Browsing by Author "Phuripoj Kaewyong"

Now showing 1 - 5 of 5
  • Default Image
    Item
    A correlation analysis between sentimental comment and numerical response in students' feedback
    (Asian Research Publishing Network, 2015) Phuripoj Kaewyong; Anupong Sukprasert; Naomie Salim; Fatin Aliah Phang; P. Kaewyong; Information Technology Department, Suan Dusit University, Thailand; email: phuripoj@yahoo.com
    This paper aims to study a qualitative measuring of students' comments using sentiment analysis to teacher evaluation and investigate its qualitative analysis. A small dataset of students' feedbacks was collected from the public website and was utilized in the experimental. We performed the lexicon based sentiment analysis to identify sentiment word and determine overall sentiment polarity of students' comment into positive and negative classes based on Opinion Lexicon automatically. A comparison between overall sentiment scores and numerical response scores of teacher evaluation aspects were evaluated and plotted into graphs in order to compare the relationship between each pair of two variables. Especially, we applied the statistical techniques using Pearson's correlation and Spearman's rank to confirm these visual correlation results. The experimental results suggested that there is a significant correlation between overall sentiment scores from its qualitative analysis and numerical response scores of teacher evaluation aspects. Based on this, it might be possible to convert from qualitative to quantitative type of teacher evaluation by performing lexicon based sentiment analysis.
  • Default Image
    Item
    An Intelligent Recommendation for Intelligently Accessible Charging Stations: Electronic Vehicle Charging to Support a Sustainable Smart Tourism City
    (MDPI, 2023) Pannee Suanpang; Pitchaya Jamjuntr; Phuripoj Kaewyong; Chawalin Niamsorn; Kittisak Jermsittiparsert; P. Suanpang; Faculty of Science & Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.th; K. Jermsittiparsert; Faculty of Education, University of City Island, Famagusta, 9945, Cyprus; email: kittisak.jermsittiparsert@adakent.edu.tr
    The world is entering an era of awareness of the preservation of natural energy sustainability. Therefore, electric vehicles (EVs) have become a popular alternative in todayÕs transportation system as they have zero emissions, save energy, and reduce pollution. One of the most significant problems with EVs is an inadequate charging infrastructure and spatially and temporally uneven charging demands. As such, EV drivers in many large cities frequently struggle to find suitable charging locations. Furthermore, the recent emergence of deep reinforcement learning has shown great promise for improving the charging experience in a variety of ways over the long term. In this paper, a Spatio-Temporal Multi-Agent Reinforcement Learning (STMARL) (Master) framework is proposed for intelligently public-accessible charging stations, taking into account several long-term spatio-temporal parameters. When compared to a random selection recommendation system, the experimental results demonstrate that an STMARL (master) framework has a long-term goal of lowering the overall charging wait time (CWT), average charging price (CP), and charging failure rate (CFR) of EVs. © 2022 by the authors.
