Search

With consideration of false data injection (FDI) on the demand side, it brings a great challenge for the optimal defensive strategy with the security issue, voltage stability, power flow, and economic cost indexes. This article proposes a Takagi-Sugeuo-Kang (TSK) fuzzy system-based reinforcement learning approach for the resilient optimal defensive strategy of interconnected microgrids. Due to FDI uncertainty of the system load, TSK-based deep deterministic policy gradient (DDPG) is proposed to learn the actor network and the critic network, where multiple indexes' assessment occurs in the critic network, and the security switching control strategy is made in the actor network. Alternating direction method of multipliers (ADMM) method is improved for policy gradient with online coordination between the actor network and the critic network learning, and its convergence and optimality are proved properly. On the basis of security switching control strategy, the penalty-based boundary intersection (PBI)-based multiobjective optimization method is utilized to solve economic cost and emission issues simultaneously with considering voltage stability and rate-of-change of frequency (RoCoF) limits. According to simulation results, it reveals that the proposed resilient optimal defensive strategy can be a viable and promising alternative for tackling uncertain attack problems on interconnected microgrids.

Leaf disease recognition using image processing and deep learning techniques is currently a vibrant research area. Most studies have focused on recognizing diseases from images of whole leaves. This approach limits the resulting models’ ability to estimate leaf disease severity or identify multiple anomalies occurring on the same leaf. Recent studies have demonstrated that classifying leaf diseases based on individual lesions greatly enhances disease recognition accuracy. In those studies, however, the lesions were laboriously cropped by hand. This study proposes a semi-automatic algorithm that facilitates the fast and efficient preparation of datasets of individual lesions and leaf image pixel maps to overcome this problem. These datasets were then used to train and test lesion classifier and semantic segmentation Convolutional Neural Network (CNN) models, respectively. We report that GoogLeNet’s disease recognition accuracy improved by more than 15% when diseases were recognized from lesion images compared to when disease recognition was done using images of whole leaves. A CNN model which performs semantic segmentation of both the leaf and lesions in one pass is also proposed in this paper. The proposed KijaniNet model achieved state-of-the-art segmentation performance in terms of mean Intersection over Union (mIoU) score of 0.8448 and 0.6257 for the leaf and lesion pixel classes, respectively. In terms of mean boundary F1 score, the KijaniNet model attained 0.8241 and 0.7855 for the two pixel classes, respectively. Lastly, a fully automatic algorithm for leaf disease recognition from individual lesions is proposed. The algorithm employs the semantic segmentation network cascaded to a GoogLeNet classifier for lesion-wise disease recognition. The proposed fully automatic algorithm outperforms competing methods in terms of its superior segmentation and classification performance despite being trained on a small dataset.

Human parsing is a fine-grained semantic segmentation task, which needs to understand human semantic parts. Most existing methods model human parsing as a general semantic segmentation, which ignores the inherent relationship among hierarchical human parts. In this work, we propose a pose-guided hierarchical semantic decomposition and composition framework for human parsing. Specifically, our method includes a semantic maintained decomposition and composition (SMDC) module and a pose distillation (PC) module. SMDC progressively disassembles the human body to focus on the more concise regions of interest in the decomposition stage and then gradually assembles human parts under the guidance of pose information in the composition stage. Notably, SMDC maintains the atomic semantic labels during both stages to avoid the error propagation issue of the hierarchical structure. To further take advantage of the relationship of human parts, we introduce pose information as explicit guidance for the composition. However, the discrete structure prediction in pose estimation is against the requirement of the continuous region in human parsing. To this end, we design a PC module to broadcast the maximum responses of pose estimation to form the continuous structure in the way of knowledge distillation. The experimental results on the look-into-person (LIP) and PASCAL-Person-Part datasets demonstrate the superiority of our method compared with the state-of-the-art methods, that is, 55.21% mean Intersection of Union (mIoU) on LIP and 69.88% mIoU on PASCAL-Person-Part.

We establish the undecidability of conditional affine information inequalities, the undecidability of the conditional independence implication problem with a constraint that one random variable is binary, and the undecidability of the problem of deciding whether the intersection of the entropic region and a given affine subspace is empty. This is a step towards the conjecture on the undecidability of conditional independence implication. The undecidability is proved via a reduction from the periodic tiling problem (a variant of the domino problem). Hence, one can construct examples of the aforementioned problems that are independent of ZFC (assuming ZFC is consistent)., 19 pages, 7 figures, presented in part at the 2021 IEEE Information Theory Workshop

We propose decentralized primal-dual methods for cooperative multi-agent consensus optimization problems over both static and time-varying communication networks, where only local communications are allowed. The objective is to minimize the sum of agent-specific convex functions over conic constraint sets defined by agent-specific nonlinear functions; hence, the optimal consensus decision should lie in the intersection of these private sets. Under the strong convexity assumption, we provide convergence rates for sub-optimality, infeasibility, and consensus violation in terms of the number of communications required; examine the effect of underlying network topology on the convergence rates., A preliminary result of this paper was presented in arXiv:1706.07907 by Hamedani and Aybat. In this paper, we generalize our results to the setting where agent-specific constraints are defined by nonlinear functions rather than linear ones which greatly improves the modeling capability. This generalization requires a more complicated analysis which is studied in this separate arXiv submission

Road region and non-road region separation in the unstructured road intends to be an important task for safe navigation and collision avoidance for autonomous driving vehicles. The road that connects rural areas and cities to the national highways are considered as unstructured roads. Absence of clear lane marking on these unstructured roads makes them more prone to accidents in comparison to highways, which have clear lane marking for indication of road and non-road regions. However, the unstructured roads have different color information from its background that paves an easy way for design and development of an efficient road detection system for recognition and classification of road and non-road regions. Hence, in this paper, we propose an efficient road detection system for the classification of unstructured roads into road and non-road regions using multiple nearest neighbors (NN) classifier and soft voting aggregation approach. The proposed system utilized the chromatic information (i.e. *a,*b, and Hue) to train the NN classifiers and aggregated their output using soft voting (SV) approach for final output response. The output results of multiple classifiers were aggregated using SV approach based on the confidence score obtained by each individual classifier. The performance of the proposed system is evaluated in terms of precision, recall, accuracy, intersection over union (IOU), true positive rate (TPR), and processing time and compared with current state of art methods reported in the literature. The proposed system achieved precision, recall, accuracy, IOU, and TPR of 96.79%, 96.92%, 97.8%, 96.08% and 96%, respectively with the processing time three times smaller than those of the existing state of art methods. The experimental results demonstrate that the proposed system can provide an effective guidance to the autonomous vehicles through recognition and classification of road and non-road regions in rural, urban, and city areas, wherein single unstructured roads connect the national highways.

