Convolutional Neural Network Configuration Research Articles

Fault diagnosis of drivetrain systems based on vibration signals and convolutional neural networks

Accurate and fast fault diagnosis can improve the reliability of drivetrain systems. The fault diagnosis model based on convolutional neural networks is tricky because the accuracy and efficiency of diagnosis depend on the neural network parameters, such as layer size and number of layers. In this paper, we developed a data pre-processing technique to format vibrational data to be receptible to a neural network. First one will study the difference in performance by inputting a spectrogram of the vibrational data compared to the raw data itself. Second, the windowizing technique is used and its parameters are explored to train different configurations of convolutional neural networks. Finally, the optimal neural network parameters are obtained to improve the computational efficiency while the training model has the highest accuracy.

Self-attention CNN based indoor human events detection with UWB radar

In the era of smart homes and healthcare automation, the ability to accurately monitor and detect indoor human activities is paramount. Ultra-wideband (UWB) radar has emerged as a promising means for event detection, given its non-invasive nature and easy deployment in diverse environments. However, despite the advances in radar-based event detection, challenges remain, such as distinguishing between similar events like falls and rapid sitting. To address these challenges, for the first time, we propose an impulse radio-ultrawideband (IR-UWB) radar system to collect over ten thousand radar echo signals of eight similar actions from different angles and design a self-attention-based low-complexity convolutional neural network (CNN) model for event classification. The model leverages global correlations in radar signal spectrograms to efficiently extract features. A comparative simulation study is conducted to evaluate the detection accuracy of the proposed model and some of the existing methods based on different dataset sizes and CNN configurations. Moreover, the influence of different self-attention structures on precision and model parameter count is analyzed. Our findings reveal that the proposed self-attention-based CNN model significantly outperforms other traditional machine learning techniques while maintaining a low level computational complexity.

Frequency and phase correction of GABA-edited magnetic resonance spectroscopy using complex-valued convolutional neural networks

PurposeTo determine the significance of complex-valued inputs and complex-valued convolutions compared to real-valued inputs and real-valued convolutions in convolutional neural networks (CNNs) for frequency and phase correction (FPC) of GABA-edited magnetic resonance spectroscopy (MRS) data. MethodsAn ablation study using simulated data was performed to determine the most effective input (real or complex) and convolution type (real or complex) to predict frequency and phase shifts in GABA-edited MEGA-PRESS data using CNNs. The best CNN model was subsequently compared using both simulated and in vivo data to two recently proposed deep learning (DL) methods for FPC of GABA-edited MRS. All methods were trained using the same experimental setup and evaluated using the signal-to-noise ratio (SNR) and linewidth of the GABA peak, choline artifact, and by visually assessing the reconstructed final difference spectrum. Statistical significance was assessed using the Wilcoxon signed rank test. ResultsThe ablation study showed that using complex values for the input represented by real and imaginary channels in our model input tensor, with complex convolutions was most effective for FPC. Overall, in the comparative study using simulated data, our CC-CNN model (that received complex-valued inputs with complex convolutions) outperformed the other models as evaluated by the mean absolute error. ConclusionOur results indicate that the optimal CNN configuration for GABA-edited MRS FPC uses a complex-valued input and complex convolutions. Overall, this model outperformed existing DL models.

Financial risk tolerance profiling from text

Traditionally, individual financial risk tolerance information is gathered via questionnaires or similar structured psychometric tools. Our abundant digital footprint, as an unstructured alternative, is less investigated. Leveraging such information can potentially support large-scale and cost-efficient financial services. Therefore, I explore the possibility of building a computational model that distills risk tolerance information from user texts in this study, and discuss the design principles discovered from empirical results and their implications. Specifically, a new quaternary classification task is defined for text mining-based risk profiling. Experiments show that pre-trained large language models set a baseline micro-F1 of circa 0.34. Using a convolutional neural network (CNN), the reported system achieves a micro-F1 of circa 0.51, which significantly outperforms the baselines, and is a circa 4% further improvement over the standard CNN configurations (micro-F1 of circa 0.47). Textual feature richness and supervised learning are found to be the key contributors to model performances, while other machine learning strategies suggested by previous research (data augmentation and multi-tasking) are less effective. The findings confirm user texts to be a useful risk profiling resource and provide several insights on this task.

