TNI Journal of Engineering and Technology

An Algorithm for the All-pair Shortest Path Problem on Circular Trapezoid Graphs

Hirotoshi Honma, Yoko Nakajima, Tsendsuren Urangoo, Yuto Tamori — Wed, 24 Jun 2020 00:00:00 +0700

The shortest path problem involves finding a path between two vertices in a graph such that the sum of the weights of its constituent edges is minimized. This is a fundamental and important problem in graph theory, and it has been applied for solving numerous problems such as the minimum connected dominating set, minimum-weight circle-cover, and minimum cardinality Steiner set problems. The single-source shortest path problem involves finding the shortest paths between a given vertex and all other vertices. The all-pair shortest path problem involves the determination of the shortest graph distances between every pair of vertices in a given graph. In general, it is known that efficient sequential or parallel algorithms can be developed by restricting the classes of graphs. Numerous studies have been conducted on the shortest path problems on several intersection graphs. A circular trapezoid graph is a proper superclass of trapezoid graphs and circular-arc graphs. In this study, we present an O(n²) time algorithm to solve the all-pair shortest path problem on circular trapezoid graphs.

Automated pH Control of Nutrient Solution in Hydroponic System using Modified Fuzzy Logic Control

Thanavin Mansakul, Kanticha Kittipeerachon — Wed, 24 Jun 2020 12:52:38 +0700

A hydroponic system can control many factors significantly, such as the amount of water and fertilizer. However, the system is a high investment and requires some skills to operate. The unsuitable quantity of pH can cause root damage from acidity and inadequate nutrient uptake. This paper presents the pH control in a nutrient solution using modified fuzzy logic control. The fuzzy logic control is a design based on experienced personal adjustment data. However, the defuzzification technique is modified to suit the controlled system using the area under an appropriately designed graph. From the results obtained from the prototype systems, it was found that the proposed system can control pH value in nutrient solution and reject disturbance better than the conventional P control system. Since the system can decide the proper quantity of acid and base automatically, the system can reduce human workload and reduce complicated procedures for the farmer.

Automatic Blurring based on Structural Similarity of Image Detail

Thitiporn Lertrusdachakul, Kanakarn Ruxpaitoon, Kasem Thiptarajan — Wed, 24 Jun 2020 12:53:41 +0700

Image smoothing is used for a variety of purposes such as removing noise, feeling enhancement, drawing attention to the object. Since the images have different details, they require an appropriate blur level for their contents and applications. Therefore, this research studies and develops automatic blurring method to increase depth impression of image. The blur levels are divided into large blur (very shallow depth of field) and small blur (preserve image structure). The method applies image quality assessment of structural similarity index (SSIM) to measure blur level between images. Only the SSIM values of image detail which affects the blur perception of human are used to compare with the values of appropriate blur levels from preliminary experiment of 100 images. The technique isolates the detail of image in SSIM map by using Otsu’s thresholding method. With the proposed approach, blurred images of both levels can be automatically created to enhance the focus to the key subject of image. The evaluation result from photography expert reveals that the proposed method can assist well in creating dimension of image, time saving of image editing especially for those who are not skilled in art.

Charcoal Drawing Style and Color Effect of Children Face Images based on Structural Similarity Index and Color Image Scale

Kanakarn Ruxpaitoon, Thitiporn Lertrusdachakul, Kasem Thiptarajan — Wed, 24 Jun 2020 12:52:49 +0700

Many people love to capture and view children pictures to catch their cute moments. The smile and innocence of children’s faces are very impressive. Therefore, this paper proposes an alternative method to create charcoal drawing style and color effect for children face images. The method applies the structural similarity index (SSIM) of image quality assessment to generate rich black tones automatically. The image is blurred with Gaussian filter to the appropriate level and compared with the original image to obtain the local SSIM values. The blurred level and the weight of neighborhood pixels for estimating local statistics in SSIM quality assessment is controlled by the threshold of the average SSIM value of image detail acquired from the preliminary experiment. The color effect is based on SSIM values and the knowledge of color image scale. The results reveal that the sophisticated intensity of lightness from SSIM map has the power to convey this expressive drawing style emotionally and naturally.

