Obtaining high-quality service function vectors and aggregating neighborhood features in service association graph are prevalent methods for Mashup service clustering. However, existing methods often focus on enhancing the service functional feature extraction while overlooking distinctions among different services when creating service function vectors. Additionally, neighborhood feature aggregation is typically considered within a single association graph, lacking contrast optimization of different association features. To address these challenges, we propose a novel framework, MSCCL (Mashup Service Clustering with Contrastive Learning). MSCCL consists of two core components: a service function vector generation module and a neighborhood feature aggregation module. Contrastive learning is employed to enhance vector quality and optimize feature aggregation in both modules. We present a service clustering method within MSSCL that combines techniques from BERT (Bidirectional Encoder Representations from Transformers) and GAT (Graph Attention Networks). Compared to state-of-the-art methods, this approach reduces DBI by 2.03% to 12.58%, while enhancing SC, NMI, and Purity by 2.24% to 15.47%, 3.34% to 11.39%, and 2.58% to 13.65%, respectively. Furthermore, the experiments demonstrate that the popular models for service function vector generation and neighborhood feature aggregation can all be integrated into MSSCL. After being integrated into MSSCL, the clustering performance of these models was significantly improved, highlighting the effectiveness and generalizability of MSSCL.

This study addresses the tracking–learning–detection (TLD) algorithm for long‐term single‐target tracking of moving vehicle from video streams. The problems leading to tracking failures in existing TLD methods are discovered, and an improved TLD (ITLD) tracking algorithm is proposed which is more robust to object occlusion and illumination variation. A square root cubature Kalman filter (SRCKF) is employed in the tracker of TLD to predict the position of the object when occlusion occurs. Besides, this study introduces fast retina keypoint (FREAK) feature into the tracker to alleviate the instability caused by illumination variation or scale variation. The overlap comparison and the normalised cross‐correlation coefficient (NCC) are introduced to the integrator of the TLD to obtain reliable bounding boxes with improved tracking precision. Experiments are conducted to compare the performance of the state‐of‐the‐art trackers and the proposed method, using the object tracking benchmark that includes 50 video sequences (OTB‐50) and TLD datasets. The experimental results show that the proposed ITLD outperforms on both tracking accuracy and robustness. The proposed method can track a moving vehicle even when it is temporally totally occluded.

A new particle optimization algorithm with dynamic topology is proposed based on small world network. The technique imitates the dissemination of information in a small world network by dynamically updating the neighborhood topology of the Particle Swarm Optimization (PSO). In comparison with other four classic topologies and two PSO algorithms based on small world network, the proposed dynamic neighborhood strategy is more effective in coordinating the exploration and exploitation ability of PSO. Simulations demonstrated that the convergence of the swarms is faster than its competitors. Meanwhile, the proposed method maintains population diversity and enhances the global search ability for a series of benchmark problems.

In this paper, geometrical analysis is used to extract novel straight line segment features from the wings around the peaks of the Hough Transform (HT). Based on these features, a practical segment detection method is proposed which has the ability to determine complete straight line segment parameters including the location of the center, length, slope and the Euclidean distance to the origin. The proposed method does not rely on edge point verification in the image space, i.e., the complete set of segment features are determined only using the information embodied in the HT data. The proposed method can distinguish between highly collinear straight line segments. Segment detection is robust to disturbing edge points, especially ones collinear with the object. A predefined collinear segment resolution that provides a theoretical criterion to determine straight line contiguity is derived. Image processing and analysis experiments show consistent robust performance.

The distance between a straight line and a straight line segment in the image space is proposed in this paper. Based on this distance, the neighborhood of a straight line segment is defined and mapped into the parameter space to obtain the parameter space neighborhood of the straight line segment. The neighborhood mapping between the image space and parameter space is a one to one reversible map. The mapped region in the parameter space is analytically derived and it is proved that it can be efficiently approximated by a quadrangle. The proposed straight line segment neighborhood technique for the HT outperforms conventional straight line neighborhood methods currently used with existing HT variations. In contrast to the straight line neighborhoods used in existing HT variations, the proposed straight line segment neighborhood has several advantages including: 1) the detection error of the proposed neighborhood is not affected by the length of the straight line segments; 2) a precision requirement in the image space described using the proposed distance can be explicitly resolved using the proposed formulation; 3) the proposed neighborhood has the ability to distinguish between segments belonging to the same straight line. A variety of experiments are executed to demonstrate that the proposed neighborhood has a variety of interesting properties of high practical value.

Original Hebbian encoding scheme of bidirectional associative memory (BAM) provides a poor pattern capacity and recall performance. Based on Rosenblatt's perceptron learning algorithm, the pattern capacity of BAM is enlarged, and perfect recall of all training pattern pairs is guaranteed. However, these methods put their emphases on pattern capacity, rather than error correction capability which is another critical point of BAM. This paper analyzes the sensitivity to noise in BAM and obtains an interesting idea to improve noise immunity of BAM. Some researchers have found that the noise sensitivity of BAM relates to the minimum absolute value of net inputs (MAV). However, in this paper, the analysis on failure association shows that it is related not only to MAV but also to the variance of weights associated with synapse connections. In fact, it is a positive monotone increasing function of the quotient of MAV divided by the variance of weights. This idea provides an useful principle of improving error correction capability of BAM. Some revised encoding schemes, such as small variance learning for BAM (SVBAM), evolutionary pseudorelaxation learning for BAM (EPRLAB) and evolutionary bidirectional learning (EBL), have been introduced to illustrate the performance of this principle. All these methods perform better than their original versions in noise immunity. Moreover, these methods have no negative effect on the pattern capacity of BAM. The convergence of these methods is also discussed in this paper. If there exist solutions, EPRLAB and EBL always converge to a global optimal solution in the senses of both pattern capacity and noise immunity. However, the convergence of SVBAM may be affected by a preset function.