With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly available nowadays. Mining valuable knowledge from spatio-temporal data is critically important to many real-world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio-temporal data increase rapidly, traditional data mining methods, especially statistics-based methods for dealing with such data are becoming overwhelmed. Recently deep learning models such as recurrent neural network (RNN) and convolutional neural network (CNN) have achieved remarkable success in many domains due to the powerful ability in automatic feature representation learning, and are also widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, anomaly detection and classification. In this paper, we provide a comprehensive review of recent progress in applying deep learning techniques for STDM. We first categorize the spatio-temporal data into five different types, and then briefly introduce the deep learning models that are widely used in STDM. Next, we classify existing literature based on the types of spatio-temporal data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, on-demand service, climate & weather analysis, human mobility, location-based social network, crime analysis, and neuroscience. Finally, we conclude the limitations of current research and point out future research directions.

Mobile applications are becoming increasingly computation-intensive, while the computing capability of portable mobile devices is limited. A powerful way to reduce the completion time of an application in a mobile device is to offload its tasks to nearby cloudlets, which consist of clusters of computers. Although there is a significant body of research in mobile cloudlet offloading technology, there has been very little attention paid to how cloudlets should be placed in a given network to optimize mobile application performance. In this paper we study cloudlet placement and mobile user allocation to the cloudlets in a wireless metropolitan area network (WMAN). We devise an algorithm for the problem, which enables the placement of the cloudlets at user dense regions of the WMAN, and assigns mobile users to the placed cloudlets while balancing their workload. We also conduct experiments through simulation. The simulation results indicate that the performance of the proposed algorithm is very promising.

Federated learning is a privacy-preserving machine learning technique that trains models across multiple devices holding local data samples without exchanging them. There are many challenging issues in federated learning, such as coordinating participants’ activities, arbitrating their benefits, and aggregating models. Most existing solutions employ a centralized approach, in which a trustworthy central authority is needed for coordination. Such an approach incurs many disadvantages, including vulnerability to attacks, lack of credibility, and difficulty in calculating rewards. Recently, blockchain was identified as a potential solution for addressing the abovementioned issues. Extensive research has been conducted, and many approaches, methods, and techniques have been proposed. There is a need for a systematic survey to examine how blockchain can empower federated learning. Although there are many surveys on federated learning, few of them cover blockchain as an enabling technology. This work comprehensively surveys challenges, solutions, and future directions for blockchain-empowered federated learning (BlockFed). First, we identify the critical issues in federated learning and explain why blockchain provides a potential approach to addressing these issues. Second, we categorize existing system models into three classes: decoupled, coupled, and overlapped, according to how the federated learning and blockchain functions are integrated. Then we compare the advantages and disadvantages of these three system models, regard the disadvantages as challenging issues in BlockFed, and investigate corresponding solutions. Finally, we identify and discuss the future directions, including open problems in BlockFed.

Non-invasive human sensing based on radio signals has attracted a great deal of research interest and fostered a broad range of innovative applications of localization, gesture recognition, smart health-care, etc., for which a primary primitive is to detect human presence. Previous works have studied the detection of moving humans via signal variations caused by human movements. For stationary people, however, existing approaches often employ a prerequisite scenario-tailored calibration of channel profile in human-free environments. Based on in-depth understanding of human motion induced signal attenuation reflected by PHY layer channel state information (CSI), we propose DeMan, a unified scheme for non-invasive detection of moving and stationary human on commodity WiFi devices. DeMan takes advantage of both amplitude and phase information of CSI to detect moving targets. In addition, DeMan considers human breathing as an intrinsic indicator of stationary human presence and adopts sophisticated mechanisms to detect particular signal patterns caused by minute chest motions, which could be destroyed by significant whole-body motion or hidden by environmental noises. By doing this, DeMan is capable of simultaneously detecting moving and stationary people with only a small number of prior measurements for model parameter determination, yet without the cumbersome scenario-specific calibration. Extensive experimental evaluation in typical indoor environments validates the great performance of DeMan in various human poses and locations and diverse channel conditions. Particularly, DeMan provides a detection rate of around 95% for both moving and stationary people, while identifies human-free scenarios by 96%, all of which outperforms existing methods by about 30%.

Traditional multiobjective evolutionary algorithms (MOEAs) consider multiple objectives as a whole when solving multiobjective optimization problems (MOPs). However, this consideration may cause difficulty to assign fitness to individuals because different objectives often conflict with each other. In order to avoid this difficulty, this paper proposes a novel coevolutionary technique named multiple populations for multiple objectives (MPMO) when developing MOEAs. The novelty of MPMO is that it provides a simple and straightforward way to solve MOPs by letting each population correspond with only one objective. This way, the fitness assignment problem can be addressed because the individuals' fitness in each population can be assigned by the corresponding objective. MPMO is a general technique that each population can use existing optimization algorithms. In this paper, particle swarm optimization (PSO) is adopted for each population, and coevolutionary multiswarm PSO (CMPSO) is developed based on the MPMO technique. Furthermore, CMPSO is novel and effective by using an external shared archive for different populations to exchange search information and by using two novel designs to enhance the performance. One design is to modify the velocity update equation to use the search information found by different populations to approximate the whole Pareto front (PF) fast. The other design is to use an elitist learning strategy for the archive update to bring in diversity to avoid local PFs. CMPSO is comprehensively tested on different sets of benchmark problems with different characteristics and is compared with some state-of-the-art algorithms. The results show that CMPSO has superior performance in solving these different sets of MOPs.

Large language models (LLMs) have shown great success in content generation and intelligent intelligent decision-making for IoT systems. Traditionally, LLMs are deployed on the cloud, incurring prolonged latency, high bandwidth costs, and privacy concerns. More recently, edge computing has been considered promising in addressing such concerns because edge devices are closer to data sources. However, edge devices are cursed by their limited resources and can hardly afford LLMs. Existing studies address such a limitation by offloading heavy workloads from edge to cloud or compressing LLMs via model quantization. These methods either still rely heavily on the remote cloud or suffer substantial accuracy loss. This work is the first to deploy LLMs on a collaborative edge computing environment, in which edge devices and cloud servers share resources and collaborate to infer LLMs with high efficiency and no accuracy loss. We design EdgeShard, a novel approach to partition a computation-intensive LLM into affordable shards and deploy them on distributed devices. The partition and distribution are non-trivial, considering device heterogeneity, bandwidth limitations, and model complexity. To this end, we formulate an adaptive joint device selection and model partition problem and design an efficient dynamic programming algorithm to optimize the inference latency and throughput. Extensive experiments of the popular Llama2 serial models on a real-world testbed reveal that EdgeShard achieves up to 50% latency reduction and 2x throughput improvement over the state-of-the-art.