Search

An increasing amount of malicious code causes harm on the internet by threatening user privacy as one of the primary sources of network security vulnerabilities. The detection of malicious code is becoming increasingly crucial, and current methods of detection require much improvement. This paper proposes a method to advance the detection of malicious code using convolutional neural networks (CNNs) and intelligence algorithm. The CNNs are used to identify and classify grayscale images converted from executable files of malicious code. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is then employed to deal with the data imbalance of malware families. A series of experiments are designed for malware image data from Vision Research Lab. The experimental results demonstrate that the proposed method is effective, maintaining higher accuracy and less loss. • A technique for converting a malware binary to an image was introduced. • In this paper, a method based on CNN is used to identify and classify the malicious codes. • An effective data equilibrium approach based on the NSGA-II was designed. • The proposed method was demonstrated through the extensive experiments. [ABSTRACT FROM AUTHOR]

In this paper an unsupervised clustering algorithm is developed for acoustic data in the context of speech recognition tasks. One of the key features of the algorithm is scalability to large data sets. Specifically, given the unlabeled training and test sets, the class-labels of the utterances are obtained in an automatic manner. The extracted labels may correspond to the speakers in the speech corpus if the data is relatively clean. The proposed scheme is attractive from an industrial perspective as it alleviates the need to store the speaker-labels manually, saving considerable amount of human efforts and expenses. The core of the algorithm comprises a three-stage architecture that processes the input data one after the other, while each stage is designed to perform a well-defined and specific task. In more detail, the first-pass involves a bottom-up clustering mechanism, the second-pass comprises a cluster splitting operation and the third-pass consists of a cluster refining process. Each of the stages allows for data parallelization using multiple CPUs that leads to faster computation. Two alternative forms of the algorithm are presented – the first considers Gaussian distributions and the other i-Vectors – to facilitate the clustering. Although the algorithm may find applications in various realms of speech recognition, in this paper, the effectiveness of the schemes are evaluated by means of speaker adaptive training (SAT) and speaker-aware training of DNN-HMM acoustic models. In particular, experiments are conducted on the Switchboard task to extract the speaker-labels for the utterances in the training and test sets. It is shown that the SAT DNN-HMM trained using the Gaussian based scheme yields a 7.2% relative improvement in the ASR accuracy over the speaker independent DNN-HMM, whereas the i-Vector approach provides an additional improvement, amounting to a 10.8% relative gain overall. The standard SAT DNN-HMM developed using the ground-truth speaker-labels is found to be only 2.7% relative better than the proposed scheme. Similar observation is made as with speaker-aware training. The analysis of computational complexity, conducted stage by stage, demonstrates the scalability of the proposed algorithms. [ABSTRACT FROM AUTHOR]

To overcome challenges in multiple-object tracking (MOT) tasks, recent algorithms use interaction cues alongside motion and appearance features. These algorithms use graph neural networks or transformers to extract interaction features that lead to high computation costs. In this paper, a novel interaction cue based on geometric features is presented aiming to detect occlusion and reidentify lost targets with low computational costs. Moreover, in the majority of algorithms, camera motion is considered negligible, which is a strong assumption that is not always true and can lead to identity (ID) switching or mismatching of targets. In this paper, a method for measuring camera motion is presented that efficiently reduces its effect on tracking. The proposed algorithm is evaluated on MOT17 and MOT20 datasets and achieves state-of-the-art performance on MOT17 with comparable results on MOT20. The code is also publicly available. 1 1 https://github.com/mhnasseri/for_tracking. • Cascade association based on the detection score. • A new similarity metric that considers detection's size. • A novel interaction model for occlusion handling and target re-identification. • A novel algorithm for estimating camera motion and removing it. • State-of-the-art results on MOT17 and comparable results on MOT20. [ABSTRACT FROM AUTHOR]

