulative total gas 1,978 ± 3.54 mL, and highest total cumulative methane 1,148 ± 5.00 mL. Therefore, this research presented that sugarcane leaf and cow dung can be used for biogas production and that sugarcane leaf that is agricultural waste can be material for producing alternative energy in the community.

The Design and Development of Public Bus Complaint Classification Process for Service Problem Tagging

2021-12-28T10:56:42+07:00

Bangkok Mass Transit Authority (BMTA) has a webboard for service user complaints on public buses. This information is important and improving service efficiency. Now, the complaints are increasing, more different and lexical error problem affect the accuracy of the complaints classification. Because the person has to analyze the data by self. This research aims 1) to the design and development of public bus complaint classification process from BMTA webboard by Thai dictionary-based approach and keywords selection by TF-IDF to create a corpus-based divided into 4 classes: driving class, person class, vehicle class and schedule class. The result of text classification algorithms, found that it was at a very good level. 2) to evaluation the accuracy of the public bus complaint classification. Then, keywords matching with user complaints again and increase the accuracy of keywords by Levenshtein Distance. In case that found the incorrectly keywords for create complaint classification tag. The accuracy assessment of complaint classification is a very good level, especially one complaint issue. The results show performance of dictionary-based approach on Thai word segmentation is suitable for the terminology that has definite scope. However, found problems in same keywords to be duplicated in some class. For example, loudness can be attribute from the person class or the vehicle-equipment class according to the origin of the sound. As well as the unique compounding of Thai language affects to the accuracy of word tokenization. These results will present an approach to data classification and will benefit to those responsible to improve the service for customers.