Parallel Convolutional Neural Network Research Articles

A hybrid machine learning model for sentiment analysis and satisfaction assessment with Turkish universities using Twitter data

Social media platforms, such as X (Twitter), contain enormous amounts of data, and collecting valuable information from that data assists in making more informed decisions. In recent years, governments and institutions have begun to explore the possibilities of utilizing social networks as a platform to supply and enhance the quality of their services. Consequently, there is an increased demand to estimate people’s satisfaction with Turkish Universities written in Turkish wherever it is challenging and requires more effort to cope with its rich morphological structure to perform a Sentiment Analysis task. This study proposes a Turkish text sentiment analysis methodology for estimating people’s satisfaction with Turkish Universities by employing nine conventional machine learning models, deep learning techniques, and BERT-based transformers upon an original manually annotated dataset consisting of 17,793 tweets in Turkish. An innovative hybrid architecture, named BERT-BiLSTM-CNN, integrates Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Long Short-Term Memory (BiLSTM), and a triple parallel Convolutional Neural Network (CNN) branch, achieving exceptional accuracy in sentiment analysis of Turkish tweets. During testing, the proposed architecture revealed an impressive accuracy rate of over 0.9101, an F1 Score of 0.8801, and a Receiver Operating Characteristic (ROC) of 0.9632 for analyzing sentiment, demonstrating that the model outperformed the state-of-the-art models, and it is capable of coping with the linguistic complexities of Turkish sentiment analysis. This work provides new insights into sentiment analysis by proposing a hybrid model that combines several computational methodologies to improve the understanding of attitudes.

Research on lung sound classification model based on dual-channel CNN-LSTM algorithm

ulmonary diseases have a significant impact on human health and life safety, and abnormalities in the lungs are a direct response to lung diseases. Establishing an effective lung sound classification model that can assist in diagnosis is of great significance for electronic auscultation.In addressing the issue of lung sound signal classification, this study introduces a deep learning classification model based on a dual-channel CNN-LSTM algorithm. Initially, Mel-scale Frequency Cepstral Coefficients (MFCC) are employed for feature extraction from the dataset, transforming lung sound signals into Mel spectrograms. On this foundation, a dual-channel algorithm classification model is constructed, with parallel Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) modules. The CNN module is designed to capture spatial dimension features of the input data, while the LSTM module focuses on temporal dimension features. These two feature sets are fused together, enabling the model to classify lung sounds and thereby assisting in diagnosing pulmonary diseases for healthcare practitioners. This experiment used the ICBHI2017 Challenge Lungs dataset and obtained 5054 pieces of data through data augmentation and sampling techniques.The results show that the accuracy, recall, and F1 score of this model reach 99.01%, 99.13%, and 0.9915, respectively, significantly superior to other models, highlighting its practical application value.

Breast Cancer Diagnosis Using YOLO-Based Multiscale Parallel CNN and Flattened Threshold Swish

In the field of biomedical imaging, the use of Convolutional Neural Networks (CNNs) has achieved impressive success. Additionally, the detection and pathological classification of breast masses creates significant challenges. Traditional mammogram screening, conducted by healthcare professionals, is often exhausting, costly, and prone to errors. To address these issues, this research proposes an end-to-end Computer-Aided Diagnosis (CAD) system utilizing the ‘You Only Look Once’ (YOLO) architecture. The proposed framework begins by enhancing digital mammograms using the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique. Then, features are extracted using the proposed CNN, leveraging multiscale parallel feature extraction capabilities while incorporating DenseNet and InceptionNet architectures. To combat the ‘dead neuron’ problem, the CNN architecture utilizes the ‘Flatten Threshold Swish’ (FTS) activation function. Additionally, the YOLO loss function has been enhanced to effectively handle lesion scale variation in mammograms. The proposed framework was thoroughly tested on two publicly available benchmarks: INbreast and CBIS-DDSM. It achieved an accuracy of 98.72% for breast cancer classification on the INbreast dataset and a mean Average Precision (mAP) of 91.15% for breast cancer detection on the CBIS-DDSM. The proposed CNN architecture utilized only 11.33 million parameters for training. These results highlight the proposed framework’s ability to revolutionize vision-based breast cancer diagnosis.

