Publications

Tobacco is a valuable plant in agricultural and commercial industry. Any disease infection to the plant may lower the harvest and interfere the operation of supply chain in the market. Image-based deep learning methods are cutting-edge technologies that can facilitate the diagnosis of diseases efficiently and effectively when large-scale dataset is available for training. However, there is not a public dataset about tobacco currently. A comprehensive dataset is appealed to take advantage of deep learning methods in tobacco cultivation urgently. In this paper, we propose to create a specific dataset for tobacco diseases, called Tobacco Plant Disease Dataset (TPDD). 2721 tobacco leaf images are taken in field. The dataset serves for two purposes: disease classification and leaf detection. For classification, we identify 12 classes and provide two types of disease annotations: 1) Whole Leaf Section; 2) Disease Fragment Section. For leaf detection, we provide two kinds of bounding box: rectangle bounding box and polygon bounding box. In addition, we conduct baseline experiments to illustrate the usefulness of TPDD: 1) using deep learning model to detect single disease and multiple diseases; 2) using YOLO-v3 and Mask-RCNN to detect leaves. We hope that the dataset could support the tobacco industry, also be a benchmark in fine-grained vision classification.

Large models and deep learning models for real-time services are trained from time to time to refresh the new features and achieve better accuracy. Multivariate time-series decomposition and recombination (MTS-DR) models effectively improve training efficiency. In this research, an MTS method that is more stable and can handle finer decomposed components helps the training process of deep learning and Large Language Model Meta AI (LLaMA), and is crucial for our subsequent study on the capabilities of adaptive features engineering. Thus, this study introduces an innovative method developed using the Multiple Seasonal-Trend Decomposition using LOESS (MSTL) algorithm, termed “Multiseasonal Scalable Sub-model MSTL decomposition and recombining” (Multiseasonal SS-MSTL-DR) model. This method is designed to upgrade the decomposition and recombining of multiseasonal trends within a scalable sub-model framework. Its architecture is specifically tailored for seamless integration into deep learning systems to enhance the efficiency of model training. The objective is to establish a robust foundation for analyzing time-series data exhibiting distinctive and intricate seasonal patterns. Research methods include conducting a State-of-the-Art (SOTA) literature review, data preparation, model building, feasibility tests, comprehensive evaluation, and summary. Through a case of subtropical urban air quality prediction, it is found that the “Multiseasonal SS-MSTL-DR” model can further reduce the complexity of time-series and highlight its inherent characteristics. The multiple seasonality design and the SS training make the characteristics easier to mine in MTS models. Those experimental results of the cold/warm seasons show that the learning speed and accuracy of deep learning and LLaMA models have been improved, especially in the MTS deep learning model. Since we have extended Multiseasonal SS-MSTL-DR to six different air pollutant concentration data sets, the six of them have completely different spatial characteristics of physical and chemical, which is equivalent to proving the commonality of application, i.e. the proposed method is suitable for other multiseasonal time-series data.

Environmental engineering plays a critical role in managing air quality services, which are of daily concern to the public, particularly as climate change alters the factors affecting air quality. Within this context, our study introduces a comprehensive approach that emphasizes predictive models relying on multivariate time-series data. By integrating data from various sources and modalities, we propose a multimodal deep learning method to enhance traditional unimodal models. This study includes a review of existing literature, the preparation of relevant datasets, the development of robust models, and extensive evaluations. The experiments feature a case study focused on air quality services in a subtropical city, aiming to provide insights for improving prediction models. The integrated multimodal approach offers a better understanding of environmental conditions by combining data from automatic air quality monitors, meteorological stations, the European Centre for Medium-Range Weather Forecasts reanalysis data, as well as public welfare information and societal disruption reports. The analysis also considers weather-related alerts, such as typhoon and rainstorm warnings, which lead to school closures and city-wide suspensions. The model incorporates emission sources and upwind areas. Preliminary causality tests confirm that augmented feature space to encompass upstream areas enhances the model analytical capability. Downstream pollution and environmental conditions are significantly influenced by socio-economic activities in upwind areas. Granger causality and Diebold-Mariano tests highlight the importance of public welfare information and societal disruption reports, addressing a critical gap in this field.

A well-known use of the blockchain technology is Decentralized Finance (DeFi). DeFi makes financial information accessible to the public but raises potential privacy and security issues. In this study, we implemented a DeFi protocol that protects privacy, which is based on the Mystiko.Network protocol. As a proxy between the user and DeFi platforms, the Mystiko.Network protocol offers an auditable confidentiality mechanism for blockchain transactions. Via the new system, users may submit anonymous DeFi transactions and get income back into a shielded tokens pool. Moreover, we implemented a rollup approach to handle anonymous DeFi transactions in groups. The evaluation results suggest that the protocol is both practical and affordable, in fact it is able to save around 90% of the cost for DeFi transactions.

The rapid developed communications and artificial intelligence technologies lead people to a higher standard of quality of life. Environmental protection and air quality are more concerned as it is necessary for planning of outdoor activities. To track the air quality, monitoring stations and conventional empirical subjective forecast are used. Because air quality data is seasonal time series, machine learning is a good way to assist the prediction by exploring the seasonality patterns. This study aims to see the implementation of a machine learning model to predict the air quality in a medium-sized urban city. We will see the performance of the multivariate artificial neural networks in predicting the future status of different air pollutant concentrations, such as respirable suspended particulate matter in small and medium-sized developing cities. The neural network was trained on hourly data from 2016 to 2020, with dataset split according to different season groups. Methodology mainly includes model building, training, and testing. Macao was selected for the study. A set of meteorological variables is chosen as multivariate inputs, including air temperature, relative humidity, precipitation, boundary layer height, sea level pressure, and wind. Contributions include seeing the performance of a LSTM model to forecast time series with multivariate inputs.

