Review Sentiment Orientation Analysis based on Deep Learning

In recent years, with the development of the Internet of Things (IoT) technology, a large amount of data can be captured from sensors for real-time analysis. By monitoring the traffic video data from the IoT, we can detect the anomalies that may occur and evaluate the security. However, the number of traffic anomalies is extremely limited, so there is a severe over-fitting problem when using traditional deep learning methods. In order to solve the problem above, we propose a similarity metric Convolutional Neural Network (CNN) based on a channel attention model for traffic anomaly detection task. The method mainly includes (1) A Siamese network with a hierarchical attention model by word embedding so that it can selectively measure similarities between anomalies and the templates. (2) A deep transfer learning method can automatically annotate an unlabeled set while fine-tuning the network. (3) A background modeling method combining spatial and temporal information for anomaly extraction. Experiments show that the proposed method is three percentage points higher than deep convolutional generative adversarial network (DCGAN) and five percentage points higher than AutoEncoder on the accuracy. No more time consumption is needed for the annotation process. The extracted candidates can be classified correctly through the proposed method.

Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit

Breast cancer is the most prevalent cancer globally and presents a significant threat to human health. The low survival rate for advanced stages highlights the importance of early and accurate diagnosis. Pathology images, providing insights into cancer's cellular aggressiveness, are crucial for breast cancer diagnosis. Advances in deep learning have transformed automated medical image diagnosis. However, traditional deep learning methods, reliant on large labeled datasets, face challenges with the typically small size of medical image datasets. To overcome this, our study combines deep transfer learning (DTL) with convolutional neural networks(CNN). We utilize and enhance a ResNet50 model pretrained on a large dataset. Additionally, we apply four different deep transfer learning methods to feature extraction and classification of the BreakHis dataset, aiming to determine if breast cancer is benign or malignant. Ultimately, our system achieved the best average accuracy rates under four different magnifications: 98.57%, 96.83%, 97.76%, and 97.16%. These results demonstrate the accuracy and potential of deep transfer learning in classifying breast cancer histopathological images and its promising application in tumor prediction.

Video application is a research hotspot in cooperative vehicle-infrastructure systems (CVIS) which is greatly related to traffic safety and the quality of user experience. Dealing with large datasets of feedback from complex environments is a challenge when using traditional video application approaches. However, the in-depth structure of deep learning has the ability to deal with high-dimensional data sets, which shows better performance in video application problems. Therefore, the research value and significance of video applications over CVIS can be better reflected through deep learning. Firstly, the research status of traditional video application methods and deep learning methods over CVIS were introduced; the existing video application methods based on deep learning were classified according to generative and discriminative deep architecture. Then, we summarized the main methods of deep learning and deep reinforcement learning algorithms for video applications over CVIS, and made a comparative study of their performances. Finally, the challenges and development trends of deep learning in the field were explored and discussed.

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.

With the rapid development of deep learning techniques, the applications have become increasingly widespread in various domains. However, traditional deep learning methods are often referred to as "black box" models with low interpretability of their results, posing challenges for their application in certain critical domains. In this study, we propose a comprehensive method for the interpretability analysis of sentiment models. The proposed method encompasses two main aspects: attention-based analysis and external knowledge integration. First, we train the model within sentiment classification and generation tasks to capture attention scores from multiple perspectives. This multi-angle approach reduces bias and provides a more comprehensive understanding of the underlying sentiment. Second, we incorporate an external knowledge base to improve evidence extraction. By leveraging character scores, we retrieve complete sentiment evidence phrases, addressing the challenge of incomplete evidence extraction in Chinese texts. Experimental results on a sentiment interpretability evaluation dataset demonstrate the effectiveness of our method. We observe a notable increase in accuracy by 1.3%, Macro-F1 by 13%, and MAP by 23%. Overall, our approach offers a robust solution for enhancing the interpretability of sentiment models by combining attention-based analysis and the integration of external knowledge.

Electronics-rich analog systems are difficult to diagnose owing to their complex working mechanisms and the variability of the working environment. In recent years, deep learning has been gradually applied to the field of circuit system fault diagnosis because of its strong ability to mine the intrinsic characteristics of signals. However, the traditional deep learning method requires a lot of effort to achieve satisfactory results due to large number of parameters, complex models, slow training speed, and large datasets. The key factors for the success of traditional deep learning methods are layer-by-layer processing, feature transformation within the model, and sufficient model complexity. Deep forest (DF) is a new feature learning model that inherits the three characteristics of the traditional deep learning model but is that it is not based on neural network. It has fewer hyperparameters, a simpler model, faster training speed. In this article, an improved DF algorithm based on nonparametric predictive inference (NPI) is proposed, named NPIDF, which can better deal with small sample data. In two typical analog filter circuit fault diagnosis experiments, it is proved that DF and NPIDF achieve good diagnosis effect, and NPIDF performance is better, showing a greater advantage in small sample data.