PCTDepth: Exploiting Parallel CNNs and Transformer via Dual Attention for Monocular Depth Estimation

Monocular depth estimation (MDE) has made great progress with the development of convolutional neural networks (CNNs). However, these approaches suffer from essential shortsightedness due to the utilization of insufficient feature-based reasoning. To this end, we propose an effective parallel CNNs and Transformer model for MDE via dual attention (PCTDepth). Specifically, we use two stream backbones to extract features, where ResNet and Swin Transformer are utilized to obtain local detail features and global long-range dependencies, respectively. Furthermore, a hierarchical fusion module (HFM) is designed to actively exchange beneficial information for the complementation of each representation during the intermediate fusion. Finally, a dual attention module is incorporated for each fused feature in the decoder stage to improve the accuracy of the model by enhancing inter-channel correlations and focusing on relevant spatial locations. Comprehensive experiments on the KITTI dataset demonstrate that the proposed model consistently outperforms the other state-of-the-art methods.

Image Forgery Detection Based on Parallel Convolutional Neural Networks

Abstract— Due to the availability of deep networks, progress has been made in the field of image recognition. Images and videos are spreading very conveniently and with the availability of strong editing tools the tampering of digital content become easy. To detect such scams, we proposed techniques. In our paper, we proposed two important aspects of employing deep convolutional neural networks to image forgery detection. We first explore and examine different preprocessing method along with convolutional neural networks (CNN) architecture. Later we evaluated the different transfer learning for pre-trained ImageNet(via-fine-tuning) and implement it over our dataset CASIA V2.0. So, it covers the pre-processing techniques with basic CNN model and later see the powerful effect of the transfer learning models. Keywords— image tampering, convolution neural network (CNN), error level analysis (ELA), transfer learning, sharpening filter, fine-tuning

A joint image super‐resolution network for multiple degradations removal via complementary transformer and convolutional neural network

AbstractWhile recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) and vision transformers in single‐image super‐resolution (SISR), the degradation assumptions are simple and usually bicubic downsampling. Thus, their performances will drop dramatically when the actual degradation does not match this assumption, and they lack the capability to handle multiple degradations (e.g. Gaussian noise, bicubic downsizing, and salt & pepper noise). To address the issues, in this paper, the authors propose a joint SR model (JIRSR) that can effectively handle multiple degradations in a single model. Specifically, the authors build the parallel Transformer and CNN branches that complement each other through bidirectional feature fusion. Moreover, the authors also adopt a random permutation of different kinds of noise and resizing operations to build the training datasets. Extensive experiments on classical SR, denoising, and multiple degradation removal demonstrate that the authors’ JIRSR achieves state‐of‐the‐art (SOTA) performance on public benchmarks. Concretely, the authors’ JIRSR outperforms the second‐best model by 0.23 to 0.74 dB for multiple degradations removal and is 0.20 to 0.36 dB higher than the SOTA methods on the Urban100 dataset under the ×4 SR task.

An ultra-short-term forecasting method for multivariate loads of user-level integrated energy systems in a microscopic perspective: based on multi-energy spatio-temporal coupling and dual-attention mechanism

An ultra-short-term multivariate load forecasting method under a microscopic perspective is proposed to address the characteristics of user-level integrated energy systems (UIES), which are small in scale and have large load fluctuations. Firstly, the spatio-temporal correlation of users’ energy use behavior within the UIES is analyzed, and a multivariate load input feature set in the form of a class image is constructed based on the various types of load units. Secondly, in order to maintain the feature independence and temporal integrity of each load during the feature extraction process, a deep neural network architecture with spatio-temporal coupling characteristics is designed. Among them, the multi-channel parallel convolutional neural network (MCNN) performs independent spatial feature extraction of the 2D load component pixel images at each moment in time, and feature fusion of various types of load features in high dimensional space. A bidirectional long short-term memory network (BiLSTM) is used as a feature sharing layer to perform temporal feature extraction on the fused load sequences. In addition, a spatial attention layer and a temporal attention layer are designed in this paper for the original input load pixel images and the fused load sequences, respectively, so that the model can better capture the important information. Finally, a multi-task learning approach based on the hard sharing mechanism achieves joint prediction of each load. The measured load data of a UIES is analyzed as an example to verify the superiority of the method proposed in this paper.

Stochastic Computing Convolutional Neural Network Architecture Reinvented for Highly Efficient Artificial Intelligence Workload on Field-Programmable Gate Array.

