In the dynamic and evolving field of computer vision, action recognition has become a key focus, especially with the advent of sophisticated methodologies like Convolutional Neural Networks (CNNs), Convolutional 3D, Transformer and spatial-temporal feature fusion. These technologies have shown promising results on well-established benchmarks but face unique challenges in real-world applications, particularly in sports analysis, where the precise decomposition of activities and the distinction of subtly different actions are crucial. Existing datasets like UCF101, HMDB51, and Kinetics have offered a diverse range of video data for various scenarios. However, there’s an increasing need for fine-grained video datasets that capture detailed categorizations and nuances within broader action categories. In this paper, we introduce the VideoBadminton dataset, which is derived from high-quality badminton footage. Through an exhaustive evaluation of leading methodologies on this dataset, this study aims to advance the field of action recognition, particularly in badminton sports. The introduction of VideoBadminton could not only serve for badminton action recognition but also provide a dataset for recognizing fine-grained actions. The insights gained from these evaluations are expected to catalyze further research in action comprehension, especially within sports contexts.

Protecting the privacy of users is one of the most important issues in recommender systems, where new items, e.g., books, movies, and friends in online social networking service/sites, are recommended to target users. To identify recommended items, encryption-based privacy-preserving collaborative filtering is widely used to generate recommendations. However, existing solutions are either slow or not scalable. To tackle this issue, in this paper, we first propose a privacy-preserving user-based CF protocol using the BGV fully homomorphic encryption scheme, which is named BGV-CF. By reducing interactions and the amount of communication traffic among users and recommendation servers, the proposed BGV-CF protocol significantly facilitates the recommendation process. Then, we propose an optimized BGV-CF (OBGV-CF) protocol where some computations are offloaded to users during the recommendation process. The security of the proposed schemes is qualitatively analyzed and quantitative analyses of the computation and communication costs are performed. In addition, provable security analysis using random oracles is provided. The BGV-CF and OBGV-CF protocols are implemented using C++, and testbeds using the MovieLens dataset are conducted. Experimental results demonstrate that the proposed BGV-CF and OBGV-CF successfully achieve their design goals.

Graph Neural Networks (GNNs) have shown promising performance in many applications, yet remain extremely difficult to train over large-scale graph datasets. Existing weight pruning techniques can prune out the layer weights; however, they cannot fully address the high computation complexity of GNN inference, caused by large graph size and complicated node connections. In this paper, we propose an Iterative Gradient Rank Pruning (IGRP) algorithm to find graph lottery tickets (GLT) of GNNs where each GLT includes a pruned adjacency matrix and a sub-network. Our IGRP can avoid layer collapse and the winning ticket achieves Maximal critical compression. We evaluate the proposed method on small-scale (Cora and Citeseer), medium-scale (PubMed and Wiki-CS), and large-scale (Ogbn-ArXiv and Ogbn-Products) graph datasets. We demonstrate that both Single-shot and Multi-shot of IGRP outperform the state-of-the-art unified GNN sparsification (UGS) framework on node classification. The source code can be found in https://github.com/poweiharn/IGRP_GNN.

The location-based alert system plays a primary factor on determining who is at risk during an emergency, such as a war zone in Ukraine. While users are willing to reveal their locations in exchange for timely alert in those situations, there is no guarantee that their private information does not fall into the wrong hands. For example, a soldier may be killed if his movement pattern is known by the enemy. One resolution to this issue is to encrypt the location information by trusted authority public key before it is transmitted. This approach provides location privacy and allows decryption only when the recipient’s location satisfies a certain predicate. However, the encryption itself may still be compromised if the location encoding is leaked. In this paper, we propose a Hilbert Curve Encoding which encrypts the user’s message along with her locations for private processing with the trusted authority. We further propose a hybrid HNGM−NEncoding which combines the Hilbert Curve Encoding and Gray Encoding. HNGM−Nhas the proprieties of a Hilbert Curve Encoding in its identifier and a Hamming distance of 1 between neighboring cells in a subgrid. As a consequence, the proposed HNGM−Nis less likely to leak neighboring cell identifier than Gray Encoding under random guessing attacks. Extensive experiment results show that our encoding methods are better than Hierarchical Encoding and comparable to Gray Encoding in terms of user response time, token remaining percentage, and execution time.

