International Journal of Pattern Recognition and Artificial Intelligence

In traditional network anomaly detection algorithms, the anomaly threshold needs to be defined manually. Keeping this as background, this study proposes an anomaly detection algorithm (VAEOCSVM), which combines the variable auto-encoder (VAE) and one-class support vector machine (OCSVM) to realize anomaly detection in industrial control networks. First, the VAE model is used to obtain the distribution of the original normal sample data represented by the low-dimensional code; the reconstruction error of the VAE model is merged into the new input. Then, using OCSVM’s hinge-loss objective function and the random Fourier feature fitting radial basis function (RBF) kernel method, the OCSVM model is represented and solved using the deep neural network and gradient descent method. Finally, the decision function of the OCSVM model is constructed by using the solved parameter information to realize the detection of abnormal data. The proposed algorithm is compared with other machine-learning-based anomaly detection algorithms in terms of multiple indicators such as precision, recall, and $F_1$ score. The experimental results using various datasets show that the proposed algorithm has a better outlier recognition ability than the machine-learning-based anomaly detection algorithms.

In this paper, we propose an automatic binary data classification method using a modified Allen–Cahn (AC) equation. The modified AC equation was originally developed for image segmentation. The equation consists of the AC equation with a fidelity term which enforces the solution to be the given data. In the proposed method, we start from a coarse grid and refine the grid until the accuracy of the data classification reaches a given tolerance. Therefore, we can avoid a laborious trial and error procedure. For a numerical method for the modified AC equation, we use a recently developed explicit hybrid scheme. We perform several 2D and 3D computational tests to demonstrate the performance of the proposed method. The computational results confirm that the proposed algorithm is automatic.

Multi-label classification addresses the problem that each instance is associated with multiple labels simultaneously. In this paper, we propose a multi-label crotch ensemble (MLCE) model for multi-label classification, which takes label correlations into consideration. In MLCE, a multi-label cluster tree is first constructed. Then, we incorporate all multi-label crotch predictors of the tree into a classifier, where the multi-label crotch predictor is the crotch formed by an inner node of the tree and its children. Finally, a flexible weighted voting scheme is designed to produce the classification output. We perform experiments on 11 benchmark datasets. Experimental results clearly demonstrate the MLCE significantly outperforms six well-established multi-label classification approaches, in terms of the widely used evaluation metrics.

Attention-based encoder-decoder models have superseded conventional techniques due to their unmatched performance on many neural machine translation problems. Usually, the encoders and decoders are two recurrent neural networks where the decoder is directed to focus on relevant parts of the source language using attention mechanism. This data-driven approach leads to generic and scalable solutions with no reliance on manual hand-crafted features. To the best of our knowledge, none of the modern machine translation approaches has been applied to address the research problem of Urdu machine transliteration. Ours is the first attempt to apply the deep neural network-based encoder-decoder using attention mechanism to address the aforementioned problem using Roman-Urdu and Urdu parallel corpus. To this end, we present (i) the first ever Roman-Urdu to Urdu parallel corpus of 1.1 million sentences, (ii) three state of the art encoder-decoder models, and (iii) a detailed empirical analysis of these three models on the Roman-Urdu to Urdu parallel corpus. Overall, attention-based model gives state-of-the-art performance with the benchmark of 70 BLEU score. Our qualitative experimental evaluation shows that our models generate coherent transliterations which are grammatically and logically correct.

In this paper, the Deep Long-short term memory Autoencoder (DLAE), a regularized deep learning model, is proposed for the automatic severity assessment of phonological deviations which are crucial stuttering markers in children. This automatic noninvasive severity assessment plays a paramount role in prevenient diagnosis, progress inference, and post-care for the patients with specific speech disorder. The proposed model is an implementation of a multi-layered Autoencoder in the Encoder–Decoder architecture of the Long-Short Term Memory (LSTM) model with hierarchically appended hidden layers and hidden units. The DLAE has definite advantage over the baseline Autoencoders. During the training phase, the proposed DLAE reconstructs the phonological features in an unsupervised fashion and the latent bottleneck features are extracted from the Encoder. The trained and regularized DLAE model with drop out is then used to predict the severity of the phonological deviation with high precision and classification accuracy compared to the baseline models.