Stochastic computing (SC) has a substantial amount of study on application-specific integrated circuit (ASIC) design for artificial intelligence (AI) edge computing, especially the convolutional neural network (CNN) algorithm. However, SC has little to no optimization on field-programmable gate array (FPGA). Scaling up the ASIC logic without FPGA-oriented designs is inefficient, while aggregating thousands of bitstreams is still challenging in the conventional SC. This research has reinvented several FPGA-efficient 8-bit SC CNN computing architectures, i.e., SC multiplexer multiply-accumulate, multiply-accumulate function generator, and binary rectified linear unit, and successfully scaled and implemented a fully parallel CNN model on Kintex7 FPGA. The proposed SC hardware only compromises 0.14% accuracy compared to binary computing on the handwriting Modified National Institute of Standards and Technology classification task and achieved at least 99.72% energy saving per image feedforward and 31× more data throughput than modern hardware. Unique to SC, early decision termination pushed the performance baseline exponentially with minimum accuracy loss, making SC CNN extremely lucrative for AI edge computing but limited to classification tasks. The SC's inherent noise heavily penalizes CNN regression performance, rendering SC unsuitable for regression tasks.

6G Traffic Prediction with a Novel Parallel Convolutional Neural Networks Architecture and Matrix Format Method Integration

In the evolving world of wireless communication, sixth generation (6G) networks represent a significant leap forward. Beyond its high-speed and reliable communication, 6G integrates Artificial Intelligence (AI), making networks intelligent entities. This elevates the infrastructure of smart cities and other ecosystems. A critical factor in 6G's success is real-time traffic analysis. As 6G aims to interconnect billions of devices, it faces unprecedented traffic patterns. Practical traffic analysis ensures optimal performance, resource distribution, and energy efficiency. It also supports the network in handling vital sectors like healthcare and transportation by anticipating congestion and prioritizing crucial data. However, traditional traffic analysis techniques designed for earlier generations cannot accommodate 6G's demands. With 6G's integration of diverse technologies, understanding traffic becomes more challenging. Recent advancements have incorporated deep learning architectures, notably Convolutional Neural Networks (CNNs), for traffic analysis. While these models show potential, adapting them to 6G's specifics remains challenging. This research presents a unique parallel CNN architecture for 6G traffic prediction. It converts network data into an image using the Matrix Format Method (MFM), making it suitable for CNN processing. This innovation addresses the limitations of traditional methods and meets 6G's requirements. Compared to other models, our parallel CNN architecture highlights enhanced performance, promising increased traffic prediction accuracy. It also paves the way for improved resource allocation, energy management, and quality of service in 6G environments.

Bearing fault diagnosis with parallel CNN and LSTM.

Intelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signals and the robustness of the model, we construct a fault diagnostic model based on convolutional neural network (CNN) and long short-term memory (LSTM) parallel network to extract their temporal and spatial features from two perspectives. First, via resampling, vibration signal is split into equal-sized slices which are then converted into time-frequency images by continuous wavelet transform (CWT). Second, LSTM extracts the time-correlation features of 1D signals as one path, and 2D-CNN extracts the local frequency distribution features of time-frequency images as another path. Third, 1D-CNN further extracts integrated features from the fusion features yielded by former parallel paths. Finally, these categories are calculated through the softmax function. According to experimental results, the proposed model has satisfactory diagnostic accuracy and robustness in different contexts on two different datasets.

Hyperspectral Target Detection-Based 2-D–3-D Parallel Convolutional Neural Networks for Hyperspectral Image Classification

Hyperspectral Target Detection-Based 2-D–3-D Parallel Convolutional Neural Networks for Hyperspectral Image Classification

HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs.

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two parallel CNN branches in a cost-efficient manner. One high-resolution branch directly takes primary high-resolution features as inputs, but uses less convolution operations. The other low-resolution branch first performs down-sampling and then utilizes more convolution operations over such low-resolution features. Experiments on both recognition task (ImageNet-1K dataset) and dense prediction tasks (COCO and ADE20K datasets) demonstrate the superiority of HIRI-ViT. More remarkably, under comparable computational cost ( ∼5.0 GFLOPs), HIRI-ViT achieves to-date the best published Top-1 accuracy of 84.3% on ImageNet with 448×448 inputs, which absolutely improves 83.4% of iFormer-S by 0.9% with 224×224 inputs.

Hybrid CNN-Transformer Network with Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-contrast CT Scans.