In this paper, we propose privacy-preserving user-based CF protocols using the BGV fully homomorphic encryption scheme, named BGV-CF and optimized BGV-CF (OBGV-CF), in order to protect privacy of users in recommender systems. The proposed schemes are implemented by C++, and testbeds using the MovieLens dataset demonstrate that the proposed protocols successfully achieve their design goals.

By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate$\mathbf{PM}_{2.5}$prediction becomes more important. In this paper, we propose a$\mathbf{PM}_{2.5}$prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Our$\mathbf{PM}_{2.5}$prediction system is composed of four parts: data collection, data preprocessing, prediction model construction, and Line platform. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K- means has the best performance among all methods. Therefore, LSTM based on K-means is chosen to provide real-time$\mathbf{PM}_{2.5}$prediction through the Linebot.

The progress of industrial development naturally leads to the demand for more electrical power. Unfortunately, due to the fear of the safety of nuclear power plants, many countries have relied on thermal power plants, which will cause more air pollutants during the process of coal burning. This phenomenon as well as increased vehicle emissions around us, have constituted the primary factors of serious air pollution. Inhaling too much particulate air pollution may lead to respiratory diseases and even death, especially PM$_{2.5}$. By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate PM$_{2.5}$prediction becomes more important. In this study, we propose a PM$_{2.5}$prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Autoencoder and Linear interpolation are adopted for solving the missing value problem. Spearman’s correlation coefficient is used to identify the most relevant features for PM$_{2.5}$. Two prediction models (i.e., LSTM and LSTM based on K-means) are implemented which predict PM$_{2.5}$value for each Airbox device. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K-means has the best performance among all methods. Therefore, LSTM based on K-means is chosen to provide real-time PM$_{2.5}$prediction through the Linebot.

This paper presents an exact solution and a heuristic solution to a UAV-assisted parcel delivery problem, in which UAVs can only be operated in Visual-Line-Of-Sight (VLOS) areas. In our proposed problem, we assume that trucks travel on road networks, and UAVs move in Euclidean spaces and can launch at any locations on roads. We first demonstrate the overview of our exact solution that iterates all permutations of destinations for an optimal delivery route. Given a specific delivery order, an intuitive approach needs to check all possible locations on roads in the VLOS areas and find a globally optimal location for every destination if UAVs are used for delivery. To avoid high computational cost of searching the optimal location at runtime, we propose an advanced index-based alternative, which computes optimal delivery routes in a pre-processing stage. Due to the nature of NP-hard problems, we also propose a heuristic approach that utilizes delivery groups for the proposed problem of practical size. All proposed solutions are evaluated through extensive experiments.

Link prediction is a fundamental problem in social network analysis. Although the link prediction problem is not new, the challenge of how to exploit various existing network information, such as network structure data and node attribute data, to enable AI-style knowledge inference for large social networks still remains unsolved. In this paper, we design and implement a scalable framework that treats link prediction as knowledge reasoning using Markov Logic Networks (MLNs). Differing from other probabilistic graphical models, MLNs allow undirected relationships with cycles and long-range (non-adjacent) dependency, which are essential and abound in social networks. In our framework, the prior knowledge is captured as the structure dependency (such as friendship) and the attribute dependency (such as social communities) in terms of inference rules, associated with uncertainty represented as probabilities. Next, we employ the random walk to discover the inference subgraph, on which probabilistic inference is performed, so that the required computation and storage cost can be significantly reduced without much sacrifice of the inference accuracy. Our extensive experiments with real-world datasets verify the superiority of our proposed approaches over two baseline methods and show that our approaches are able to provide a tunable tradeoff between inference accuracy and efficiency.

A variety of optimal location problems have been extensively studied in the literature. However, limited visualization systems have been developed for illustrating optimal location selection process. In this demonstration, we present a system that visualizes an advanced solution that can efficiently answer multi-criteria optimal location updating query by incrementally updating the Minimum Overlapping Voronoi Diagram (MOVD) model. Not only does our system display an example as a practical multi-criteria optimal location updating query, but also visualizes the process of the query evaluation in a more intuitive manner. With the object insertion and deletion operations defined over the MOVD model, any object changes in an MOVD can be represented by removing the objects from initial datasets and adding them back with updated attributes. Moreover, Haxe toolkit is used to provide friendly and flexible user interfaces in our system.

