The task of lane detection involves identifying the boundaries of driving areas in real-time. Recognizing lanes with variable and complex geometric structures remains a challenge. In this paper, we explore a novel and flexible way of implicit lanes representation named Elastic Lane Map (ELM), and introduce an efficient physics-informed end-to-end lane detection framework, namely, ElasticLaneNet (Elastic interaction energy-informed Lane detection Network). The approach considers predicted lanes as moving zero-contours on the flexibly shaped ELM that are attracted to the ground truth guided by an elastic interaction energy-loss function (EIE loss). Our framework well integrates the global information and low-level features. The method performs well in complex lane scenarios, including those with large curvature turns, intersections, various crossing lanes, Y-shapes lanes, dense lanes, etc. We apply our approach on three datasets: SDLane, TuSimple and CULane. The results demonstrate exceptional performance of our method, with the state-of-the-art results on the structurally diverse SDLane, achieving F1-score of 89.51, Recall of 87.50, and Precision of 91.61 with fast inference speed.

Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.

Abstract The stomata on the leaf surface are mainly responsible for the material exchange between the internal and external environments of the plant, a large number of methods have been proposed to automatically measure the distribution position and number of stomatal, but few methods could achieve both stomatal count and open/closed‐state judgment. Therefore, this study proposes an automatic detection method for leaf stomatal morphology analysis based on an attention mechanism and deep learning. In order to obtain more stomatal feature information and send it to the network for learning, the proposed method adds a coordinate attention (CA) mechanism to the YOLOV5 backbone part. At the same time, in order to avoid the overfitting of the model during the training process, the authors added the training trick of label smoothing. Finally, the detection ability of the proposed method for stomata is verified on the broad bean leaves stomata dataset. The experimental results show that our method achieves a detection accuracy of 0.934 and an mAP of 0.968. By comparing with other state‐of‐the‐art algorithms, the detection capability of our method has been significantly improved. The generalization of the model is verified on the wheat leaf stomatal dataset. The experimental results show that our method can achieve a detection accuracy of 0.894 and an mAP of 0.907.

Gravitational search algorithm (GSA) is a stochastic search algorithm based on the law of gravity and mass which is widely used nowadays for efficient solution of optimization problems. For the purpose of enhancing the performance of original GSA, this paper proposes a new GSA called Bird Flock Gravitational Search Algorithm (BFGSA) based on the collective response of birds. Although GSA performs well in many problems, algorithms in this category lack mechanisms which add diversity to exploration in the search process. Our proposed algorithm introduces a new mechanism into GSA to add diversity, a mechanism which is inspired by the collective response behavior of birds. This mechanism performs its diversity enhancement through three main major steps including initialization, identification of the nearest neighbors and orientation change. The initialization is to generate candidate populations for the second steps and the orientation change updates the position of objects based on the nearest neighbors. Due to the collective response mechanism, the BFGSA explores a wider range of the search space and thus escapes suboptimal solutions. The efficiency and robustness of the proposed algorithm is demonstrated using multiple traditional and newly composed benchmark functions presented in CEC2005 competition and the results are compared with recent variants of the original particle swarm optimization and state-of-the-art GSA algorithms. Furthermore, we applied BFGSA to a real-world application of data clustering. The results show that BFGSA improves the performance of the original GSA and obtains the best results compared with our selected GSA-type algorithms in benchmarking experiments and clustering experiments.

Extreme learning machine (ELM), proposed by Huang et al., was developed for generalized single hidden layer feedforward networks with a wide variety of hidden nodes. ELMs have been proved very fast and effective especially for solving function approximation problems with a predetermined network structure. However, it may contain insignificant hidden nodes. In this paper, we propose dynamic adjustment ELM (DA-ELM) that can further tune the input parameters of insignificant hidden nodes in order to reduce the residual error. It is proved in this paper that the energy error can be effectively reduced by applying recursive expectation-minimization theorem. In DA-ELM, the input parameters of insignificant hidden node are updated in the decreasing direction of the energy error in each step. The detailed theoretical foundation of DA-ELM is presented in this paper. Experimental results show that the proposed DA-ELM is more efficient than the state-of-art algorithms such as Bayesian ELM, optimally-pruned ELM, two-stage ELM, Levenberg-Marquardt, sensitivity-based linear learning method as well as the preliminary ELM.