The unavailability and variability of training samples are the two essential concerns in the training of deep neural network models for image classification. For automated image monitoring systems, these problems are difficult when training a model through supervised learning methods because of the time and effort required. This paper proposes an adaptive solution to this problem by applying online semi-supervised learning to an automated insect pest monitoring system. The method used includes unsupervised pseudo-labelling of insect images and the training of semi-supervised classifier models for insect image recognition. The pseudo-labelling algorithm includes three major components: image labelling, label reconfirmation, and sample cleaning. Experiments were conducted on two unlabelled 1-year insect image datasets to evaluate the efficacy of the proposed method. It was found that the pseudo-labelling algorithm could achieve accuracy up to 0.963, hence enabling automated training data collection. The temporal improvement of the insect recognition performance by including new training data to retrain the classifier model was comparable in performance to the supervised learning approach as evaluated by cluster density, silhouette score, and F 1 -score. The proposed method was also able to automatically collect quality samples and train models regardless of the complexity of the images, making it a good alternative to replace laborious supervised learning. The proposed method can prevent contamination of a training dataset when images from new locations are collected. The presented techniques may also be used in other continuous learning applications that require automated training data collection and online model update. [Display omitted] • Semi-supervised learning method for an insect pest monitoring system was proposed. • Accuracy of the pseudo-labelling algorithm can be as high as 0.963. • Characteristics and variation of training data in classifier models were assessed. • Performance of classifier models can be improved through semi-supervised learning. • Techniques can be used for automated training data collection and model update. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have recently been successful in many applications and have become a popular approach for speech recognition. Training a DNN model for speech recognition is computationally expensive due to the model large number of parameters. Pre-training improves DNN modeling. However, DNN learning is challenging if pre-training is inefficient. This paper introduces a new framework for pre-training that utilizes label information in lower layers (layers near input) for better recognition. The proposed pre-training method dynamically inserts discriminative information not only in the last layer but also in other layers. In this algorithm, the lower layers achieve more generative information while the higher layers achieve more discriminative information. In addition, this method uses speaker information by employing the Subspace Gaussian Mixture Model (SGMM), which improves recognition accuracy. Experimental results on TIMIT, MNIST, Switchboard, and English Broadcast News datasets show that this approach significantly outperforms current state-of-the-art methods such as the Deep Belief Network and the Deep Boltzmann Machine. Moreover, the proposed algorithm has minimal memory requirements. [ABSTRACT FROM AUTHOR]

Abstract: A great many computational algorithms developed over the past half-century have been motivated or suggested by biological systems or processes, the most well-known being the artificial neural networks. These algorithms are commonly grouped together under the terms soft or natural computing. A property shared by most natural computing algorithms is that they allow exploration of, or learning from, data. This property has proved extremely valuable in the solution of many diverse problems in science and engineering. The current paper is intended as a tutorial overview of the basic theory of some of the most common methods of natural computing as they are applied in the context of mechanical systems research. The application of some of the main algorithms is illustrated using case studies. The paper also attempts to give some indication as to which of the algorithms emerging now from the machine learning community are likely to be important for mechanical systems research in the future. [Copyright &y& Elsevier]