Center loss is widely used as a supervision tool in deep learning method. However, the center loss also has some shortcomings, the most important of which is that it must be combined with softmax loss to run well. In this article, we sum up five shortcomings of center loss and solve all of them by proposing a dual distance center loss (DDCL). Compared with center loss, DDCL can run without the combination of softmax to supervise training the model. In addition, we verify the inconsistency between the proposed DDCL and softmax loss in the feature space. To be specifically, we add the Pearson distance on the basis of the Euclidean distance to the same center, which makes all features of the same class be confined to the intersection of a hypersphere and a hypercone in the feature space, strengthens the intraclass compactness of the center loss, and enhances the generalization ability of center loss. Moreover, by designing a Euclidean distance threshold between all center pairs, we not only strengthen the interclass separability of center loss, but also make the center loss (or DDCL) works well without the combination of softmax loss. We verify the effectiveness of DDCL in four datasets, two of which are widely used in the field of vehicle re-identification named VeRi-776 dataset and VehicleID dataset, and two other datasets are widely used in the field of person re-identification named Market1501 dataset and MSMT17 dataset. The experimental results of the proposed DDCL exceed that of the softmax loss in all the four datasets, indicating that our proposed method not only can run without the combination of softmax, but also has a high accuracy.

Set containment search, which aims to retrieve all set records containing a query set, has received considerable attention. Meanwhile, due to the dramatic growth of data, data owners tend to outsource their data to the cloud and deploy the cloud server to offer the set containment search services. However, as the cloud server is not fully trustable and the data may be sensitive, a straightforward strategy for the data owners is to encrypt the data before outsourcing them. Although the encryption technique can preserve data privacy, it inevitably hinders the functionality of set containment search. Existing studies on the set containment search over outsourced data still suffer from the search efficiency and security issues. In this paper, aiming at the above issues, we propose an efficient and privacy-preserving set containment search scheme. Specifically, we first deploy an asymmetric scalar-product-preserving encryption technique to design a set containment/intersection encryption (SCIE-Enc) scheme. Then, we build a radix tree to represent the set records. Based on the radix tree and SCIE-Enc construction, we present our scheme that can achieve efficient set containment search while preserving the privacy of set records, query sets, and query results, as indicated in our security analysis and performance evaluation.

Cooperative vehicle safety (CVS) systems have been receiving significant attention as key enablers of important intelligent transportation system (ITS) applications, such as cooperative collision warning, emergency braking, and auto driving. In CVS systems, vehicles periodically broadcast short packets that include various types of vehicular information, e.g., position and speed. In this paper, we propose an optimization method for the broadcast rate in vehicle-to-vehicle (V2V) broadcast communications at an intersection based on theoretical analysis. We consider a model in which the locations of vehicles are modeled separately as queuing, and running segments and derive key performance metrics of V2V broadcast communications through a stochastic geometry approach. We develop closed-form approximate formulas for the theoretical expressions because they are mathematically intractable. Based on approximate analysis, we optimize the broadcast rate such that the interference at an intersection is mitigated and the overall performance of V2V communications is maximized. Because of the closed-form approximation, the optimal rate can be used as a guideline for a real-time control-method, which cannot be achieved through time-consuming simulations. We evaluate our method through numerical examples and demonstrate its effectiveness.

Multi-dimensional range queries, especially over the cloud platform, have received considerable attention in recent years. However, as the cloud server is not fully trustable, designing multi-dimensional range queries over encrypted data becomes a research trend, and many solutions have been proposed in the literature. Nevertheless, most existing solutions suffer from the leakage of single-dimensional privacy. Although a few existing works have addressed the problem of single-dimensional privacy, they are impractical in some real scenarios due to the issues of inefficiency, inaccuracy, and two-cloud-server requirement. Aiming at solving these issues, in this paper, we propose a practical and privacy-preserving multi-dimensional range query (PRQ) scheme. Specifically, in our PRQ scheme, we first index the multi-dimensional database with an R-tree and reduce R-tree based range queries to the problem of point intersection and range intersection. Then, by employing the lightweight matrix encryption technique, we design two novel algorithms for PRQ, i.e., multi-dimensional point intersection predicate encryption (PIPE) and multi-dimensional range intersection predicate encryption (RIPE), which can preserve the privacy of the proposed point intersection algorithm and range intersection algorithm, and further preserve the single-dimensional privacy in the PRQ scheme. Security analysis and extensive simulations show that our PRQ scheme is privacy-preserving and efficient.

It is necessary for cost consideration to minimize the number of the used layers in a PCB design. Traditionally, the number of the used layers outside components in bus assignment depends on the locations of the bus pins inside components in escape routing in a PCB design. In this paper, the concept of introducing the flexible escape directions in escape routing is considered in the bus assignment outside components in a PCB design. Clearly, the flexible consideration of the escape directions inside components can lead to the reduction on the number of the used layers in the bus assignment outside components. Given a set of buses on a set of components in a PCB design, based on the introduction of the flexible escape directions in escape routing and the construction of the possible bus connections in bus assignment, the two upper bounds of the layer numbers inside and outside components can be firstly computed. By eliminating the redundant bus connections for the given buses, an integrated algorithm can be further proposed to minimize the number of the used layers in a PCB design. Based on the assignment constraints from the intersection relations inside components, the physical connections of the given buses can be assigned onto a minimal set of used layers. Compared with the two-phase algorithm using Yan’s routing algorithm in direction-constrained rectangle escape routing and Yan’s assignment algorithm in bus assignment, the experimental results show that our proposed integrated algorithm use reasonable CPU time to reduce 32.1% of the layer number for 10 tested examples in a PCB design on the average.

