Search

This paper plans to implement a novel detection model of maliciously encrypted internet protocol network flow using the deep structured concept. The major processing levels are (i) data collection, (ii) feature extraction, (iii) optimal feature selection, and (iv) detection. In the beginning, the standard dataset is taken from online databases. The deep convolutional neural network (DCNN) is introduced for the deep feature extraction process. The accurate features are chosen by the crossover decision-based krill herd algorithm (CD-KHA) which helps to minimize the training complexity of the deep structured architecture. These selected features are given to the hybridized deep learning with long short-term memory (LSTM) and deep neural network (DNN). Here, the structural design of the model is improved by the same CD-KHA. Through the comparison and analysis, the accuracy rate of the offered method shows higher performance than the other baseline approaches. [ABSTRACT FROM AUTHOR]

Monitoring and managing litter on the roadways is important not only for preserving the cleanliness and esthetic appeal of our cities but also for safeguarding the overall health and sanitary environment of citizens. With the development of artificial intelligence, it is now possible to design algorithms capable of autonomously assessing the sanitation status of roadways. In this paper, we propose a method for detecting garbage on roads as our solution to tackle the issue. The proposed model is a deep learning model with an attention mechanism introduced to detect garbage in real-time scenarios. Furthermore, the object recognition capability of the model is enhanced through transfer learning to mitigate the influence of irrelevant content during training. The refined network can detect rubbish on roads with higher efficiency than the existing models. Also, compared with other methods, it consumes less amount of data for training. The experimental results demonstrate the efficiency of our proposed model, with a performance boost of 7.62% over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning has enabled significant advancements in the classification of remote sensing images; however, the task of classifying images in remote sensing remains a formidable challenge because of the high item diversity and complexity that result from spatial and temporal combination and connection. The problem of insufficient differentiation of feature representations generated by deep learning remains, which is mostly due to the similarity and variety of inter-class and intra-class images, respectively. This paper introduces a novel hexagonal network architecture called DenseNet-169, which is based on end-to-end convolutional methods (Bi-LSTM and RNN model) known as CRLSTM-Hexnet. The proposed model comprises three distinct components: (1) a module for extracting features, (2) a feature selection module utilizing the Harris Hawk optimization (HHO) algorithm, and (3) a sub-network based on LSTM and RNN, incorporating a class attention module learning layer. Positive quantitative and qualitative findings from experiments on the RSI-CB256 multi-label dataset confirm the efficacy of our model. [ABSTRACT FROM AUTHOR]

Retail demand forecasting is a highly intricate and multilevel problem as it may include numerous products, under multiple categories, and potentially sold in many different stores. Forecasts may also process products in isolation or collectively so as to detect mutual correlations. In technical terms, retail demand forecasting may be broken down to a multivariate time series forecasting problem where the time axis is prevalent and introduces added complexity which necessitates proper usage of advanced methodologies with machine/deep learning backgrounds. Popular boosting regressors, such as XGBoost and LightGBM, are excellent machine learning candidates with extensive bibliographic backgrounds covering multiple scientific fields and applications including generic multivariate time series forecasts. The Temporal Convolutional Network and the Temporal Fusion Transformer are recently proposed deep neural network architectures that found success in specific multivariate scenarios but are yet to be tested in a variety of related fields such as retail demand forecasting. Therefore, within this paper, these novel in-the-field models are compared to the aforementioned boosting approaches alongside popular statistical univariate methods, namely Exponential Smoothing and SARIMA. To properly compare the selected models and attempt to generalize their usability, two separate datasets are analyzed and forecasted; an item sales dataset with 500 time series and a category sales dataset with 540 time series. The findings suggest that the deep learning solutions are the better predictors, with the Transformer model surpassing the Boosting solutions by up to 16.8% sMAPE decrease and the statistical approaches by up to 28.6% decrease, further substantiating the notion that deep learning techniques are exceptionally promising in handling large-scale, non-linear and outlier data whilst suggesting that retail demand forecasting does benefit from multivariate approaches and the application of advanced machine learning methods. [ABSTRACT FROM AUTHOR]