The annotation-free word spotting method that is proposed in this paper makes document images searchable without requiring any labeled training data. Thus, our method supports the exploration of a document collection directly without demanding any manual efforts from the users for the preparation of a training dataset. Our method works in the query-by-example scenario where the user selects an exemplary occurrence of the query word. Afterwards, the entire collection of document images is searched according to visual similarity to the query. The proposed method requires only minimal assumptions about the visual appearance of text. This is achieved by processing document images as a whole without requiring a given segmentation of the images on word level or on line level. Therefore, the method is also segmentation-free. Word size variabilities can be handled by representing the sequential structure of text with a statistical sequence model. In order to make the computationally costly application of the sequence model feasible in practice, regions are retrieved according to approximate similarity with an efficient model decoding algorithm. Re-ranking these regions according to the visual similarity obtained with the sequence model leads to highly accurate word spotting results. The method is evaluated on five benchmark datasets. In the segmentation-free query-by-example scenario where no annotated training data is available, the method outperforms all other methods that have been evaluated on any of these five benchmarks.

On the basis of the research status of image quality comprehensive assessment, a no-reference image quality comprehensive assessment function model is proposed in this paper. First, the image quality is classified as contrast, sharpness, and signal-to-noise ratio (SNR), and the interrelation of each assessment index is researched and analyzed; second, the weights in the comprehensive assessment model are studied when only contrast, sharpness, and SNR are changed. Finally, on the basis of studying each kind of distortion separately, and considering the different types of image distortion, we studied how to determine the weights of each index in the comprehensive image quality assessment. The results show that the no-reference image quality comprehensive assessment function model proposed in this paper can better fit human visual perception, and it has a good correlation with Difference Mean Opinion Score (DMOS). Correlation Coefficient (CC) reached 0.8331, Spearman Rank Order Correlation Coefficient (SROCC) reached 0.8206, Mean Absolute Error (MAE) was only 0.0920, Root Mean Square Error (RMSE) was only 0.1122, Outlier Ratio (OR) was only 0.0365. The method proposed in this paper can be applied to photoelectric measurement equipment television system and give an accurate and reliable quality assessment to no reference television images.

In order to improve the segmentation accuracy of plant lesion images, multi-channels segmentation algorithm of plant disease image was proposed based on linear discriminant analysis (LDA) method’s mapping and K-means’ clustering. Firstly, six color channels from RGB model and HSV model were obtained, and six channels of all pixels were laid out to six columns. Then one of these channels was regarded as label and the others were regarded as sample features. These data were grouped for linear discrimination analysis, and the mapping values of the other five channels were applied to the eigen vector space according to the first three big eigen values. Secondly, the mapping value was used as the input data for K-means and the points with minimum and maximum pixel values were used as the initial cluster center, which overcame the randomness for selecting the initial cluster center in K-means. And the segmented pixels were changed into background and foreground, so that the proposed segmentation method became the clustering of two classes for background and foreground. Finally, the experimental result showed that the segmentation effect of the proposed LDA mapping-based method is better than those of K-means, ExR and CIVE methods.

Binarization plays a crucial role in Optical Character Recognition (OCR) ancillary domains, such as recovery of degraded document images. In Document Image Analysis (DIA), selecting threshold is not trivial since it differs from one problem (dataset) to another. Instead of trying several different thresholds for one dataset to another, we consider noise inherency of document images in our proposed binarization scheme. The proposed stochastic architecture implements the local thresholding technique: Niblack’s binarization algorithm. We introduce a stochastic comparator circuit that works on unipolar stochastic numbers. Unlike the conventional stochastic circuit, it is simple and easy to deploy. We implemented it on the Xilinx Virtex6 XC6VLX760-2FF1760 FPGA platform and received encouraging experimental results. The complete set of results are available upon request. Besides, compared to conventional designs, the proposed stochastic implementation is better in terms of time complexity as well as fault-tolerant capacity.

Stereo vision and 3D reconstruction technologies are increasingly concerned in many fields. Stereo matching algorithm is the core of stereo vision and also a technical difficulty. A novel method based on super pixels is mentioned in this paper to reduce the calculating amount and the time. Stereo images from University of Tsukuba are used to test our method. The proposed method spends only 1% of the time spent by the conventional method. Through a two-step super-pixel matching optimization, it takes 6.72 s to match a picture, which is 12.96% of the pre-optimization.

