International Journal of Pattern Recognition and Artificial Intelligence

With the rapid development of information technology, we have already access to the era of big data. Time series is a sequence of data points associated with numerical values and successive timestamps. Time series not only has the traditional big data features, but also can be continuously generated in a high speed. Therefore, it is very time- and resource-consuming to directly apply the traditional time series similarity search methods on the raw time series data. In this paper, we propose a novel online segmenting algorithm for streaming time series, which has a relatively high performance on feature representation and similarity search. Extensive experimental results on different typical time series datasets have demonstrated the superiority of our method.

Capture effect is a very common phenomenon in wireless channel. By using capture effect, the collision tags can be identified in a certain probability, so the identification efficiency and speed of the system can be improved. In this paper, we extend the Maximum a Posterior probability method to capture effect environment and propose a novel tag anti-collision algorithm MAPCE for RFID tags identification. The proposed algorithm can not only estimate the number of tags, but also estimate the capture effect probability. Based on the estimation, we can derive the optimal frame length in the tag identification systems. The experimental results show that when the tags’ number is larger than 600 and less than 1000, the proposed algorithm has lower computational complexity and lower estimation error rate.

With the increase in the total population of the society and the continuous increase in the number of trips, the traffic pressures faced by people are increasing. With the development and advancement of computer technology, the emergence of intelligent transportation provides a better way to solve the problem of effectively alleviating traffic pressure and reducing the incidence of traffic accidents. In recent years, intelligent traffic monitoring system, as one of the important branches in the field of intelligent transportation, has also received more and more attention. Among them, video-based moving target recognition technology involves theoretical knowledge in various fields such as artificial intelligence, image processing, pattern recognition and computer vision. It is an important means to realize “safe city” and “smart city” and a key technology for intelligent monitoring. Therefore, the research on human motion target recognition algorithm in complex traffic environment has important theoretical and practical value. In the field of intelligent traffic monitoring, the moving target detection and recognition effect of video images will have certain influence on the classification and behavior understanding of subsequent moving targets. In this paper, the commonly used moving target detection methods are studied first, and the convergence problem of the traditional Adaboost algorithm is improved. An Adaboost algorithm based on adaptive weight update is proposed, and then the support vector machine (SVM) is used. The algorithm identifies the detected moving target. Finally, through simulation experiments on the acquired video images, the results show that the proposed human motion target recognition algorithm based on adaptive weight update Adaboost and SVM has good feasibility and rationality.

Reliable remaining useful life (RUL) prediction of industrial equipment key components is of considerable importance in condition-based maintenance to avoid catastrophic failure, promote reliability and reduce cost during the production. Diamond-coated mechanical seal is one of the most critical wearing components in petroleum chemical, nuclear power and other process industries. Estimating the RUL is of critical importance. We consider the data-driven approaches for diamond-coated mechanical seal RUL estimation based on AE sensor data, since it is difficult to construct an explicit mathematical degradation model of seal. The challenges of this work are dealing with the noisy AE sensor data and modeling the degradation process with fluctuation. Faced with these challenges, we propose a pipeline method CDF-CNN to estimate the RUL for mechanical seal: WPD-KLD to raise the signal-to-noise ratio, novel CDF-based statistics to represent seal degradation process and CNN structure to estimate RUL. To acquire AE sensor data, several diamond-coated seals are tested from new to failure in three working conditions. Experimental results demonstrate that the proposed method can accurately predict the RUL of diamond-coated mechanical seal based on AE signals. The proposed prediction method can be generalized to other various mechanical assets.

