International Journal of Pattern Recognition and Artificial Intelligence

DNA-binding proteins are an essential part of the DNA. It also an integral component during life processes of various organisms, for instance, DNA recombination, replication, and so on. Recognition of such proteins helps medical researchers pinpoint the cause of disease. Traditional techniques of identifying DNA-binding proteins are expensive and time-consuming. Machine learning methods can identify these proteins quickly and efficiently. However, the accuracies of the existing related methods were not high enough. In this paper, we propose a framework to identify DNA-binding proteins. The proposed framework first uses PseKNC (ps), MomoKGap (mo), and MomoDiKGap (md) methods to combine three algorithms to extract features. Further, we apply Adaboost weight ranking to select optimal feature subsets from the above three types of features. Based on the selected features, three algorithms (k-nearest neighbor (knn), Support Vector Machine (SVM), and Random Forest (RF)) are applied to classify it. Finally, three predictors for identifying DNA-binding proteins are established, including $\mathrm{\text{ps}}+\mathrm{\text{mm}}$, $\mathrm{\text{ps}}+\mathrm{\text{md}}$, $\mathrm{\text{ps}}+\mathrm{\text{mm}}+\mathrm{\text{md}}$. We utilize benchmark and independent datasets to train and evaluate the proposed framework. Three tests are performed, including Jackknife test, 10-fold cross-validation and independent test. Among them, the accuracy of ps+md is the highest. We named the model with the best result as psmdDBPs and applied it to identify DNA-binding proteins.

Character shape reconstruction in video is challenging due to low contrast, complex backgrounds and arbitrary orientation of characters. This work proposes an Improved Ring Radius Transform (IRRT) for reconstructing impaired characters through medial axis prediction. At first, the technique proposes a novel idea based on the Tangent Vector (TV) concept that identifies each actual pair of end pixels caused by gaps in impaired character components. Next, the actual direction to predict medial axis pixels using IRRT for each pair of end pixels is proposed with a new normal vector concept. The process of prediction repeats iteratively to find all the medial axis pixels for every gap in question. Further, medial axis pixels with their radii are used to reconstruct the shapes of impaired characters. The proposed technique is tested on benchmark datasets consisting of video, natural scenes, objects and multi-lingual data to demonstrate that it reconstructs shapes well, even for heterogeneous data. Comparative studies with different binarization and character recognition methods show that the proposed technique is effective, useful and outperforms existing methods.

Traffic signs detection has become an important feature of Advanced driving assisting systems and even self-driving cars. In this paper, we present an implementation of a traffic signs detection method on Graphics Processing Units (GPU) under real-time conditions. The proposed model is based on deep convolutional neural networks, a deep learning model used in computer vision applications. The deep convolutional neural networks have recently been used to solve many computer vision tasks successfully. Unlike old techniques, the model is used to detect and identify the traffic signs at the same time without the need for any external modules. To achieve real-time inference, we implement the proposed model on the GPU as a natural choice for the implementation of deep learning-based models. Also, we build large traffic signs detection dataset. The dataset contains 10000 images captured from the Chinese roads under real-world factors like lightning, occlusion, complex background, etc. 73 traffic sign classes were considered in this dataset. The evaluation of the proposed model on the proposed dataset shows robust performance in terms of speed and accuracy.

This work presents the deep learning networks-based method using fine-tuning for classification and search of a diversity of action videos. First, a 3D convolutional neural networks (3D CNN) model which performs pre-training operation and fine-tuning strategy is employed to extract the spatiotemporal features of videos. It is first pre-trained on UCF-101 datasets to train model with initial parameters. Then, a small new dataset is employed to fine-tune the initial model for the training of the new model. Once features are extracted by the final CNNs model, distance measure can be adopted to calculate the similarities between the query video and the test dataset for the video search. The searched video is returned and ranked according to the priority when it has higher similarity with the query video. The comparison results in the experiment shows that the search method using fine-tuning obtains better performance than the method without using fine-tuning. Second, the classification results based on the 3D CNN model using fine-tuning are also presented for the consideration of a query by keyword. Accuracy result obtained using the model with the help of fine-tuning is approximately 2.8% higher than that without using fine-tuning.

The fact that the existing traffic sign images are easily affected by external factors, and the traffic signs are generally small targets on the images at different scales, has made it difficult in feature extraction when doing traffic sign detection. To achieve better detection results, a multi-target traffic sign detection method with channel attention and feature fusion network (CAFFNet in short) is proposed. This method effectively learns the correlation between feature channels through a lightweight channel attention network, realizes local cross-channel interaction without dimensionality reduction, and enhances the representation ability of the network. The feature pyramid network is used to achieve feature fusion and generate high-resolution multiscale semantic information. The dilated convolution is utilized to capture the multiscale context information to narrow the difference between features and improve the detection effect of the model. The experimental results show that the proposed method on the two datasets GTSDB and CTSD has achieved superior performance in the evaluation criteria compared with the existing detection algorithms.