In the research of uncertain information processing, Dempster-Shafer Theory (DST) provides a framework for dealing with uncertain information, where evidence is defined on a Frame of Discernment (FOD) consisting of mutually exclusive elements. However, the requirement of exclusiveness on FOD sometimes is not satisfied, as shown in Dezert-Smarandache Theory(DSmT), a derivative of DST. In DSmT, the non-exclusiveness is expressed by propositions’ intersection and the fusion of evidence is realized through a Proportional Conflict Redistribution (PCR) rule. In order to handle non-exclusive FODs, a new framework called D Number Theory (DNT) has been proposed recently, which quantifies the non-exclusive degree between propositions different from DSmT. In previous studies, an Exclusive Conflict Redistribution (ECR) rule has been designed in DNT to implement the fusion of evidence defined on a non-exclusive FOD, but there are some deficiencies in the ECR rule. In this paper, a new rule called ECR-PCR rule is proposed by combining the ECR and PCR rules to better implement the fusion of evidence defined on a non-exclusive FOD. Within the proposed rule, the definition of conflict utilizes the idea of ECR’s exclusive conflict, and the disposal of conflict is following the idea of PCR’s proportional redistribution. Properties of the ECR-PCR rule are presented. The effectiveness of the proposed new rule is verified through numerical examples and applications, in comparison with other fusion methods.

We present GridSet, a novel set visualization for exploring elements, their attributes, intersections, as well as entire sets. In this set visualization, each set representation is composed of glyphs, which represent individual elements and their attributes utilizing different visual encodings. In each set, elements are organized within a grid treemap layout that can provide space-efficient overviews of the elements structured by set intersections across multiple sets. These intersecting elements can be connected among sets through visual links. These visual representations for the individual set, elements, and intersection in GridSet facilitate novel interaction approaches for undertaking analysis tasks by utilizing both macroscopic views of sets, as well as microscopic views of elements and attribute details. In order to perform multiple set operations, GridSet supports a simple and straightforward process for set operations through dragging and dropping set objects. Our use cases involving two large set-typed datasets demonstrate that GridSet facilitates the exploration and identification of meaningful patterns and distributions of elements with respect to attributes and set intersections for solving complex analysis problems in set-typed data.

An intelligent cleaning vehicle improves the efficiency of road cleaning to a great extent. In this case, road garbage recognition is fundamental and crucial. Usually, the pebbles are too small, and the sand has an inconspicuous boundary and unfixed shape on the roads. These issues make the stones and sand too hard to be detected by a garbage recognition system. Hence, we designed a novel semantic segmentation network that acquires the areas and categories of road garbage. We designed a Deep Supervision and High Fusion (DSHF) block to improve the road garbage segmentation accuracy. The designed block with a backbone network of HFCN and UNet++ is comparable with a model that only has either a deep supervision block or a high fusion block. According to the collected road garbage segmentation dataset comprising four categories (stones, leaves, sand and bottles), the model we designed has improved the metric value of MPA by 3% over the state-of-art methods and achieved the highest MIoU (Mean Intersection over Union) with the value of 77.92%. The results of our experiments show that the semantic segmentation of road garbage is feasible and that the proposed DSHF block is practical for improving the segmentation effect of road garbage.

This paper constructs a conjunction and a disjunction operator for type-2 fuzzy sets that cannot be expressed by the sup-t-norm extension principle applied to conjunction and disjunction of type-1 fuzzy sets by means of t-norms and t-conorms on the unit interval. This result answers affirmatively an open problem posed by Hernandez et al. in 2015. The duality between the set-theoretic operators for type-2 fuzzy sets is obtained from the duality of set-theoretic operations on type-1 fuzzy sets.

Lane detection is one of the indispensable and key elements of self-driving environmental perception. Many lane detection models have been proposed, solving lane detection under challenging conditions, including intersection merging and splitting, curves, boundaries, occlusions and combinations of scene types. Nevertheless, lane detection will remain an open problem for some time to come. The ability to cope well with those challenging scenes impacts greatly the applications of lane detection on advanced driver assistance systems (ADASs). In this paper, a spatio-temporal network with double Convolutional Gated Recurrent Units (ConvGRUs) is proposed to address lane detection in challenging scenes. Both of ConvGRUs have the same structures, but different locations and functions in our network. One is used to extract the information of the most likely low-level features of lane markings. The extracted features are input into the next layer of the end-to-end network after concatenating them with the outputs of some blocks. The other one takes some continuous frames as its input to process the spatio-temporal driving information. Extensive experiments on the large-scale TuSimple lane marking challenge dataset and Unsupervised LLAMAS dataset demonstrate that the proposed model can effectively detect lanes in the challenging driving scenes. Our model can outperform the state-of-the-art lane detection models., Comment: 13 pages, 9 figures, 8 tables, Accepted by IEEE Transactions on Intelligent Transportation Systems

In recent years, research has been conducted on dynamic map systems, which are information and communication platforms that manage vehicle sensor information and run applications. However, there is a concern about scalability in the dynamic map system, which operates on a cloud on the Internet, when the number of vehicles that transmit and receive sensor information increases. Therefore, it is considered that the application load can be distributed by distributing multiple edge servers geographically and having the information managed in the cloud by the edge servers. However, the edge server that controls the vehicle information and the edge server that receives the data do not always match depending on the actual radio wave conditions. Therefore, some applications are difficult to manage, such as intersection collision danger warning and merging arbitration when edge servers are assigned in the same way as base stations that receive data from vehicles. Such an application should receive all vehicle data for the target road area. Therefore, we divide the area on the road where a vehicle travels as ``lane section ID'' and assign an edge server to each lane section ID on the basis of that area. In addition, we implemented a dynamic map system that connects vehicles and edge servers by linking multiple edge servers. This enables the edge server to aggregate vehicle data without being affected by radio traffic conditions. We evaluated the scalability of the dynamic map system and verified the effectiveness of the load balancing mechanism using multiple edge servers.

This article proposes a new discrete collision handling method (DCH method) that can be used for resolving tanglements in clothing simulation, based on the existing continuous collision handling methods (CCH methods). The proposed method performs intersection analysis of the clothing mesh at every time step, and stores the result in the form of coloring the vertices, edges, and triangles. Referring to the coloring, the method resolves the tanglements in the out-to-in manner by applying the proposed operations, the triangle shrinkage and vertex pull, to the triangles and vertices around the intersection path. We take note of the CCH methods that use some small tolerance value to defend the round-off errors for the purpose of preventing false negatives. This work gives a second thought to that tolerance value, and proposes a new DCH method which uses the tolerance value for the resolution purpose. Under certain conditions, the method turns out to guarantee resolution of the tanglements in a finite number of time steps.

