ISAS 2021:Papers with Abstracts

Papers
Abstract. Electrical Impedance Tomography (EIT) is known as non-invasive method to detect and classify the abnormal breast tissues. Reimaging conductivity distribution within an area of the subject reveal abnormal tissues inside that area. In this work, we have created a very low-cost system with a simple 16-electrode phantom for doing research purposes. The EIT data were measured and reconstructed with EIDORS software.
Abstract. In the industrial context, there are key factors that directly affect the system’s efficiency. Higher demands for both quantity and quality in today’s market call for constant research and development of technologies for automating production and quality control. Machine vision is a solution to increase speed and accuracy in defect detection. However, applications from machine vision are only effective if there is good data input. This is the reason why a machine vision system, needs high-quality input images from a well-designed illumination system. These illumination systems are designed to highlight faults in products. Therefore, the images obtained will provide optimized data for easier image processing thus directly increase the processing speed, accuracy, and overall system performance. To achieve this goal, this paper presents a few approaches to enhance and optimize images by implements illumination techniques into a miniature model of pharmaceutical bottle assembly line using machine vision as the inspector block. In this paper, we will evaluate the critical needs of using customize illumination system for quality inspection on an assembly line.
Abstract. Applying laser technology to the growth of plants to limit the use of chemical fertilizers is an interesting topic in agriculture. The main idea is to preserve the environment, ensuring product quality while still achieving high productivity, we decided to carry out this research project, to investigate the effect of the low-level laser (the wavelengths 532nm, 850nm, and 940nm) on stems and leaf development. It is expected that with these research results, the implementation method will be widely disseminated in the high agricultural sector, coming closer to farmers. Moreover, the results of the analysis of the composition of bitter melon stems and leaves will be applied in medical treatment (such as diabetes, wound treatment, anti-oxidation, anti-bacteria ...)
Abstract. Low back pain is a common disease. A common cause of this problem is a herniated disc in the lumbar spine. Lumbar disc herniation represents the displacement of the disc (annular fibrosis or medullary nuclei). While most cases, the pain will disappear in a few days to a few weeks; however, it can last for three months or more. Detection and diagnosis are the two most important tasks in a computer-aided diagnostic system. In this article, we use images taken from the results of the MRI imaging of the patient. Through the use of image inversion to highlight the position of degenerative discs. This result wishes to provide a simple and inexpensive diagnostic image processing method to help doctors quickly determine the degree of disc herniation, the status of lumbar discs, they can give the appropriate treatment to the patient.
Abstract. The equilibrium problem and its generalizations had a great influence in the development of some branches of pure and applied sciences. The equilibrium problems theory provides a natural and novel approach for some problems arising in nonlinear analysis, physics and engineering, image reconstruction, economics, finance, game theory and optimization. In recent times, there were many methods in order to solve the equilibrium problem and its generalizations. Some authors proposed many iterative methods and studied the convergence of such iterative methods for equilibrium problems and nonexpansive mappings in the setting of Hilbert spaces and Banach spaces. Note that a generalized mixed equilibrium problem is a generalization of an equilibrium problem and a Bregman totally quasi-asymptotically nonexpansive mapping is a generalization of a nonexpansive mapping in reflexive Banach spaces. The purpose of this paper is to combine the parallel method with the Bregman distance and the Bregman projection in order to introduce a new parallel hybrid iterative process which is to find common solutions of a finite family of Bregman totally quasi-asymptotically nonexpansive mappings and a system of generalized mixed equilibrium problems. After that, we prove that the proposed iteration strongly converges to the Bregman projection of initial element on the intersection of common fixed point set of a finite family of Bregman totally quasi-asymptotically nonexpansive mappings and the solution set of a system of generalized mixed equilibrium problems in reflexive Banach spaces. As application, we obatin some strong convergence results for a Bregman totally quasi-asymptotically nonexpansive mapping and a generalized mixed equilibrium problem in reflexive Banach spaces. These results are extensions and improvements to the main results in [7, 8]. In addition, a numerical example is provided to illustrate for the obtained result.
Abstract. In this paper we consider two matrix equations that involve the weighted geometric mean. We use the fixed point theorem in the cone of positive definite matrices to prove the existence of a unique positive definite solution. In addition, we study the multi-step stationary iterative method for those equations and prove the corresponding convergence. A fidelity measure for quantum states based on the matrix geometric mean is introduced as an application of matrix equation.