Smart cars are the result of the combination of the latest technological achievements in the fields of artificial intelligence, sensors, control science, computer, and network technology with the modern automobile industry. Intelligent cars usually have functions, such as automatic shifting, automatic driving, and automatic road condition recognition. The research of intelligent car technology involves many disciplines. This thesis focuses on the field of smart car visual navigation, focusing on image denoising, image information recognition, extraction, and pattern recognition control algorithms. The traditional trajectory tracking algorithm is mainly used in industrial computer or high-performance computer. The computational complexity leads to poor real-time control, and it is easily interfered by external complex terrain environment and internal disordered electromagnetic environment during vehicle driving. In general, on a regular basis, by the image analysis of the driver or the driver information, the image information is proposed using way trace processing technology, vehicle tracking control method and automatic driving rules. The simulation and experimental results show that the proposed control methods and rules used to carry out automatic driving vehicle are feasible. The algorithm reduces the complexity of the algorithm, improves the real-time and stability of the control and finally achieves a good trajectory tracking effect of the car on high-speed automatic driving.

With the economic growth of our country and the continuous improvement of people’s living standards, cars have begun to enter thousands of households and become a necessity for people. However, the rapid growth of the number of automobiles has led to a sustained increase in carbon dioxide emissions and a significant decline in urban air quality, which seriously restricts the sustainable development of cities. With the introduction of the national air quality protection policy, electric vehicles will eventually replace the existing fuel vehicles and become a new generation of transportation for people to travel. At the same time, the large expansion of the number of cars has increased the hidden dangers of traffic accidents. In order to ensure the safety of pedestrians, drivers are given a more intelligent driving environment. This paper presents the research of pedestrian detection and pedestrian distance algorithm based on image processing. By comparing the performance of pedestrian detection algorithm based on SSD with traditional HOG+SVM pedestrian detection algorithm, the results of pedestrian–vehicle distance calculation are detected, and the feasibility and effectiveness of the algorithm are obtained. The results show that the proposed algorithm has good feasibility and practicability, and provide a good reference for the research of pedestrian detection algorithm for electric vehicles.

Target recognition is an important application in the time of high-resolution remote sensing images. However, the traditional target recognition method has the characteristics of artificial design, and the generalization ability is not strong, which makes it difficult to meet the requirement of the current mass data. Therefore, it is urgent to explore new methods for feature extraction and target recognition and location in remote sensing images. Convolutional neural network in deep learning can extract representative and discriminative multi-level features of typical features from images, so it can be used for multi-target recognition of remote sensing big data in complex scenes. In this study, NWPU VHR-10 data was selected, 50% was used for training, and the remainder was used for verification. The target recognition effects of two kinds of convolutional neural network models, Faster R-CNN and SSD, were studied and compared, and the mean average precision (mAP) was used for evaluation. The evaluation results show that the Faster R-CNN has three categories with an accuracy of more than 80%, and the SSD has seven categories with an accuracy of more than 80%, all of which show good results. The SSD model is particularly prominent in running time and recognition results, which proves convolutional neural networks have broad application prospects in the target recognition of remote sensing image data.

Image segmentation is a classical problem in the field of computer vision. Fuzzy $c$-means algorithm (FCM) is often used in image segmentation. However, when there is noise in the image, it easily falls into the local optimum, which results in poor image boundary segmentation effect. A novel method is proposed to solve this problem. In the proposed method, first, the image is transformed into a neutrosophic image. In order to improve the ability of global search, a combined FCM based on particle swarm optimization (PSO) is proposed. Finally, the proposed algorithm is applied to the neutrosophic image segmentation. The results of experiments show that the novel algorithm can eliminate image noise more effectively than the FCM algorithm, and make the boundary of the segmentation area clearer.

One of the effective ways to improve task performance is to trace the sources of the task failures, that is, error factors, and take them into consideration for the optimization design of the system interactive interface. In this study, the digital instrument control equipment of a nuclear power safety injection system plant was taken as an example to construct an error factor–visual perception–interface layout (EF–VP–IL) correlation model. The visual perception intensity (VPI) levels in the functional sections of the interface were obtained by extracting the error factors and performing weight analysis on each functional section. A set of optimal solutions of the interface layout was obtained using the genetic algorithm, and the interface layout was optimized accordingly. The calculation results showed that the proposed method increased the visual communication index (VCI) of the original interface from $Z=11.9662$ to $Z=14.761$ after optimization, which is an improvement of 23.36%.

