Your search

Recently, a lot of Chinese patients consult treatment plans through social networking platforms, but the Chinese medical text contains rich information, including a large number of medical nomenclatures and symptom descriptions. How to build an intelligence model to automatically classify the text information consulted by patients and recommend the correct department for patients is very important. In order to address the problem of insufficient feature extraction from Chinese medical text and low accuracy, this paper proposes a dual channel Chinese medical text classification model. The model extracts feature of Chinese medical text at different granularity, comprehensively and accurately obtains effective feature information, and finally recommends departments for patients according to text classification. One channel of the model focuses on medical nomenclatures, symptoms and other words related to hospital departments, gives different weights, calculates corresponding feature vectors with convolution kernels of different sizes, and then obtains local text representation. The other channel uses the BiGRU network and attention mechanism to obtain text representation, highlighting the important information of the whole sentence, that is, global text representation. Finally, the model uses full connection layer to combine the representation vectors of the two channels, and uses Softmax classifier for classification. The experimental results show that the accuracy, recall and F1-score of the model are improved by 10.65%, 8.94% and 11.62% respectively compared with the baseline models in average, which proves that our model has better performance and robustness.

Cantonese opera has a long and profound history and has evolved over 700 years, making it unique and distinctive. In a diversified media and entertainment, Cantonese opera culture in Macao, like many other aspects of traditional Chinese cultures, is facing a general decline. Specific challenges include loss of audience, the decline and disintegration of professional groups, and reduced scope of the active repertoire. How can a new venue for traditional Cantonese opera promote a positive response to the contemporary challenges that threaten its cultural vitality? How can a new design approach respond to local issues and contemporary architectural production? Can programmatic diversification of a performance venue (cultural exchange, art display, education) be a useful strategy? This thesis consists of five parts. Part 1 of this thesis outlines the background of research, describes the purpose and significance of the research, and deal with issues of research method. Part 2 considers the artistic characteristics of Cantonese opera, including the spatial characteristics of traditional Cantonese opera theatres, the characteristics of Cantonese opera costumes, and the changing characteristics forms of performance. Part 3 is focused on the uses of parametric models in architectural design. Part 4 offers three case studies of opera houses in China, the Guangzhou Opera House, the Harbin Grand Theatre, and the Xiqu Centre in Hong Kong. Part 5, the core of this thesis, proposes a design of a new performance venue for Cantonese Opera House in Macao. Overall, this thesis offers an account of main considerations in the transformation process from traditional Cantonese opera venues to modern Cantonese opera houses and situates these considerations in the context of contemporary discussions of parametric architecture

There are a large number of symptom consultation texts in medical and healthcare Internet communities, and Chinese health segmentation is more complex, which leads to the low accuracy of the existing algorithms for medical text classification. The deep learning model has advantages in extracting abstract features of text effectively. However, for a large number of samples of complex text data, especially for words with ambiguous meanings in the field of Chinese medical diagnosis, the word-level neural network model is insufficient. Therefore, in order to solve the triage and precise treatment of patients, we present an improved Double Channel (DC) mechanism as a significant enhancement to Long Short-Term Memory (LSTM). In this DC mechanism, two channels are used to receive word-level and char-level embedding, respectively, at the same time. Hybrid attention is proposed to combine the current time output with the current time unit state and then using attention to calculate the weight. By calculating the probability distribution of each timestep input data weight, the weight score is obtained, and then weighted summation is performed. At last, the data input by each timestep is subjected to trade-off learning to improve the generalization ability of the model learning. Moreover, we conduct an extensive performance evaluation on two different datasets: cMedQA and Sentiment140. The experimental results show that the DC-LSTM model proposed in this paper has significantly superior accuracy and ROC compared with the basic CNN-LSTM model.