Reinforcement learning is an efficient, widely used machine learning technique that performs well in problems with a reasonable number of states and actions. This is rarely the case regarding control-related problems, as for instance controlling traffic signals, where the state space can be very large. One way to deal with the curse of dimensionality is to use generalization techniques such as function approximation. In this paper, a linear function approximation is used by traffic signal agents in a network of signalized intersections. Specifically, a true online SARSA(λ) algorithm with Fourier basis functions (TOS(λ)-FB) is employed. This method has the advantage of having convergence guarantees and error bounds, a drawback of non-linear function approximation. In order to evaluate TOS(λ)-FB, we perform experiments in variations of an isolated intersection scenario and a scenario of the city of Cottbus, Germany, with 22 signalized intersections, implemented in MATSim. We compare our results not only to fixed-time controllers, but also to a state-of-the-art rule-based adaptive method, showing that TOS(λ)-FB shows a performance that is highly superior to the fixed-time, while also being at least as efficient as the rule-based approach. For more than half of the intersections, our approach leads to less congestion and delay, without the need for the knowledge that underlies the rule-based approach.

This article proposes a novel attack detection approach based on zonotopes for linear parameter-varying (LPV) systems with unknown-but-bounded (UBB) noises. The following three types of attacks are considered: 1) denial-of-service (DoS) attacks; 2) replay attacks (RAs); and 3) false-data-injection (FDI) attacks. In order to reduce the conservativeness, a free-weighting matrix is introduced, which can be computed by solving an optimization problem. Moreover, the radius of the intersection zonotope can be guaranteed to be limited as well. Furthermore, it is not necessary to acquire the knowledge about the specific type of attack in advance. Finally, a numerical example is given to illustrate the validity of the given method.

This research proposes a TSPcut controller that enables connected and automated buses to cut through traffic to make TSP green light. The proposed controller overcomes the shortcomings of conventional TSP strategies and is able to: 1) overtake slowing moving vehicles in order to catch TSP green time; 2) decide the best time to pass the intersection; 3) considering the stochasticity of surrounding traffic; and 4) functional under partially connected and automated environment. It takes full advantage of connected vehicle technology by taking in real-time vehicle and infrastructure information as optimization input. The problem is formulated as an SMPC problem and is solved by a high-efficient dynamic programming algorithm. The nonlinear bicycle model is adopted as the system dynamics to realize CAV bus's lane-changing and overtaking function. The stochasticity of surrounding traffic is considered as a probability distribution which is transformed into a linear chance constraint. Simulation evaluation is conduct to compare the TSPcut against NTSP, CTSP and BocTSP. Sensitive analysis is conducted for congestion levels. The evaluation results demonstrate that the TSPcut improves the bus delay reduction by 17.9%-49.1%, and the benefits are 3.5% to 16.1% greater than that of other TSP systems. The range is caused by different congestion levels. In addition. Further tests are conducted to analyze how CAV bus's arrival time and the speed of background traffic influence the performance of the TSPcut.

There is an increasing trend in the use of wireless communication along with new traffic signal control (TSC) algorithms to leverage and accommodate connected and autonomous vehicles. However, this development has increased the potential for cyber-attacks on TSC that can undermine the benefits of these new algorithms. An advanced persistent adversary can learn the behavior of TSC algorithms and launch attacks to preferentially get green time and/or to create traffic congestion in one intersection which can spread to the entire network. In this paper, we consider backpressure-based (BP-based) TSC algorithms and compare their performance under two misinformation attacks - 1) time spoofing attack in which vehicles alter their arrival times at the intersection and 2) ghost vehicle attack in which vehicles disconnect the wireless communication and thereby hide from the TSC. We show that these misinformation can influence the signal phases determined by BP-based TSC algorithms. We consider an adversary that determines a set of arriving vehicles to be attack vehicles from many candidate sets (attack strategies) in order to maximize the number of disrupted signal phases. We show that by formulating the problem as a 0/1 Knapsack problem, the adversary can explore the space of attack strategies and determine the optimal strategy that maximally compromises the performance in terms of average delay and fairness. We propose two protection algorithms, namely, auction-based (APA) and hybrid-based (HPA) algorithms and show that they are able to mitigate the impacts of the misinformation attacks.

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety and control constraints. For affine control systems and quadratic costs, it has been shown that Control Barrier Functions (CBF) guaranteeing safety and Control Lyapunov Functions (CLF) enforcing convergence can be used to reduce the optimal control problem to a sequence of Quadratic Programs. In this paper, we propose High Order CBFs (HOCBF), which can accommodate systems of arbitrary relative degree. We construct a set of controls that renders the intersection of a set of sets forward invariant for the system, which implies the satisfaction of the original safety constraint. Our notion of HOCBF is more general than the recently proposed exponential CBF. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods - the penalty and the parameterization methods - to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on a cruise control system and on a robot control problem.

The secretary problem became one of the most prominent online selection problems due to its numerous applications in online mechanism design. The task is to select a maximum weight subset of elements subject to given constraints, where elements arrive one-by-one in random order, revealing a weight upon arrival. The decision whether to select an element has to be taken immediately after its arrival. The different applications that map to the secretary problem ask for different constraint families to be handled. The most prominent ones are matroid constraints, which both capture many relevant settings and admit strongly competitive secretary algorithms. However, dealing with more involved constraints proved to be much more difficult, and strong algorithms are known only for a few specific settings. In this paper, we present a general framework for dealing with the secretary problem over the intersection of several matroids. This framework allows us to combine and exploit the large set of matroid secretary algorithms known in the literature. As one consequence, we get constant-competitive secretary algorithms over the intersection of any constant number of matroids whose corresponding (single-)matroid secretary problems are currently known to have a constant-competitive algorithm. Moreover, we show that our results extend to submodular objectives., 45 pages

Three-dimensional (3D) imaging, such as micro-computed tomography (micro-CT), is increasingly being used by organismal biologists for precise and comprehensive anatomical characterization. However, the segmentation of anatomical structures remains a bottleneck in research, often requiring tedious manual work. Here, we propose a pipeline for the fully-automated segmentation of anatomical structures in micro-CT images utilizing state-of-the-art deep learning methods, selecting the ant brain as a test case. We implemented the U-Net architecture for 2D image segmentation for our convolutional neural network (CNN), combined with pixel-island detection. For training and validation of the network, we assembled a dataset of semi-manually segmented brain images of 94 ant species. The trained network predicted the brain area in ant images fast and accurately; its performance tested on validation sets showed good agreement between the prediction and the target, scoring 80% Intersection over Union (IoU) and 90% Dice Coefficient (F1) accuracy. While manual segmentation usually takes many hours for each brain, the trained network takes only a few minutes. Furthermore, our network is generalizable for segmenting the whole neural system in full-body scans, and works in tests on distantly related and morphologically divergent insects (e.g., fruit flies). The latter suggest that methods like the one presented here generally apply across diverse taxa. Our method makes the construction of segmented maps and the morphological quantification of different species more efficient and scalable to large datasets, a step toward a big data approach to organismal anatomy.