Abstract. Today, freight is an extremely important industry for the world we are living. Fast transportation, large volume...will optimize the cost, time and effort. Besides, ensuring the products safety is a matter of concern. During transporting, it is inevitable that the vibration caused by the engine, rough road surface...the cargo inside can be damaged. Automobile industries have prime importance to vibration testing. Sine vibration testing is performed when we have been given with only one frequency at given time instant. Trend to perform random vibration testing has been increased in recent times. As random vibration considers all excited frequencies in defined spectrum at known interval of time, it gives real-time data of vibration severities. The vibration severity is expressed in terms of Power Spectral Density (PSD). KLT box is an industrial stacking container conforming to the VDA 4500 standard that was defined by German Association of the Automotive Industry (VDA) for the automotive industry. The aim of this paper is study about random vibration and power spectral density analysis, how it can be used to predict the impact of hash road to the KLT box on container / truck during transportation. Finite element model is developed in ANSYS, modal analysis and random vibration analysis were done.
Abstract. Crash-dynamics research has always concentrated significantly in the safety, survivability of passengers in a car crash. To identify the capability of energy absorption of a crash box, a thin-walled structure will be modeled and simulated by ABAQUS software. Investigate the influence of material, cross-sectional, thickness factors on the energy absorption capacity of the tube, using MCDM – Multi-Criteria Decision-Making to get the best option and testing the improvement while filling the tube with Foam material. In this study, beside the cross-sectional, aluminum alloys and steel materials and thickness are factors that influence the energy absorption evaluation criteria, the foam material with difference density are surveyed to compare effectiveness between the foam-filled and hollow crashboxes. The results show that the folds of the foam-filled tube after deformation along the compressive direction will be more continuous and stable. More, the higher foam density, the greater the energy absorption. This prevents the crashbox from deviating from the direction of the force, help directing the collapse of the tube, thereby improving energy absorption without significantly increasing the weight of the structure.
Abstract. In this paper, we present some results obtained from the simulation of low power 633, 780, 850, and 940 nm laser in the liver by Monte Carlo method, with the model of the liver, consisting of 5mm derm, 7mm subcutaneous fat, 5 mm muscle layer. Based on these results, we fabricated devices called “Laser Semiconductor Optoacupuncture and phototherapy Device” using 780 and 940nm semiconductor lasers to treat chronic hepatitis. We combined with the doctor in An Giang province to clinical practice for 50 voluntary patients with chronic hepatitis. We used a 650 nm wavelength intravascular semiconductor laser treatment clinically to provide high-quality blood to the patients’ liver. Treating the phototherapy of the skin with two semiconductor laser beams with 780 nm and 940 nm wavelengths directly affects the liver from the surface of the abdomen. At the moment, we use the treatment on acupoint with 940nm- wavelength laser. A treatment course consists of 20 times for the patients is treated continuously. The patients tested with the ALT and AST before and after treatment with 3 courses. We use the SPSS 23 statistical method to evaluate the outcomes of treatment. The clinical symptoms of the patients such as fatigue, nausea, indigestion, fever, jaundice, yellow eyes almost completely have gone out after treatment. Low-level laser therapy offers a good response in patients with moderate to severe hepatic impairment such as the AST of 56.380 ± 10.162 and 39.260 ± 4.869; The ALT of 56.540 ± 13.580 and 41,360 ± 7,488 for before- and after treatments, respectively. Low-level laser therapy for patients initially has good results, high therapeutic effectiveness, no catastrophic or side Effects, and the statistical significance is p < 0.001.
This research applied the ethical principles of the Helsinki Declaration in human researches. The research was carried out using non-invasive methods on humans with the regulations of the University of Technology, Vietnam National University Ho Chi Minh City, and the relevant regulations.
Abstract. With people's health status according to statistics getting worse and worse, improving the quality of health is an inevitable need that many researchers are interested in. In addition to improving through eating, improving the living environment in homes and workplaces is also essential. Nowadays, many countries around the world have implemented many house models that apply natural ventilation instead of artificial air conditioning system, because natural wind is better and also feels more comfortable. Therefore, the study of controlled natural wind-catching architecture is necessary and consistent. Research in this field can help improve the living environment for people. The objective of the paper is to simulate ventilation solutions based on experience in construction works by finite volume method through ANSYS software to consider and evaluate the feasibility of these solutions. If the simulation results match or approximate the actual verified results, they can be applied to the improvement of natural ventilation structures to create a better indoor living environment, meeting the requirements of the environment. more comfortable diagnostics.