To solve the problem of one-sided pursuit of the shortest distance but ignoring the tourist experience in the process of tourism route planning, an improved ant colony optimization algorithm is proposed for tourism route planning. Contextual information of scenic spots significantly effect people’s choice of tourism destination, so the pheromone update strategy is combined with the contextual information such as weather and comfort degree of the scenic spot in the process of searching the global optimal route, so that the pheromone update tends to the path suitable for tourists. At the same time, in order to avoid falling into local optimization, the sub-path support degree is introduced. The experimental results show that the optimized tourism route has greatly improved the tourist experience, the route distance is shortened by 20.5% and the convergence speed is increased by 21.2% compared with the basic algorithm, which proves that the improved algorithm is notably effective.

The number of tourist attractions reviews, travel notes and other texts has grown exponentially in the Internet age. Effectively mining users’ potential opinions and emotions on tourist attractions, and helping to provide users with better recommendation services, which is of great practical significance. This paper proposes a multi-channel neural network model called Pre-BiLSTM combined with a pre-training mechanism. The model uses a combination of coarse and fine- granularity strategies to extract the features of text information such as reviews and travel notes to improve the performance of text sentiment analysis. First, we construct three channels and use the improved BERT and skip-gram methods with negative sampling to vectorize the word-level and vocabulary-level text, respectively, so as to obtain more abundant textual information. Second, we use the pre-training mechanism of BERT to generate deep bidirectional language representation relationships. Third, the vectors of the three channels are input into the BiLSTM network in parallel to extract global and local features. Finally, the model fuses the text features of the three channels and classifies them using SoftMax classifier. Furthermore, numerical experiments are conducted to demonstrate that Pre-BiLSTM outperforms the baselines by 6.27%, 12.83% and 18.12% in average in terms of accuracy, precision and F1-score.

Text classification is an important topic in natural language processing, with the development of social network, many question-and-answer pairs regarding health-care and medicine flood social platforms. It is of great social value to mine and classify medical text and provide targeted medical services for patients. The existing algorithms of text classification can deal with simple semantic text, especially in the field of Chinese medical text, the text structure is complex and includes a large number of medical nomenclature and professional terms, which are difficult for patients to understand. We propose a Chinese medical text classification model using a BERT-based Chinese text encoder by N-gram representations (ZEN) and capsule network, which represent feature uses the ZEN model and extract the features by capsule network, we also design a N-gram medical dictionary to enhance medical text representation and feature extraction. The experimental results show that the precision, recall and F1-score of our model are improved by 10.25%, 11.13% and 12.29%, respectively, compared with the baseline models in average, which proves that our model has better performance.

Hydrothermal activity on mid-ocean ridges is an important mechanism for the delivery of Zn from the mantle to the surface environment. Zinc isotopic fractionation during hydrothermal activity is mainly controlled by the precipitation of Zn-bearing sulfide minerals, in which isotopically light Zn is preferentially retained in solid phases rather than in solution during mineral precipitation. Thus, seafloor hydrothermal activity is expected to supply isotopically heavy Zn to the ocean. Here, we studied sulfide-rich samples from the Duanqiao-1 hydrothermal field, located on the Southwest Indian Ridge. We report that, at the hand-specimen scale, late-stage conduit sulfide material has lower δ66Zn values (−0.05 ± 0.15 ‰; n = 19) than early-stage material (+0.13 ± 0.15 ‰; n = 10). These lower values correlate with enrichments in Pb, As, Cd, and Ag, and elevated δ34S values. We attribute the low δ66Zn values to the remobilization of earlier sub-seafloor Zn-rich mineralization. Based on endmember mass balance calculations, and an assumption of a fractionation factor (αZnS-Sol.) of about 0.9997 between sphalerite and its parent solution, the remobilized Zn was found consist of about 1/3 to 2/3 of the total Zn in the fluid that formed the conduit samples. Our study suggests that late-stage subsurface hydrothermal remobilization may release isotopically-light Zn to the ocean, and that this process may be common along mid-ocean ridges, thus increasing the size of the previously identified isotopically light Zn sink in the ocean.