Complex industrial process data often exhibit nonlinear static and dynamic characteristics. Traditional deep learning methods such as stacked autoencoder (SAE) have excellent nonlinear static feature learning capabilities, but they ignore the dynamic correlation existing in process data. Feature learning based on manifold learning using neighborhood structure preserving has been widely used in industrial dynamic process monitoring. However, most of the manifold learning methods extract linear features, and complex nonlinearities in process data are ignored. Therefore, a novel spatiotemporal neighborhood preserving stack autoencoder (STNP-SAE) is proposed to simultaneously learn deep nonlinear static and dynamic features of process data in this article. By constructing the spatial and temporal adjacent graphs, STNP-SAE can capture the spatiotemporal neighborhood structure information of process data during the feature learning process. Then, STNP-SAE is used to construct a soft sensor framework for quality prediction. The prediction performance of the proposed method is validated on a practical industrial process.

Aiming at the problem that traditional deep learning methods have low detection rate of hidden attacks when processing high-dimensional data, an intrusion detection model based on recurrent neural network is proposed. Use the Borderline-Smote algorithm to oversample the data set, On the basis of LSTM, double-layer attention mechanism is introduced to extract the main feature information through byte and sequence dimensions to generate a more accurate feature representation. Finally, the softmax classifier is used to obtain the classification results. Use UNSW-NB15 data set as the experimental data, the experimental results show that this model is compared with the similar deep learning detection model has higher accuracy and lower the rate of false positives.

Cross-modal multiscale multi-instance learning for long-term ECG classification

Multiscale attentional residual neural network framework for remaining useful life prediction of bearings

In recent years, fatigue driving has become the main cause of traffic accidents, leading to increased attention towards fatigue detection systems. However, the pooling and strided convolutional operations in fatigue detection algorithm based on traditional deep learning methods may led to the loss of some useful information. This paper proposed a novel -shaped convolutional network ( ) aiming to address this issue. Unlike traditional network structures, incorporates the operations of upsampling features and concatenating high- and low-level features, enabling full utilization of useful information. Moreover, considering that the fatigue state is a mental state involving temporal evolution, we proposed the novel long short-term memory (LSTM)- -shaped convolutional network (LSTM- ), a parallel structure composed of LSTM and for fatigue detection, where extracts time-invariant features with location information, and LSTM extracts long temporal dependencies. We compared LSTM- with six competing methods based on two datasets. Results showed that the proposed algorithm achieved higher classification accuracy than the other methods, with 94.25% on EEG data (binary classification) and 82.19% on EOG data (triple classification). Additionally, the proposed algorithm exhibits low computational cost, good training stability, and robustness against insufficient training. Therefore, it is promising for further implementation of fatigue online detection systems.

Research on green supply chain finance risk identification based on two-stage deep learning

Recently, machine learning, especially deep learning, has been a core algorithm to be widely used in many fields such as natural language processing, speech recognition, object recognition, and so on. At the same time, another trend is that more and more applications are moved to wearable and mobile devices. However, traditional deep learning methods such as convolutional neural network (CNN) and its variants consume a lot of memory resources. In this case, these powerful deep learning methods are difficult to apply on mobile memory-limited platforms. In order to solve this problem, we present a novel memory-management strategy called mmCNN in this paper. With the help of this method, we can easily deploy a trained large-size CNN on any memory size platform such as GPU, FPGA, or memory-limited mobile devices. In our experiments, we run a feed-forward CNN process in some extremely small memory sizes (as low as 5 MB) on a GPU platform. The result shows that our method saves more than 98% memory compared to a traditional CNN algorithm and further saves more than 90% compared to the state-of-the-art related work “vDNNs” (virtualized deep neural networks). Our work in this paper improves the computing scalability of lightweight applications and breaks the memory bottleneck of using deep learning method on memory-limited devices.

Calibration performed by a robotic manipulator is crucial in the field of industrial intelligent production, as it ensures precise and accurate measurements. In this paper, we present a new method for addressing the hand-to-eye calibration problem using deep reinforcement learning. Our proposed algorithm utilizes an actor-critic framework and incorporates neurodynamics adaptive reward and action functions, which allows for better convergence, reduces the dependence on the initial value, and overcomes the local convergence issues of traditional deep reinforcement learning method. Additionally, we introduce a step-wise mechanism under the guidance of the attention mechanism, and zero stability to handle the complexity of the calibration task in challenging environments. A number of experiments were conducted to demonstrate the validity of the proposed algorithm. The experimental results show that our proposed algorithm can achieve a nearly 100% success rate after training phase. Additionally, we compared our proposed algorithm with other widely used methods, such as deterministic deep policy gradient (DDPG) and soft actor-critic (SAC) to further demonstrate its effectiveness.