Development of A Food Categories and Calories Estimation Full Stack System Based on Multi-CNNs Structures

Kanjanapan Sukvichai, Warayut Muknumporn — Wed, 24 Jun 2020 12:53:53 +0700

Humans require different food amounts and nutrition depended on age, gender and health. Amount of food intake can create health problems especially for infants, elderly or diabetics. Tradition nutrition booklet is not suitable for most people since it is hard to understand. Thai-foods are hard to extract the nutrition and most of the Thai dishes are not in the book since it focused on Western dishes. This research focused on development on a full stack AI system that categorizes Thai-food dishes, classifies and localizes the ingredients in each dish and estimate nutrition and calories. Multi-Convolutional Neural Networks (CNNs) are used to achieve these categorize, classify and localize tasks. The designed system is separated into AI backend and Mobile application frontend based on OpenCV in an Android smartphone. MobileNet is used as a food categorizer while You-Only-Look-Once (YOLO) network works as the ingredient’s classifier and localizer. Then, ingredients in the pictures are cropped and passed through traditional image processing algorithm with predetermined parameters to calculate and transformed pixel into real-dimension area referenced by Thai coins. Pixel area of non-uniform shape ingredients are segmented and the nutrition and calories can be estimated via a standard reference lookup table. Full stack system is developed in this research based on RESTful protocol with JSON format that used to communicate between a smartphone and AI server. The designed CNNs and full stack system are trained, tested, verified and deployed then the food image captured from a smartphone application can be used to estimated nutrition and calories. Finally, useful information is display on a smartphone screen.

Performance of Electroplated Copper Coating on Graphite Electrode in EDM Process

Nattawut Chindaladdha, Don Kaewdook — Wed, 24 Jun 2020 12:52:13 +0700

Electrical Discharge Machining (EDM) is a nonconventional manufacturing process whereby a desired shape is obtained by using electrical discharges. Material is removed from the workpiece by current discharges between tool-electrode and workpiece, separated by a dielectric liquid. Copper electroplating is the process to produce a layer of copper on the surface of the substrate in this research was used graphite which is the tool-electrode. The study aims to investigate the performance of EDM product which used graphite coated with the copper layer. The experiment designed by using Taguchi-grey relational approach based multi-response optimization to find the optimal electroplating parameters. The considered electroplating parameters including 3 parameters 2 levels, current density 3.7 A/dm2 and 5.4 A/dm2, electrolyte concentration 0.1 mol and 1.0 mol, plating time 3 hours and 5 hours. The electrode's machining performance of the surface roughness (SR) of workpiece, tool wear rate (TWR) and material removal rate (MRR) will be investigated and compared with the conventional copper electrode.

Power Consumption and Surface Quality Optimization of Cutting Condition for S50C Material in Turning Process using Means Utility Concept and Taguchi Method

Akaranun Asavarutpokin, Jinjutha Sae-Lee, Don Kaewdook — Wed, 24 Jun 2020 00:00:00 +0700

This paper aims to study the effects of cutting condition to the power consumption and surface quality in tuning process on mild steel S50C. The machine was used in this study is CNC turning and carbide cutting tool. The optimize process parameters by means utility concept and Taguchi technique applied to identify the machinability and energy efficiency. The three types of process parameters with five different levels including, cutting speed, feed rate, and depth of cut have been used in this work. The selection of these parameters was based on literature review, and tool manufacturing recommendations. The Taguchi orthogonal array L₂₅(5³) have been used for conducting the experiments. The results shown that most significant factor for power consumption is depth of cut (60.58%) followed by feed rate (30.27%) and cutting speed (4.36%). For surface roughness, the most significant factor is feed rate (98.49%) followed by depth of cut (0.99%), and cutting speed (0.02%). Nevertheless, the minimum power consumption of machine condition is in contrast to the surface roughness quality. Therefore, this technique can be applied for production planning to control the product quality and machining cost.

Study on The Color Feature of Harajuku-type Kawaii Fashion Comparison with Street Snap Images Using Colorfulness

Peeraya Sripian, Keiko Miyatake, Michiko Ohkura — Wed, 24 Jun 2020 12:53:04 +0700

This research focuses on Harajuku-type Kawaii fashion style. Based on the fashion experience of the second author, we made the hypothesis that Harajuku-type Kawaii fashion contains high saturation and a large variety of color. In this work, we objectively tested these hypotheses by preparing original data sets of 3 styles: Harajuku-type Kawaii fashion, Harajuku Street snaps, and Shibuya Street snaps. We calculate saturation and employ colorfulness to quantify the variety of colors. The data sets were selected and properly modified based on heuristic rules according to the fashion experience so that each data set contains only images with typical features of its style. From the data analysis, we found that the saturation and colorfulness of Harajuku-type Kawaii fashion is statistically higher than the other two data sets. As a result, we successfully verified that Harajuku-type Kawaii fashion is very distinct in its saturation and colorfulness with statistical evidence.