International Journal of Pattern Recognition and Artificial Intelligence

Many classification algorithms aim to minimize just their training error count; however, it is often desirable to minimize a more general cost metric, where distinct instances have different costs. In this paper, an instance-based cost-sensitive Bayesian consistent version of exponential loss function is proposed. Using the modified loss function, the derivation of instance-based cost-sensitive extensions of AdaBoost, RealBoost and GentleBoost are developed which are termed as ICSAdaBoost, ICSRealBoost and ICSGentleBoost, respectively. In this research, a new instance-based cost generation method is proposed instead of doing this expensive process by experts. Thus, each sample takes two cost values; a class cost and a sample cost. The first cost is equally assigned to all samples of each class while the second cost is generated according to the probability of each sample within its class probability density function. Experimental results of the proposed schemes imply 12% enhancement in terms of $F$-measure and 13% on cost-per-sample over a variety of UCI datasets, compared to the state-of-the-art methods. The significant priority of the proposed method is supported by applying the pair of $T$-tests to the results.

The aim of this study is to test the freshness of horse mackerels by using a low cost electronic nose system composed of eight different metal oxide sensors. The process of freshness evaluation covers a scala of seven different classes corresponding to 1, 3, 5, 7, 9, 11, and 13 storage days. These seven classes are categorized according to six different classifiers in the proposed binary decision tree structure. Classifiers at each particular node of the tree are individually trained with the training dataset. To increase success in determining the level of fish freshness, one of the k-Nearest Neighbors (k-NN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA) and Bayes methods is selected for every classifier and the feature spaces change in every node. The significance of this study among the others in the literature is that this proposed decision tree structure has never been applied to determine fish freshness before. Because the freshness of fish is observed under actual market storage conditions, the classification is more difficult. The results show that the electronic nose designed with the proposed decision tree structure is able to determine the freshness of horse mackerels with 85.71% accuracy for the test data obtained one year after the training process. Also, the performances of the proposed methods are compared against conventional methods such as Bayes, k-NN, and LDA.

Underground square, as a recreation and activity place for citizens, represents the underground space quality of a city, so its spatial experience is of great significance. This research discussed the influence and effects of underground squares’ interface morphology on spatial experience. By field research of ten large-scale urban underground spaces, the basic elements and related numerical interval of underground squares’ interface morphology were summarized, and on basis of this, underground square virtual models with different interface morphology were built. Based on the platform of immersive virtual reality system (IVRS), combing the isovist method and the SD method, this paper made a quantitative analysis on the relevance between interface morphology and spatial experience, and the relevant compliance indicators of interface morphology were summarized. The experimental results show that the spatial experience is good at the interface density of 0.402 and interface opening’s aspect ratio of 2–3. This can provide reference and foundation for urban underground spatial design in future.

As the physical environment of urban underground streets space is continuously perfect, people start to anticipate that underground streets with negative impression could satisfy their psychological comfort appeal as traditional ground streets do. Streets’ pavement is of great significance in creating humanized and comfortable underground spatial atmosphere, and different ground pavements of underground commercial streets display different visual comfort effects. We conducted field investigations of a dozen typical underground streets in eight big cities in China with 42 test samples, and this research obtained the pavement elements’ data of underground commercial streets, built virtual 3D scenes based on orthogonal analysis and virtual reality technology of computer vision, acquired the psychological data of spatial experience through virtual reality test, and analyzed the relationship between six elements (glossiness, roughness, color, dimension, pattern, and collage of ground pavement in underground commercial streets) and spatial visual comfort based on quantitative analysis of experimental data. Results show that, “Cold–hot sensation”, “Glossiness”, and “Collage ordered degree” are chief elements for underground commercial streets’ pavement design. The pavement design featured with neutral color, medium- and large-scale and ordered collage form are the design preference and emphasis for underground commercial streets. Neutral color of underground commercial streets pavement may have a great influence on the recognition of pavement glossiness.

As a classical clustering model, Gaussian Mixture Model (GMM) can be the footstone of dominant machine learning methods like transfer learning. Evolving GMM is an approximation to the classical GMM under time-critical or memory-critical application scenarios. Such applications often have constraints on time-to-answer or high data volume, and raise high computation demand. A prominent approach to address the demand is GPGPU-powered computing. However, the existing evolving GMM algorithms are confronted with a dilemma between clustering accuracy and parallelism. Point-wise algorithms achieve high accuracy but exhibit limited parallelism due to point-evolutionary pattern. Block-wise algorithms tend to exhibit higher parallelism. Whereas, it is challenging to achieve high accuracy under a block-evolutionary pattern due to the fact that it is difficult to track evolving process of the mixture model in fine granularity. Consequently, the existing block-wise algorithm suffers from significant accuracy degradation, compared to its batch-mode counterpart: the standard EM algorithm. To cope with this dilemma, we focus on the accuracy issue and develop an improved block-evolutionary GMM algorithm for GPGPU-powered computing systems. Our algorithm leverages evolving history of the model to estimate the latest model order in each incremental clustering step. With this model order as a constraint, we can perform similarity test in an elastic manner. Finally, we analyze the evolving history of both mixture components and the data points, and propose our method to merge similar components. Experiments on real images show that our algorithm significantly improves accuracy of the original general purpose bock-wise algorithm. The accuracy of our algorithm is at least comparable to that of the standard EM algorithm and even outperforms the latter under certain scenarios.

