As a promising computing paradigm driven by 5 G, mobile edge computing (MEC) empowers smart vehicles to offload computation-intensive tasks to edge devices in the Internet of Vehicles (IoV), thereby providing a plethora of exciting applications (e.g. on-board AR/VR, autonomous driving, etc.) with the unique quality of service (QoS) guarantees. However, a key challenge of MEC is how to keep the delay and energy consumption to a minimum in the computation offloading process, while ensuring the privacy security of offloaded data and the load balancing of edge resources. Namely, how to simultaneously optimize multiple indicators that affect computation offloading, which creates a challenging multi-objective optimization (MOO) problem. Aiming at the MOO problem, we propose a novel multi-objective reinforcement learning (MORL) algorithm based on double deep Q-network (DDQN). Each DDQN agent obtains rewards on different objectives according to different reward functions, and dynamically approximates the optimal offloading decision on multiple objectives. To conquer the trade-off problem among multiple conflicting objectives, we propose a weight-learning network based on radial basis function (RBF) networks, which dynamically adjusts the weights by learning the value changes among the objectives. Interestingly, we discovered encouraging potential of MORL for solving computation offloading problems in IoV, and numerical results show that the proposed algorithm outperforms traditional reinforcement learning methods by 30.24% in terms of overall energy consumption.

Background: The automatic glioma segmentation is of great significance for clinical practice. This study aims to propose an automatic method based on superpixel for glioma segmentation from the T2 weighted Magnetic Resonance Imaging. Methods: The proposed method mainly includes three steps. First, we propose an adaptive superpixel generation algorithm based on simple linear iterative clustering version with 0 parameter (ASLIC0). This algorithm can acquire a superpixel image with fewer superpixels and better fit the boundary of region of interest (ROI) by automatically selecting the optimal number of superpixels. Second, we compose a training set by calculating the statistical, texture, curvature and fractal features for each superpixel. Third, Support Vector Machine (SVM) is used to train classification model based on the features of the second step. Results: The experimental results on Multimodal Brain Tumor Image Segmentation Benchmark 2017 (BraTS2017) show that the proposed method has good segmentation performance. The average Dice, Hausdorff distance, sensitivity, and specificity for the segmented tumor against the ground truth are 0.8492, 3.4697 pixels, 81.47, and 99.64%, respectively. The proposed method shows good stability on high- and low-grade glioma samples. Comparative experimental results show that the proposed method has superior performance. Conclusions: This provides a close match to expert delineation across all grades of glioma, leading to a fast and reproducible method of glioma segmentation.

Three-dimensional (3D) NAND flash is one of the most prospective advances in flash memory industry. While 3D flash improves cell density and reduces lithography cost through die stacking, it suffers from severe program disturbance, which leads to significant performance and lifetime degradation for 3D flash based SSDs. To address the above challenge, we propose ApproxFTL, an approximate-write aware flash translation layer design, that uses approximate-write operations to store error-resilient data of modern applications. By reducing the maximal threshold voltage and tightening the guard bands between multi-level cell states, approximate write operations not only finish early but also exhibit large disturbance reduction, which can be exploited to alleviate disturbance in physical blocks that save both precise and approximate data. ApproxFTL maximizes the disturbance mitigation through approximate-write aware data placement, wear leveling, and garbage collection enhancements. Our experimental results show that ApproxFTL, while preserving high data quality, improves the read and write response time of flash accesses by 41.38% and 45.64% on average, respectively, and extends the lifetime of 3D flash based SSDs by 5.75% when comparing to the state-of-the-art.