Advanced patch attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks (DNNs). However, little attention has been paid to this topic...
详细信息
Advanced patch attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks (DNNs). However, little attention has been paid to this topic in optical remote sensing images (O-RSIs). To this end, we focus on this research, i.e., PAs on object detection in O-RSIs, and propose a more threatening patch attack (TPA) without the scarification of the visual quality. Specifically, to address the problem of inconsistency between the local and global landscapes in existing patch selection schemes, we propose leveraging the first-order difference (FOD) of the objective function before and after masking to select the subpatches to be attacked. Furthermore, considering the problem of gradient inundation when applying existing coordinate-based loss (CBL) to PAs directly, we design an IoU-based objective function specific for PAs, dubbed bounding box (Bbox) drifting loss (BDL), which pushes the detected Bboxes far from the initial ones until there are no intersections between them. Finally, on two widely used benchmarks, i.e., DIOR and DOTA, comprehensive evaluations of our TPA with four typical detectors (faster R-CNN, FCOS, RetinaNet, and YOLO-v4) witness its remarkable effectiveness. To the best of our knowledge, this is the first attempt to study the PAs on object detection in O-RSIs, and we hope this work can get our readers interested in studying this topic.
In this paper, we propose a linear programming based interactive method for multiobjective linear programming problems, in which fuzzy coefficients and random variable coefficients are involved in the objective functi...
详细信息
In this paper, we propose a linear programming based interactive method for multiobjective linear programming problems, in which fuzzy coefficients and random variable coefficients are involved in the objective functions simultaneously. In the proposed method, it is assumed that the decision maker has a fuzzy goal for each objective function, and such a fuzzy goal can be quantified by eliciting the membership function. Through the possibility measure and a fractile optimization model, the original problem is transformed to the well-defined multiobjective programming problem. Then, a generalized Pareto optimal concept is defined, and a linear programming based interactive algorithm is proposed to obtain a satisfactory solution from among a generalized Pareto optimal solution set.
When linear programming is used to decode low-density parity-check (LDPC) codes, the outcome is a codeword or a pseudocodeword that contains fractional symbol values. It is possible to make pseudocodewords infeasible ...
详细信息
When linear programming is used to decode low-density parity-check (LDPC) codes, the outcome is a codeword or a pseudocodeword that contains fractional symbol values. It is possible to make pseudocodewords infeasible and increase the performance of linear programming decoders by generating redundant parity check equations. In this paper, redundant parity check equations that can eliminate pseudocodewords are searched using an integer programming based optimization approach. We show that the generated parity check equations increase the performance of the adaptive linear programming decoder and that its performance can converge that of a maximum-likelihood decoder.
Based on the Delsarte-Yudin linear programming approach, we extend Levenshtein's framework to obtain lower bounds for the minimum henergy of spherical codes of prescribed dimension and cardinality, and upper bound...
详细信息
Based on the Delsarte-Yudin linear programming approach, we extend Levenshtein's framework to obtain lower bounds for the minimum henergy of spherical codes of prescribed dimension and cardinality, and upper bounds on the maximal cardinality of spherical codes of prescribed dimension and minimum separation. These bounds are universal in the sense that they hold for a large class of potentials h and in the sense of Levenshtein. Moreover, codes attaining the bounds are universally optimal in the sense of Cohn-Kumar. Referring to Levenshtein bounds and the energy bounds of the authors as "first level", our results can be considered as "next level" universal bounds as they have the same general nature and imply necessary and sufficient conditions for their local and global optimality. For this purpose, we introduce the notion of Universal Lower Bound space (ULB-space), a space that satisfies certain quadrature and interpolation properties. While there are numerous cases for which our method applies, we will emphasize the model examples of 24 points (24-cell) and 120 points (600-cell) on S-3 . In particular, we provide a new proof that the 600-cell is universally optimal, and in so doing, we derive optimality of the 600-cell on a class larger than the absolutely monotone potentials considered by Cohn-Kumar.
The aim of this paper is to present a simple new class of recurrent neural networks, which solves linear programming. It is considered as a sliding mode control problem, where the network structure is based on the Kar...
详细信息
The aim of this paper is to present a simple new class of recurrent neural networks, which solves linear programming. It is considered as a sliding mode control problem, where the network structure is based on the Karush-Kuhn-Tucker (KKT) optimality conditions, and the KKT multipliers are the control inputs to be implemented with finite time stabilizing terms based on the unit control, instead of common used activation functions. Thus, the main feature of the proposed network is the fixed number of parameters despite of the optimization problem dimension, which means, the network can be easily scaled from a small to a higher dimension problem. The applicability of the proposed scheme is tested on real-time optimization of an electrical Microgrid prototype.
This paper proposes a multi-kernel linear programming support vector regression with prior knowledge in order to obtain an accurate regression model in the case of the scarcity of measured data available. In the algor...
