This paper constructs a counterexample showing that not every locally $L^0$--convex topology is necessarily induced by a family of $L^0$--seminorms. Random convex analysis is the analytic foundation for $L^0$--convex conditional risk measures, this counterexample, however, shows that a locally $L^0$--convex module is not a proper framework for random convex analysis. Further, this paper also gives a necessary and sufficient condition for a locally $L^0$--convex topology to be induced by a family of $L^0$--seminorms. Finally, we give some comments showing that based on random locally convex modules, we can establish a perfect random convex analysis to meet the needs of the study of $L^0$--convex conditional risk measures.
High-definition map is an essential tool for route measurement, planning and navigation of intelligent vehicles. Yet its creation is still a persisting challenge, especially in creating the semantic and topology layer of the map based on visual sensing. However, current semantic mapping approaches do not consider the map applicability in navigation tasks while the topology mapping approaches face the issues of limited location accuracy or expensive hardware cost. In this paper, we propose a joint mapping framework for both semantic and topology layers, which are learned in a lane-level and based on a monocular camera sensor and an on-board GPS positioning device. A map management approach "RoadSegDict" is also proposed to support the efficient updating of semantic map in a crowdsourced manner. Moreover, a new dataset is proposed, which includes a variety of lane structures with detailed semantic and topology annotations.
In this paper, we embed each $L^\infty$-normed module $E$ into an appropriate and unique complete random normed module $E_0$ so that the properties of $E$ are closely related to the properties of $E_0$.
Intelligent vehicles are constrained by road, resulting in a disparity between the assumed six degrees of freedom (DoF) motion within the Visual Simultaneous Localization and Mapping (SLAM) system and the approximate planar motion of vehicles in local areas, inevitably causing additional pose estimation errors. To address this problem, a stereo Visual SLAM system with road constraints based on graph optimization is proposed, called RC-SLAM. Addressing the challenge of representing roads parametrically, a novel method is proposed to approximate local roads as discrete planes and extract parameters of local road planes (LRPs) using homography. Unlike conventional methods, constraints between the vehicle and LRPs are established, effectively mitigating errors arising from assumed six DoF motion in the system. Furthermore, to avoid the impact of depth uncertainty in road features, epipolar constraints are employed to estimate rotation by minimizing the distance between road feature points and epipolar lines, robust rotation estimation is achieved despite depth uncertainties. Notably, a distinctive nonlinear optimization model based on graph optimization is presented, jointly optimizing the poses of vehicle trajectories, LPRs, and map points. The experiments on two datasets demonstrate that the proposed system achieved more accurate estimations of vehicle trajectories by introducing constraints between the vehicle and LRPs. The experiments on a real-world dataset further validate the effectiveness of the proposed system.
Background: Before the COVID-19 pandemic, tuberculosis is the leading cause of death from a single infectious agent worldwide for the past 30 years. Progress in the control of tuberculosis has been undermined by the emergence of multidrug-resistant tuberculosis. The aim of the study is to reveal the trends of research on medications for multidrug-resistant pulmonary tuberculosis (MDR-PTB) through a novel method of bibliometrics that co-occurs specific semantic Medical Subject Headings (MeSH). Methods: PubMed was used to identify the original publications related to medications for MDR-PTB. An R package for text mining of PubMed, pubMR, was adopted to extract data and construct the co-occurrence matrix-specific semantic types. Biclustering analysis of high-frequency MeSH term co-occurrence matrix was performed by gCLUTO. Scientific knowledge maps were constructed by VOSviewer to create overlay visualization and density visualization. Burst detection was performed by CiteSpace to identify the future research hotspots. Results: Two hundred and eight substances (chemical, drug, protein) and 147 diseases related to MDR-PTB were extracted to form a specific semantic co-occurrence matrix. MeSH terms with frequency greater than or equal to six were selected to construct high-frequency co-occurrence matrix (42 × 20) of specific semantic types contains 42 substances and 20 diseases. Biclustering analysis divided the medications for MDR-PTB into five clusters and reflected the characteristics of drug composition. The overlay map indicated the average age gradients of 42 high-frequency drugs. Fifteen top keywords and 37 top terms with the strongest citation bursts were detected. Conclusion: This study evaluated the literatures related to MDR-PTB drug therapy, providing a co-occurrence matrix model based on the specific semantic types and a new attempt for text knowledge mining. Compared with the macro knowledge structure or hot spot analysis, this method may have a wider scope of application and a more in-depth degree of analysis. Keywords: multidrug-resistant tuberculosis, pulmonary tuberculosis, medication trends, specific semantic types, MeSH tree, pubMR
This article applies deep learning and electromechanical technology to plant phenotype measurement. First, an electromechanical device is designed to collect plant phenotype images, which solves the difficulty of collecting deep learning training data. The data set required for deep learning model training for plant phenotype detection is made by an automated method. This paper takes the Lactuca sativa plant image as an example and uses the ASM-based data enhancement method to solve the problem of insufficient image data of Lactuca sativa leaf pests and effectively avoid the phenomenon of overfitting. The plant image recognition method based on deep learning proposed breaks through the limitations of plant local feature recognition, gets rid of the limitation of highly specialized data collection, lowers the threshold of plant image recognition, and has advantages in recognition speed and accuracy. This method requires a large amount of training data. In the future, we can explore the collection of massive plant pictures from the Internet as a training set to achieve rapid iteration and optimization of the model.