Graphical abstract Highlights • A feature visualization for CNNs method is exploited to improve co-segmentation. • Visualization is used as an auxiliary information to discriminate salient regions. • The visualization information is used as an extra energy term in the cost function. • Region occlusion sensitivity is introduced for feature visualization. • An adaptive strategy is designed to detect correct foreground/background regions. This paper addresses the co-segmentation problem using feature visualization for CNNs. Visualization is exploited as an auxiliary information to discriminate salient image regions (dubbed as “heat-regions”) from non-salient ones. Region occlusion sensitivity is proposed for feature visualization. The co-segmentation problem is formulated via a convex quadratic optimization which is initialized by the heat-regions. The information obtained through the visualization is considered as an extra energy term in the cost function. The results of the visualization demonstrate that there exist some heat-regions which are not productive in the co-segmentation. To detect helpful regions among them, an adaptive strategy in the form of an iterative algorithm is proposed according to the consistency among all images. Comparison experiments conducted on two benchmark datasets, iCoseg and MSRC, illustrate the superior performance of the proposed approach over state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Conventional model-based or statistical analysis methods for functional MRI (fMRI) are easy to implement, and are effective in analyzing data with simple paradigms. However, they are not applicable in situations in which patterns of neural response are complicated and when fMRI response is unknown. In this paper the “neural gas” network is adapted and rigourosly studied for analyzing fMRI data. The algorithm supports spatial connectivity aiding in the identification of activation sites in functional brain imaging. A comparison of this new method with Kohonen’s self-organizing map and with a fuzzy clustering scheme based on deterministic annealing is done in a systematic fMRI study showing comparative quantitative evaluations. The most important findings in this paper are: (1) both “neural gas” and the fuzzy clustering technique outperform Kohonen’s map in terms of identifying signal components with high correlation to the fMRI stimulus, (2) the “neural gas” outperforms the two other methods with respect to the quantization error, and (3) Kohonen’s map outperforms the two other methods in terms of computational expense. The applicability of the new algorithm is demonstrated on experimental data. [Copyright &y& Elsevier]

• Rethinking the PASCAL-VOC and MS-COCO dataset for small object detection. • There are different labeling errors in these two benchmarks by visual analysis. • Building several specific datasets to analyze small object detection. • Data quality is another factor that affects the performance of small object detection. The data and the algorithm are critical to deep learning-based small object detectors. In this paper, we rethink the PASCAL-VOC and MS-COCO dataset for small object detection. By visual analysis of the original annotations, we find that there are different labeling errors in these two datasets. To solve these problems, we build specific datasets, including SDOD, Mini6K, Mini2022 and Mini6KClean. The experimental results of several typical algorithms (e.g. SSD, YOLOv5, Faster RCNN and Deformable DETR) on the datasets show that data labeling errors (such as missing labels, category label errors, inappropriate labels) are another factor that affects the detection performance of small objects. [ABSTRACT FROM AUTHOR]

In the field of human speech capturing systems, a fundamental role is played by the source localization algorithms. In this paper a Speaker Localization algorithm (SLOC) based on Deep Neural Networks (DNN) is evaluated and compared with state-of-the art approaches. The speaker position in the room under analysis is directly determined by the DNN, leading the proposed algorithm to be fully data-driven. Two different neural network architectures are investigated: the Multi Layer Perceptron (MLP) and Convolutional Neural Networks (CNN). GCC-PHAT (Generalized Cross Correlation-PHAse Transform) Patterns, computed from the audio signals captured by the microphone are used as input features for the DNN. In particular, a multi-room case study is dealt with, where the acoustic scene of each room is influenced by sounds emitted in the other rooms. The algorithm is tested by means of the home recorded DIRHA dataset, characterized by multiple wall and ceiling microphone signals for each room. In detail, the focus goes to speaker localization task in two distinct neighboring rooms. As term of comparison, two algorithms proposed in literature for the addressed applicative context are evaluated, the Crosspower Spectrum Phase Speaker Localization (CSP-SLOC) and the Steered Response Power using the Phase Transform speaker localization (SRP-SLOC). Besides providing an extensive analysis of the proposed method, the article shows how DNN-based algorithm significantly outperforms the state-of-the-art approaches evaluated on the DIRHA dataset, providing an average localization error, expressed in terms of Root Mean Square Error (RMSE), equal to 324 mm and 367 mm, respectively, for the Simulated and the Real subsets. [ABSTRACT FROM AUTHOR]