Abstract. This research aims to evaluate the effect of low-level laser therapy (LLLT) on the healing of the burn for the mouse. Four mouses are divided into 4 groups. Group 1, 2, 3 are irradiated by a wavelength of 532nm, 850nm, and 940nm. Group 4 is a control group that has a natural recovery. Low-level laser therapy makes the regenerative process, healing occurs faster, and rehabilitation of mouse activity during treatment.
Abstract. Segmentation is one of the most common methods for analyzing and processing medical images, assisting doctors in making accurate diagnoses by providing detailed information about the required body part. However, segmenting medical images presents a number of challenges, including the need for medical professionals to be trained, the fact that it is time-consuming and prone to errors. As a result, it appears that an automated medical image segmentation system is required. Deep learning algorithms have recently demonstrated superior performance for segmentation tasks, particularly semantic segmentation networks that provide a pixel-level understanding of images. U- Net for image segmentation is one of the modern complex networks in the field of medical imaging; several segmentation networks have been built on its foundation with the advancements of Recurrent Residual convolutional units and the construction of recurrent residual convolutional neural network based on U-Net (R2U-Net). R2U-Net is used to perform trachea and bronchial segmentation on a dataset of 36,000 images. With a variety of experiments, the proposed segmentation resulted in a dice-coefficient of 0.8394 on the test dataset. Finally, a number of research issues are raised, indicating the need for future improvements.
Abstract. The rate of penetration (ROP) is an important parameter that affects the success of a drilling operation. In this paper, the research approach is based on different artificial neural network (ANN) models to predict ROP for oil and gas wells in Nam Con Son basin. The first is the process of collecting and evaluating drilling parameters as input data of the model. Next is to find the network model capable of predicting ROP most accurately. After that, the study will evaluate the number of input parameters of the network model. The ROP prediction results obtained from different ANN models are also compared with traditional models such as the Bingham model, Bourgoyne & Young model. These results have shown the competitiveness of the ANN model and its high applicability to actual drilling operations.
Abstract. As society develops, many aspects of life are concerned by people, including facial skincare, avoiding acne-related diseases. In this work, we will propose a complete solution for treating acne at home, including 4 processors. First, the anomaly detector uses image processing techniques by Multi-Threshold and Color Segmentation, depending on each color channel corresponding to each type of acne. The sensitivity of the detector is 89.4%. Second, the set of anomalies classifiers into 6 main categories, including 4 major acne types and 2 non-acne types. By applying the convolutional neural model, the accuracy, sensitivity, and F1 are 84.17%, 81.5%, and 82%, respectively. Third, the acne status assessment kit is based on the mGAGS method to classify the condition of a face as mild, moderate, severe, or very severe with an accuracy of 81.25%. Finally, the product recommender, which generalizes from the results of the previous processors with an accuracy of 70-90%. This is the premise that helps doctors as well as general users to evaluate the level of acne on a face effectively and save time.
Abstract. Nowadays in the construction of modem buildings, it is necessary to accommodate pipes and ducts necessary services, such as air conditioning, water supply, sewerage, electricity, computer networks, and telephone networks. Cellular members – steel I‐ shaped structural elements with circular web openings at regular intervals – have been used as beams for more than 35 years now. Although in the past already a large deal of research was performed into the subject of the behavior of cellular beams, almost no attention has been paid to the application of cellular members as columns. The column will be analyzed using the finite element method to calculate the critical load and compared with the Eurocode3 standard, web-post buckling, and frame using cellular member by FEM.
Abstract. Diabetic retinopathy (DR) is a complication of diabetes mellitus that causes retinal damage that can lead to vision loss if not detected and treated promptly. The common diagnosis stages of the disease take time, effort, and cost and can be misdiagnosed. In the recent period with the explosion of artificial intelligence, deep learning has become the most popular tool with high performance in many fields, especially in the analysis and classification of medical images. The Convolutional Neural Network (CNN) is more widely used as a deep learning method in medical imaging analysis with highly effective. In this paper, the five-stage image of modern DR (healthy, mild, moderate, severe, and proliferative) can be detected and classified using the deep learning technique. After cross-validation training and testing on the corresponding 5,590-image dataset, a pre-MobileNetV2 training model is proposed in classifying stages of diabetic retinopathy. The average accuracy of the model achieved was 93.89% with the precision of 94.00%, recall 92.00% and f1-score 90.00%. The corresponding thermal image is also given to help experts for evaluating the influence of the retina in each different stage.