Latest Accepted Articles
This paper aims to propose a framework for manifold regularization (MR) based distributed semi-supervised learning (DSSL) using single layer feed-forward neural network (SLFNN). The proposed framework, denoted as DSSL-SLFNN is based on the SLFNN, MR framework, and distributed optimization strategy. Then, a series of algorithms are derived to solve DSSL problems. In DSSL problems, data consisting of labeled and unlabeled samples are distributed over a communication network, where each node has only access to its own data and can only communicate with its neighbors. In some scenarios, DSSL problems cannot be solved by centralized algorithms. According to the DSSL-SLFNN framework, each node over the communication network exchanges the initial parameters of the SLFNN with the same basis functions for semi-supervised learning (SSL). All nodes calculate the global optimal coefficients of the SLFNN by using distributed datasets and local updates. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that DSSL-SLFNN based algorithms work in a fully distributed fashion and are privacy preserving methods. Finally, several simulations are presented to show the efficiency of the proposed framework and the derived algorithms.
Many isolation approaches, such as zoning search, have been proposed to preserve the diversity in the decision space of multimodal multi-objective optimization (MMO). However, these approaches allocate the same computing resources for subspaces with different difficulties and evolution states. In order to solve this issue, this paper proposes a dynamic resource allocation strategy (DRAS) with reinforcement learning for multimodal multi-objective optimization problems (MMOPs). In DRAS, relative contribution and improvement are utilized to define the aptitude of subspaces, which can capture the potentials of subspaces accurately. Moreover, the reinforcement learning method is used to dynamically allocate computing resources for each subspace. In addition, the proposed DRAS is applied to zoning searches. Experimental results demonstrate that DRAS can effectively assist zoning search in finding more and better distributed equivalent Pareto optimal solutions in the decision space.
The digital camouflage spraying of special vehicles carried out by robots can greatly improve the spraying efficiency, spraying quality, and rapid adaptability to personalized patterns. The selection of spray tool and the accuracy of the adopted mathematical spray tool model has a great impact on the effectiveness of spray path planning and spraying quality. Since traditional conical spray tool models are not suitable for spraying rectangular digital camouflage, according to the characteristics of digital camouflage, the coating thickness cumulative distribution model of strip nozzle spray tool for 2D plane spraying and 3D surface spraying is derived, and its validity is verified by simulation. Based on the accumulation velocity model of the coating thickness (AVCT) on the curved surface and aiming at spraying path planning within the same surface and different surfaces, a path parameter optimization method based on coating uniformity evaluation of adjacent path overlapping area is proposed. Combined with the vehicle surface model, parameters such as path interval, spray tool angle and spray tool motion velocity can be calculated in real-time to ensure uniform coating. Based on the known local three-dimensional model of vehicle surface and the comprehensive spraying simulation, the validity of the purposed models: the coating thickness on the adjacent path area (CTAPA), the coating thickness on the intersection of two surfaces (CTITS), the coating thickness on the intersection of a plane and a surface (CTIPS), and the optimization method of path parameters are verified. The results show that compared with the traditional spray tool, the strip nozzle can better ensure the uniformity of the coating thickness of digital camouflage spray. Finally, according to a practical spraying experiment, the results prove that the proposed models not only are effective but also meet the practical industrial requirements and are of great practical value.
Low-resolution face images can be found in many practical applications. For example, faces captured from surveillance videos are typically in small sizes. Existing face recognition deep networks, trained on high-resolution images, perform poorly in recognizing low-resolution faces. In this work, an improved multi-branch network is proposed by combining ResNet and feature super-resolution modules. ResNet is for recognizing high-resolution facial images and extracting features from both high- and low-resolution images. Feature super-resolution modules are inserted before the classifier of ResNet for low-resolution facial images. They are used to increase feature resolution. The proposed method is effective and simple. Experimental results show that the recognition accuracy for high-resolution face images is high, and the recognition accuracy for low-resolution face images is improved.
The main aim of an educational institute is to offer high-quality education to students. The system to achieve better quality in the educational system is to find the knowledge from educational data and to discover the attributes that manipulate the performance of students. Student performance prediction is a major issue in education and training, specifically in the educational data mining system. This research presents the student performance prediction approach with the MapReduce framework based on the proposed Fractional Competitive Multi-Verse Optimization-based Deep Neuro-Fuzzy Network. The proposed Fractional Competitive Multi-Verse Optimization-based Deep Neuro-Fuzzy Network is derived by integrating Fractional Calculus with Competitive Multi Verse Optimization. The MapReduce framework is designed with the mapper and the reducer phase to perform the student performance prediction mechanism with the deep learning classifier. The input data is partitioned at the mapper phase to perform the data transformation process, and thereby the features are selected using the distance measure. The selected unique features are employed for the data segmentation process, and thereafter the prediction strategy is accomplished at the reducer phase by the Deep Neuro-Fuzzy Network classifier. The proposed method obtained the performance in terms of Mean Square Error, Root Mean Square Error and Mean Absolute Error with the values of 0.3383, 0.5817, and 0.3915, respectively.