No existing review has synthesized key questions about acculturation experiences among international migrant workers. This review aimed to explore (1) What are global migrant workers’ experiences with acculturation and acculturative stress? (2) What are acculturative stress coping strategies used by migrant workers? And (3) how effective are these strategies for migrant workers in assisting their acculturation in the host countries? Peer-reviewed and gray literature, without time limitation, were searched in six databases and included if the study: focused on acculturative stress and coping strategies; was conducted with international migrant workers; was published in English; and was empirical. Eleven studies met the inclusion criteria. Three-layered themes of acculturation process and acculturative stress were identified as: individual layer; work-related layer; and social layer. Three key coping strategies were identified: emotion-focused; problem-focused; and appraisal-focused. These coping strategies were used flexibly to increase coping effectiveness and evidence emerged that a particular type of acculturative stress might be solved more effectively by a specific coping strategy. Migrant workers faced numerous challenges in their acculturative process. Understanding this process and their coping strategies could be used in developing research and interventions to improve the well-being of migrant workers.

The aim of this study is to examine the online learning experiences of university students with Special Educational Needs (SEN), and how their experiences might differ from their typically developing peers. Fifty typically developing students (mean age = 22; 29 females) and 31 students with SEN (mean age = 22; 15 females) from a local

There are many systematic reviews on predicting stock. However, each reveals a different portion of the hybrid AI analysis and stock prediction puzzle. The principal objective of this research was to systematically review the existing systematic reviews on Artificial Intelligence (AI) models applied to stock market prediction to provide valuable inputs for the development of strategies in stock market investments. Keywords that would fall under the broad headings of AI and stock prediction were looked up in Scopus and Web of Science databases. We screened 69 titles and read 43 systematic reviews, including more than 379 studies, before retaining 10 for the final dataset. This work revealed that support vector machines (SVM), long short-term memory (LSTM), and artificial neural networks (ANN) are the most popular AI methods for stock market prediction. In addition, the time series of historical closing stock prices are the most commonly used data source, and accuracy is the most employed performance metric of the predictive models. We also identified several research gaps and directions for future studies. Specifically, we indicate that future research could benefit from exploring different data sources and combinations, while we also suggest comparing different AI methods and techniques, as each may have specific advantages and applicable scenarios. Lastly, we recommend better evaluating different prediction indicators and standards to reflect prediction models’ actual value and impact.

Stock price prediction has always been challenging due to its volatility and unpredictability. This paper performs a preliminary exploratory comparison that utilizes Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) algorithms to forecast the stock market in Hong Kong. It considers a public dataset publicly available and uses feature engineering to extract relevant features. Then, LSTM and SVM algorithms are applied to predict stock prices. Our results show that the proposed machine learning techniques can predict stock prices in Hong Kong's share market with the error metrics presented, and, for this purpose, LSTM achieved better results than SVM, with MSE = 0.0026, RMSE = 0.0508, MAE = 0.0406, and MAPE = 1.325.

There are many systematic reviews on predicting stock. However, each of them reveals a different portion of the hybrid AI analysis and stock prediction puzzle. The principal objective of this research was to systematically review and conclude the systematic reviews on AI and stock to provide particularly useful predictions for making future strategies for stock markets. Keywords that would fall under the broad headings of AI and stock prediction were looked up in two databases, Scopus and Web of Science. We screened 69 titles and read 43 systematic reviews which include more than 379 studies before retaining 10 of them.

