HighTech and Innovation Journal
Not a member yet
317 research outputs found
Sort by
Aspect-Level Sentiment Analysis through Aspect-Oriented Features
Full text linkAspect-level sentiment analysis is essential for businesses to comprehend sentiment polarities associated with various aspects within unstructured texts. Although several solutions have been proposed in recent studies in sentiment analysis, a few challenges persist. A significant challenge is the presence of multiple aspects within a single written text, each conveying its own sentiments. Besides this, the exploration of ensemble learning in the existing literature is limited. Therefore, this study proposes a novel aspect-level sentiment analysis solution that utilizes an ensemble of Bidirectional Long Short-Term Memory (BiLSTM) models. This innovative solution extracts aspects and sentiments and incorporates a rule-based algorithm to combine accurate sets of aspect and sentiment features. Experimental analysis demonstrates the effectiveness of the proposed methodology in accurately extracting aspect-level sentiment features from input texts. The proposed solution was able to obtain an F1 score of 92.98% on the SemEval-2014 Restaurant dataset when provided with the correct set of aspect-level sentiment features and an F1 score of 95.54% on the SemEval-2016 Laptop dataset when provided with the aspect-level sentiment features generated by the aspect-sentiment mapper algorithm. Doi: 10.28991/HIJ-2024-05-01-09 Full Text: PD
Improving Sensing Measurements Using Laser Self-Mixing Interference in Non-Line-of-Sight Optical Communication via Systems
Full text linkObjective: Mobile robots leverage laser self-mixing interference for sensing in non-line-of-sight optical communications, allowing for a wide range of measures such as distance, velocity, and displacement, while also improving accuracy and flexibility in robotic navigation and interaction. Interference, restricted range, and sensitivity to environmental factors are challenges that affect the precision and reliability of sensing measures. Methods: This paper presents a detailed introduction to theory and various algorithms of channel estimation in wireless communication. Combining the characteristics of UV channels, a channel estimation algorithm suitable for UV optical communication systems is selected, and relevant simulations are carried out. A theoretical analysis of channel estimation SNR and a proposed angle measurement method using laser self-mixing interference are discussed. A device is designed to implement this method, utilizing self-mixing interferometric fringe counting to measure rotation displacement in mobile robots. Findings: In results, sensing measurement and modality are employed for SNR and robotic localization performance. Distance (15 dB), velocity (12 dB), and object shape (18 dB) in SNR and laser range finder (5 cm), camera (15 cm), and LiDAR (3 cm) in robotic localization performance. Conclusion: Incorporating laser self-mixing interference effects into non-line-of-sight optical communication for mobile robotics enhances sensing precision across diverse measurements, fostering robustness and adaptability in dynamic environments. Doi: 10.28991/HIJ-2024-05-04-012 Full Text: PD
Evaluating the Performance of Topic Modeling Techniques for Bibliometric Analysis Research: An LDA-based Approach
Full text linkDigital technologies have been used for a vast amount of bibliometric analysis research. Although these technologies have made scientific investigation more accessible and efficient, scholars now face the daunting task of sifting through an overwhelming number of documents. This study aims to identify bibliometric research analysis's primary topics, categories, and latent topics from a global perspective. This study utilized topic modeling techniques to analyze the abstracts of 16,039 eligible papers published between 1977 and 2023 in the Scopus database. Through the use of Latent Dirichlet Allocation (LDA) topic modeling, the study was able to identify four distinct research topics and observe how they have evolved over time. The research topic has shifted its focus from individual concepts and words to relationships between nodes and conceptual, intellectual, and social structures. The study's findings have significant implications for bibliometric analysis-related research, providing valuable insights into trends and patterns in bibliometric analysis content within large digital article archives. The LDA has proven to be an efficient tool for analyzing these trends and patterns quickly. This study's novel approach considers factors for word embedding usage and optimal topic numbers. It focuses on a full understanding of the LDA results and combines statistical analysis, domain knowledge, and temporal exploration to better understand how data structures work. Doi: 10.28991/HIJ-2024-05-02-07 Full Text: PD
Using Multilayer Perceptron Neural Network to Assess the Critical Factors of Traffic Accidents
Full text linkThis study is based on the traffic accident data of Taoyuan City from the government's open data. The study compiled the data set of traffic accidents in Taiwan from 2012 to 2017, and six classifiers were applied to evaluate the effectiveness of traffic accident prediction with the number of injuries as the prediction target. In order to verify the classifier's stability, cross-validation was used to evaluate the model during the training process, and the multilayer perceptron neural network (MLPNN) classifier performed best in testing the dataset's accuracy and evaluating the model's best performance. Then, a boosting ensemble learning approach and a combination of traffic accident factors improve the experiment's performance. According to this experiment, the results show that this study uses the Pearson Chi-square feature selection method to select important traffic factor combinations, and the boosting method indeed helps improve the effectiveness of the construction of the traffic accident model. Finally, the experimental results of the NN-MLP model have a correct rate of 77% and AUC is 78.7%. In constructing the model, it was found that the degree of injury, the part of the vehicle hit, the type of accident, the leading cause, the type of vehicle, and the period of the accident were the main factors causing dangerous traffic accidents. Doi: 10.28991/HIJ-2024-05-01-012 Full Text: PD