We address the problem of motion planning for four-way intersection crossings with right-of-ways. Road safety typically assigns liability to the follower in rear-end collisions and to the approaching vehicle required to yield in side crashes. As an alternative to previous models based on heuristic state machines, we propose a planning framework which changes the prediction model of other cars (e.g. their prototypical accelerations and decelerations) depending on the given longitudinal or lateral priority rules. Combined with a state-of-the-art trajectory optimization approach ROPT (Risk Optimization Method) this allows to find ego velocity profiles minimizing risks from curves and all involved vehicles while maximizing utility (needed time to arrive at a goal) and comfort (change and duration of acceleration) under the presence of regulatory conditions. Analytical and statistical evaluations show that our method is able to follow right-of-ways for a wide range of other vehicle behaviors and path geometries. Even when the other cars drive in a non-priority-compliant way, ROPT achieves good risk-comfort tradeoffs.

Temporal action detection is a challenging task in video understanding, due to the complexity of the background and rich action content impacting high-quality temporal proposals generation in untrimmed videos. Capsule networks can avoid some limitations of the invariance caused by pooling and inability from convolutional neural networks, which can better understand the temporal relations for temporal action detection. However, because of the extremely computationally expensive procedure, capsule network is difficult to be applied to the task of temporal action detection. To address this issue, this paper proposes a novel U-shaped capsule network framework with a k-Nearest Neighbor (k-NN) mechanism of 3D convolutional dynamic routing, which we named U-BlockConvCaps. Furthermore, we build a Capsules Boundary Network (CapsBoundNet) based on U-BlockConvCaps for dense temporal action proposal generation. Specifically, the first module is one 1D convolutional layer for fusing the two-stream with RGB and optical flow video features. The sampling module further processes the fused features to generate the 2D start-end action proposal feature maps. Then, the multi-scale U-Block convolutional capsule module with 3D convolutional dynamic routing is used to process the proposal feature map. Finally, the feature maps generated from the CapsBoundNet are used to predict starting, ending, action classification, and action regression score maps, which help to capture the boundary and intersection over union features. Our work innovatively improves the dynamic routing algorithm of capsule networks and extends the use of capsule networks to the temporal action detection task for the first time in the literature. The experimental results on benchmarks THUMOS14 show that the performance of CapsBoundNet is obviously beyond the state-of-the-art methods, e.g., the mAP@tIoU=0.3, 0.4, 0.5 on THUMOS14 are improved from 63.6% to 70.0%, 57.8% to 63.1%, 51.3% to 52.9%, respectively. We also got competitive results on the action detection dataset of ActivityNet1.3.

This work proposes a novel data-driven robust model predictive control (DDRMPC) framework for automatic control of greenhouse in-door climate. The framework integrates dynamic control models of greenhouse temperature, humidity, and CO₂ concentration level with data-driven robust optimization models that accurately and rigorously capture uncertainty in weather forecast error. Data-driven uncertainty sets for ambient temperature, solar radiation, and humidity are constructed from historical data by leveraging a machine learning approach, namely, support vector clustering with weighted generalized intersection kernel. A training-calibration procedure that tunes the size of uncertainty sets is implemented to ensure that data-driven uncertainty sets attain an appropriate performance guarantee. In order to solve the optimization problem in DDRMPC, an affine disturbance feedback policy is utilized to obtain tractable approximations of optimal control. A case study of controlling temperature, humidity, and CO₂ concentration of a semiclosed greenhouse in New York City is presented. The results show that the DDRMPC approach ends up with 14% and 4% lower total cost than rule-based control and robust model predictive control with L₁-norm-based uncertainty set, respectively. The constraint violation probability, which is the percentage of time that the greenhouse system states violate the constraint throughout the whole growing period, for DDRMPC is only 0.39%. Hence, the proposed DDRMPC framework can prevent the greenhouse climate from becoming harmful to plants and fruits. In conclusion, the proposed DDRMPC approach can improve the greenhouse climate control performance and reduce cost compared with other control strategies.

Verifiable delegated set intersection over outsourced private datasets (VDPSI) enables two parties to outsource their private datasets and delegate the computation of set intersection to the cloud while being able to check the correctness of the result. In this process, the cloud learns nothing about the datasets and the intersection result. However, the existing VDPSI schemes suffer from three substantial shortcomings that limit their use: i) the whole dataset consists of only one subset, ii) they are designed for the static data, and iii) they cannot support other operations. To resolve these problems, we introduce a novel primitive called tag-based VDPSI (TVDPSI), which is designed for the multisubset case where each subset is associated with one single tag for data classification. To protect privacy, the data is encrypted before being resided to the cloud. The tag is implicitly hidden in each encrypted element. As a result, the cloud cannot learn which data belongs to the same subset beyond the intersection set. Besides, the cloud cannot calculate the intersection except under the permissions of data owners. To the best of our knowledge, TVDPSI is the first VDPSI scheme supporting dynamic update and count operations. The detailed performance evaluation and simulation show that our protocol is more practical in cloud computing.

This article is concerned with set-membership global estimation for a networked system under unknown-but-bounded process and measurement noises. First, a group of local set-membership estimators is deployed to obtain the local ellipsoidal estimate of the true system state. Each estimator is capable of communicating with its neighbors within its communication range. Second, a global estimation approach is proposed which generates a trace-maximal ellipsoid within the intersection of all the local estimation sets with an aim to improve the difference of the local estimate at each time instant. Sufficient conditions for providing a global estimate under both complete and incomplete measurement transmissions are derived. Third, as an application, a modified distributed photovoltaic grid-connected generation system is provided to verify the effectiveness of the developed set-membership global estimation approach. Furthermore, an islanding fault detection scheme is derived based on the calculated global ellipsoidal estimate. Finally, simulation verification of the obtained theoretical results on the distributed generation system is presented.

