The LoRaWAN network is proposed for IoT applications and has the advantages of long range transmission and low power consumption. However, it suffers from very low data throughputs and long transmission duty cycle delays. In our real on-campus LoRaWAN deployment that has been lasting for one year, we found that even though we placed LoRaWAN end devices (nodes) at a short distance such as less than 700 meters from a LoRaWAN gateway, the packet loss rates at some locations are still too high to be acceptable. In this paper, we propose two approaches to overcome this high packet loss rate problem. We modified the IoT application running on nodes to let a node retransmit its lost data in multiple packets and help transmit its neighboring node's data. Our experimental results show that our approaches can effectively increase the application-layer message delivery success rate of LoRaWAN.

3D hand pose estimation is a hot research topic in recent years. It's been widely used in many advanced applications for virtual reality and human-computer interaction, since it provides a natural interface for communication between human and cyberspace. Despite the fast development of this field, it is still a difficult task due to the various challenges. In this paper, we aim to build a 3D hand pose estimation system which can correctly detect human hands and accurately estimate its pose using depth images. To guarantee the robustness of our system, we design a hand model called spherical part model (SPM), and train a deep convolutional neural network using this model. Moreover, to reduce the influence of human's omissions, we use a data-driven approach to integrate them together. Our network can more accurately estimate hand pose based on prior knowledge of human hand. To demonstrate the superiority of our method, a complete experiment is conducted on two public and one self-built datasets. The results show that our system can detect human hands with average precision at almost 90% and the average error distance of the pose estimation is about 10 millimeters, and is better than the other state of the art works.

To promote smart campus, National Chiao Tung University is deploying several location-based IoT applications based on wireless communications technologies including LoRa and NB-IoT. The applications are indoor/outdoor environment conditions monitoring (such as PM2.5, temperature, and humidity), emergency buttons, and so on. This paper uses PM2.5 measurement application as an example to present the performance of LoRa when it is used on campus. We investigated the LoRa transmission performance from LoRa end-devices to the LoRa gateway. We show how packet losses were affected by the distance between the end-device and the gateway, the transmit power, the payload length, the antenna angle, the time of day, and the weather conditions. The pattern of LoRa packet losses were also measured and we found that in our long-term PM2.5 monitoring application, more than 99\% of LoRa packet losses occurred with three or less consecutive packet losses.

We propose a novel framework which integrates human hand detection and pose estimation into one single pipeline. Unlike most of previous works which only focus on the pose estimation part subject to some strong assumptions or relying on a weak detector to detect human hands, we employ a deep learning architecture to complete both aforementioned tasks. By letting three different neural networks share the convolutional layers, this deeply learning architecture can efficiently and accurately detect human hands and compute their hand pose configuration. Moreover, we propose a new energy function to optimize the predicted result of convolutional neural network. To validate the proposed framework, experiments have been conducted and the results show that our approach is highly reliable and suitable for real-world applications.

In this paper, we present an efficient framework for human activity recognition in daily environment. We use depth information mainly for privacy protection, and then focus on the motion analysis of informative body parts, since most activities are much associated with these particular parts, e.g., head and hands in upper body. Based on the idea, we propose two novel features with intuitive physical meaning, which are Histogram of Located Displacements (HOLD) and Local Depth Motion Maps (L-DMM) based Gabor representation. They can capture discriminative posture and motion cues from skeletal joints and depth data respectively. Combing the advantages of joint and depth features as well as emphasizing the reliable parts can enhance the robustness of classification ability. The experimental results show that our proposed feature representation is very discriminative for the task of daily activity recognition and outperforms several state-of-the-art methods.