With the development of computed tomography (CT), the contrast-enhanced CT scan is widely used in the diagnosis of thyroid nodules. However, due to the artifacts and high complexity of thyroid CT images, traditional machine learning has difficulty in detecting thyroid nodules in contrast-enhanced CT. A fully automated detection algorithm for thyroid nodules using contrast-enhanced CT images is developed. A modified U-Net architecture of fully convolutional networks is employed to segment the thyroid region of interest (ROI), and a fusion of convolutional neural networks (CNN-Fs) is proposed to detect benign and malignant thyroid nodules from the ROI images and original contrast-enhanced CT images. Experimental results demonstrate that the proposed cascade and fusion method of multitask convolutional neural networks (CNNs) is efficient in diagnosing thyroid diseases with contrast-enhanced CT images and has superior performance compared with other CNN methods.

In recent years, due to the rapidly growing capacities of physical layer, device-free passive detection holds great importance for a broad range of application. Most recent works focus on motion detection, intrusion detection, and vital sign with commodity WiFi devices in the indoor environment. Conventional device-free motion detection techniques, which utilize received signal strength (RSS), may suffer from coarse granularity and high variability problems. In resorting to the finer-grained channel state information (CSI), we propose PhaseMode, a novel approach for device-free motion detection leveraging CSI phase difference data between adjacent antenna pairs. We implement our approach on commercial WiFi devices and validate its performance. We conduct experiments in different test periods of three indoor environments; the results show that the proposed scheme achieves an average accuracy over 99.4% of motion detection in different scenarios.

Mobile edge computing (MEC) is a promising technique to support the emerging delay-sensitive and compute-intensive applications for user equipment (UE) by means of computation offloading. However, designing a computation offloading algorithm for the MEC network to meet the restrictive requirements towards system latency and energy consumption remains challenging. In this paper, we propose a joint user-association, task-partition, and resource-allocation (JUTAR) algorithm to solve the computation offloading problem. In particular, we first build an optimization function for the computation offloading problem. Then, we utilize the user association and smooth approximation to simplify the objective function. Finally, we employ the particle swarm algorithm (PSA) to find the optimal solution. The proposed JUTAR algorithm achieves a better system performance compared with the state-of-the-art (SOA) computation offloading algorithm due to the joint optimization of the user association, task partition, and resource allocation for computation offloading. Numerical results show that, compared with the SOA algorithm, the proposed JUTAR achieves about $21\%$ system performance gain in the MEC network with 100 pieces of UE.

Acquisition is a key technology in DSSS system. The differential correlation is usually employed to eliminate the effect of frequency deviation. However, as the length of pseudo-code grows and the decrease of the SNR, the traditional differential acquisition algorithms will result in great loss of SNR. This paper presents an improved differential acquisition method, named as M-orders Auto-Correlation based on Differential correlation (MAC-DF). In the proposed method, the input signal is multiplied by the complex conjugate of the pseudo-code to eliminate its effect. After that, the product is applied to the M-orders Auto-Correlation to compensate the SNR loss caused by the differential process. By means of mathematical model to analyze its acquisition performance. We compare MAC-DF acquisition algorithm with the differential coherent and non-coherent acquisition algorithms through simulation. The simulation results indicate that this algorithm is approximately 5-6dB superior to the traditional differential acquisition algorithms in improving acquisition sensitivity and more adaptive to work under low SNR.

Data gathering is an attractive operation for obtaining information in wireless sensor networks (WSNs). But one of important challenges is to minimize energy consumption of networks. In this paper, an integration of distributed compressive sensing (CS) and virtual multi-input multi-output (vMIMO) in WSNs is proposed to significantly decrease the data gathering cost. The scheme first constructs a distributed data compression model based on low density parity check-like (LDPC-like) codes. Then a cluster-based dynamic virtual MIMO transmission protocol is proposed. The number of clusters, number of cooperative nodes and the constellation size are determined by a new established optimization model under the restrictions of compression model. Finally, simulation results show that the scheme can reduce the data gathering cost and prolong the sensor network’s lifetime in a reliable guarantee of sensory data recovery quality.

The traditional LTE-A algorithm validation is limited to pure computer software simulation, which can't simulate the actual link scenes, missing scene parameters, the simulation results is invaluable in practice. Therefore, this paper designs LTE-A hardware-in-the-loop simulation system based on software-defined radio device USRP, and the physical layer real-time test level downlink is designed on the system. The downlink scheduled by the scheduling algorithm of the PC simulation platform, with scene parameters feedback to MAC layer in real time. The downlink designed with power interference between cells and users simulate the actual scene. Compare to current design of LTE hardware-in-the-loop simulation, this design presents data interaction between MAC layer and physical layer, implement of specific requirements for physical layer link, instead of generation of vector signal only. The results show that the system is running normally with easy scalability.