• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.158-168
• /
• 2024

There is hardly any person in modern times who has not taken soft drinks instead of drinking water. The rate of people taking soft drinks being surprisingly high, researchers around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases and so on. Therefore, in this work an image-based tool is developed to monitor the nutritional information of soft drinks by using deep convolutional neural network with transfer learning. At first, visual saliency, mean shift segmentation, thresholding and noise reduction technique, collectively known as 'pre-processing' are adopted to extract the location of drinks region. After removing backgrounds and segment out only the desired area from image, we impose Discrete Wavelength Transform (DWT) based resolution enhancement technique is applied to improve the quality of image. After that, transfer learning model is employed for the classification of drinks. Finally, nutrition value of each drink is estimated using Bag-of-Feature (BoF) based classification and Euclidean distance-based ratio calculation technique. To achieve this, a dataset is built with ten most consumed soft drinks in Bangladesh. These images were collected from imageNet dataset as well as internet and proposed method confirms that it has the ability to detect and recognize different types of drinks with an accuracy of 98.51%.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.522-530
• /
• 2002

This paper introduces a neural network (NN) -based nonlinear predictor for the LP (Linear Prediction) residual. To evaluate the effectiveness of the NN-based nonlinear predictor for LP-residual, we first compared the average prediction gain of the linear long-term predictor with that of the NN-based nonlinear long-term predictor. Then, the effects on the quantization noise of the nonlinear prediction residuals were investigated for the NN-based nonlinear predictor A new NN predictor takes into consideration not only prediction error but also quantization effects. To increase robustness against the quantization noise of the nonlinear prediction residual, a constrained back propagation learning algorithm, which satisfies a Kuhn-Tucker inequality condition is proposed. Experimental results indicate that the prediction gain of the proposed NN predictor was not seriously decreased even when the constrained optimization algorithm was employed.

• Korean Institute of Interior Design Journal
• /
• v.23 no.5
• /
• pp.165-173
• /
• 2014

Located in Dornach, Switcherland Eurythmeum Anbau zu Haus Brodbeck (Rudolf Steiner-Halde, Eurythmeum Anbau zu Haus Brodbeck, 1923-1935) is one of the architectural works created by Rudolf Steiner (1861-1925) who has studied and established the cognitive and spiritual aspects of a human being, and is often cited as being the founder of anthroposophy. In fact, Eurythmeum Anbau zu Haus Brodbeck is not as well known as Steiner's other works, and it is perceived as less important than his major works of architecture including "Goetheanum", "Modellbau zu Malsch", and "Rudolf Steiner Haus Stuttgart". Nonetheless, this study is meaningful in itself since it is an important piece of architecture to gain an understanding of the characteristics of Steiner's late works, and the architectural characteristics of the Waldorf School where various active educational activities are taking place around the world. Eurythmeum Anbau zu Haus Brodbeck clearly exhibits the characteristics of the architectural space based on Steiner's anthroposophy as well as provides a window into promoting space efficiency by extending an existing building. Moreover, it provides a good learning opportunity to find out about how Steiner's architectural disposition has changed and developed with the use of new materials. With these points as a backdrop, the study aims to develop an understanding of the architectural characteristics of Eurythmeum Anbau zu Haus Brodbeck. Another important objective of this paper is to gain insight into the architectural implications in connection with the influence Eurythmeum Anbau zu Haus Brodbeck has had on Steiner's later works, by comparing his early works of architecture with those of his late works.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.415-420
• /
• 2002

This paper presents an efficient text categorization algorithm that generates high quality bigrams by using the information gain metric, combined with various frequency thresholds. The bigrams, along with unigrams, are then given as features to a Naive Bayes classifier. The experimental results suggest that the bigrams, while small in number, can substantially contribute to improving text categorization. Upon close examination of the results, we conclude that the algorithm is most successful in correctly classifying more positive documents, but may cause more negative documents to be classified incorrectly.

• East Asian mathematical journal
• /
• v.26 no.2
• /
• pp.165-177
• /
• 2010

The purpose of this study is to review previous studies regarding the relationship between graphing calculators usage and teaching and learning school mathematics and to suggest practical implications for further research in mathematics education. Through reviewing the total of 21 studies five subsections are divided in order to gain the answers to the research questions. The results of this study are as follows: students typically used graphing calculators in drawing graphs of functions, and they used graphing calculators as a tool for calculations, transformations, data collection and analysis, visualization, and checking. The implications for further research are suggested corresponding to these results.

• Research in Mathematical Education
• /
• v.13 no.3
• /
• pp.217-233
• /
• 2009

The purpose of this study is to describe how dynamic geometry systems can be useful in proof activity; teaching sequences based on the use of dynamic geometry systems and to analyze the possible roles of dynamic geometry systems in both teaching and learning of proof. And also dynamic geometry environments can generate powerful interplay between empirical explorations and formal proofs. The point of this study was to show that how using dynamic geometry software can provide an opportunity to link between empirical and deductive reasoning, and how such software can be utilized to gain insight into a deductive argument.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.259-265
• /
• 2022

This research aims to increase understanding of family participation in special education programs, to gain a deeper understanding of the programs themselves, and to determine the consequences of the research findings. It addresses the opportunities for families to participate in their children's learning journey and focuses on enhancing the experience of families participating in the education of students with intellectual disabilities. This study interviews four teachers of students with intellectual disabilities, and three important themes emerge from their discussion of whether parents should participate in special education programs for their children. The findings of this study have several important implications for future practice.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.2
• /
• pp.5-25
• /
• 2011

This study aims to identify the most effective statistical feature selecting method and context window size for word sense disambiguation using supervised methods. In this study, features were selected by four different methods: information gain, document frequency, chi-square, and relevancy. The result of weight comparison showed that identifying the most appropriate features could improve word sense disambiguation performance. Information gain was the highest. SVM classifier was not affected by feature selection and showed better performance in a larger feature set and context size. Naive Bayes classifier was the best performance on 10 percent of feature set size. kNN classifier on under 10 percent of feature set size. When feature selection methods are applied to word sense disambiguation, combinations of a small set of features and larger context window size, or a large set of features and small context windows size can make best performance improvements.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• Journal of Audiology & Otology
• /
• v.23 no.3
• /
• pp.121-128
• /
• 2019

Background and Objectives: There is a scant evidence on the use of simulations in audiology (especially in Malaysia) for case-history taking, although this technique is widely used for training medical and nursing students. Feedback is one of the important components in simulations training; however, it is unknown if feedback by instructors could influence the simulated patient (SP) training outcome for case-history taking among audiology students. Aim of the present study is to determine whether the SP training with feedback in addition to the standard role-play and seminar training is an effective learning tool for audiology case-history taking. Subjects and Methods: Twenty-six second-year undergraduate audiology students participated. A cross-over study design was used. All students initially attended two hours of seminar and role-play sessions. They were then divided into three types of training, 1) SP training (Group A), 2) SP with feedback (Group B), and 3) a non-additional training group (Group C). After two training sessions, the students changed their types of training to, 1) Group A and C: SP training with feedback, and 2) Group B: non-additional training. All the groups were assessed at three points: 1) pre-test, 2) intermediate, and 3) post-test. The normalized median score differences between and within the respective groups were analysed using non-parametric tests at 95% confidence intervals. Results: Groups with additional SP trainings (with and without feedback) showed a significantly higher normalized gain score than no training group (p<0.05). Conclusions: The SP training (with/without feedback) is a beneficial learning tool for history taking to students in audiology major.