In this demonstration, we present a visualization system offering two advanced solutions that can efficiently address a novel multi-criteria optimal location query by using Overlapping Voronoi Diagrams (OVDs). Our system not only displays an example that applies the advanced solutions to a practical optimal location query, but also visualizes the process of query evaluation by using the solutions, which can help users better understand the two solutions in a more intuitive way. The Real Region as Boundary (RRB) approach calculates real regions of overlapped Voronoi cells, while the Minimum Bounding Rectangle as Boundary (MBRB) approach approximates the cells by their MBRs to simplify region overlapping calculation. For efficient query evaluation and better demonstration, global and local datasets are managed separately and only the local dataset is displayed in a limited visualization area. User interactions are provided in diverse manners in our system by using the Standard Widget Toolkit (SWT) and Open Graphics Library (OpenGL).

This paper presents a novel optimal location selection problem, which can be applied to a wide range of applications.After providing a formal definition of the novel query type, we explore an intuitive approach that sequentially scans all possible object combinations in the search space.Then, we propose an Overlapping Voronoi Diagram (OVD) model that defines OVDs and Minimum OVDs, and construct an algebraic structure under an OVD overlap operation.Based on the OVD model, we design an advanced approach to answer the query.Due to the high complexity of Voronoi diagram overlap computation, we improve the overlap operation by replacing the real boundaries of Voronoi diagrams with their Minimum Bounding Rectangles (MBR).We also propose a cost-bound iterative approach that efficiently processes a large number of Fermat-Weber problems.Our experimental results show that the proposed algorithms can evaluate the novel query type effectively and efficiently.

In this paper, we propose two parameterized frameworks, namely the Uniform Watchtower (UW) framework and the Hot zone-based Watchtower (HW) framework, for the evaluation of spatial queries on large road networks. The motivation of this research is twofold: (1) how to answer spatial queries efficiently on large road networks with massive POI data and (2) how to take advantage of social data in spatial query processing. In UW, the network traversal terminates once it acquires the Point of Interest (POI) distance information stored in watchtowers. In HW, by observing that users' movements often exhibit strong spatial patterns, we employ probabilistic clustering to model mobile user check-in data as a mixture of 2-dimensional Gaussian distributions to identify hot zones so that watchtowers can be deployed discriminatorily. Our analyses verify the superiority of HW over UW in terms of query response time.

People spend a significant amount of time in indoor spaces (e.g., office buildings, subway systems, etc.) in their daily lives. Therefore, it is important to develop efficient indoor spatial query algorithms for supporting various location-based applications. However, indoor spaces differ from outdoor spaces because users have to follow the indoor floor plan for their movements. In addition, positioning in indoor environments is mainly based on sensing devices (e.g., RFID readers) rather than GPS devices. Consequently, we cannot apply existing spatial query evaluation techniques devised for outdoor environments for this new challenge. Because particle filters can be employed to estimate the state of a system that changes over time using a sequence of noisy measurements made on the system, in this research, we propose the particle filter-based location inference method as the basis for evaluating indoor spatial queries with noisy RFID raw data. Furthermore, two novel models, indoor walking graph model and anchor point indexing model, are created for tracking object locations in indoor environments. Based on the inference method and tracking models, we develop innovative indoor range and k nearest neighbor (kNN) query algorithms. We validate our solution through extensive simulations with real-world parameters. Our experimental results show that the proposed algorithms can evaluate indoor spatial queries effectively and efficiently.