Convolutional neural network (CNN) model based on deep learning has excellent performance for target detection. However, the detection effect is poor when the object is circular or tubular because most of the existing object detection methods are based on the traditional rectangular box to detect and recognize objects. To solve the problem, we propose the circular representation structure and RepVGG module on the basis of CenterNet and expand the network prediction structure, thus proposing a high-precision and high-efficiency lightweight circular object detection method RebarDet. Specifically, circular tubular type objects will be optimized by replacing the traditional rectangular box with a circular box. Second, we improve the resolution of the network feature map and the upper limit of the number of objects detected in a single detect to achieve the expansion of the network prediction structure, optimized for the dense phenomenon that often occurs in circular tubular objects. Finally, the multibranch topology of RepVGG is introduced to sum the feature information extracted by different convolution modules, which improves the ability of the convolution module to extract information. We conducted extensive experiments on rebar datasets and used AB-Score as a new evaluation method to evaluate RebarDet. The experimental results show that RebarDet can achieve a detection accuracy of up to 0.8114 and a model inference speed of 6.9 fps while maintaining a moderate amount of parameters, which is superior to other mainstream object detection models and verifies the effectiveness of our proposed method. At the same time, RebarDet’s high precision detection of round tubular objects facilitates enterprise intelligent manufacturing processes.

In the wave of digital transformation, Chinese banks have prioritized digital banking services as key strategic goals, aiming to revolutionize the mobile banking experience. This study aims to assess the factors influencing the willingness to use the various financial and contextual services offered through digital banking. Specifically, it is proposed a model based on users' perceptions of mobile banking scenarios and examines how the development of digital banking services influences users' willingness to use them. The study involved qualitative in-depth interviews with 12 mobile banking users, with the interview content analyzed using Nvivo qualitative analysis software. The data analysis identified 9 core coding categories: Financial Professionalism, Security, Marketing Stimulation, Innovative Products, Use Experience, Strong Relationship, Trust, Perceived Usefulness, and Willingness to Use. These categories were further refined to construct a theoretical model of user willingness in digital banking services, drawing from the optimized Technology Acceptance Model (TAM). The findings provide valuable insights for the banking industry in Macau, aiding in understanding customer needs and supporting the positive development of mobile finance and contextual digital banking services in the region.

In the wave of digital transformation, Chinese banks have taken digital and scenario-based finance as primary strategic goals. The goal is to revolutionize the mobile banking experience and encourage frequent use of mobile banking services. However, assessing customer satisfaction with the various financial and contextual services mobile banking provides is crucial. The main objective of this study is to propose a model based on users' perception of financial usage in mobile banking scenarios and how the development of mobile banking finance and scenarios affects users' choice motivations. The study examined the interview records of 12 mobile banking users through qualitative in-depth interviews and utilized Nvivo qualitative analysis software to analyze the interview content. Through repeated thinking, sorting, and differentiating the data, nine core coding categories were formed. The coding was further refined and deepened to include Financial professionalism, Security, Marketing Stimulation, Innovative Products, Use Experience, Strong Relationship, Trust, Perceived usefulness, and Willingness to use. Based on these categories, a theoretical model of user willingness in the financial scenario of mobile banking has been proposed by referring to the optimized TAM model. The results may provide support to the banking industry in Macau in understanding customers' needs and fostering the positive development of mobile finance and the scene field in Macau

In a fast-paced and densely populated city, community activity centers can provide a social place for residents. This thesis is a study of this promise of social life for a new urban development in Macau. Community centers play an important role in promoting community cohesion and resident participation. Yet, public space for Macau residents is increasingly unable to meet growing and diversified needs. In what ways can the development of activity centers improve the quality of life of residents? Can transitional spaces between different functional areas in community centers play a more effective role in promoting social interaction within the community? The principal tasks of this thesis are as follows: (1) an in-depth examination of the impact of shared transitional spaces on the overall design of community activity centers, (2) a discussion of transitional spaces in community centers in terms of the functional efficiency of these centers and the interactive experience of users, and (3) articulation of principles and recommendations for the design of transitional spaces in community centers. Overall, this thesis argues that, by designing efficient and user-friendly shared transitional spaces, architects can better serve the community and its users, and foster a closer connection between architecture, people, and communities