Search

Fast and accurate detection of ripe tomatoes on plant, which replaces manual labor with a robotic vision-based harvesting system, is a challenging task. Tomatoes in adjacent positions are easily mistaken as a single tomato by image recognition methods. In this study, a ripe tomato detection method that combines deep learning with edge contour detection is proposed. Our approach efficiently separates target tomatoes from overlapping tomatoes to detect individual fruits. This approach yields several improvements. First, deep learning requires less time and extracts deeper features than traditional methods for assessing candidate ripe tomato regions. Second, we use Gaussian density function of H and S in the HSV color space to help segment tomato regions from the background, followed by erosion and dilation on the tomato body to separate adjacent tomatoes and remove peripheral subpixels from all detected ripe tomatoes. Third, an adaptive threshold intuitionistic fuzzy set (IFS) method was developed to identify the tomato's edge, and it performs well in detecting blurred edges in overlapping regions. To improve the efficiency and stability of edge detection under natural conditions, we adopted an illumination adjustment algorithm for the tomato image before edge detection. As samples, we collected images showing tomatoes that were separated, adjacent, overlapped, and even shaded by leaves. The widths and heights of these tomato samples were calculated and analyzed to evaluate the detection performance of the proposed method. The root mean square error (RMSE) results for tomato width and height using the proposed method are 2.996 pixels and 3.306 pixels, respectively. The mean relative error percent (MRE%) values for horizontal and vertical center position shift are 0.261% and 1.179%, respectively. These results demonstrate that the proposed method improves tomato detection accuracy and that it can be further applied in the harvesting process of agricultural robots.

Triangle count is a critical parameter in mining relationships among people in social networks. However, directly publishing the findings obtained from triangle counts may bring potential privacy concern, which raises great challenges and opportunities for privacy-preserving triangle counting. In this paper, we choose to use differential privacy to protect triangle counting for large scale graphs. To reduce the large sensitivity caused in large graphs, we propose a novel graph projection method that can be used to obtain an upper bound for sensitivity in different distributions. In particular, we publish the triangle counts satisfying the node-differential privacy with two kinds of histograms: the triangle count distribution and the cumulative distribution. Moreover, we extend the research on privacy preserving triangle counting to one of its applications, the local clustering coefficient. Experimental results show that the cumulative distribution can fit the real statistical information better, and our proposed mechanism has achieved better accuracy for triangle counts while maintaining the requirement of differential privacy. [ABSTRACT FROM AUTHOR]

Despite the success of stochastic variance-reduced gradient (SVRG) algorithms in solving large-scale problems, their stochastic gradient complexity often scales linearly with data size and is expensive for huge data. Accordingly, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly convex problems with linear prediction structure, e.g., least squares and logistic/softmax regression. HSDMPG enjoys improved computational complexity that is data-size-independent for large-scale problems. It iteratively samples an evolving minibatch of individual losses to estimate the original problem, and can efficiently minimize the sampled subproblems. For strongly convex loss of $n$ n components, HSDMPG attains an $\epsilon$ ε -optimization-error within $\mathcal {O} \left(\kappa \log ^{\zeta +1}\left(\frac{1}{\epsilon }\right)\frac{1}{\epsilon }\bigwedge n\log ^{\zeta }\left(\frac{1}{\epsilon }\right)\right)$ O κ log ζ + 1 1 ε 1 ε ⋀ n log ζ 1 ε stochastic gradient evaluations, where $\kappa$ κ is condition number, $\zeta =1$ ζ = 1 for quadratic loss and $\zeta =2$ ζ = 2 for generic loss. For large-scale problems, our complexity outperforms those of SVRG-type algorithms with/without dependence on data size. Particularly, when $\epsilon =\mathcal {O}(1/\sqrt{n})$ ε = O (1 / n) which matches the intrinsic excess error of a learning model and is sufficient for generalization, our complexity for quadratic and generic losses is respectively $\mathcal {O} (n^{0.5}\log ^{2}(n))$ O (n 0. 5 log 2 (n)) and $\mathcal {O} (n^{0.5}\log ^{3}(n))$ O (n 0. 5 log 3 (n)) , which for the first time achieves optimal generalization in less than a single pass over data. Besides, we extend HSDMPG to online strongly convex problems and prove its higher efficiency over the prior algorithms. Numerical results demonstrate the computational advantages of HSDMPG. [ABSTRACT FROM AUTHOR]

Large volumes of video data recorded by the increasing mobile devices and embedded sensors can be leveraged to answer queries of our lives, physical world and our evolving society. Especially, the rapid development of convolutional neural networks (CNNs) in the past few years offers the great advantage for multiple tasks in video analysis. However, adopting running CNNs directly on mobile devices and embedded sensors for video analytics brings heavy burden due to their limited capacity, especially for learning a large volume of data. A promising approach is to outsource the computation-intensive part of CNN to cloud. However, the reveal of data to cloud may cause privacy leakage. In addition, the cloud-assisted approach may also bring some communication efficiency challenges for large volume of data. To address both privacy and efficiency issues, we design a privacy-preserving and computationally efficient framework for mobile video analytics. To protect the private information, we split the CNN model into two subnetworks, and first part is used as a feature extractor deployed in the mobile side and the second part is utilized as a classifier deployed in the cloud side. A specific-designed adversarial training process is adopted in order to extract features for normal task classification while hiding the features for sensitive task. In addition, to improve video process efficiency, we design a two-stage framework. The first stage is to extract key frames and necessary intermediate frames, while skipping redundant ones. The second stage is to extract the features of key frames by CNN-based feature extractor but apply optical-flow-based feature propagation algorithm to obtain the features of intermediate frames. Extensive experiments demonstrate our proposed system PrivacyEye can effectively protect private information while keep the accuracy of the normal tasks with less than 2 percent drop, and it saves up to 82.9 percent execution time and 78.8 percent energy consumption. [ABSTRACT FROM AUTHOR]

Training a neural network requires retraining the same model many times to search for the configuration of hyper-parameters with the best training result. It is common to launch multiple training jobs and evaluate them in stages. At the completion of each stage, jobs with unpromising configurations will be terminated and jobs with new configurations will start. Each job typically performs distributed training across multiple GPUs, and GPUs periodically synchronize their models over the network. However, model synchronizations of running jobs cause severe network congestion, significantly increasing the stage completion time (SCT) and thus the time to successfully search for the desired configuration. Existing flow schedulers are ineffective to reduce SCT since they are agnostic to training stages. In this paper, we propose a stage-aware coflow scheduling method to minimize the average SCT. In this method, an algorithm is designed to order coflows by considering stage information and then coflows are scheduled according to the order. Mathematical analysis shows that the method achieves the average SCT within 20/3 of the optimal. We implement the method in a real system called Beamer. Extensive testbed experiments and simulations show that Beamer significantly outperforms advanced network designs, such as Sincronia, FIFO-LM, and per-flow fair sharing. [ABSTRACT FROM AUTHOR]