The price of carbon emission rights in the market fluctuates greatly due to various factors from economy, finance, and climate. For an enterprise that needs to conduct carbon trading activities, it is extremely necessary to fully grasp the price of carbon trading in the future period. Thus in this paper, a deep neural network-based assistive decision model for financial risk prediction in carbon trading market is proposed for this purpose. Specifically, the dynamic risk spillover effects of domestic and international carbon trading markets are studied, and a frontier time-varying model is utilized to measure the risk spillover effects. Then, the deep neural network is used for quantitative research and to construct an intelligent decision scheme that outputs financial risk prediction results. Four perspectives, energy price, climate environment, carbon market price, and macroeconomics, are selected as the input to analyze the influence factors of carbon emission rights price. Finally, several linear regression models are adopted as the baseline methods for comparison, and experimental results show that the proposed method can achieve better prediction performance compared with baseline methods. [ABSTRACT FROM AUTHOR]

Several hardware Trojan (HT) detection techniques are available today to ensure the security of hardware systems. However, the existing pre-silicon HT detection techniques have problems such as difficulties in capturing HT path features and poor applicability. To address these challenges, this paper proposes a gate-level HT detection scheme based on a deep learning model. We parse the circuit gate-level netlist and develop an algorithm to extract circuit path sentences based on the signal propagation rule. Path sentences consisting of gate names are extracted as experimental datasets. We apply the theory of natural language processing (NLP) to the task of HT detection and use three neural networks to filter the length of path sentences. Then, based on the deep learning model text convolutional neural network (TextCNN), we propose PS-TextCNN for HT detection. Our approach is verified on seven benchmark circuits of the RS232-series and eight benchmark circuits of the s-series. We achieve an average true positive rate (TPR) of 88.9%. The TPR of the RS232-series reaches a high score of 99.5%. The TPR of the s-series is 79.5%, which is significantly higher than that of the existing gate-level HT detection techniques. [ABSTRACT FROM AUTHOR]

Deep neural network has made surprising achievements in natural language processing, image pattern classification recognition, and other domains in the last few years. It is still tough to apply to hardware-constrained or mobile equipment because of the huge number of parameters, high storage as well as computing costs. In this paper, a new sparse iteration neural network architecture is proposed. First, the pruning method is used to compress the model size and make the network sparse. Then the architecture is iterated on the sparse network model, and the network performance is improved without adding additional parameters. Finally, the hybrid deep learning model was carried out on CV tasks and NLP tasks on ANN, CNN, and Transformer. Compared with the sparse network architecture, we finally found that the accuracy of the MINST, CIFAR10, PASCAL VOC 2012, and SQuAD datasets is improved by 0.47%, 0.64%, 3.75%, and 15.06%, respectively. [ABSTRACT FROM AUTHOR]

Malware developers often employ code obfuscation techniques to conceal their malicious functionality, making it challenging to detect and analyze such software. While various de-obfuscation techniques exist, the majority of them require prior knowledge of the obfuscation tools and techniques in use. Identifying the specific obfuscation tools or algorithms applied to the obfuscated code is thus of vital importance, which, however, typically demands in-depth expert knowledge and substantial efforts. Therefore, this paper presents DeObA, a deep learning (DL) driven approach for the precise and efficient detection of obfuscation algorithms on the fine-grained function-level code snippets. To comprehensively capture unique patterns or features of different obfuscation algorithms from code, DeObA works on multiple distinct code views, encompassing token sequences, abstract syntax trees (AST) and program dependency graphs (PDG), which will reflect the code's lexical morphology, syntactic and structural aspects. After individually collecting obfuscation-indicative features with well-matched DL encoder from each code view, a self-attention-based fusion strategy is performed on these features to produce an integrated, dense, yet feature-rich vector. This vector is then fed into a softmax classification layer for prediction. Due to the lack of a moderately sized dataset, a large obfuscation corpus is curated with 7 different obfuscation tools and a total of 12 obfuscation algorithms on 39,070 C/C + + functions. The experimental evaluations conducted on the dataset exhibit a distinguished detection performance of DeObA, which achieve accuracy rates of 99.90% and 99.19% on the obfuscation tool detection and obfuscation algorithm detection tasks, respectively. The ablation study also confirms the active role of considering multiple distinct code views and the effectiveness of the designed self-attention-based fusion strategy. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Variable selection is one of the most important contents of machine learning research and a large number of variable selection methods have been proposed at present. From deep learning perspective, we propose a new variable selection method based on multi-layer artificial neural networks in this paper. The method propagates errors gained form a trained network model through the network from output layer to input layer and the values gained by input layer give information about the relative contribution. The variables with big contribution value are selected, which we call neural inverse propagation (NIP). Specifically, after training a neural network, the gained errors between the actual network outputs and the desired outputs go through the network from top to down and arrive at the input layer. The absolute values gained by input units provide information about the relative importance (contribution) of input units, which is that the larger the value is, the more important the corresponding input variable is. We remove k variables corresponding to the first k minimum absolute value gained by input units to the predictive variables, to perform variable selection. The efficiency of the proposed method is illustrated through its application to classification and regression tasks on a number of synthetic datasets and a real-world image classification dataset. [ABSTRACT FROM AUTHOR]