  • Default Image
    Item
    Autonomous Energy Management by Applying Deep Q-Learning to Enhance Sustainability in Smart Tourism Cities
    (MDPI, 2022) Pannee Suanpang; Pitchaya Jamjuntr; Kittisak Jermsittiparsert; Phuripoj Kaewyong; P. Suanpang; Faculty of Science and Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.th
    Autonomous energy management is becoming a significant mechanism for attaining sustainability in energy management. This resulted in this research paper, which aimed to apply deep reinforcement learning algorithms for an autonomous energy management system of a microgrid. This paper proposed a novel microgrid model that consisted of a combustion set of a household load, renewable energy, an energy storage system, and a generator, which were connected to the main grid. The proposed autonomous energy management system was designed to cooperate with the various flexible sources and loads by defining the priority resources, loads, and electricity prices. The system was implemented by using deep reinforcement learning algorithms that worked effectively in order to control the power storage, solar panels, generator, and main grid. The system model could achieve the optimal performance with near-optimal policies. As a result, this method could save 13.19% in the cost compared to conducting manual control of energy management. In this study, there was a focus on applying Q-learning for the microgrid in the tourism industry in remote areas which can produce and store energy. Therefore, we proposed an autonomous energy management system for effective energy management. In future work, the system could be improved by applying deep learning to use energy price data to predict the future energy price, when the system could produce more energy than the demand and store it for selling at the most appropriate price; this would make the autonomous energy management system smarter and provide better benefits for the tourism industry. This proposed autonomous energy management could be applied to other industries, for example businesses or factories which need effective energy management to maintain microgrid stability and also save energy. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
  • Default Image
    Item
    IoT Smart Innovation Bin for Promote Learning Garbage Segregation
    (2023-12-19) Chutiwan Boonarchatong; Thinnagorn Chunhapataragul; Saisuda Pantrakool; Phuripoj Kaewyong; Kanitta Wongma; Kongsak Boonarchatong
    The aims of this research were to develop smart innovative trash bins to be used as learning media for garbage segregation and to assessment the learning outcomes after playing the game with smart innovative trash bins. The sample group consisted of 400 grade 4, 5, and 6 students. A set of smart innovative trash bin contains four trash bins classified by type: 1) biodegradable garbage (green bin), 2) hazardous garbage (red bin), 3) general garbage (blue bin), and 4) recycle garbage (yellow bin). The bin embedded the program code in the Arduino board. Twelve garbage items, four types, had RFID tags. When users bring garbage into the correct type of garbage bin, the trash bin lid will open and close by itself. On the other hand, if the garbage is placed in the wrong garbage bin, the lid will not open. The result shown the sample group’s learning outcome of garbage segregation increased by with 3.52 scores or 17.6%. In summary, smart innovative trash bins able to promote learning outcomes of garbage segregation.
  • Default Image
    Item
    Tourism Service Scheduling in Smart City Based on Hybrid Genetic Algorithm Simulated Annealing Algorithm
    (MDPI, 2022) Pannee Suanpang; Pitchaya Jamjuntr; Kittisak Jermsittiparsert; Phuripoj Kaewyong; P. Suanpang; Faculty of Science & Technology, Suan Dusit University, Bangkok, 10300, Thailand; email: pannee_sua@dusit.ac.th
    The disruptions in this era have caused a leap forward in information technology being applied in organizations to create a competitive advantage. In particular, we see this in tourism services, as they provide the best solution and prompt responses to create value in experiences and enhance the sustainability of tourism. Since scheduling is required in tourism service applications, it is regarded as a crucial topic in production management and combinatorial optimization. Since workshop scheduling difficulties are regarded as extremely difficult and complex, efforts to discover optimal or near-ideal solutions are vital. The aim of this study was to develop a hybrid genetic algorithm by combining a genetic algorithm and a simulated annealing algorithm with a gradient search method to the optimize complex processes involved in solving tourism service problems, as well as to compare the traditional genetic algorithms employed in smart city case studies in Thailand. A hybrid genetic algorithm was developed, and the results could assist in solving scheduling issues related to the sustainability of the tourism industry with the goal of lowering production requirements. An operation-based representation was employed to create workable schedules that can more effectively handle the given challenge. Additionally, a new knowledge-based operator was created within the context of function evaluation, which focuses on the features of the problem to utilize machine downtime to enhance the quality of the solution. To produce the offspring, a machine-based crossover with order-based precedence preservation was suggested. Additionally, a neighborhood search strategy based on simulated annealing was utilized to enhance the algorithmÕs capacity for local exploitation, and to broaden its usability. Numerous examples were gathered from the Thailand Tourism Department to demonstrate the effectiveness and efficiency of the proposed approach. The proposed hybrid genetic algorithmÕs computational results show good performance. We found that the hybrid genetic algorithm can effectively generate a satisfactory tourism service, and its performance is better than that of the genetic algorithm. © 2022 by the authors.