Human body motion pattern recognition in video images is an important research direction in the field of pattern recognition. It has a very broad application prospect in many fields such as intelligent video surveillance, human-computer interaction, motion analysis, video retrieval, etc. Research has also received extensive attention from scholars at home and abroad. Pattern recognition is essentially a branch of artificial intelligence. It has its unique role in the field of artificial intelligence. Accurate recognition of human body motion patterns in video images is of great help in image classification, retrieval, human tracking and video surveillance. Based on the human visual perception mechanism, this paper proposes a human behavior recognition algorithm based on semantic saliency map. Through the combination of sliding window and similarity measure, the behavioral region that best exhibits the semantic features of the image is found, which is the semantically significant region. The semantic significant region and the original image are used as the dual input source to study the human behavior recognition, and the image is enhanced. The utilization of significant regional information better reveals the identifiable area of the image and contributes to the recognition of human behavior.

Early diagnosis of osteoporosis can efficiently predict fracture risk. There is a great demand to prevent this disease. The goal of this study was to distinguish osteoporotic cases from healthy controls on 2D bone radiograph images, using texture analysis and genetic algorithms (GAs). Gray Level Co-occurrence Matrix (GLCM), Run length Matrix (RLM) and Binarized Statistical Image Features (BSIF) were used for texture analysis. Features are numerous and parameter-dependent. The related experts can pick out the useful input features for the classifier. It however remains a difficult task and may be inefficient or even harmful as the data pattern is not clear. In this paper, GAs were used to optimize the two parameters of the co-occurrence matrix (distance parameter or pixel separation, orientation or direction) and the number of gray levels used in the preprocessing quantification step. GAs were also used to select the best combination of features extracted from GLCM and RLM matrices. Experiments were conducted on two populations composed of Osteoporotic Patients and Control Subjects. Results show that GAs combined with GLCM and BSIF features can improve the classification rates (ACC = 87.50%) obtained using GLCM (ACC = 77.8%) alone.

The spine of mammals aids in the stability of locomotion. Central Pattern Generators (CPGs) located in spinal cord can rapidly provide a rhythmic output signal during loss of sensory feedback on the basis of a simulated quadruped agent. In this paper, active spine of quadruped robot is shown to be extremely effective in motion. An active spine model based on the Parallel Kinematic Mechanism (PKM) system and biological phenomena is described. The general principles involved in constructing a neural network coupled with limbs and spine to solve specific problems are discussed. A CPG mathematical model based on Hopf nonlinear oscillators produces rhythmic signal during locomotion is described, where many parameters to be solved must be formulated in terms of desired stability, often subject to vertical stability analysis. Our simulations demonstrate that active spine with setting reasonable CPG parameters can reduce unnecessary lateral displacement during trot gait, improving the stability of quadruped robot. In addition, we demonstrate that physical prototype mechanism provides a framework which shows correctness of simulation, and stability can thus be easily embodied within locomotion.

Needle-based percutaneous prostate interventions include biopsy and brachytherapy and the former is the gold standard for the diagnosis of prostate cancer and the latter is often used in the treatment of prostate cancer. This paper introduces a novel robotic assistant system for prostate intervention and the system architecture and workflow are described, which is significant for the design of similar systems. In order to offer higher precision and better real-time performance, a Ultrasound (US)/Magnetic Resonance Imaging (MRI) fusion method is proposed to guide the procedures in this study. Moreover, image registration is a key step and a hot issue in image fusion, especially in multimodal image fusion. In this work, we adopt a novel registration method based on active demons and optic flow for prostate image fusion. To verify the availability of the system, we evaluate our approach of the US/MRI image fusion by using data acquired from six patients, and root mean square error (RMSE) for anatomical landmarks is 3.15mm. In order to verify the accuracy and validity of the system developed in this paper, a system experimental platform was built and used for bionic tissue puncture of prostate under the guidance of MR and Transrectal Ultrasound (TRUS) fusion images. The experimental results show that the deviations of the final actual needle points of the three target points on the bionic tissue model measured in the laboratory environment are less than 2.5mm.