Visual Instruction Tuning for Drone Accident Forensics
Full text linkThe increasing use of drones in both commercial and personal use has led to a growing demand for effective forensic analysis following drone-related accidents. This research focuses on improving forensic analysis through the development of LLaVAFor, a fine-tuned version of the Large Language and Vision Assistant (LLaVA) model. The objective of this study is to enhance the interpretability of visual instruction tuning for drone accident forensics. LLaVAFor was developed by fine-tuning LLaVA via a specialized dataset of drone accident scenarios. The model's performance was evaluated via the BLEU score, a metric commonly used to assess machine translation and natural language processing models. The results demonstrated that LLaVAFor achieved superior BLEU scores compared with baseline models such as LLaVA, Google Gemini, and ChatGPT. It demonstrates its ability to provide more accurate and contextually relevant analyses. The key innovation in LLaVAFor is its ability to explain forensic findings in the context of drone accidents, making it a valuable tool for investigators. The results show that the model's fine-tuning process on drone-specific datasets enables it to offer detailed, domain-specific insights, improving the accuracy and reliability of forensic analyses in this field. Through these advancements, LLaVAFor represents a step forward in the integration of AI into drone accident investigations. Doi: 10.28991/HIJ-2024-05-04-01 Full Text: PD
The New Way of Tourism in Green Economy Style for Sustainable Community Development and Empowerment
Full text linkThe New way of Tourism in Green Economy Style" has been adopted in Thailand to strengthen the social development of the communities and enhance the local development to achieve a sustainable and resilient framework. This article aims to study the context, model, process, success factors, and ways to expand tourism management results of the model to the communities in Thailand. This study adopts mixed methodology research. The study area consisted of the Pak Phanang Community in Pak Phanang District, Nakhon Si Thammarat Province; the Ton Duan Community in Khuan Khanun District, Phatthalung Province; and the Khlong Dan Community in Ranod District, Songkhla Province. The sample size is 1200 respondents, inclusive of 400 respondents from each of three study area communities. The key informants consisted of a group of tourists in the model community, a group of executives/boards/vendors, and a group of academics and travel agency representatives. The study found that the context of the three communities facilitated the emergence of management of the "New Way of Tourism in Green Economy Style”. The process is divided into three steps. Firstly, Community Based (CBT) consists of Natural Resources and Culture, Community Organization, Management and Learning. Secondly, the 7 Greens consist of Green Hearts, Green Communities, Green Attractions, Green Activities, Green Logistics, Green Services, and Green Plus. Lastly, the Profit RBG-P-C Concept, which consists of Return of Profit to Community, Bring Profit to Take Care of Community, and Giving Profit Back to the Community. Factors contributing to the success of tourism management in the model communities include leadership factors, structural and workflow factors, participation factors, and other factors. The guidelines for expanding tourism management will use the model for expanding the results together with the propulsion mechanism, including building cooperation from the people, management of natural resource use and the environment, building faith for green tourism, and the distribution of profits universally and fairly. Doi: 10.28991/HIJ-2024-05-04-015 Full Text: PD
Innovative Label Embedding for Food Safety Comment Classification: Fusion of Self-Semantic and Self-Knowledge Features
Full text linkFood safety comment classification represents a specialized task within the realm of text classification. The objective is to efficiently identify a large volume of food safety comments, aiding relevant authorities in timely food analysis and safety alerts. Traditional methods typically employ one-hot encoding for label processing. However, in real-world situations, classified labels often convey valuable semantic information and guidance. This paper introduces an innovative approach to enhance the classification performance of food safety comments by embedding label information. Initially, we extracted generic sentiment pivot words from various classification labels as label description information. Subsequently, we employ a joint embedding approach to integrate this label description information into the text. This process will pool the expressions of the pivot word into the corresponding sentiment labels in the known domains after averaging to get the embedded expression. This aims to acquire highly detailed self-semantic feature vectors and self-knowledge feature vectors that are integrated with labeled descriptive information. Then, feed the semantic representation