Stereo matching has been studied for many years and is still a challenge problem. The Markov Random Fields (MRF) model and the Conditional Random Fields (CRF) model based methods have achieved good performance recently. Based on these pioneer works, a deep conditional random fields based stereo matching algorithm is proposed in this paper, which draws a connection between the Convolutional Neural Network (CNN) and CRF. The object knowledge is used as a soft constraint, which can effectively improve the depth estimation accuracy. Moreover, we proposed a CNN potential function that learns the potentials of CRF in a CNN framework. The inference of the CRF model is formulated as a Recurrent Neural Network (RNN). A variety of experiments have been conducted on KITTI and Middlebury benchmark. The results show that the proposed algorithm can produce state-of-the-art results and outperform other MRF-based or CRF-based methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose forward and backward stochastic differential equations (FBSDEs) based deep neural network (DNN) learning algorithms for the solution of high dimensional quasi-linear parabolic partial differential equations (PDEs), which is related to the FBSDEs from the Pardoux-Peng theory. The algorithms rely on a learning process by minimizing the path-wise difference between two discrete stochastic processes, which are defined by the time discretization of the FBSDEs and the DNN representation of the PDE solution, respectively. The proposed algorithms are shown to generate DNN solution for a 100-dimensional Black–Scholes–Barenblatt equation, which is accurate in a finite region in the solution space, and has a convergence rate close to that of the Euler–Maruyama scheme used for discretizing the FBSDEs. • FBSDE deep neural network (DNN) with loss comparing two stochastic processes for the PDEs from Pardoux-Peng theory. • Strong 1/2 Convergence as the Euler-Maruyama method in solving a 100-dimensional Black-Scholes-Barenblatt equation. • Use of Richardson extrapolation for accuracy enhancement. • Multiscale DNN captures temporal high frequency content of the PDEs more accurately. [ABSTRACT FROM AUTHOR]

Convolution neural networks based methods can derive deep features from training images. However, one challenge is that the dimension of the extracted image features increases dramatically with more network layers. To solve this problem, this paper focuses on the study of dimension reduction. After using deep learning to extract image features, the PCA algorithm is used to achieve dimension reduction. Specifically, we first leverage deep convolutional neural network to extract image features. Then, we introduce and leverage PCA algorithm to achieve dimension reduction. Aiming at the problem that it is difficult to process high-dimensional sparse big data based on PCA algorithm. This paper optimizes the PCA algorithm. After image preprocessing, the feasibility of PCA algorithm for dimension reduction of image feature extraction by deep learning is verified by simulation experiments. The efficiency of the proposed algorithm is proved by comparing the performance of PCA algorithm before and after optimization. [ABSTRACT FROM AUTHOR]

Person re-identification(ReID) is an intelligent video surveillance technology that retrieves the same person from different cameras. This task is extremely challenging due to changes in person poses, different camera views, and occlusion. In recent years, person ReID based on deep learning technology has received widespread attention due to the rapid development and excellent performance of deep learning. In this paper, we first divide person ReID based on deep learning approaches into seven types, i.e., fused hand-crafted features deep model, representation learning model, metric learning model, part-based deep model, video-based model, GAN-based model, unsupervised model. Furthermore, we launched a brief overview of the seven types. Then, we introduce some examples of commonly used datasets, compare the performance of some algorithms on image and video datasets in recent years, and analyze the advantages and disadvantages of various methods. Finally, we summarize the possible future research directions of person ReID technology. • Dividing person ReID based on deep learning approaches into seven types. • Introducing some examples of commonly used datasets. • Comparing the performance of some algorithms on image and video datasets in recent years. • Analyzing the advantages and disadvantages of various methods. • Summarizing the possible future research directions of person ReID technology. [ABSTRACT FROM AUTHOR]

