Junhong Xu

Survey on Prediction Algorithms in Smart Homes

The world has entered into a “smart” era. One area becoming smart is the place where we live—homes. Smart homes are expected to be equipped with numerous sensors to continually monitor, sense, and actuate the space. The data from these sensors can be used to provide various types of services by automating common tasks while causing minimal disruption to daily life. In order to provide these services, a system must have sufficient intelligence to predict future events based on its observations. This paper first examines the requirements for smart home predictions. It then comprehensively reviews prediction algorithms and variations that have been proposed and investigated in smart environments, such as smart homes. It is these prediction algorithms that provide the intelligence required by a smart home. Comparisons are also made upon these prediction algorithms on their features and models.

A Deep Residual convolutional neural network for facial keypoint detection with missing labels

Abstract Keypoint detection is critical in image recognitions. Deep learning such as convolutional neural network (CNN) has recently demonstrated its tremendous success in detecting image keypoints over conventional image processing methodologies. The deep learning solutions, however, heavily rely on labeling target images for their reliability and accuracy. Unfortunately, most image datasets do not have all labels marked. To address this problem, this paper presents an effective and novel deep learning solution, Masked Loss Residual Convolutional Neural Network (ML-ResNet), to facial keypoint detection on the datasets that have missing target labels. The core of ML-ResNet is a masked loss objective function that ignores the error in predicting the missing target keypoints in the output layer of a CNN. To compensate for the loss induced by the masked loss objective function that likely results in overfitting, ML-ResNet is designed of a data augmentation strategy to increase the number of training data. The performance of ML-ResNet has been evaluated on the image dataset from Kaggle Facial Keypoints Detection competition, which consists of 7049 training images, but with only 2140 images that have full target keypoints labeled. In the experiments, ML-ResNet is compared to a pioneer literature CNN facial keypoint detection work. The experiment results clearly show that the proposed ML-ResNet is robust and advantageous in training CNNs on datasets with missing target values. ML-ResNet can improve the learning time by 30% during the training and the detection accuracy by eight times in facial keypoint detection.

In-band full duplex wireless communications and networking for IoT devices: Progress, challenges and opportunities

Abstract The new era of IoT devices call for wireless communications with high spectral efficiency because of the congested spectral space in reality. Current wireless communication systems work at half duplex mode in an either time-division or frequency-division approach to transmit and receive wireless signals. Half duplex results in poor spectral efficiency because only unidirectional communications are allowed. Recent research has aimed at enabling In-band full duplex wireless communication that allows a wireless node for simultaneous transmission and reception of signals. The benefits of in-band full duplex includes the doubled spectra efficiency which is in great need in the rapidly growing IoT devices and the potentials to solve the hidden terminals, unfairness and the exposed problems presented in the current single channel half duplex wireless communications. This paper investigates the research background and progress of in-band full duplex wireless. It also presents the research problems as well as opportunities. In addition, this paper summarizes the performance of literature solutions with experiment results in achieving in-band full duplex wireless communications. It also compares the Throughput and Packet Reception Ratio performance of full duplex to that of half duplex from a Software Defined Radio platform.