详细信息
This paper proposes a multi-kernel linear programming support vector regression with prior knowledge in order to obtain an accurate regression model in the case of the scarcity of measured data available. In the algorithm, multi-kernel and prior knowledge which may be exact or biased from a calibrated simulator have been incorporated into the framework of linear programming support vector regression by utilizing multiple feature spaces and modifying optimization formulation. Some experiments from a synthetic example have been carried out, and the results show that the proposed algorithm is effective, and that the obtained model is sparse and accurate. The proposed algorithm shows great potential in some practical applications where the experimental data is few and the prior knowledge from a simulator is available.
This paper focuses on the optimal operation of electric vehicle (EV) battery swapping station (BSS), proposes a BSS operation mechanism considering the EV user response sensitive factors and the grid dispatch demand, ...
详细信息
ISBN:
(数字)9798331517540
ISBN:
(纸本)9798331517557
This paper focuses on the optimal operation of electric vehicle (EV) battery swapping station (BSS), proposes a BSS operation mechanism considering the EV user response sensitive factors and the grid dispatch demand, and at the same time formulates a specific reward and punishment mechanism to guarantee the operation of the mechanism, and establishes a day-ahead optimization dispatch model of the BSS on the basis of this mechanism. The model takes maximizing the daily revenue of BSS as the objective function, and makes the charging and discharging strategy of the battery in BSS effectively optimized by modeling the user response sensitive factors and the battery allocation strategy. The implementation of the reward and punishment mechanism makes the BSS respond more actively to the grid demand while satisfying the user demand. Finally, the proposed mechanism and model are tested through simulation experiments. By comparison, the batteries in the BSS are utilized more efficiently, while the daily revenue of the BSS is significantly improved.
One of the most critical goals in the operation and planning of distribution networks is the creation of networks with sufficient reliability. Existing models are often simulation-based or try to introduce topology-in...
详细信息
One of the most critical goals in the operation and planning of distribution networks is the creation of networks with sufficient reliability. Existing models are often simulation-based or try to introduce topology-independent algebraic reliability measures with simplifications or extensive computations. This paper presents new and efficient topology-variable-based linear expressions that can evaluate the reliability indices of practical radial distribution networks. Furthermore, the model is extended to consider the inclusion of renewable distributed generation (DG) units to restore part of restorable loads in the islanded mode of operation. Also, the stochastic nature of renewable generation, as well as load demand, is considered. Therefore, the proposed model can be readily used in various optimization models to operate and plan distribution networks with reliability concerns. The application of the proposed method to several small- to large-scale test cases ranging from standard 37-node up to practical 1080-node benchmarks shows the proposed model's accuracy and computational effectiveness compared to the state-of-the-art conventional simulation-based topology-variable-based approaches. The impact of the system's islanded operation on the reliability indices is also evaluated on the modified DG-enhanced 37node test system.
Traditional methods for flexible capacity allocation do not take into account the actual operation status of resources, and this can lead to redundancy of allocation results in a high renewable penetration power syste...
详细信息
Traditional methods for flexible capacity allocation do not take into account the actual operation status of resources, and this can lead to redundancy of allocation results in a high renewable penetration power system. Using collaborative optimization during the flexibility resource planning stage can significantly improve the overall economics and flexibility. Therefore, a bilevel operation-planning joint optimization model for flexible capacity allocation is proposed in this paper. The aim is to optimize the annual total cost and flexibility of the system. The upper planning level introduces the economic costs, flexibility resource capacity, and flexibility index which are used as the evaluation index of system flexibility, while in the lower operation level, a morphological clustering algorithm based on the multiscale and entropy weight method is proposed for obtaining typical scenarios of flexibility demand. On this basis, the lower level simulates production to estimate daily operating costs. In addition, the model is solved iteratively using the nondominated sorting genetic algorithm-II (NSGA-II) and the linear programming method to obtain the Pareto solutions. Case studies are carried out based on a practical town area, and the results verify the validity and rationality of the proposed bilevel capacity allocation model.
The aim of this paper is to present a new dynamical system which solves linear programming. Its design is considered as a sliding mode control problem, where its structure is based on the Karush-Kuhn-Tucker optimality...
详细信息
ISBN:
(纸本)9781467360890
The aim of this paper is to present a new dynamical system which solves linear programming. Its design is considered as a sliding mode control problem, where its structure is based on the Karush-Kuhn-Tucker optimality conditions, and its multipliers are the control inputs to be implemented by using fixed time stabilizing terms with vectorial structure, based on the unit control, instead of common terms used in other approaches. Thus, the main features of the proposed system are the fixed convergence time to the programming solution and the fixed parameters number despite of the optimization problem dimension. That is, there is a time independent to the initial conditions in which the system converges to the solution and, the proposed structure can be easily scaled from a small to a higher dimension problem. The applicability of the proposed scheme is tested on real-time optimization of an electrical Microgrid prototype.
暂无评论