Lesion segmentation is a fundamental step for the diagnosis of acute ischemic stroke (AIS). Non-contrast CT (NCCT) is still a mainstream imaging modality for AIS lesion measurement. However, AIS lesion segmentation on NCCT is challenging due to low contrast, noise and artifacts. To achieve accurate AIS lesion segmentation on NCCT, this study proposes a hybrid convolutional neural network (CNN) and Transformer network with circular feature interaction and bilateral difference learning. It consists of parallel CNN and Transformer encoders, a circular feature interaction module, and a shared CNN decoder with a bilateral difference learning module. A new Transformer block is particularly designed to solve the weak inductive bias problem of the traditional Transformer. To effectively combine features from CNN and Transformer encoders, we first design a multi-level feature aggregation module to combine multi-scale features in each encoder and then propose a novel feature interaction module containing circular CNN-to-Transformer and Transformer-to-CNN interaction blocks. Besides, a bilateral difference learning module is proposed at the bottom level of the decoder to learn the different information between the ischemic and contralateral sides of the brain. The proposed method is evaluated on three AIS datasets: the public AISD, a private dataset and an external dataset. Experimental results show that the proposed method achieves Dices of 61.39% and 46.74% on the AISD and the private dataset, respectively, outperforming 17 state-of-the-art segmentation methods. Besides, volumetric analysis on segmented lesions and external validation results imply that the proposed method is potential to provide support information for AIS diagnosis.

Fully Parallel Stochastic Computing Hardware Implementation of Convolutional Neural Networks for Edge Computing Applications.

Edge artificial intelligence (AI) is receiving a tremendous amount of interest from the machine learning community due to the ever-increasing popularization of the Internet of Things (IoT). Unfortunately, the incorporation of AI characteristics to edge computing devices presents the drawbacks of being power and area hungry for typical deep learning techniques such as convolutional neural networks (CNNs). In this work, we propose a power-and-area efficient architecture based on the exploitation of the correlation phenomenon in stochastic computing (SC) systems. The proposed architecture solves the challenges that a CNN implementation with SC (SC-CNN) may present, such as the high resources used in binary-to-stochastic conversion, the inaccuracy produced by undesired correlation between signals, and the complexity of the stochastic maximum function implementation. To prove that our architecture meets the requirements of edge intelligence realization, we embed a fully parallel CNN in a single field-programmable gate array (FPGA) chip. The results obtained showed a better performance than traditional binary logic and other SC implementations. In addition, we performed a full VLSI synthesis of the proposed design, showing that it presents better overall characteristics than other recently published VLSI architectures.

Integrate memory mechanism in multi-granularity deep framework for driver drowsiness detection

Driver drowsiness detection is a critical task for early warning of safe driving, while existing spatial feature-based methods face the challenges of large variations of head pose. This paper proposes a novel approach to integrate the memory mechanism in a multi-granularity deep framework to detect driver drowsiness, and the temporal dependencies over sequential frames are well integrated with the spatial deep learning framework on the frontal faces. The proposed approach includes two steps. First, the spatial Multi-granularity Convolutional Neural Network is designed to utilize a group of parallel Convolutional Neural Network extractors on well-aligned facial patches of different granularities and extract facial representations effectively for large variations of head pose. Furthermore, it can flexibly fuse detailed appearance clues of the main parts and local-to-global spatial constraints. Second, the memory mechanism is set up using a deep long short-term memory network of facial representations to explore long-term relationships with variable length over sequential frames, which is capable of distinguishing the states with temporal dependencies, such as blinking and closing eyes. The proposed approach achieves 90.05% accuracy and about 37 frames per second (FPS) speed on the evaluation set of the National Tsing Hua University Driver Drowsiness Detection dataset, which is applied to the intelligent vehicle for driver drowsiness detection. A dataset named Forward Instant Driver Drowsiness Detection is also built and will be publicly accessible to speed up the study of driver drowsiness detection.

DeepHLAPred: a deep learning-based method for non-classical HLA binder prediction

Human leukocyte antigen (HLA) is closely involved in regulating the human immune system. Despite great advance in detecting classical HLA Class I binders, there are few methods or toolkits for recognizing non-classical HLA Class I binders. To fill in this gap, we have developed a deep learning-based tool called DeepHLAPred. The DeepHLAPred used electron-ion interaction pseudo potential, integer numerical mapping and accumulated amino acid frequency as initial representation of non-classical HLA binder sequence. The deep learning module was used to further refine high-level representations. The deep learning module comprised two parallel convolutional neural networks, each followed by maximum pooling layer, dropout layer, and bi-directional long short-term memory network. The experimental results showed that the DeepHLAPred reached the state-of-the-art performanceson the cross-validation test and the independent test. The extensive test demonstrated the rationality of the DeepHLAPred. We further analyzed sequence pattern of non-classical HLA class I binders by information entropy. The information entropy of non-classical HLA binder sequence implied sequence pattern to a certain extent. In addition, we have developed a user-friendly webserver for convenient use, which is available at http://www.biolscience.cn/DeepHLApred/. The tool and the analysis is helpful to detect non-classical HLA Class I binder. The source code and data is available at https://github.com/tangxingyu0/DeepHLApred.

