The wireless sensor network (WSN) is mainly composed of a large number of sensor nodes that are equipped with limited energy and resources. Therefore, energy consumption in wireless sensor networks is one of the most challenging problems in practice. On the other hand, data fusion can effectively decrease data redundancy, reduce the amount of data transmission and energy consumption in the network, extend the network life cycle, improve the utilization of bandwidth, and thus overcome the bottleneck on energy and bandwidth consumption. This paper proposes a new data fusion algorithm based on Hesitant Fuzzy Entropy (DFHFE). The new algorithm aims to reduce the collection of repeated data on sensor nodes from the source, and strives to utilize the information provided by redundant data to improve the data reliability. Hesitant fuzzy entropy is exploited to fuse the original data from sensor nodes in the cluster at the sink node to obtain higher quality data and make local decisions on the events of interest. The sink nodes periodically send local decisions to the base station that aggregates the local decisions and makes the final judgment, in which process the burden for the base station to process all the data is significantly released. According to our experiments, the proposed data fusion algorithm greatly improves the robustness, accuracy, and real-time performance of the entire network. The simulation results demonstrate that the new algorithm is more efficient than the state-of-the-art in terms of both energy consumption and real-time performance.

Many applications deployed to public clouds are concerned about the confidentiality of their outsourced data, such as financial services and electronic patient records. A plausible solution to this problem is homomorphic encryption (HE), which supports certain algebraic operations directly over the ciphertexts. The downside of HE schemes is their significant, if not prohibitive, performance overhead for data-intensive workloads that are very common for outsourced databases, or database-as-a-serve in cloud computing. The objective of this work is to mitigate the performance overhead incurred by the HE module in outsourced databases. To that end, this paper proposes a radix-based parallel caching optimization for accelerating the performance of homomorphic encryption (HE) of outsourced databases in cloud computing. The key insight of the proposed optimization is caching selected radix-ciphertexts in parallel without violating existing security guarantees of the primitive/base HE scheme. We design the radix HE algorithm and apply it to both batch- and incremental-HE schemes; we demonstrate the security of those radix-based HE schemes by showing that the problem of breaking them can be reduced to the problem of breaking their base HE schemes that are known IND-CPA (i.e. Indistinguishability under Chosen-Plaintext Attack). We implement the radix-based schemes as middleware of a 10-node Cassandra cluster on CloudLab; experiments on six workloads show that the proposed caching can boost state-of-the-art HE schemes, such as Paillier and Symmetria, by up to five orders of magnitude.

In this paper, we propose a semantic segmentation method based on superpixel region merging and convolutional neural network (CNN), referred to as regional merging neural network (RMNN). Image annotation has always been an important role in weakly-supervised semantic segmentation. Most methods use manual labeling. In this paper, super-pixels with similar features are combined using the relationship between each pixel after super-pixel segmentation to form a plurality of super-pixel blocks. Rough predictions are generated by the fully convolutional networks (FCN) so that certain super-pixel blocks will be labeled. We perceive and find other positive areas in an iterative way through the marked areas. This reduces the feature extraction vector and reduces the data dimension due to super-pixels. The algorithm not only uses superpixel merging to narrow down the target’s range but also compensates for the lack of weakly-supervised semantic segmentation at the pixel level. In the training of the network, we use the method of region merging to improve the accuracy of contour recognition. Our extensive experiments demonstrated the effectiveness of the proposed method with the PASCAL VOC 2012 dataset. In particular, evaluation results show that the mean intersection over union (mIoU) score of our method reaches as high as 44.6%. Because the cavity convolution is in the pooled downsampling operation, it does not degrade the network’s receptive field, thereby ensuring the accuracy of image semantic segmentation. The findings of this work thus open the door to leveraging the dilated convolution to improve the recognition accuracy of small objects.

The Kirchhoff law is one of the most widely used physical laws in many engineering principles, e.g., biomedical engineering, electrical engineering, and computer engineering. One challenge of applying the Kirchhoff law to real-world applications at scale lies in the high, if not prohibitive, computational cost to solve a large number of nonlinear equations. Despite recent advances in leveraging a convolutional neural network (CNN) to estimate the solutions of Kirchhoff equations, the low performance is still significantly hindering the broad adoption of CNN-based approaches. This paper proposes a high-performance deep-learning-based approach for Kirchhoff analysis, namely HDK. HDK employs two techniques to improve the performance: (i) early pruning of unqualified input candidates and (ii) parallelization of forward labelling. To retain high accuracy, HDK also applies various optimizations to the data such as randomized augmentation and dimension reduction. Collectively, the aforementioned techniques improve the analysis speed by 8× with accuracy as high as 99.6%.

The isolation and observation of cardiomyocytes serve as the fundamental approach to cardiovascular research. The state-of-the-practice for the isolation and observation relies on manual operation of the entire culture process. Such a manual approach not only incurs high human errors, but also takes a long period of time. This paper proposes a new computer-aided paradigm to automatically, accurately, and efficiently perform the clustering and counting of cardiomyocytes, one of the key procedures for evaluating the success rate of cardiomyocytes isolation and the quality of culture medium. The key challenge of the proposed method lies in the unique, rod-like shape of cardiomyocytes, which has been hardly addressed in literature. Our proposed method employs a novel algorithm inspired by hesitant fuzzy sets and integrates an efficient implementation into the whole process of analyzing cardiomyocytes. The system, along with the data extracted from adult rats’ cardiomyocytes, has been experimentally evaluated with Matlab, showing promising results. The false accept rate (FAR) and the false reject rate (FRR) are as low as 1.46% and 1.97%, respectively. The accuracy rate is up to 98.7%—20% higher than the manual approach—and the processing time is reduced from tens of seconds to 3–5 s—an order of magnitude performance improvement.