Semantic segmentation of ground-based all-sky images (ASIs) can provide high-resolution cloud coverage information of distinct cloud types, applicable for meteorology-, climatology- and solar-energy-related applications. Since the shape and appearance of clouds is variable, and there is high similarity between cloud types, a clear classification is difficult. Therefore, most state-of-the-art methods focus on the distinction between cloudy and cloud-free pixels without taking into account the cloud type. On the other hand, cloud classification is typically determined separately at the image level, neglecting the cloud's position and only considering the prevailing cloud type. Deep neural networks have proven to be very effective and robust for segmentation tasks; however they require large training datasets to learn complex visual features. In this work, we present a self-supervised learning approach to exploit many more data than in purely supervised training and thus increase the model's performance. In the first step, we use about 300 000 ASIs in two different pretext tasks for pretraining. One of them pursues an image reconstruction approach. The other one is based on the DeepCluster model, an iterative procedure of clustering and classifying the neural network output. In the second step, our model is fine-tuned on a small labeled dataset of 770 ASIs, of which 616 are used for training and 154 for validation. For each of them, a ground truth mask was created that classifies each pixel into clear sky or a low-layer, mid-layer or high-layer cloud. To analyze the effectiveness of self-supervised pretraining, we compare our approach to randomly initialized and pretrained ImageNet weights using the same training and validation sets. Achieving 85.8 % pixel accuracy on average, our best self-supervised model outperforms the conventional approaches of random (78.3 %) and pretrained ImageNet initialization (82.1 %). The benefits become even more evident when regarding precision, recall and intersection over union (IoU) of the respective cloud classes, where the improvement is between 5 and 20 percentage points. Furthermore, we compare the performance of our best model with regards to binary segmentation with a clear-sky library (CSL) from the literature. Our model outperforms the CSL by over 7 percentage points, reaching a pixel accuracy of 95 %.

Visible light sensing technique has shown great potential in locating human in the building. For indoor positioning using fingerprints, how to reduce the offline labor cost while maintaining accurate location estimation is of vital importance. In this paper, a novel coarse fingerprint-assisted device-free localization (DFL) approach is proposed for locating multiple targets via visible light sensing, which does not need too much calibration effort to build high accurate fingerprint database. Furthermore, a successive cancellation algorithm based on the coarse single target fingerprint database is designed to address the problem of pseudo target positioning in the multi-target DFL. Since the intersection points of shadowed links could not be guaranteed to be symmetrically located around the center of mass of the human body, the estimated location would be biased from the true location of the target. To solve this problem, a convex hull-based localization algorithm is introduced to improve positioning accuracy. Extensive simulation results show that our proposed approach exhibits superior performance in terms of target counting and localization accuracy.

The detection of infrared small targets under low signal-to-clutter ratio (SCR) and complex background conditions has been a challenging and popular research topic. In this article, a spatial-temporal feature-based detection framework is proposed. First, several factors, such as the infrared target's small sample, the sensitive size, and the usual sample selection strategy, that affect the detection of small targets are analyzed. In addition, the small intersection over union (IOU) strategy, which helps to solve the false convergence and sample misjudgment problem, is proposed. Second, aiming at the difficulties due to the target's dim information and complex background, the interframe energy accumulation (IFEA) enhancement mechanism-based end-to-end spatial-temporal feature extraction and target detection framework is proposed. This framework helps to enhance the target's energy, suppress the strong spatially nonstationary clutter, and detect dim small targets. Experimental results show that using the small IOU strategy and IFEA mechanism, the proposed multiple frame-based detection framework performs better than some popular deep learning (DL)-based detection algorithms.

We are lifting classical combinatorial problems from single instances to regular sets of instances. The task of finding a positive instance of the combinatorial problem P in a potentially infinite given regular set is equivalent to the so called in t Reg -problem of P, which asks for a given DFA A, whether the intersection of P with L ( A ) is non-empty. The in t Reg -problem generalizes the idea of considering multiple instances at once and connects classical combinatorial problems with the field of automata theory. While the question of decidability of the in t Reg -problem has been answered positively for several NP and even PSPACE -complete problems, we are presenting some natural problems even from LOGSPACE with an undecidable in t Reg -problem. We also discuss alphabet sizes and different encoding-schemes elaborating the boundary between problem-variants with a decidable respectively undecidable in t Reg -problem.

In recent years, the automatic extraction of remote-sensing image information has attracted full attention. However, the particularity of remote-sensing images and the scarcity of data sets with label information have brought new challenges to existing methods. Therefore, we develop a lightweight semantic segmentation network based onmultiscale feature fusion (MFF) and attention refinement (MFFANet). Our network relies on three crucial modules for improved performance. The multiscale attention refinement module strengthens the representation ability of feature maps extracted by the deep residual network. The MFF module aggregates the information carried by the high-level and low-level features while restoring the image resolution. Furthermore, the boundary enhancement module captures boundary details to solve the semantic ambiguity problem. We achieve 83.5% mean intersection over union (MIoU) on the Urban Semantic 3-D (US3D) data set and 69.3% MIoU on the Vaihingen data set with only 8.2M parameters.

This study develops a deep learning (DL) model to classify the sea ice and open water from synthetic aperture radar (SAR) images. We use the U-Net, a well-known fully convolutional network (FCN) for pixel-level segmentation, as the model backbone. We employ a DL-based feature extracting model, ResNet-34, as the encoder of the U-Net. To achieve high accuracy classifications, we integrate the dual-attention mechanism into the original U-Net to improve the feature representations, forming a dual-attention U-Net model (DAU-Net). The SAR images are obtained from Sentinel-1A. The dual-polarized information and the incident angle of SAR images are model inputs. We used 15 dual-polarized images acquired near the Bering Sea to train the model and employ the other three images to test the model. Experiments show that the DAU-Net could achieve pixel-level classification; the dual-attention mechanism can improve the classification accuracy. Compared with the original U-Net, DAU-Net improves the intersection over union (IoU) by 7.48.% points, 0.96.% points, and 0.83.% points on three test images. Compared with the recently published model DenseNetFCN, the three improvement IoU values of DAU-Net are 3.04.% points, 2.53.% points, and 2.26.% points, respectively.

Considering the success of generative adversarial networks (GANs) for image-to-image translation, researchers have attempted to translate satellite images to maps (si2map) through GAN for cartography. However, these studies involved limited scales, which hinders multi-scale map creation. By extending their method, high-resolution satellite images can be trivially translated to multi-scale maps through scale-wise si2map generators trained for certain scales. However, this strategy has two theoretical limitations. First, inconsistency between high-resolutions satellite images and object generalization on multi-scale maps (SI-M inconsistency) increasingly complicates the extraction of geographical information from satellite images for generators with decreasing scale. Second, as si2map translation is cross-domain, generators incur high computation costs to transform the pixel distribution on satellite images to that on maps. Thus, we designed a series strategy of generators for multi-scale si2map translation to address these limitations. In this strategy, high-resolution satellite images are inputted to an si2map generator to output large-scale maps, which are translated to multi-scale maps through series multi-scale map generators. The series strategy avoids SI-M inconsistency as high-resolution satellite images are only translated to large-scale maps, and transforms cross-domain translation to approximately intradomain translation when generates multi-scale maps. Our experimental results showed better quality multi-scale map generation with the series strategy, as shown by average increases of 11.69%, 53.78%, 55.42%, and 72.34% in the structural similarity index, edge structural similarity index, intersection over union (road), and intersection over union (water) for data from Mexico City and Tokyo at zoom level 17–13.