Hybrid deep learning and quantum-inspired neural network for day-ahead spatiotemporal wind speed forecasting

Wind is an essential, clean and sustainable renewable source of energy; however, wind speed is stochastic and intermittent. Accurate wind power generation forecasts are required to ensure that power generation can be scheduled economically and securely. This work proposes a hybrid deep learning technique that incorporates a quantum-inspired neural network to predict wind speeds 24 h in advance. An innovative neural network technique is implemented by cascading parallel convolutional neural networks (CNNs) with a long short-term memory (LSTM) and a quantum-inspired neural network (QINN). The proposed hybrid model is optimized using two iterative loops: the outer loop is implemented by using quantum particle swarm optimization (QPSO) to tune the structure of model and other hyperparameters/parameters. The inner loop uses an Adam optimizer to tune the weights and biases of the proposed model. Spatiotemporal wind speeds at various locations provide the 2D input data. Simulation results reveal that the proposed method outperforms other methods for 24 h-ahead wind speed forecasting.

Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis

This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR).

Parallel CNN-ELM: A multiclass classification of chest X-ray images to identify seventeen lung diseases including COVID-19.

Numerous epidemic lung diseases such as COVID-19, tuberculosis (TB), and pneumonia have spread over the world, killing millions of people. Medical specialists have experienced challenges in correctly identifying these diseases due to their subtle differences in Chest X-ray images (CXR). To assist the medical experts, this study proposed a computer-aided lung illness identification method based on the CXR images. For the first time, 17 different forms of lung disorders were considered and the study was divided into six trials with each containing two, two, three, four, fourteen, and seventeen different forms of lung disorders. The proposed framework combined robust feature extraction capabilities of a lightweight parallel convolutional neural network (CNN) with the classification abilities of the extreme learning machine algorithm named CNN-ELM. An optimistic accuracy of 90.92% and an area under the curve (AUC) of 96.93% was achieved when 17 classes were classified side by side. It also accurately identified COVID-19 and TB with 99.37% and 99.98% accuracy, respectively, in 0.996 microseconds for a single image. Additionally, the current results also demonstrated that the framework could outperform the existing state-of-the-art (SOTA) models. On top of that, a secondary conclusion drawn from this study was that the prospective framework retained its effectiveness over a range of real-world environments, including balanced-unbalanced or large-small datasets, large multiclass or simple binary class, and high- or low-resolution images. A prototype Android App was also developed to establish the potential of the framework in real-life implementation.

A CNN-GRU Approach to the Accurate Prediction of Batteries’ Remaining Useful Life from Charging Profiles

Predicting the remaining useful life (RUL) is a pivotal step in ensuring the reliability of lithium-ion batteries (LIBs). In order to enhance the precision and stability of battery RUL prediction, this study introduces an innovative hybrid deep learning model that seamlessly integrates convolutional neural network (CNN) and gated recurrent unit (GRU) architectures. Our primary goal is to significantly improve the accuracy of RUL predictions for LIBs. Our model excels in its predictive capabilities by skillfully extracting intricate features from a diverse array of data sources, including voltage (V), current (I), temperature (T), and capacity. Within this novel architectural design, parallel CNN layers are meticulously crafted to process each input feature individually. This approach enables the extraction of highly pertinent information from multi-channel charging profiles. We subjected our model to rigorous evaluations across three distinct scenarios to validate its effectiveness. When compared to LSTM, GRU, and CNN-LSTM models, our CNN-GRU model showcases a remarkable reduction in root mean square error, mean square error, mean absolute error, and mean absolute percentage error. These results affirm the superior predictive capabilities of our CNN-GRU model, which effectively harnesses the strengths of both CNNs and GRU networks to achieve superior prediction accuracy. This study draws upon NASA data to underscore the outstanding predictive performance of the CNN-GRU model in estimating the RUL of LIBs.