Search

Error-Correcting Output Codes (ECOC) is widely deployed to tackle the multiclass classification problem by reducing the original multi-class problem to several binary sub-problems. This study attempts to design a dynamic ensemble selection strategy to promote the performance of ECOC algorithms. Concretely, each column in a coding matrix is matched with a set of feature subsets generated by various feature selection methods. In the decoding process, a novel criterion based on the data complexity theory is proposed to pick up an optimal feature subset from the candidate subsets, so as to better distinguish unknown samples. As this strategy can be embedded in all types of ECOC algorithms, seven classical ECOC algorithms are deployed to verify the effectiveness of our strategy. Experiments are carried out on a set of UCI data sets, and the results confirm that despite different working principle, the proposed strategy can further improve the performance of various ECOC algorithms in most cases. Our python source code is available at: https://github.com/MLDMXM2017/ECOC_DES .

Based on the conventional attentional encoder-decoder framework, multi-modal neural machine translation (NMT) further incorporates spatial visual features through a separate visual attention mechanism. In this aspect, most current multi-modal NMT models first separately learn the semantic representations of text and image and then independently produce two modalities of context vectors for word predictions, neglecting their semantic interactions. In this paper, we argue that learning text-image semantic interactions is more reasonable in the sense of jointly modeling two modalities for multi-modal NMT and propose a novel multi-modal NMT model with deep semantic interactions. Specifically, our model extends the conventional multi-modal NMT by introducing the following two attention neural networks: (1) a bi-directional attention network for modeling text and image representations, where the semantic representations of text are learned by referring to the image representations, and vice versa; (2) a co-attention network for refining text and image context vectors, which first summarizes the text into a context vector, then attends it to the image for obtaining the text-aware visual context vector. The final context vector is calculated by re-attending the visual context vector to the text. Results on the Multi30k dataset for different language pairs show that our model significantly improves on the state-of-the-art baselines. We have released our code at https://github.com/DeepLearnXMU/MNMT .

Early detection and intervention of cerebral palsy can promote neural remodeling in the process of brain development, thus reducing the negative effects of cerebral palsy. In this paper, we proposed a novel method for early prediction of infant cerebral palsy based on General Movements Assessment (GMA) theory with RGB-D videos. Firstly, we explored the human pose recognition in supine position based on RGB-D videos. Then we further apply it to auto-GMA. Specifically, we employ current pose estimation method on RGB images to achieve the infant full body 2D key points. By combining the depth information, the 3D movement of infant in supine position can be obtained. Then the infant’s movement complexity index is achieved by extracting the infant’s whole-body movement characteristic. In order to verify the effectiveness of the method, we did some experiments on a public dataset consisting 12 real recorded infants’ movement RGB-D videos, with 4 of the samples were diagnosed as abnormal infants by a GMA expert. We use expert GMA ratings of these recorded movements as the gold standard. Our method achieved state-of-the-art with sensitivity of 100%, specificity of 87.5%, and accuracy of 91.7%. The results show that the method has great potential in assisting doctors in diagnose infant cerebral palsy.

Nowadays, a lot of new classification and clustering techniques have been proposed for microarray data analysis. However, the multiclass microarray data classification is still regarded as a tough task because of the small sample size problem and the class imbalance problem. In this paper, we propose a novel error correcting output code (ECOC) algorithm for the classification of multiclass microarray data based on the data complexity (DC) theory. In this algorithm, an ECOC coding matrix is generated based on a hierarchical partition of the class space with the aim of Minimizing Data Complexity (named as ECOC-MDC). As the partition process can be mapped as a binary tree, a compact ensemble with high discrimination power is produced. The performance of ECOC-MDC is compared with some state-of-art ECOC algorithms on six multiclass microarray data sets, and it is found that the proposed algorithm can obtain better results in most cases. The correlation between DC measures and the dichotomizers’ performances is checked, and the observations confirm that high complexity in data usually leads to high error rates of the connected dichotomizers. But the error correcting mechanism in the ECOC framework can effectively improve our algorithm's generalization ability. In short, ECOC-MDC can produce a compact ensemble system with high error correction capability through the application of diverse DC measures. Our Matlab code is available at: github.com/MLDMXM2017/ECOC-MDC.