Abstract: This paper investigates failure in Carbon Fibre Reinforced Plastics CFRP using Acoustic Emission (AE). Signals have been collected and post-processed for various test configurations: tension, Compact Tension (CT), Compact Compression (CC), Double Cantilever Beam (DCB) and four-point bend End Notched Flexure (4-ENF). The signals are analysed with three different pattern recognition algorithms: k-means, Self Organising Map (SOM) combined with k-means and Competitive Neural Network (CNN). The SOM combined with k-means appears as the most effective of the three algorithms. The results from the clustering analysis follow patterns found in the peak frequencies distribution. A detailed study of the frequency content of each test is then performed and the classification of several failure modes is achieved. [Copyright &y& Elsevier]

Abstract: BackPropagation (BP) is the most famous learning algorithm for Artificial Neural Networks (ANN). BP has received intensive research efforts to exploit its parallelism in order to reduce the training time for complex problems. A modified version of BP based on matrix–matrix multiplication was proposed for parallel processing. In this paper, we present the implementation of Matrix BackPropagation (MBP) using scalar, vector, and matrix Instruction Set Architectures (ISAs). Besides this, we show that the performance of the MBP is improved by switching from scalar ISA to vector ISA. It is further improved by switching from vector ISA to matrix ISA. On a practical application, speech recognition, the speedup of training a neural network using unrolling scalar ISA over scalar ISA is 1.83. On eight parallel lanes, the speedups of using vector, unrolling vector, and matrix ISAs are respectively 10.33, 11.88, and 15.36, where the maximum theoretical speedup is 16. The results obtained show that the use of matrix ISA gives a performance close to optimal, because of reusing the loaded data, decreasing the loop overhead, and overlapping the memory operations with arithmetic operations. [Copyright &y& Elsevier]

Abstract: This paper describes the application of a collection of data mining methods to solve a calibration problem in a quantitative chemistry environment. Experimental data obtained from reactions which involve known concentrations of two or more components are used to calibrate a model that, later, will be used to predict the (unknown) concentrations of those components in a new reaction. This problem can be seen as a one, where the goal is to obtain good values for the variables to predict while minimizing the number of the input variables needed, taking a small subset of really significant ones. Initial approaches to the problem were principal components analysis and filtering combined with two prediction techniques: artificial neural networks and partial least squares regression. Finally, a parallel estimation of distribution algorithm was used to reduce the number of variables to be used for prediction, yielding the best models for all the considered problems. [Copyright &y& Elsevier]

This paper presents a new method for fault diagnosis using a newly developed method, support vector machine (SVM). First, the basic theory of the SVM is briefly reviewed. Next, a fast implementation algorithm is given. Then the method is applied for the fault diagnosis in sheet metal stamping processes. According to the tests on two different examples, one is a simple blanking and the other is a progressive operation, the new method is very effective. In both cases, its success rate is over 96.5%. In comparison, the success rate of the popular artificial neural network (ANN) is just 93.3%. In addition, the new method requires only few training samples, which is an attractive feature for shop floor applications. [Copyright &y& Elsevier]

Magnetorheological (MR) damper is one of the more promising new devices for vibration control of structures. External energy required by the adjustable fluid damper is minuscule while speed of its response is in the order of milliseconds. The MR damper is a semi-active control device and has been characterized by a set of non-linear differential equations which represent a forward model of the MR damper, i.e., the model can generate a force to a given displacement and applied voltage.This paper presents an inverse model of the MR damper, i.e., the model can predict the required voltage so that the MR damper can produce the desired force for the requirement of vibration control of structures. The inverse model has been constructed by using a multi-layer perceptron optimal neural network and system identification, which are Gauss–Newton-based Levenberg–Marquardt training algorithm, optimal brain surgeon strategy and autoregressive with exogenous variables (ARX) model. Based on the data from numerical simulation of the MR damper, the trained optimal neural networks can accurately predict voltage. If the inverse model is used in a control system, the semi-active vibration control can be implemented easily by using the semi-active MR damper. [Copyright &y& Elsevier]