Recently, object detection has gained significant progress in remote sensing images. Nevertheless, we conclude two defects in remote sensing image object detection. At first, most methods rely on feature pyramid, but the features of different levels would influence each other when we use top-down operation. Second, the traditional label assignment strategy cannot assign suitable labels, as it adopts the fixed intersection over union (IoU) threshold to divide positive samples and negative samples during training. According to the problems we pointed out, a simple yet effective framework is employed to eliminate these two limitations. It integrates two novel components: aware feature pyramid network (AFPN) and group assignment strategy (GAS). AFPN is to mitigate the adverse effects caused by the first problem. Specifically, it learns a vector for the higher level features in the feature pyramid to obtain clean features. As for the second limitation, we recommend a new label assignment strategy named GAS to address this problem. Samples will be grouped according to their overlaps with ground truth, and then, they are assigned to positive or negative labels in each group. Extensive experiments are conducted on the large-scale object detection dataset DIOR and DOTA. With the newly introduced two key components, our model significantly improves the detection accuracy. Without bells and whistles, our proposed method achieves 2.0% and 1.9% higher mean average precision (mAP) than Faster R-CNN with FPN when using ResNet50 and ResNet101 as the backbones, respectively. Finally, we obtain 73.3% mAP on the DIOR dataset without any tricks. Our code is available at https://github.com/hm-better/dior_detect.

Although good performance has been recently achieved in point cloud semantic segmentation based on deep learning, it has not been promoted due to differences in actual scenes and the time-consuming production of labeled data sets. Unsupervised domain adaptation (UDA) aims to solve the problem of how to adapt the classifier from one scene (source domain) to another unlabeled scene (target domain), which can reduce the performance drop caused by the domain shift. Since spatial information is important for light detection and ranging (LiDAR) point and the causes of domain gap in image and point cloud tasks are different, projecting point cloud into image for processing is not suitable and how to apply the image-oriented domain adaptation (DA) methods to point cloud is not trivial. In this letter, we propose a 3D point-based UDA method for point cloud semantic segmentation. This model introduces point- and set-level domain adaptive modules to achieve feature alignment between the domains. We evaluate the proposed method with two experiments, including cross terrain adaptation and airborne to mobile adaptation. Compared with the results without using DA, the mean intersection over union (mIoU) increased by 10.45% and 24.69%, respectively, indicating the effectiveness of our method.

Water extraction is an important prerequisite for the protection and rational use of water resources. The existing waterbody extraction methods are mostly used for the extraction of large- and medium-sized waterbodies, whereas less attention has been paid to small waterbodies. In this letter, we adapt the U-Net convolutional neural network to extract small waterbodies from Zhuhai-1 satellite hyperspectral remote sensing image. To the best of our knowledge, this is the first time that U-Net framework has been used for small waterbody extraction from satellite hyperspectral image. Specifically, we increase the depth of the network, and because there are far more negative samples (non-waterbodies) in remote sensing data than positive samples (waterbodies), Intersection over Union (IoU) is used as an evaluation indicator during model training. The results show that this method can accurately extract small waterbodies in the complex scenes. Compared with the traditional methods of support vector machine and the normalized waterbody index, the accuracy of this method is significantly higher, and both the Recall and the Precision are close to 90%.

There are limited studies on the semantic segmentation of high-resolution polarimetric synthetic aperture radar (PolSAR) images due to the scarcity of training data and the complexity of managing speckle noise. The Gaofen contest has provided open access a high-quality PolSAR semantic segmentation dataset. Taking this opportunity, we propose a multipath residual network (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multiscale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multilevel feature fusion design in its decoder to effectively exploit the features learned from its different branches. Comparisons with the baseline method of fully connected network (FCN with ResNet34) show that the MP-ResNet has achieved significant accuracy improvements. It also surpasses several state-of-the-art methods in terms of overall accuracy (OA), mF₁ and frequency weighted intersection over union (fwIoU), with only a limited increase of computational costs. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

Road information from high-resolution remote sensing images is widely used in various fields, and deep-learning-based methods have effectively shown high road-extraction performance. However, for the detection of roads sealed with tarmac, or covered by trees in high-resolution remote sensing images, some challenges still limit the accuracy of extraction: 1) large intra-class differences between roads, and unclear inter-class differences between urban objects, especially roads and buildings; 2) roads occluded by trees, shadows, and buildings are difficult to extract; and 3) lack of high-precision remote-sensing datasets for roads. To increase the accuracy of road extraction from high-resolution remote-sensing images, we propose a split depth-wise (DW) separable graph convolutional network (SGCN). Firstly, we split DW-separable convolution to obtain channel and spatial features, to enhance the expression ability of road features. Thereafter, we present a graph convolutional network to capture global contextual road information in channel and spatial features. The Sobel gradient operator is used to construct an adjacency matrix of the feature graph. A total of thirteen deep-learning networks were used on the Massachusetts Roads Dataset and nine on our self-constructed mountain road dataset, for comparison with our proposed SGCN. Our model achieved a mean Intersection over Union (IOU) of 81.65% with an F1-score of 78.99% for the Massachusetts Roads dataset, and a mean IOU of 62.45% with an F1-score of 45.06% for our proposed dataset. The visualization results showed that SGCN performs better in extracting covered and tiny roads and is able to effectively extract roads from high-resolution remote-sensing images.

In this letter, we introduce acentralized planner with low computational cost to schedule the motions of multiple Automated Guided Vehicles (AGVs) at the intersection of pre-defined polynomial curves. In particular, we find that the collision conditions between two AGVs along polynomial paths can be formulated as a set of polynomial inequalities. Furthermore, by solving these inequalities, the continuous boundaries of potential collision areas for vehicles can be determined offline and stored in a table. During the online phase, by also taking into account the priority setup among AGVs, the planner will use efficient table lookup to determine a list of intermediate goals for each AGV to move toward based on their real-time position feedback. In this way, the multiple robots are able to navigate on polynomial guide paths safely and efficiently at the crossroad, and the performance of our approach is demonstrated in a number of simulated scenarios. Videos of the experiments are available at https://sites.google.com/view/zqzhang/agvsplanner .