As one of the most important Semantic Web applications, social network analysis has attracted more and more interest from researchers due to the rapidly increasing availability of massive social network data. A desired solution for social network analysis should address the following issues. First, in many real world applications, inference rules are partially correct. An ideal solution should be able to handle partially correct rules. Second, applications in practice often involve large amounts of data. The inference mechanism should scale up towards large-scale data. Third, inference methods should take into account probabilistic evidence data because these are domains abounding with uncertainty. Various solutions for social network analysis have existed for quite a few years; however, none of them support all the aforementioned features. In this paper, we design and implement LinkProbe, a prototype to quantitatively predict the existence of links among nodes in large-scale social networks, which are empowered by Markov Logic Networks (MLNs). MLN has been proved to be an effective inference model which can handle complex dependencies and partially correct rules. More importantly, although MLN has shown acceptable performance in prior works, it is also reported as impractical in handling large-scale data due to its highly demanding nature in terms of inference time and memory consumption. In order to overcome these limitations, LinkProbe retrieves the k-backbone graphs and conducts the MLN inference on both the most globally influencing nodes and most locally related nodes. Our extensive experiments show that LinkProbe manages to provide a tunable balance between MLN inference accuracy and inference efficiency.

The past few years have witnessed the emergence of an increasing number of applications for tracking and tracing based on radio frequency identification (RFID) technologies. However, raw RFID readings are usually of low quality and may contain numerous anomalies. An ideal solution for RFID data cleansing should address the following issues. First, in many applications, duplicate readings of the same object are very common. The solution should take advantage of the resulting data redundancy for data cleaning. Second, prior knowledge about the environment may help improve data quality, and a desired solution must be able to take into account such knowledge. Third, the solution should take advantage of physical constraints in target applications to elevate the accuracy of data cleansing. There are several existing RFID data cleansing techniques. However, none of them support all the aforementioned features. In this paper, we propose a Bayesian inference-based framework for cleaning RFID raw data. We first design an n-state detection model and formally prove that the three-state model can maximize the system performance. Then, we extend the n-state model to support two-dimensional RFID reader arrays and compute the likelihood efficiently. In addition, we devise a Metropolis-Hastings sampler with constraints, which incorporates constraint management to clean RFID data with high efficiency and accuracy. Moreover, to support real-time object monitoring, we present the streaming Bayesian inference method to cope with realtime RFID data streams. Finally, we evaluate the performance of our solutions through extensive experiments.

Radio Frequency Identification (RFID) technologies are used in many applications for data collection. However, raw RFID readings are usually of low quality and may contain many anomalies. An ideal solution for RFID data cleansing should address the following issues. First, in many applications, duplicate readings (by multiple readers simultaneously or by a single reader over a period of time) of the same object are very common. The solution should take advantage of the resulting data redundancy for data cleaning. Second, prior knowledge about the readers and the environment (e.g., prior data distribution, false negative rates of readers) may help improve data quality and remove data anomalies, and a desired solution must be able to quantify the degree of uncertainty based on such knowledge. Third, the solution should take advantage of given constraints in target applications (e.g., the number of objects in a same location cannot exceed a given value) to elevate the accuracy of data cleansing. There are a number of existing RFID data cleansing techniques. However, none of them support all the aforementioned features. In this paper we propose a Bayesian inference based approach for cleaning RFID raw data. Our approach takes full advantage of data redundancy. To capture the likelihood, we design an n-state detection model and formally prove that the 3-state model can maximize the system performance. Moreover, in order to sample from the posterior, we devise a Metropolis-Hastings sampler with Constraints (MH-C), which incorporates constraint management to clean RFID raw data with high efficiency and accuracy. We validate our solution with a common RFID application and demonstrate the advantages of our approach through extensive simulations.

Trip planning search (TPS) represents an important class of queries in Geographic Information Systems (GIS). In many real-world applications, TPS requests are issued with a number of constraints. Unfortunately, most of these constrained TPS cannot be directly answered by any of the existing algorithms. By formulating each restriction into rules, we propose a novel form of route query, namely the multi-rule partial sequenced route (MRPSR) query. Our work provides a unified framework that also subsumes the well-known trip planning query (TPQ) and the optimal sequenced route (OSR) query. In this paper, we first prove that MRPSR is NP-hard and then present three heuristic algorithms to search for near-optimal solutions for the MRPSR query. Our extensive simulations show that all of the proposed algorithms can answer the MRPSR query effectively and efficiently. Using both real and synthetic datasets, we investigate the performance of our algorithms with the metrics of the route distance and the response time in terms of the percentage of the constrained points of interest (POI) categories. Compared to the LORD-based brute-force solution, the response times of our algorithms are remarkably reduced while the resulting route length is only slightly longer than the shortest route.