Posture recognition in the human lying position is of great significance for the rehabilitation evaluation of lying patients and the diagnosis of infants with early cerebral palsy. In this paper, we proposed a novel method for human 3D pose estimation in a lying position with the RGB image and corresponding depth information. Firstly, we employ current pose estimation method on RGB images to achieve the human full body 2D keypoints. By combining the depth information and coordinate transformation, the 3D movement of human in lying position can be obtained. We validate our method with two public datasets. The results show that the accuracy can reach the state-of-the-art.

In this paper, we propose a stacked model with autoencoder for financial time series prediction. A stacked autoencoder model is used for feature extraction of high-dimensional stock factors. The factors after dimensionality reduction serve as input to the stacked model to predict the next-day returns of the stocks. In this paper, the stacked autoencoder not only has the effect of reducing the dimension, but also eliminates the redundant information in the data to a certain extent, which can effectively improve the predictive capacity of the model. The constituent stocks of CSI300 are used as backtest samples, and the experiment shows that the stacked model with autoencoder can obtain more than 50% of excess return in 2019.

Many of current human pose estimation methods based on depth images require training stage. However, the training stage costs huge work on making samples. And many methods for human pose occlusion condition cannot work well. In this study, a novel approach to estimate human pose with a depth image called model-based recursive matching (MRM) is introduced. A human skeleton model with customised parameters is created based on T-pose to fit different body types. The authors use depth image and 3D point cloud corresponding to input. In contrast to previous work, the proposed method avoids training step and can give an accurate estimation in the case of the human occlusion condition. They demonstrate the method by comparing to the method Kinect offered by using random forest on 20 human poses. And the ground truth of coordinates of pose joint is made by the motion capture system. The result shows that the proposed method not only works well on the general human pose but also can deal with human occlusion better. And the authors' method can be also applied to the disabled people and other creatures.

Translation model containing translation rules with probabilities plays a crucial role in statistical machine translation. Conventional method estimates translation probabilities with only the consideration of cooccurrence frequencies of bilingual translation units, while ignoring document-level context information. In this paper, we extend the conventional translation model to a topic-triggered one. Specifically, we estimate topic-specific translation probabilities of translation rules by leveraging topical context information, and online score selected translation rules according to topic posterior distributions of translated sentences. As compared with the conventional model, our model allows for more fine-grained distinction among different translations. Experiment results on large data set demonstrate the effectiveness of our model.

With the increasingly expanding application of RFID technology, the security and privacy issues of RFID system has also been a widespread concern. The existing RFID security protocol can’t simultaneously meet the requirements of low-cost, low computing, high efficiency and high security. In this paper, through the analysis of common principles and shortcomings of RFID security protocols based on Hash Function, we improve the security protocols, so as to achieve the objectives of two-way authentication. This paper theoretically proves the protocol security through BAN logic. And the new protocols can effectively solve the security and privacy problems such as replay attack, fake attack, location privacy, anonymous tags and so on. The paper proposes a kind of authentication and communication security mechanism that makes full use of the functions of the conditional Access Module (CAM) which exist in the original remote education system and when authenticating the nodes of the system, we use the proposed security scheme. Analysis showed that the mechanism is safe, reliable, strong compatibility, economic and applicable.

The steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) usually has the advantages of high information transfer rate (ITR) and no need for training. However, low frequencies, such as the human stride motion frequency, cannot easily induce SSVEP. To solve this problem, a light spot humanoid motion paradigm modulated by the change of brightness was designed in this study. The characteristics of the brain response to the motion paradigm modulated by the change of brightness were analyzed for the first time. The results showed that the designed paradigm could induce not only the high flicker frequency but also the modulation frequencies between the change of brightness and the motion in the primary visual cortex. Thus, the stride motion frequency can be recognized through the modulation frequencies by using the designed paradigm. Also, in an online experiment, this paradigm was employed to control a lower limb robot to achieve same frequency stimulation, which meant that the visual stimulation frequency was the same as the motion frequency of the robot. Also, canonical correlation analysis (CCA) was used to distinguish three different stride motion frequencies. The average accuracies of the classification in three walking speeds using the designed paradigm with the same and different high frequencies reached 87 and 95% respectively. Furthermore, the angles of the knee joint of the robot were obtained to demonstrate the feasibility of the electroencephalograph (EEG)-driven robot with same stimulation.

Due to the high complexity of vascular system network, the geometry reconstruction of vasculatures from raw medical datasets remains a very challenging task. In this paper, we present a novel skeleton-based method for the geometry reconstruction of vascular structures from standard 3D medical datasets. With the proposed techniques, the geometry of vascular structures with high level of smoothness and accuracy can be reconstructed from the raw medical datasets. The experimental results and comparison with other techniques demonstrate that our method can achieve faithful and smooth vascular structures. In addition, quantitative validation has been conducted to evaluate the accuracy and smoothness of the reconstructed vessel geometry based on the proposed method.

Human action recognition using 3D pose data has gained a growing interest in the field of computer robotic interfaces and pattern recognition since the availability of hardware to capture human pose. In this paper, we propose a fast, simple, and powerful method of human action recognition based on human kinematic similarity. The key to this method is that the action descriptor consists of joints position, angular velocity and angular acceleration, which can meet the different individual sizes and eliminate the complex normalization. The angular parameters of joints within a short sliding time window (approximately 5 frames) around the current frame are used to express each pose frame of human action sequence. Moreover, three modified KNN (k-nearest-neighbors algorithm) classifiers are employed in our method: one for achieving the confidence of every frame in the training step, one for estimating the frame label of each descriptor, and one for classifying actions. Additional estimating of the frame's time label makes it possible to address single input frames. This approach can be used on difficult, unsegmented sequences. The proposed method is efficient and can be run in real time. The research shows that many public datasets are irregularly segmented, and a simple method is provided to regularize the datasets. The approach is tested on some challenging datasets such as MSR-Action3D, MSRDailyActivity3D, and UTD-MHAD. The results indicate our method achieves a higher accuracy.

Identification of gas-oil reservoir is always important but rather difficult in global gas-oil exploration. It is of the great significance to improve the accuracy of reservoir recognition. Seismic exploration is one of the most valuable methods of gas-oil exploration, and the huge amounts of seismic attribute data can be useful for gas-oil exploration. One limitation of the Generative Topographic Mapping (GTM) algorithm is that it cannot determine the classifications of the data points with close probabilities accurately, and it would be more likely to result in confused clarification and fuzzy boundary. To overcome the limitation, an advanced GTM algorithm with Euclidean Distance (GTM-ED) is proposed in this paper, and we use Euclidean Distance to compute the distance from the edge points to the neighbor centroids, and classify it to the closet class to avoid the problems of confused classification. And then the GTM-ED algorithm is used in the research of reservoir identification model, experiments are made with actual seismic data set. First of all, the GTM algorithm is discussed, and then the GTM-ED algorithm is introduced. And afterwards, many experiments are made. In the experiments, the log data and geological data are selected as the labels, and the comparison and analysis are made through three aspects, including relative criteria, absolute criteria, and run-time, and then the results of each model are visualized. The experimental results indicate that the GTM-ED can achieve better results in reservoir clustering and unknown reservoir identification. And in the actual application, the visualization of the GTM-ED can behave better than the GTM in showing the geological characteristics of paleochannel, the string of beads-like reservoirs and linear lava.