In this article, we consider in improving the throughput of existing multicast routing protocols by using multiple multicast trees in ad hoc wireless networks. To achieve our goal, we propose virtual layer, a multi-layer container for multicast trees, that provides an scalable routing structure with transmission gain in multicast routing. Without modification of multicast routing protocols, we enable a layer concept into the protocols so that multiple multicast trees can be constructed in a multicast group. Although virtual layer improves throughput, excessive data traffic will be introduced into a network that may cause network congestion. To resolve this situation, we consider a random coding scheme, a practical network coding implementation that encodes data packets for routing in disjoint-path tree while avoiding congestion. We observed in our simulations that a transmission gain trades off the excessive traffic that causes network congestion.

This study examines the application of deep learning (DL) in predicting multivariate time-series (MTS), emphasizing the significance of novel feature exploration for intensive model re-training. This approach is essential for adaptive feature engineering, as the numerical properties of the foundational features differ from their statistical attributes. Elements such as the population density, resident count and land area, as well as foreign exchange rates, goods and hedging indicators, illustrate this disparity. The augmentation of feature space aims to improve the model’s efficiency without compromising performance by unnecessarily expanding the dataset dimension. This objective can be achieved by implementing an adaptive screening approach, specifically a multi-aspect feature dependency screening (MFDS), for the augmentation of derivative feature space (DFS). This can be accomplished through an adaptive screening process, an MFDS for augmentation of DFS. The methodology includes literature review and experimental modelling. The application of the Variance Inflation Factor (VIF) as an adaptive weighting method to evaluate redundancy is crucial for establishing effective screening mechanisms enabling them to self-adjust to subtle changes and emerging patterns that may otherwise go unnoticed, and for ensuring sustainable advancement and enhancing dynamic training processes within the DL domain. Those multi statistical indicators include: cross-correlation for monitoring movements, Granger causality for evaluating predictor-predictand effectiveness, R-squared for assessing coincidence, amplitude-square coherence for estimating response degree, and Pearson coefficient for measuring linear dependence. In a seasonal context, formulating air temperature and humidity into water vapour pressure deficit facilitates a comprehensive analysis of critical features. Furthermore, the efficiency of predictive models is enhanced through the use of this adaptive screening and auto augmentation, as these methodologies incorporate new essential feature spaces. This research effectively combines physical knowledge with statistical screening techniques of feature dependency weighted mean (FDWM), resulting in a significant reduction in loss for DL models. Additionally, the distinct temporal-spatial and physical properties of the six air pollutants exhibit considerable variation, yet to a certain extents the commonalities.

Triangle routing is one of the serious attacks to the Internet infrastructure. It can be caused by malicious routers which misroute packets to wrong directions. This kind of attacks creates network problems such as network congestion, denial of service and network partition and results in degrade of network performance. This paper gives a comprehensive study on how the path analysis combats the triangle routing attacks. We discuss the method, implementation and limitation of path analysis to detect triangle routing in IPv4 network. We also discuss the implementation of path analysis in IPv6 by proposing a new extension header.

Artificial intelligence (AI) currently exhibits considerable potential within the realm of biodiversity conservation. However, high-quality regionally customized datasets remain scarce, particularly within urban environments. The existing large-scale bird image datasets often lack a dedicated focus on endangered species endemic to specific geographic regions, as well as a nuanced consideration of the complex interplay between urban and natural environmental contexts. Therefore, this paper introduces Macao-ebird, a novel dataset designed to advance AI-driven recognition and conservation of endangered bird species in Macao. The dataset comprises two subsets: (1) Macao-ebird-cls, a classification dataset with 7341 images covering 24 bird species, emphasizing endangered and vulnerable species native to Macao; and (2) Macao-ebird-det, an object detection dataset generated through AI-agent-assisted labeling using grounding DETR with improved denoising anchor boxes (DINO), significantly reducing manual annotation effort while maintaining high-quality bounding-box annotations. We validate the dataset’s utility through baseline experiments with the You Only Look Once (YOLO) v8–v12 series, achieving a mean average precision (mAP50) of up to 0.984. Macao-ebird addresses critical gaps in the existing datasets by focusing on region-specific endangered species and complex urban–natural environments, providing a benchmark for AI applications in avian conservation.

COVID-19 pandemic has led to serious economic and life losses. Face Masks serve as first infection barrier when used in public spaces. In this paper, we propose a new near-realtime method to automatically recognize face mask wearing that combines human posture recognition with convolutional neural network (CNN). We use the power of human posture recognition to perform background filtering and spatial reduction in the original images. The outcome is then used by a trained CNN model to identify if the subject is wearing a mask. We exploit Openpose to identify the skeleton of human body and locate the facial region thus spatially reducing the area to be processed by the CNN framework. We then adopt supervised learning approach to detect if a face mask is present. The CNN is trained using images, cropped to the supposed face mask covered region. This approach led to a substantial reduction in neural network complexity yet improving the recognition accuracy. The system has been evaluated in a multitude of scenarios using images taken in public places at different time of day and with different angles. Overall, our system achieves a recognition accuracy of 95.8% and 94.6% in daytime and nighttime respectively.