Video Deepfake classification using particle swarm optimization-based evolving ensemble models

The recent breakthrough of deep learning based generative models has led to the escalated generation of photo-realistic synthetic videos with significant visual quality. Automated reliable detection of such forged videos requires the extraction of fine-grained discriminative spatial-temporal cues. To tackle such challenges, we propose weighted and evolving ensemble models comprising 3D Convolutional Neural Networks (CNNs) and CNN-Recurrent Neural Networks (RNNs) with Particle Swarm Optimization (PSO) based network topology and hyper-parameter optimization for video authenticity classification. A new PSO algorithm is proposed, which embeds Muller's method and fixed-point iteration based leader enhancement, reinforcement learning-based optimal search action selection, a petal spiral simulated search mechanism, and cross-breed elite signal generation based on adaptive geometric surfaces. The PSO variant optimizes the RNN topologies in CNN-RNN, as well as key learning configurations of 3D CNNs, with the attempt to extract effective discriminative spatial-temporal cues. Both weighted and evolving ensemble strategies are used for ensemble formulation with aforementioned optimized networks as base classifiers. In particular, the proposed PSO algorithm is used to identify optimal subsets of optimized base networks for dynamic ensemble generation to balance between ensemble complexity and performance. Evaluated using several well-known synthetic video datasets, our approach outperforms existing studies and various ensemble models devised by other search methods with statistical significance for video authenticity classification. The proposed PSO model also illustrates statistical superiority over a number of search methods for solving optimization problems pertaining to a variety of artificial landscapes with diverse geometrical layouts.

A convolutional neural network to identify mosquito species (Diptera: Culicidae) of the genus Aedes by wing images

Accurate species identification is crucial to assess the medical relevance of a mosquito specimen, but requires intensive experience of the observers and well-equipped laboratories. In this proof-of-concept study, we developed a convolutional neural network (CNN) to identify seven Aedes species by wing images, only. While previous studies used images of the whole mosquito body, the nearly two-dimensional wings may facilitate standardized image capture and reduce the complexity of the CNN implementation. Mosquitoes were sampled from different sites in Germany. Their wings were mounted and photographed with a professional stereomicroscope. The data set consisted of 1155 wing images from seven Aedes species as well as 554 wings from different non-Aedes mosquitoes. A CNN was trained to differentiate between Aedes and non-Aedes mosquitoes and to classify the seven Aedes species based on grayscale and RGB images. Image processing, data augmentation, training, validation and testing were conducted in python using deep-learning framework PyTorch. Our best-performing CNN configuration achieved a macro F1 score of 99% to discriminate Aedes from non-Aedes mosquito species. The mean macro F1 score to predict the Aedes species was 90% for grayscale images and 91% for RGB images. In conclusion, wing images are sufficient to identify mosquito species by CNNs.

Efficient analysis of hydrological connectivity using 1D and 2D Convolutional Neural Networks

Understanding hydrological connectivity is essential to investigate ecological processes in river catchments and floodplains. Assessing flooding behavior, including flooded areas and connection times, is required to analyze hydrological connectivity in river floodplains. Deep learning, especially Convolutional Neural Networks (CNNs), is an attractive alternative to hydrodynamic modeling, which is more computationally expensive. This paper aims to develop a methodology to analyze the functional connectivity in remote and field measurement data-scarce areas using remote sensing data, CNN models, and connectivity metrics. The northern Lakes of the Narran River catchment, located in the Condamine–Balonne River floodplain in New South Wales, Australia, is the showcase for this method. One-dimensional CNN and two-dimensional U-Net configurations were applied and yielded comparable flood extents to the satellite images with Hit Rate values of 0.853 and 0.873, respectively. Two algorithms for determining hydrological connectivity were investigated, including the geostatistical Connectivity Function (CF) and the newly proposed Potential Connection Length (PCL). It was found that the connection along the main Narran River stream was more substantial than between the river and the floodplain lakes. The analysis using the PCL shows that the connectivity patterns in different stages of a flood event can vary depending on the initial condition of the floodplain. The overall conclusion from this work is that hydrological connectivity can be assessed computationally efficiently using only remote sensing, discharge data, and CNN models.

MLNet: Metaheuristics-Based Lightweight Deep Learning Network for Cervical Cancer Diagnosis.