In classification of fashion article images based on e-commerce image recommendation system, the classification accuracy and computation time cannot meet the actual requirements. Herein, for the first time to our knowledge, we present two diverse image recognition approaches for classification of fashion article images called random-forest method based on genetic algorithm (GA-RF) and Visual Geometry Group-Image Enhancement algorithm (VGG-IE) to solve classification accuracy and computation time problem. In GA-RF, the number of segmentation times and the decision trees are the key factors affecting the classification results. Improved genetic algorithm is introduced into the parameter optimization of forests to determine the optimal combination of the two parameters with minimal manual intervention. Finally, we propose six different Deep Neural Network architectures, including VGG-IE, to improve classification accuracy. The VGG-IE algorithm uses batch normalization and seven kinds training-data augmentation for ease and promotion of learning process. We investigate the effectiveness of the proposed method using Fashion-MNIST dataset and 70000 pictures, Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 10 categories of image recognition, our VGG algorithm has the shortest computational time when it satisfies certain classification accuracy. VGG-IE approach has the highest classification accuracy.

Projective synchronization (PS) is a type of chaos synchronization where the states of slave system are scaled replicas of the states of master system. This paper studies the asymptotic projective synchronization (APS) between master–slave chaotic neural networks (NNs) with mixed time-delays and unmatched coefficients. Based on useful inequality techniques and constructing a suitable Lyapunov functional, some simple criteria are derived to ensure the APS of considered networks via designing a novel adaptive feedback controller. In addition, a numerical example and its MATLAB simulations are provided to check the feasibility of the obtained results. The main innovation of our work is that we dealt with the APS problem between two different chaotic NNs, while most of the existing works only concerned with the PS of chaotic systems with the same topologies. In addition, compared with the controllers introduced in the existing papers, the designed controller in this paper does not require any knowledge about the activation functions, which can be seen as another novelty of the paper.

An interesting research area that permits the user to mine the significant information, called frequent subgraph, is Graph-Based Data Mining (GBDM). One of the well-known algorithms developed to extract frequent patterns is GASTON algorithm. Retrieving the interesting webpages from the log files contributes heavily to various applications. In this work, a webpage recommendation system has been proposed by introducing Chronological Cuckoo Search (Chronological-CS) algorithm and the Laplace correction based k-Nearest Neighbor (LKNN) to retrieve the useful webpage from the interesting webpage. Initially, W-Gaston algorithm extracts the interesting subgraph from the log files and provides it to the proposed webpage recommendation system. The interesting subgraphs subjected to clustering with the proposed Chronological-CS algorithm, which is developed by integrating the chronological concept into Cuckoo Search (CS) algorithm, provide various cluster groups. Then, the proposed LKNN algorithm recommends the webpage from the clusters. Simulation of the proposed webpage recommendation algorithm is done by utilizing the data from MSNBC and weblog database. The results are compared with various existing webpage recommendation models and analyzed based on precision, recall, and F-measure. The proposed webpage recommendation model achieved better performance than the existing models with the values of 0.9194, 0.8947, and 0.86736, respectively, for the precision, recall, and F-measure.

Optical properties of water distort the quality of underwater images. Underwater images are characterized by poor contrast, color cast, noise and haze. These images need to be pre-processed so as to get some information. In this paper, a novel technique named Fusion of Underwater Image Enhancement and Restoration (FUIER) has been proposed which enhances as well as restores underwater images with a target to act on all major issues in underwater images, i.e. color cast removal, contrast enhancement and dehazing. It generates two versions of the single input image and these two versions are fused using Laplacian pyramid-based fusion to get the enhanced image. The proposed method works efficiently for all types of underwater images captured in different conditions (turbidity, depth, salinity, etc.). Results obtained using the proposed method are better than those for state-of-the-art methods.