In this paper, we tackle the task of natural language video localization (NLVL): given an untrimmed video and a description language query, the goal is to localize the temporal segment within the video that best describes the natural language description. NLVL is challenging at the intersection of language and video understanding because a video may contain multiple segments of interests and the language may describe complicated temporal dependencies. Though existing approaches have achieved good performance, most of them did not fully consider the inherent differences between language and video modalities. Here, we propose Moment Relation Network (MRN) to reduce the divergence of the probability distribution of these two modalities. Specifically, MRN trains video and language subnets, and then uses transfer learning techniques to map the extracted features into an embedding-shared space where we calculate the similarity of two modalities using Mahalanobis distance metric, which is used to localize moments. Extensive experiments on benchmark datasets show that the proposed MRN significantly outperforms the state-of-the-art under the widely used metrics by a large margin.

In optical remote sensing image reconstruction, image registration is an important issue to address in order to ensure satisfactory reconstruction performance. In this study, a multi-frame image registration algorithm for high-resolution images and its parallel design method are proposed. The algorithm realizes an improved feature point detection method based on an adaptive gradient bilateral tensor filter and carries out weighted Gaussian surface sub-pixel interpolation to obtain more accurate corner positions, which better guarantees the registration accuracy. On this basis, multi-scale expansion is carried out to generate descriptors for image registration. In addition, the operation-level parallel analysis and design are carried out on a GPU platform based on compute unified device architecture (CUDA), and the memory model of the GPU is utilized reasonably. The task-level parallel analysis and design are carried out based on the GPU stream model. Moreover, based on the open multi-processing (OpenMP) platform, a multi-core CPU carries out parallel design at the operation level and task level, which realizes post-processing operations such as optical remote sensing images loading, accurate matching, and coordinate mapping, thereby effectively improving registration speed. Compared with feature point algorithms and deep learning algorithm, our algorithm and its parallel design significantly improve the registration accuracy and speed of high-resolution optical remote sensing images.

The existing image retrieval methods generally require at least one complete image as a query sample. From the practical point of view, a user may not have an image sample in hand for query. Instead, partial information from multiple image samples would be available. This paper therefore attempts to deal with this problem by presenting a novel framework that allows a user to make an image query composed of several partial information extracted from multiple image samples via Boolean operations (i.e. AND, OR and NOT). Based on the request from the query, a Descriptor Cluster Label Table (DCLT) is designed to efficiently find out the result of Boolean operations on partial information. Experiments show the promising result of the proposed framework on commodity query and criminal investigation, respectively, although it is essentially applicable to different scenarios as well by changing descriptors.

The new coronavirus spreads widely through droplets, aerosols and other carriers. Wearing a mask can effectively reduce the probability of being infected by the virus. Therefore, it is necessary to monitor whether people wear masks in public to prevent the virus from spreading further. However, there is no mature general mask wearing detection algorithm. Based on tiny YOLOv3 algorithm, this paper realizes the detection of face with mask and face without mask, and proposes an improvement to the algorithm. First, the loss function of the bounding box regression is optimized, and the original loss function is optimized as the Generalized Intersection over Union (GIoU) loss. Second, the network structure is improved, the residual unit is introduced into the backbone to increase the depth of the network and the detection of two scales is expanded to three. Finally, the size of anchor boxes is clustered based on $k$-means algorithm. The experimental results on the constructed dataset show that, compared with the tiny YOLOv3 algorithm, the algorithm proposed in this paper improves the detection accuracy while maintaining high-speed inference ability.

Classification of brain tumors is one of the daunting tasks in medical imaging and incorrect decisions during the diagnosis process may lead to increased human fatality. Latest advances in artificial intelligence and deep learning have opened the path for the success of numerous medical image analysis tasks, including the recognition of brain tumors. In this paper, we propose a simple architecture based on deep learning that results in strong generalization without needing much preprocessing. The proposed Multi-modal Squeeze and Excitation model (MSENet) receives multiple representations of a given tumor image, learns end-to-end and effectively predicts the severity level of tumor. Convolution feature descriptors from multiple deep pre-trained models are used to effectively describe the tumor images and are supplied as input to the proposed MSENet. The squeeze and excitation blocks of the MSENet allow the model to prioritize tumor regions while giving less emphasis to the rest of the image, serving as an attention mechanism in the model. The proposed model is evaluated on the benchmark brain tumor dataset that is publicly accessible from the Figshare repository. Experimental studies reveal that in terms of model parameters, the proposed approach is simple and leads to competitive performance compared to those of existing complex models. By increasing complexity, the proposed model leads to generalize better and achieves state-of-the-art accuracy of 96.05% on Figshare dataset. Compared to the existing models, the proposed model neither uses segmentation nor uses augmentation techniques and without much pre-processing achieves competitive performance.

