Agent-based modeling of collaborative interaction in ubiquitous learning environment using local dynamic behavior

This paper focuses on modeling collaborative interaction in Ubiquitous Learning Environment (ULE) based on the assumption that the collaborative interaction can be perceived through interpersonal interactions, which can be described as local dynamic behaviors of the team. In this paper, the collaborative interaction is collected from the experiment with 50 students having 5 members per team. Then the collaborative interaction is coded with 16 participation shift (P-shifts) from 5 different types of turns including turn receiving, turn claiming, turn usurping, turn continuing, and turn noreturning to represent the participation status of each member. Three types of participation statuses used in this paper are the contributor, the target and the unaddressed recipient. Then the discovered local dynamic behavior is used for constructing the model by using agent-based modeling. The model consists of student agents working together according to the discovered behavior. Then, the constructed model is verified by comparing the actual behavior with the simulated behavior. Finally, the comparison result shows that the constructed model can reasonably be the model for modeling collaborative interaction in ULE.     

Effect of vacuum packaging on shelf-life extension of cooked and peeled harpiosquillid mantis shrimp (Harpiosquilla raphidea) during refrigerated storage

Effects of vacuum packaging (VP) on quality changes of cooked and peeled harpiosquillid mantis shrimp (HMS) during storage at 4 °C of 15 days were investigated. VP inhibited bacterial growth as ascertained by the lower rate of increases in total viable and psychrotrophic bacteria counts as well as other pathogenic and spoilage bacteria counts. VP samples had lower total volatile base and trimethylamine contents as compared to the sample packed in air (AP). Clostridium perfringens was undetectable in both samples. During storage, VP samples possessed lower pH than AP counterpart. Exudate and TCA-soluble peptide (TSP) contents of sample increased during the storage, regardless of packaging atmospheres. Fatty acid (FA) content, especially PUFA and MUFA, was decreased after 9 and 15 days of storage for AP and VP samples, respectively. The cooked and peeled HMS contained 32 volatile organic compounds, consisting of several aldehydes and alcohols. Carnobacterium and Pseudomonas were mainly involved in spoilage in samples as confirmed by next generation sequencing.     

Determining Significant Classification Factors for Senior Learning: A Case Study of Thai Seniors and Social Media Skill Learning

The senior learns in order to have a better quality of life. The challenge of seniors in learning is their learning ability that deteriorates because of age. Suitable management for different types of seniors, so called personalized learning is required. Therefore, this study focuses on determining significant classification factors for classification of seniors which is an important component of personalized learning. In this study, the assumption of personal background and health issue can be used for classifying types of seniors. The decision tree is used for determining significant classification factors and constructing the model. The study is conducted with 75 seniors for social network skill learning. The classification results show that the significant classification factors affecting the classification model of senior learning are age, daily internet time spending, number of applications, memory problem, and education background. The model constructed by decision tree provides 93.33% classification accuracy. Also, the obtained factors are verified by testing with two machine learning methods including artificial neural network (ANN) and K-nearest neighbors (K-NN). The comparison results show that 5 factors provide high classification accuracy for both classifiers, which are 93.33% and 92.00% for ANN, and K-NN, respectively.

     

A group signature based buyer coalition scheme with trustable third party

Despite the large number of existing buyer coalition schemes and increasing need for trusting relationship in buyer coalitions, no current buyer coalition scheme explicitly addresses trust issues within these schemes in a formalised manner. Without establishing a trusting relationships among various roles, many buyers may not be willing to join the coalitions. This study proposes a solution, in the form of an algorithmic design, as a response to the above need. Specific features of the proposed solution are: (i) the use of ‘group signature’ in order to guarantees anonymity within a group that results in trustfulness of the relationships and (ii) introducing a new role called ‘authority’ to maintain and implement anonymity. In addition, the proposed scheme is capable of maintaining ‘correctness’ and ‘accountability’ by both identifying misbehaved buyers as well as implementing various punishment methods.Knowledge domain of the study is the common space between three overlapping fields including Electronic Commerce, Communication Technologies and Information Systems.     