As an intersection of artificial intelligence and human communication analysis, Emotion Recognition in Conversation (ERC) has attracted much research attention in recent years. Existing studies, however, are limited in adequately exploiting latent relations among the constituent utterances. In this paper, we address this issue by proposing a novel approach named Latent Relation-Aware Graph Convolutional Network (LR-GCN), where both speaker dependency of the interlocutors is leveraged and latent correlations among the utterances are captured for ERC. Specifically, we first establish a graph model to incorporate the context information and speaker dependency of the conversation. Afterward, the multi-head attention mechanism is introduced to explore the latent correlations among the utterances and generate a set of all-linked graphs. Here, aiming to simultaneously exploit the original modeled speaker dependency and the explored correlation information, we introduce a dense connection layer to capture more structural information of the generated graphs. Through a multi-branch graph network, we achieve a unified representation of each utterance for final prediction. Detailed evaluations on two benchmark datasets demonstrate LR-GCN outperforms the state-of-the-art approaches.

In remote sensing images (RSIs), accurate semantic segmentation faces more challenges because of small targets, unbalanced categories, and complex scenes. Restricted by local receptive field of convolution layers, the traditional semantic segmentation models cannot use global information of RSIs. According to the characteristics of RSIs, we propose an RSANet based on regional self-attention mechanism. Our model is no longer limited by the locality of convolution, but transfers the information flow in the whole image. It can mine out the relationship between pixels in the surrounding areas, which is more logical for understanding images content. Moreover, compared with the traditional self-attention mechanism, RSANet can effectively reduce the noise of feature maps and the interference of redundant features. Our model can get better semantic segmentation results than other current models on the DroneDeploy data set and the Chreos semantic segmentation data set. The experiments show that our RSANet achieves 2% higher mean intersection over union (mIoU) than the baseline model, especially in terms of fineness, edge integrity, and classification accuracy.

In the past few years, multitask learning (MTL) has been widely used in a single model to solve the problems of multiple businesses. MTL enables each task to achieve high performance and greatly reduces computational resource overhead. In this work, we designed a collaborative network that simultaneously solves the super-resolution semantic segmentation and super-resolution image reconstruction. This algorithm can obtain high-resolution semantic segmentation and super-resolution reconstruction results by taking relatively low-resolution images as input when high-resolution data are inconvenient or computing resources are limited. The framework consists of three parts: the semantic segmentation branch (SSB), the super-resolution branch (SRB), and the structural affinity block (SAB). Specifically, the SSB, SRB, and SAB are responsible for completing super-resolution semantic segmentation, image super-resolution reconstruction, and associated features, respectively. Our proposed method is simple and efficient, and it can replace the different branches with most of the state-of-the-art models. The International Society for Photogrammetry and Remote Sensing (ISPRS) segmentation benchmarks were used to evaluate our models. In particular, super-resolution semantic segmentation on the Potsdam dataset reduced Intersection over Union (IoU) by only 1.8% when the resolution of the input image was reduced by a factor of two. The experimental results showed that our framework can obtain more accurate semantic segmentation and super-resolution reconstruction results than the single model.

Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the global model based on the local model updates. While FL methods offer several advantages, including scalability and data privacy, they assume there are available computational resources at each edge-device/client. However, the Internet-of-Things (IoTs) enabled devices, e.g., robots, drone swarms, and low-cost computing devices (e.g., Raspberry Pi), may have limited processing ability, low bandwidth and power, or limited storage capacity. In this survey paper, we propose to answer this question: how to train distributed machine learning models for resource-constrained IoT devices? To this end, we first explore the existing studies on FL, relative assumptions for distributed implementation using IoT devices, and explore their drawbacks. We then discuss the implementation challenges and issues when applying FL to an IoT environment. We highlight an overview of FL and provide a comprehensive survey of the problem statements and emerging challenges, particularly during applying FL within heterogeneous IoT environments. Finally, we point out the future research directions for scientists and researchers who are interested in working at the intersection of FL and resource-constrained IoT environments.

Ocean fronts have an important influence on global ocean-atmosphere interactions and marine fishery. Hence, it is of great significance to obtain the positions of the ocean fronts. However, current ocean front detection research confronts two challenges: scarcity of labeled data and limitations of ocean front detection algorithms. To address these two problems, we have collected and labeled an ocean front data set and proposed a new deep learning model for ocean front detection. For concreteness, due to the weak edge property of the ocean fronts, we formulate ocean front detection as a weak edge identification problem and propose the weak edge identification network (WEIN) for ocean front detection. WEIN consists of four convolutional blocks. Each block has a side output layer used to detect front edges at a specific image representation level. The side outputs are then fused to predict (detect) the locations of the ocean fronts. In this work, we adopt two metrics to measure the experimental results, i.e., the F₁-score and intersection over union (IoU). The experimental results with comparison to traditional and deep learning approaches demonstrate the superiority of WEIN for ocean front detection.

Although widely exploited in recent decades, road extraction is still a very significant and challenging research in the field of remote sensing image processing due to the complex background and road distribution. Among the existing CNN-based methods, U-shape architectures composed of encoders and decoders have shown their effectiveness. In this letter, we propose an improved encoder-decoder method, named DBRANet, for extracting roads from remote sensing images. In the encoding phase, we present a dual-branch network module (DBNM) to construct more effective features, thus improving the fusion feature maps of different scales. One branch utilizes the residual block, and the other branch utilizes the refined asymmetric block, which effectively increases the feature extraction capability of the backbone. In the decoding phase, considering the sinuous shape and the unbalanced distribution of roads in remote sensing images, we design a novel attention module, named the regional attention network module (RANM), to automatically learn the importance of each channel according to the regional information. Extensive experiments on several public remote sensing road data sets show that our DBRANet achieves higher segmentation [F1 score and Intersection over Union (IoU)] and connectivity [average path length similarity (APLS)] accuracy, which verifies the effectiveness of our approach.

Linear codes with complementary duals, shortly named LCD codes, are linear codes whose intersection with their duals is trivial. In this paper, we outline a construction for LCD codes over finite fields from the adjacency matrices of two-class association schemes. These schemes consist of either strongly regular graphs (SRGs) or doubly regular tournaments (DRTs). Under certain conditions, the method yields formally self-dual codes. Further, we propose a decoding algorithm that can be feasible for the LCD codes obtained using one of the given methods.