of comments and the word-embedded representation of labeled description information into a time-step-based multilayer Bi-LSTM and a step-based multilayer CNN, respectively. Ultimately, we concatenate these two feature vectors to facilitate matching, thereby fusing the self-semantic and self-knowledge features of labeled description information to train a classification model for food safety comments. Experimental results on the food safety comment dataset showcase a noteworthy improvement of 1.74% and 1.27% in Macro_Precision and Macro_F1 metrics, respectively, compared to BERT, BERT-RNN, and BERT-CNN. Through extensive ablation experiments and additional studies, our method effectively embeds labeling information, demonstrating a clear advantage over traditional methods in the task of classifying food safety comments. Doi: 10.28991/HIJ-2024-05-01-013 Full Text: PD
Social Media, Knowledge Management, and Learning in Farmer Innovation
Full text linkThis study aims to address the research gap by investigating how social media influences the innovation ability of new professional farmers, with a specific focus on technological perspectives. Grounded in embeddedness theory and taking into account the roles of knowledge management and learning orientation, the research aims to unveil the dynamics shaping farmer innovation within the context of social media engagement. Employing a structural equation model and utilizing survey data from 336 farmers, the empirical research concludes that social media embedding significantly and positively impacts the innovation ability of new professional farmers. Knowledge management acts as a partial intermediary between network media embedding and the innovation ability of new professional farmers, and a complete intermediary between network community embedding and their innovation ability. Learning orientation positively moderates the relationship between network media embedding, network community embedding, and knowledge management. The study seeks to contribute to the comprehension of how social media can foster innovation among farmers, thereby promoting high-quality and sustainable development in agriculture. In light of this, recommendations are suggested for the government to encourage social media usage, for farmers to enhance their media literacy, strengthen knowledge management, and cultivate a learning-oriented mindset. Doi: 10.28991/HIJ-2024-05-02-06 Full Text: PD
Spatial-Temporal Characteristics of Green Development Level in River Basin
Full text linkThe Tuojiang Basin accounts for 30.8% of Sichuan Province's GDP, but the total water resources account for only 3.5%, resulting in increasing problems of water shortage, environmental deterioration and pollution, which further affects green development in the Basin. The objective of this paper is to investigate the green development of the Basin, expose deficiencies and ultimately unravel the path toward green development in the river basin of China. This paper was based on a green development measurement system under Economy-Nature-Resource-Society-Pollution perspectives and used Crtic method to calculate the weights of system indicators. Then Gray Correlation-Topsis evaluation model was used to measure green development level from 2009 to 2020. Finally, spatial evolution of green development in Tuojiang Basin was analyzed through Moran Index. The results showed that economy and pollution are the important factors of green development. And overall green development level was showing a trend of decreasing first then rising, which reached the lowest in 2014 and highest in 2019. Moreover, all cities in Tuojiang Basin except Ziyang reached a high level of green development in 2020. This paper added various pressure indicators produced by environmental pollution to the index system and enriched the evaluation index system for green development. Doi: 10.28991/HIJ-2024-05-04-014 Full Text: PD
Improving the Air Quality Monitoring Framework Using Artificial Intelligence for Environmentally Conscious Development
Full text linkThis study aims to significantly improve air quality monitoring through the innovative application of Artificial Intelligence (AI). Introducing the Artificial Intelligence Kualitas Udara (AIKU) model, this research offers a novel approach by integrating advanced machine learning algorithms with environmental sensors to predict air quality in real-time more accurately than traditional methods. The novelty of the AIKU model lies in its sophisticated data analytics framework, which processes high-frequency environmental data to assess air quality changes dynamically. The technique employs calibrating and deploying the AIKU model across various urban and suburban settings and analyzing its performance against conventional monitoring systems such as the Internet of Things (IoT) and Wireless Sensor Networks (WSNs). The results demonstrate that AIKU significantly outperforms these traditional systems in both accuracy and speed of response, highlighting its effectiveness in real-time environmental monitoring. Furthermore, the AIKU model's scalability and adaptability are tested, showing promising potential for application in densely populated urban areas and less populated rural settings. This research contributes to environmental monitoring by demonstrating how AI can transform traditional methodologies into more effective, scalable, and intelligent ecological management systems. This research provides substantial evidence that the AIKU model can serve as a powerful tool for sustainable and smart development worldwide, enhancing the ability of governments and organizations to respond to environmental challenges promptly and effectively. Doi: 10.28991/HIJ-2024-05-03-017 Full Text: PD