Recent advances in speaker embeddings promote a great development of speaker diarization. However, determining 'who spoke when' in the meeting scenarios is still challenging due to similar speaker voices and unknown speaker quantity. In this paper, this research proposes enhanced discriminative features for speaker diarization, including discriminative speaker-specific features based on Siamese networks, and a speaker re-verification method. With Siamese architecture, SiamTDNN, this research first explores latent representations which is capable of modeling intra-class and inter-class differences between speakers, by training with audio pairs. Then, the re-verification method is introduced with a local-global strategy to identify speakers in a multi-person talking scene. Our method provides a novel speaker embedding with enhanced discriminative power for disambiguated speakers and achieves an elevated upper bound on the number of speakers. The proposed speaker embedding achieved an EER of 1.1% and a minDCF of 0.1192 on VoxCeleb1 for the speaker verification task. Extensive experiments on AiShell-4, ICSI, AMI and VoxConverse demonstrate the effectiveness of the proposed method with an average DER reduction of 3% and an RTF of 0.0792. [ABSTRACT FROM AUTHOR]

This paper aims to propose an improved image classification model to reduce the cost of model construction. Aiming at the problem that network training usually requires the support of a large number of labeled samples, an image classification model based on semi-supervised deep learning is proposed, which uses labeled samples to guide the network to learn unlabeled samples. A convolutional neural network model for simultaneous processing of labeled and unlabeled data is constructed. The tagged data is used to train the Softmax classifier and provide the initial K-means clustering center for the untagged data. The nonsubsampling contourlet layer is used to replace the first convolutional layer of the full convolutional neural network to extract multi-scale depth features, and the nonsubsampling contourlet full convolutional neural network is constructed. The network can extract multi-scale information of the images to be classified, and extract more discriminative deep image features. In addition, the parameters of the nonsubsampled contourlet layers are pre-set and do not require network training. The proposed method has higher classification accuracy than the contrast method on polarimetric SAR images using the nonsubsampled contourlet full convolutional neural network. [ABSTRACT FROM AUTHOR]

Rapid development of artificial intelligence techniques significantly promotes important medical imaging applications such as disease diagnosis, medical image analysis and cross-modality synthesis. It is valuable to synthesize Computed Tomography (CT) scans of human brains from Magnetic Resonance Imaging (MRI) scans because CT images contain particular information for diseases such as malignant tumors, cerebrovascular malformations and aneurysms. Although there has been many studies trying to apply machine learning methods (e.g., fully convolutional neural networks and generative adversarial networks) to predict CT images based on MRI, there are still opportunities to increase the quality of synthesized CT images using the latest machine learning algorithms. In this study, we aim to synthesize high-credibility human brain CT images from MRI images using machine learning approaches. We build a dataset of both CT and MRI images of 41 patients from The Cancer Imaging Archive. A data pre-processing pipeline is designed to guarantee that the processed images are suitable as inputs to machine learning algorithms. The pipeline includes (1) pairing MRI and CT scans according to a certain time interval between CT and MRI exams of the same patient, (2) registering all MRI images to a standard MRI template, (3) registering all CT images to paired MRI images, (4) intensity normalization and (5) extracting 2D slices from 3D CT and MRI volumes. Three deep neural networks with encoder–decoder structure are selected and implemented including U-Net, U-Net++ and pix2pix to synthesize human brain CT images from MRI images. Experimental results illustrate that U-Net++ shows better performance than U-Net and pix2pix in synthesizing CT images from MRI by achieving a Mean Squared Error of 0.025, a Mean Absolute Error of 0.082 and a Peak Signal-to-Noise Ratio of 67.90, respectively. The trained machine learning models from this work can be applied in future human brain CT image prediction where CT images are absent and MRI images are available for specific patients, thereby supporting disease diagnosis based on CT images. [ABSTRACT FROM AUTHOR]