Addable Stress Speech Recognition with Multiplexing HMM: Training and Non-training Decision

In stress speech recognition, a recognition model that is capable of processing multi-stress speech needs to be designed in the view points of accuracy and add-ability. This paper proposes addable stress speech recognition with multiplexing Hidden-Markov model (HMM). To achieve multi-stress speech, we propose a multiplexing topology that combines multiple stress speech models. Since each stress affects a speech in different way, having a speech recognition model that specifically trained to recognize words effected by the stress help improve the recognition rates. However, since each stress speech model gives it own independent recognized word, we need to have an effective decision module to choose the correct word. In each stress speech model, a MFCC is applied to the input speech. The result is fed into a HMM that is segmented into N parts. Each part of the segmentation provides its own tentative recognized word which in turn is an input to the proposed non-training decision module. Based on these tentative recognized words from segments of all stress speech models, the final recognized word is decided using coarse-to-fine concept performed by a majority vote, segment-weighted difference square score and next best score, respectively. Besides neutral speech, the proposed method was verified using three stresses including angry, loud, and Lombard. The results showed that the proposed method achieved 94.7 % recognition rate comparing to 94.2 % of the training-based decision method.     

Personalized Recommendation Method for Preventing Elderly People from Cardiovascular Disease Complication Using Integrated Objective Distance

Wireless Personal Communications - Nowadays, people are living longer than in the past which leads to dramatically increasing numbers of elderly people in the world’s populations....     

Ubiquitous Learning Environment: Smart Learning Platform with Multi-Agent Architecture

Ubiquitous learning (u-learning) has become popular nowadays in education area. The key factor of u-leaning is that the learners are situated in a context-aware learning environment and they may not even be conscious of the learning process. This paper aims to develop the ubiquitous learning environment (ULE) being able to provide the content to the learners appropriately and adaptively. The developed ULE consists of several leaning objects (LOs) having the multi-agent architecture to achieve adaptability. Each LO consists of three different agents coordinating together including a personal agent for keeping the users’ profiles and their historic actions, a content agent for selecting LO to the learners, and a representation agent for presenting the content to the learners. Two empirical studies are conducted in this paper including architecture and learning mode empirical study. For both empirical studies, the learning efficiency enhancement and students’ satisfaction in terms of functionality and adaptability are evaluated. The results show that the developed ULE with multi agent architecture can enhance the students’ learning efficiency significantly for both individual and collaborative learning modes. Additionally, the students satisfy their learning through the developed ULE in the “satisfied” level in terms of functionality and adaptability for both empirical studies.     

Smart Care Environment with Food Recognition for Personalization Support: A Case Study of Thai Seniors

Like many countries worldwide, Thailand will become complete aging society shortly. The challenging of an aging society in the digital era is to enhance the quality of life for seniors through the employment of advanced and modern technology. This study proposes a smart care environment with food recognition module for personal healthcare purpose. More specifically, it is the mobile application for promoting personalized support for seniors. With context-aware perspective, the proposed environment employs clinical data and personal data for user modeling. It is designed to have the user-friendly interface providing convenient use for the seniors. Additionally, food recognition module is integrated for gathering real-time energy consumption with less distraction to the seniors. It is trained with a set of Thai food images using a convolution neural network. The case study is conducted with 50 Thai seniors in Chiang Rai, Thailand. Overall, the seniors strongly agree on both provided functional and personalized support. Also, they strongly agree that food recognition module can engage them to use this developed care environment.

     

Special Issue on: Towards a “Smart Society” Through Digital and Wireless Communication Technology

Wireless Personal Communications -     

VARK Learning Style Classification Using Decision Tree with Physiological Signals

Learning style is deemed crucial for different types of age groups. It is essential, especially for individual learning achievement. Learning is a part of cognitive processes affecting the human central nervous system, which can be monitored by using the physiological signals. In this study, physiological signals thus are proposed as key attributes for the classification of learning styles to avoid biased data from completing the questionnaire and promote the real-time response in the classroom environment. More specifically, heart rate and blood pressure signals are chosen for this study. Following the VARK model, the physiological signals of learners are classified with the decision tree into four different types, including visual, aural, read and write, and kinesthetic learners. There are 40 primary school children and 30 university students involved in the whole study. The results show that the proposed factors obtain 85% and 90% classification accuracy for children and university students, respectively. Both heart rate and blood pressure are thus reasonably impacted as the classification attributes.