First, this paper introduces the notion of L0-convex compactness for a special class of closed convex subsets–closed L0-convex subsets of a Hausdorff topological module over the topological algebra L0(F,K), where L0(F,K) is the algebra of equivalence classes of random variables from a probability space (Ω,F,P) to the scalar field K of real numbers or complex numbers, endowed with the topology of convergence in probability. Then, this paper continues to develop the theory of L0-convex compactness by establishing various kinds of characterization theorems on L0-convex compactness for closed L0-convex subsets of a class of important topological modules – complete random normed modules, in particular, we make full use of the theory of random conjugate spaces to establish the characterization theorem of James type on L0-convex compactness for a closed L0-convex subset of a complete random normed module, which also surprisingly implies that our notion of L0-convex compactness coincides with Gordan Žitković's notion of convex compactness in the context of a closed L0-convex subset of a complete random normed module. As the first application of our results, we give a fundamental theorem on random convex optimization (or, L0-convex optimization), which includes Hansen and Richard's famous result as a special case. As the second application, we give an existence theorem of solutions of random variational inequalities, which generalizes H. Brezis' classical result from a reflexive Banach space to a random reflexive complete random normed module. It should be emphasized that a new method, namely the L0-convex compactness method, is presented for the second application since the usual weak compactness method is no longer applicable in the present case. Besides, our fundamental theorem on random convex optimization can be also applied in the study of optimization problems of conditional convex risk measures, which will be given in our future papers.
The convolutional neural network (CNN) has been widely used in the field of self-driving cars. To satisfy the increasing demand, the deeper and wider neural network has become a general trend. However, this leads to the main problem that the deep neural network is computationally expensive and consumes a considerable amount of memory. To compress and accelerate the deep neural network, this paper proposes a filter pruning method based on feature maps clustering. The basic idea is that by clustering, one can know how many features the input images have and how many filters are enough to extract all features. This paper chooses Retinanet and WIDER FACE datasets to experiment with the proposed method. Experiments demonstrate that the hierarchical clustering algorithm is an effective method for filtering pruning, and the silhouette coefficient method can be used to determine the number of pruned filters. This work evaluates the performance change by increasing the pruning ratio. The main results are as follows: Firstly, it is effective to select pruned filters based on feature maps clustering, and its precision is higher than that of a random selection of pruned filters. Secondly, the silhouette coefficient method is a feasible method for finding the best clustering number. Thirdly, the detection speed of the pruned model improves greatly. Lastly, the method we propose can be used not only for Retinanet, but also for other CNN models. Its effect will be verified in future work.
Motivated by Gordan \v{Z}itkovi\'{c}'s idea of convex compactness for a convex set of a linear topological space, we introduce the concept of $L^0$--convex compactness for an $L^0$--convex set of a topological module over the topological algebra $L^0$, where $L^0$ is the algebra of equivalence classes of real--valued random variables on a given probability space $(\Omega,\mathcal{F},P)$ and endowed with the topology of convergence in probability. This paper continues to develop the theory of $L^0$--convex compactness by establishing various kinds of characterization theorems for $L^0$--convex subsets of a class of important topological modules--random reflexive random normed modules. As applications, we successfully generalize some basic theorems of classical convex optimization and variational inequalities from a convex function on a reflexive Banach space to an $L^0$--convex function on a random reflexive random normed module. Since the usual weak compactness method fails to be valid, we are forced to use the $L^0$--convex compactness method so that a series of new skills can be discovered. These new skills actually also provide a new proof for the corresponding classical case and thus they are of new interest themselves.
<div>With the development of automotive intelligence and networking, the communication architecture of automotive network is evolving toward Ethernet. To improve the real-time performance and reliability of data transmission in traditional Ethernet, time-sensitive network (TSN) has become the development direction of next-generation of automotive networks. The real-time advantage of TSN is based on accurate time synchronization. Therefore, a reliable time synchronization mechanism has become one of the key technologies for the application of automotive Ethernet technology. The protocol used to achieve accurate time synchronization in TSN is IEEE 802.1AS. This protocol defines a time synchronization mechanism suitable for automotive Ethernet. Through the master clock selection algorithm, peer link delay measurement, and clock synchronization and calibration mechanism, the time of each node in the vehicle network is synchronized to a reference master clock. In addition, the protocol clearly states the requirements for node synchronization accuracy in the vehicle network. In this article, it is proposed that an automated test methodology for time synchronization mechanism in the case of multi-device network topology for the IEEE 802.1AS protocol in TSN is applicable to in-vehicle environments. The test methodology automates the process of achieving time synchronization and automatically tests the time synchronization mechanism. In addition, a corresponding test system was designed and developed, and a physical test platform was built to physically test and verify the time synchronization mechanism of the protocol. The results show that the test method proposed can realize the automated testing of the time synchronization mechanism in the case of automotive Ethernet networks. The presented results can contribute to the practical application of automotive TSN technology.</div>
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)