Extreme learning machines (ELMs) have been proposed for generalized single-hidden-layer feedforward networks which need not be neuron alike and perform well in both regression and classification applications. The problem of determining the suitable network architectures is recognized to be crucial in the successful application of ELMs. This paper first proposes a dynamic ELM (D-ELM) where the hidden nodes can be recruited or deleted dynamically according to their significance to network performance, so that not only the parameters can be adjusted but also the architecture can be self-adapted simultaneously. Then, this paper proves in theory that such D-ELM using Lebesgue p-integrable hidden activation functions can approximate any Lebesgue p-integrable function on a compact input set. Simulation results obtained over various test problems demonstrate and verify that the proposed D-ELM does a good job reducing the network size while preserving good generalization performance.

Credit risk evaluation has become an increasingly important field in financial risk management for financial institutions, especially for banks and credit card companies. Many data mining and statistical methods have been applied to this field. Extreme learning machine (ELM) classifier as a type of generalized single hidden layer feed-forward networks has been used in many applications and achieve good classification accuracy. Thus, we use ELM (kernel based) as a classification tool to perform the credit risk evaluation in this paper. The simulations are done on two credit risk evaluation datasets with three different kernel functions. Simulation results show that the kernel based ELM is more suitable for credit risk evaluation than the popular used Support Vector Machines (SVMs) with consideration of overall, good and bad accuracies.

Extreme learning machines (ELMs) have been proposed for generalized single-hidden-layer feedforward networks which need not be neuron-like and perform well in both regression and classification applications. In this brief, we propose an ELM with adaptive growth of hidden nodes (AG-ELM), which provides a new approach for the automated design of networks. Different from other incremental ELMs (I-ELMs) whose existing hidden nodes are frozen when the new hidden nodes are added one by one, in AG-ELM the number of hidden nodes is determined in an adaptive way in the sense that the existing networks may be replaced by newly generated networks which have fewer hidden nodes and better generalization performance. We then prove that such an AG-ELM using Lebesgue p-integrable hidden activation functions can approximate any Lebesgue p-integrable function on a compact input set. Simulation results demonstrate and verify that this new approach can achieve a more compact network architecture than the I-ELM.

Online Sequential Extreme Learning Machine (OS-ELM) proposed by Liang et al [1] is a faster and more accurate online sequential learning algorithm as compared to other current sequential algorithms. It can learn data one-by-one or chunk-by-chunk with fixed or varying chunk size. However, there is one of the remaining challenges for OS-ELM that it could not determine the optimal network structure automatically. In this paper, we propose a Constructive Enhancement for OS-ELM (CEOS-ELM), which can add random hidden nodes one-by-one or group-by-group with fixed or varying group size. CEOS-ELM is searching for the optimal network architecture during the sequential learning process, and it can handle both additive and radial basis function (RBF) hidden nodes. The optimal number of hidden nodes can be obtained automatically after training. The simulation results show that with CEOS-ELM, the network can achieve comparable generalization performance with OS-ELM and more compact network structure.

In this paper, Extreme Learning Machine (ELM) is introduced to predict the subcellular localization of proteins based on the frequent subsequences. It is proved that ELM is extremely fast and can provide good generalization performance. We evaluated the performance of ELM on four localization sites with frequent subsequences as the feature space. A new parameter called Comparesup was introduced to help the feature selection. The performance of ELM was tested on data with different number of frequent subsequences, which were determined by different range of Comparesup. The results demonstrated that ELM performed better than previously reported results, for all of the four localization sites.