As the practical applications in other fields, high-resolution images are usually expected to provide a more accurate assessment for the air-coupled ultrasonic (ACU) characterization of wooden materials. This paper investigated the feasibility of applying single image super-resolution (SISR) methods to recover high-quality ACU images from the raw observations that were constructed directly by the on-the-shelf ACU scanners. Four state-of-the-art SISR methods were applied to the low-resolution ACU images of wood products. The reconstructed images were evaluated by visual assessment and objective image quality metrics, including peak signal-to-noise-ratio and structural similarity. Both qualitative and quantitative evaluations indicated that the substantial improvement of image quality can be yielded. The results of the experiments demonstrated the superior performance and high reproducibility of the method for generating high-quality ACU images. Sparse coding based super-resolution and super-resolution convolutional neural network (SRCNN) significantly outperformed other algorithms. SRCNN has the potential to act as an effective tool to generate higher resolution ACU images due to its flexibility.

In order to study the detection methods of weak transient electromagnetic radiation signals, a detection algorithm integrating generalized cross-correlation and chaotic sequence prediction is proposed in this paper. Based on the dual-antenna test and cross-correlation information estimation method, the detection of aperiodic weak discharge signals under low signal-to-noise ratio is transformed into the estimation of periodic delay parameters, and the noise is reduced at the same time. The feasibility of this method is verified by simulation and experimental analysis. The results show that under the condition of low signal-to-noise ratio, the integrated method can effectively suppress the influence of 10 noise disturbances. It has a high detection probability for weak transient electromagnetic radiation signals, and needs fewer pulse accumulation times, which improves the detection efficiency and is more suitable for long-distance detection of weak electromagnetic radiation sources.

Combining the advantages of graphical visualization in the field of information dissemination, aiming at a large number of complicated information data in the stage of product design preparation, this paper discusses the guidance and reference function of drawing visual product design outline for product design behavior. The principle of information graphics is introduced into the field of the style design for the industrial products, and it is put forward in this paper that the formation principle and the decision points of a certain kind of modeling can be analyzed through the calculation of the characteristic variables of the pairwise modeling based on the principle of the information graphics. The industrial products are taken as an example, and the representative samples are selected to extract the modeling characteristic variables and calculate the information graphics on the basis of the principle of the information graphics. The results show that the formation principle and design decision sequence for different types of modeling can be obtained. The instance has verified the feasibility of the method put forward in this paper, which can provide an effective reference for the design of the modeling for the industrial products.

With the rapid development of digital phones, the digital image forensics system in current times has had a great impact. It will lead to a serious threat for us, and especially the emergence of the recaptured image makes the existing digital image forensics algorithm invalid. So, it needs an effective image detection algorithm for us to identify recaptured images. In this paper, a new detection algorithm of the recaptured image is presented based on gray level co-occurrence matrix by analyzing the differences between the real and recaptured images. In order to analyze the differences, a new image evaluation model was put forward in this paper, which is called image variance ratio. Firstly, the algorithm proposed extracted high-frequency and low-frequency information of images by wavelet transform, based on which we calculated the relative gray level co-occurrence matrices. Secondly, the features of gray level co-occurrence matrix were extracted. At last, the recaptured image was classified by the support vector machine according to the features. The experimental results showed the algorithm proposed can not only effectively identify the recaptured image obtained from different media but also have better identification rate.

Matrix factorization models often reveal the low-dimensional latent structure in high-dimensional spaces while bringing space efficiency to large-scale collaborative filtering problems. Improving training and prediction time efficiencies of these models are also important since an accurate model may raise practical concerns if it is slow to capture the changing dynamics of the system. For the training task, powerful improvements have been proposed especially using SGD, ALS, and their parallel versions. In this paper, we focus on the prediction task and combine matrix factorization with approximate nearest neighbor search methods to improve the efficiency of top-N prediction queries. Our efforts result in a meta-algorithm, MMFNN, which can employ various common matrix factorization models, drastically improve their prediction efficiency, and still perform comparably to standard prediction approaches or sometimes even better in terms of predictive power. Using various batch, online, and incremental matrix factorization models, we present detailed empirical analysis results on many large implicit feedback datasets from different application domains.

In modern intelligent algorithms and real-industrial applications, there are many fields involving multi-objective particle swarm optimization algorithms, but the conflict between each objective in the optimization process will easily lead to the algorithm falling into local optimal. In order to prevent the algorithm from quickly falling into local optimization and improve the robustness of the algorithm, a multi-objective particle swarm optimization algorithm based on grid distance (GDMOPSO) was proposed, which has to improve the diversity of the algorithm and the search ability. Based on the MOPSO algorithm, a new external archive control strategy was established by using the grid technology and Pareto-dominant ordering principle, and the learning samples were improved. The proposed GDMOPSO is compared with a group of benchmark function tests and four classical algorithms. The results of experiment show that our proposed algorithm can effectively avoid premature convergence in terms of generational distance and hyper-volume (HV) indicator compared with other four classical MOPSO algorithms.