Brain tumors have high morbidity and may lead to highly lethal cancer. In clinics, accurate segmentation of tumors is the means for diagnosis and determination of subsequent treatment options. Due to the irregularity and blurring of tumor boundaries, accurately segmenting the tumor lesions has received extensive attention in medical image analysis. In view of this situation, this paper proposed a brain tumor segmentation method based on generative adversarial networks (GANs). The GAN architecture consists of a densely connected three-dimensional (3D) U-Net used for segmentation and a classification network for discrimination, both of which use 3D convolutions to fuse multi-dimensional context information. The densely connected 3D U-Net model introduces a dense connection to accelerate network convergence, extracting more detailed information. The adversarial training makes the distribution of segmentation results closer to that of labeled data, which enables the network to segment some unexpected small tumor subregions. Alternately, train two networks and finally achieve a highly accurate classification of each voxel. The experiments conducted on BraTS2017 brain tumor MRI dataset show that the proposed method has higher accuracy in brain tumor segmentation.

In recent years, globalization has highlighted the importance of having machines that can truly provide customized communication for different languages. Majority of the research in the field focus on developing technologies for widely used languages such as English. In this study, we apply HMM-based speech synthesis (HTS) technology for Indonesian language. The proposed hybrid HTS-based framework, PFHTS-IDSS, uses phoneme and full-context lab to synthesize Indonesian with higher accuracy. First, we identify a list of Indonesian phonemes according to the initial-final structure of Chinese language. Based on this, we add zero-initials that match the Indonesian acoustic performance and HTS, which can make the synthesized speech natural and smooth. Second, we consider Indonesian phonemes as synthetic units to synthesize speech through the triphone and full-context lab. In addition, we design context properties of the full-context lab and the corresponding question set to train the acoustic model, which can eliminate machine sounds. Experimental results suggest that the accuracy of phoneme segmentation (PSA) and the naturalness of speech synthesis (SSN) are significantly improved via PFHTS-IDSS. Especially, the PSA of selecting phonemes as synthetic units reaches 88.3% and the corresponding SSN based on full-context lab is 4.1. The results demonstrated by PFHTS-IDSS presented in this paper may be used in multilingual free interactive system to promote better communication in terms of voice navigation, intelligent speaker and question-answering system.

Since the internal heat transfer is a complicated process, the heat pipe heat exchanger of the engine has not been fully understood yet, which is originated from its extreme complexity. In theoretical studies, the involvement of two-phase flow and phase change processes usually simplifies the processing very much, and the model built differs too much from the actual one, resulting in reduced simulation accuracy. In this study, the prediction model of heat transfer and heat resistance of the heat pipe intercooler is established based on artificial neural networks (ANNs). Then the performance of the heat pipe intercooler from heat transfer and heat resistance aspects is investigated. The average relative error between the heat transfer prediction model and the test value is 3.6%, and the average relative error between the resistance prediction model and the test value is 12.68%, which shows that the prediction model can predict the thermal performance of heat pipe intercooler more accurately. Finally, the proposed model is applied to optimize the structural parameters of the heat pipe intercooler, and the optimal parameters are obtained accordingly. These optimal design parameters can provide the basis for further investigation and development of the heat pipe intercooler in diverse applications.

In order to effectively improve the accuracy of Consumer Price Index (CPI) prediction so as to more truly reflect the overall level of the country’s macroeconomic situation, a CPI big data prediction method based on wavelet twin support vector machine (SVM) is proposed. First, the historical CPI data are decomposed into high-frequency part and low-frequency part by wavelet transform. Then a more advanced twin SVM is used to build a prediction model to obtain two kinds of prediction results. Finally, the wavelet reconstruction method is used to fuse the two kinds of prediction results to obtain the final CPI prediction results. The wavelet twin SVM model is used to fit and predict CPI index. Experimental results show that compared with the similar prediction methods, the proposed prediction method has higher fitting accuracy and smaller root mean square error.

Since the pneumatic artificial muscle is usually employed to actuate the robot, it is inevitable that it will collide with obstacles and/or other objects such that there will be impacts. The typical impacts include the axial and radial ones. This paper detects these two kinds of impact by a designed differential pressure measurement system, and achieves the goal of identifying them by the autocorrelations of their differential pressure signals in both static and dynamic processes, which are the two main work processes of the pneumatic artificial muscle. In detail, first we design an experiment scheme by connecting the pneumatic artificial muscle to the differential pressure sensor through two pressure tubes; then the axial and radial impact signals are acquired via the impact experiments under different work conditions (impact strength, internal pressure, load, and impact position); finally, the identification of the axial and radial impact signals are achieved based on the autocorrelation technique with a well-selected threshold. The experiments illustrate the effectiveness of the whole method.