This paper presents an intelligent system to locate human faces within images. The proposed system can handle facial pattern variations due to certain changes in pose, illumination, and expression, as well as existence of spectacles, facial-hair, and occlusion. The system consists of three modules: preprocessing, face-components extraction, and final decision-making. In the first module, image processing algorithms are performed on images captured by cameras. Face components are extracted in the second module. A fuzzy neural network-based algorithm is designed for this purpose. In the last module, a commonsense-knowledge base is used for final evaluation of the identified features and determination of the face locations. The performance of the system is evaluated by conducting experiments on seven large test sets. [Copyright &y& Elsevier]

This paper describes a method of extracting diagnostic rules from trained diagnostic feedforward neural nets that are constructed to recognise different mechanical faults using automated weight and structure learning algorithms. The rule extracting method is based on an interpretation that considers hidden neurons as partitions in the input space. An initial set of rules is then generated from the training data and the subspaces defined by the partitions. A procedure consisting of a number of algorithms is then used to simplify and reduce the set of initial rules step by step. To demonstrate and evaluate the rule extraction method, diagnostic rules for detecting a high-pressure air compressor''s (HPAC) suction and discharge valve faults were extracted from static measurements including temperatures and pressures of various stages of the compressor. [Copyright &y& Elsevier]

In this paper, we propose a methodology (in the form of a software package) for automatic extraction of the cancerous nuclei in lung pathological color images. We first segment the images using an unsupervised Hopfield artificial neural network classifier and we label the segmented image based on chromaticity features and histogram analysis of the RGB color space components of the raw image. Then, we fill the holes inside the extracted nuclei regions based on the maximum drawable circle algorithm. All corrected nuclei regions are then classified into normal and cancerous using diagnostic rules formulated with respect to the rules used by experimented pathologist. The proposed method provides quantitative results in diagnosing a lung pathological image set of 16 cases that are comparable to an expert’s diagnosis. [Copyright &y& Elsevier]

This paper describes a new methodology to identify multi-degree-of-freedom non-linear systems from the system''s operating data. The methodology includes a new non-linear model architecture which embeds feedforward neural networks to represent unknown non-linearities in a lumped parameter model, and a learning algorithm to train the embedded neural networks as well as the other model parameters to obtain model fidelity. Three simulated and experimental examples are used to validate the proposed methodology. [Copyright &y& Elsevier]

• We do not take end-to-end approach but utilize a neural network structure combined with multi-LSTM layer and fully connected layers, to encode the initial word-embedding sequence of a sentence to its meaningful sentence representation. Then the downstream classification is performed by KNN classifier. • We propose a novel label-oriented loss function, which takes the positive label-embedding and the negative labelembeddings into account. • We report attractive performances achieved on several sentiment and sentence classification datasets in our evaluation. Neural network methods which leverage word-embedding obtained from unsupervised learning models have been widely adopted in many natural language processing (NLP) tasks, including sentiment analysis and sentence classification. Existing sentence representation generation approaches which serve for classification tasks generally rely on complex deep neural networks but relatively simple loss functions, such as cross entropy loss function. These approaches cannot produce satisfactory separable sentence representations because the usage of cross entropy may ignore the sentiment and semantic information of the labels. To extract useful information from labels for improving the distinguishability of the obtained sentence representations, this paper proposes a label-oriented loss function. The proposed loss function takes advantage of the word-embeddings of labels to guide the production of meaningful sentence representations which serve for downstream classification tasks. Compared with existing end-to-end approaches, the evaluation experiments on several datasets illustrate that using the proposed loss function can achieve competitive and even better classification results. [ABSTRACT FROM AUTHOR]

Conventional face image generation using generative adversarial networks (GAN) is limited by the quality of generated images since generator and discriminator use the same backpropagation network. In this paper, we discuss algorithms that can improve the quality of generated images, that is, high-quality face image generation. In order to achieve stability of network, we replace MLP with convolutional neural network (CNN) and remove pooling layers. We conduct comprehensive experiments on LFW, CelebA datasets and experimental results show the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]