With the rapid development of Internet technology, online learning and online education are becoming more and more popular. Intelligent learning diagnosis has become an effective means to guarantee the quality of online learning, and has become a research hotspot in the direction of education informatization. Concept map is an intuitive visual tool that can discover the concepts poorly mastered by students, and provide useful clues for identifying learning disabilities of students. This paper proposed a learning diagnosis method constructed based on the concept map. First, it groups learners, then uses direct hashing and pruning (DHP) to generate association rules between the different concepts, and finally uses the DHP algorithm to produce and construct the concept map automatically to discover the concepts poorly mastered by students, and realize the automatic diagnosis of learning problems. Case studies that have been done in college mathematics classes in some universities of Lianyungang have fully verified the effectiveness of our method.

Multimodal multiobjective problems (MMOPs) exist in scientific research and practical projects, and their Pareto solution sets correspond to the same Pareto front. Existing evolutionary algorithms often fall into local optima when solving such problems, which usually leads to insufficient search solutions and their uneven distribution in the Pareto front. In this work, an improved membrane algorithm is proposed for solving MMOPs, which is based on the framework of P system. More specifically, the proposed algorithm employs three elements from P system: object, reaction rule, and membrane structure. The object is implemented by real number coding and represents a candidate solution to the optimization problem to be solved. The function of the reaction rule of the proposed algorithm is similar to the evolution operation of the evolutionary algorithm. It can evolve the object to obtain a better candidate solution set. The membrane structure is the evolutionary logic of the proposed algorithm. It consists of several membranes, each of which is an independent evolutionary unit. This structure is used to maintain the diversity of objects, so that it provides multiple Pareto sets as output. The effectiveness verification study was carried out in simulation experiments. The simulation results show that compared with other experimental algorithms, the proposed algorithm has a competitive advantage in solving all 22 multimodal benchmark test problems in CEC2019.

Short-term wind speed prediction is an essential task for wind resource and wind energy planning. However, most of this literature does not take into account the spatio-termporal correlation of wind data from the geographical field. For this reason, we propose an integrated spatio-temporal kriging and functional kriging strategy to exploit such spatio-temporal correlation into the wind speed prediction. First, the deterministic trend component in wind data is estimated to be removed. The residuals are used for spatio-temporal modeling and prediction. Based on the spatio-temporal kriging framework, four spatio-temporal covariance models (product-sum model, separable exponential product model, separable and nonseparable Gneiting models) are considered which describe the spatio-temporal correlation of wind data. In particular, the flexibility of using the nonseparable Gneiting model is highlighted. More specifically, four spatio-temporal random fields are modeled from the 12 wind monitoring stations over Ireland. We also use an involved weighted least squares method for estimating parameters of the four covariance models involved in the spatio-temporal kriging strategy. We apply the fitted covariance models to generate day-ahead wind speed predictions at both observed and nonobserved locations where wind station already exist but also to nearby locations. Leave-one-out cross-validation is applied to check the significance of the difference among the four models, these spatio-temporal ordinary kriging (STOK), functional ordinary kriging (FOK) and autoregressive integrated moving average (ARIMA) methods are compared for day-ahead wind speed predictions. Forecasting results indicate that the predicting accuracy is improved almost 33.5% using FOK compared with three approaches which confirm the effectiveness of the functional kriging method in the paper.

Transactions in web data are huge amounts of data, often consisting of fuzzy and quantitative values. Mining fuzzy association rules can help discover interesting relationships between web data. The quality of these rules depends on membership functions, and thus, it is essential to find the suitable number and position of membership functions. The time spent by users on each web page, which shows their level of interest in those web pages, can be considered as a trapezoidal membership function (TMF). In this paper, the optimization problem was finding the appropriate number and position of TMFs for each web page. To solve this optimization problem, a learning automata-based algorithm was proposed to optimize the number and position of TMFs (LA-ONPTMF). Experiments conducted on two real datasets confirmed that the proposed algorithm enhances the efficiency of mining fuzzy association rules by extracting the optimized TMFs.