• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Proceedings of the Microbiological Society of Korea Conference
• /
• 2007.05a
• /
• pp.65-67
• /
• 2007

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.879-884
• /
• 2004

This paper describes the development of a synthetic multi-agent called KMITL Cadence 2003. KMITL Cadence 2003 is a robotic soccer simulation team consisting of eleven autonomous software agents. Each agent operates in a physical soccer simulation model called Robocup Soccer Server which provides fully distributed and real-time multi-agent system environment. All teammates have to cooperate to achieve the common goal of winning the game. The simulation models many aspects of the football field such as noise in ball movements, noisy sensors, unreliable communication channel between teammates and actuators, limited physical abilities and restricted communication. This paper addresses the algorithm to develop the soccer agents to perform basic actions which are scoring, passing ball and blocking the opponents effectively. The result of this development is satisfactory because the successful scoring attempts is increased from 11.1% to 33.3%, successful passing ball attempts is increased from 22.08% to 63.64%, and also, successful intercepting attempts is increased from 88% to 97.73%.

• Membrane and Water Treatment
• /
• v.3 no.2
• /
• pp.113-121
• /
• 2012

Up-flow multi-layer bioreactor (UMBR) is a hybrid system using dual sludge that consists of an up-flow multi-layer bioreactor as anaerobic/anoxic suspended growth microorganisms followed by an aeration tank. The UMBR acts as a primary settling tank, anaerobic/anoxic reactor, thickener which requires low energy due to mixing by up-flow stream. This study focused on using a pilot UMBR plant with capacity of 20-30 $m^3$/day for domestic wastewater in HCMC. HRTs of UMBR and aeration tank were 4.8 h and 7.2 h, respectively. The average MLSS of UMBR ranged from 10,000-13,600 mg/l SS. Internal recycle rate and sludge return were 200-300% and 150-200%, respectively. The results obtained from this study at flow rate of 20 $m^3$/day showed that removal of COD, SS, TKN, N-$NH_4$, T-N, and color were 91%, 87%, 86%, 80%, 91% and 91%, respectively.

• Steel and Composite Structures
• /
• v.37 no.6
• /
• pp.695-709
• /
• 2020

The buckling properties of a single-layered graphene sheet (SLGS) are examined using nonlocal integral first shear deformation theory (FSDT) by incorporating the influence of visco-Pasternak's medium. This model contains only four variables, which is even less than the conventional FSDT. The visco-Pasternak's medium is introduced by considering the damping influence to the conventional foundation model which modeled by the linear Winkler's coefficient and Pasternak's (shear) foundation coefficient. The nanoplate under consideration is subjected to compressive in- plane edge loads per unit length. The impacts of many parameters such as scale parameter, aspect ratio, the visco-Pasternak's coefficients, damping parameter, and mode numbers on the stability investigation of the SLGSs are examined in detail. The obtained results are compared with the corresponding available in the literature.

• Nutrition Research and Practice
• /
• v.2 no.2
• /
• pp.85-92
• /
• 2008

The present study was conducted to develop a Multi-dimensional Body Image Scale for Malaysian female adolescents. Data were collected among 328 female adolescents from a secondary school in Kuantan district, state of Pahang, Malaysia by using a self-administered questionnaire and anthropometric measurements. The self-administered questionnaire comprised multiple measures of body image, Eating Attitude Test (EAT-26; Gamer & Garfinkel, 1979) and Rosenberg Self-esteem Inventory (Rosenberg, 1965). The 152 items from selected multiple measures of body image were examined through factor analysis and for internal consistency. Correlations between Multi-dimensional Body Image Scale and body mass index (BMI), risk of eating disorders and self-esteem were assessed for construct validity. A seven factor model of a 62-item Multi-dimensional Body Image Scale for Malaysian female adolescents with construct validity and good internal consistency was developed. The scale encompasses 1) preoccupation with thinness and dieting behavior, 2) appearance and body satisfaction, 3) body importance, 4) muscle increasing behavior, 5) extreme dieting behavior, 6) appearance importance, and 7) perception of size and shape dimensions. Besides, a multidimensional body image composite score was proposed to screen negative body image risk in female adolescents. The result found body image was correlated with BMI, risk of eating disorders and self-esteem in female adolescents. In short, the present study supports a multi-dimensional concept for body image and provides a new insight into its multi-dimensionality in Malaysian female adolescents with preliminary validity and reliability of the scale. The Multi-dimensional Body Image Scale can be used to identify female adolescents who are potentially at risk of developing body image disturbance through future intervention programs.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.4
• /
• pp.284-287
• /
• 2008

In this paper, we introduce multi-intuitionistic fuzzy sets and intuitionistic fuzzy hybrid sets. The basic operations between such structures are defined. The use of these structures in the definition of intuition is tic fuzzy variants of P systems and their properties are presented.

• Nonlinear Functional Analysis and Applications
• /
• v.27 no.4
• /
• pp.731-742
• /
• 2022

In this paper, we present a new mixed type iterative process for approximating the common fixed points of single-valued nonexpansive mapping and multi-valued nonexpansive mapping in a CAT(0) space. We demonstrate strong and weak convergence theorems for the new iterative process in CAT(0) spaces, as well as numerical results to support our theorem.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.263-265
• /
• 2003

The computation cost of image registration is affected by searching data size and space. This paper proposes an efficient image registration algorithm that uses multi-resolution wavelet decomposed image to reduce the data size search. The algorithm determines the correlation detection at low resolution on low-pass sub bands of wavelet and generate mask for higher resolution as part of a coarse to fine registration algorithm. The correlation matching is defined for coarse resolution similarity measurement, while mutual information (MI) is used at fine resolution. The results show that the new efficient mask-based algorithm improves computational efficiency and yields robust and consistent image registration results.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.25-32
• /
• 2023

Decision-making refers to identifying the best alternative among a set of alternatives. When a set of criteria are involved, the decision-making is called multi-criteria decision-making (MCDM). In some cases, the involved criteria may be prioritized by the human decision-maker, which determines the importance degree for each criterion; hence, the decision-making becomes prioritized multi-criteria decision-making. The essence of prioritized MCDM is raking the different alternatives concerning the criteria and selecting best one(s) from the ranked list. This paper introduces a generic multi-level algorithm for ranking multiple alternatives in prioritized MCDM problems. The proposed algorithm is implemented by a decision support system for selecting the most critical short-road requests presented to the transportation ministry in the Kingdom of Saudi Arabia. The ranking results show that the proposed ranking algorithm achieves a good balance between the importance degrees determined by the human decision maker and the score value of the alternatives concerning the different criteria.