One of the leading causes of cancer-related deaths among women is cervical cancer. Early diagnosis and treatment can minimize the complications of this cancer. Recently, researchers have designed and implemented many deep learning-based automated cervical cancer diagnosis models. However, the majority of these models suffer from over-fitting, parameter tuning, and gradient vanishing problems. To overcome these problems, in this paper a metaheuristics-based lightweight deep learning network (MLNet) is proposed. Initially, the hyper-parameters tuning problem of convolutional neural network (CNN) is defined as a multi-objective problem. Particle swarm optimization (PSO) is used to optimally define the CNN architecture. Thereafter, Dynamically hybrid niching differential evolution (DHDE) is utilized to optimize the hyper-parameters of CNN layers. Each particle of PSO and solution of DHDE together represent the possible CNN configuration. F-score is used as a fitness function. The proposed MLNet is trained and validated on three benchmark cervical cancer datasets. On the Herlev dataset, MLNet outperforms the existing models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 1.6254%, 1.5178%, 1.5780%, 1.7145%, and 1.4890%, respectively. Also, on the SIPaKMeD dataset, MLNet achieves better performance than the existing models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 2.1250%, 2.2455%, 1.9074%, 1.9258%, and 1.8975%, respectively. Finally, on the Mendeley LBC dataset, MLNet achieves better performance than the competitive models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 1.4680%, 1.5845%, 1.3582%, 1.3926%, and 1.4125%, respectively.

Deep learning models for real-life human activity recognition from smartphone sensor data

Nowadays, the field of human activity recognition (HAR) is a remarkably hot topic within the scientific community. Given the low cost, ease of use and high accuracy of the sensors from different wearable devices and smartphones, more and more researchers are opting to do their bit in this area. However, until very recently, all the work carried out in this field was done in laboratory conditions, with very few similarities with our daily lives. This paper will focus on this new trend of integrating all the knowledge acquired so far into a real-life environment. Thus, a dataset already published following this philosophy was used. In this way, this work aims to be able to identify the different actions studied there. In order to perform this classification, this paper explores new designs and architectures for models inspired by the ones which have yielded the best results in the literature. More specifically, different configurations of Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) have been tested, but on real-life conditions instead of laboratory ones. It is worth mentioning that the hybrid models formed from these techniques yielded the best results, with a peak accuracy of 94.80% on the dataset used.

Detection of the rotator cuff tears using a novel convolutional neural network from magnetic resonance image (MRI)

The rotator cuff tear is a common situation for basketballers, handballers, or other athletes that strongly use their shoulders. This injury can be diagnosed precisely from a magnetic resonance (MR) image. In this paper, a novel deep learning-based framework is proposed to diagnose rotator cuff tear from MRI images of patients suspected of the rotator cuff tear. First, we collected 150 shoulders MRI images from two classes of rotator cuff tear patients and healthy ones with the same numbers. These images were observed by an orthopedic specialist and then tagged and used as input in the various configurations of the Convolutional Neural Network (CNN). At this stage, five different configurations of convolutional networks have been examined. Then, in the next step, the selected network with the highest accuracy is used to extract the deep features and classify the two classes of rotator cuff tear and healthy. Also, MRI images are feed to two quick pre-trained CNNs (MobileNetv2 and SqueezeNet) to compare with the proposed CNN. Finally, the evaluation is performed using the 5-fold cross-validation method. Also, a specific Graphical User Interface (GUI) was designed in the MATLAB environment for simplicity, which allows for testing by detecting the image class. The proposed CNN achieved higher accuracy than the two mentioned pre-trained CNNs. The average accuracy, precision, sensitivity, and specificity achieved by the best selected CNN configuration are equal to 92.67%, 91.13%, 91.75%, and 92.22%, respectively. The deep learning algorithm could accurately rule out significant rotator cuff tear based on shoulder MRI.

Enhanced Emotion Recognition in Videos: A Convolutional Neural Network Strategy for Human Facial Expression Detection and Classification

The human face is essential in conveying emotions, as facial expressions serve as effective, natural, and universal indicators of emotional states. Automated emotion recognition has garnered increasing interest due to its potential applications in various fields, such as human-computer interaction, machine learning, robotic control, and driver emotional state monitoring. With artificial intelligence and computational power advancements, visual emotion recognition has become a prominent research area. Despite extensive research employing machine learning algorithms like convolutional neural networks (CNN), challenges remain concerning input data processing, emotion classification scope, data size, optimal CNN configurations, and performance evaluation. To address these issues, we propose a comprehensive CNN-based model for real-time detection and classification of five primary emotions: anger, happiness, neutrality, sadness, and surprise. We employ the Amsterdam Dynamic Facial Expression Set – Bath Intensity Variations (ADFES-BIV) video dataset, extracting image frames from the video samples. Image processing techniques such as histogram equalization, color conversion, cropping, and resizing are applied to the frames before labeling. The Viola-Jones algorithm is then used for face detection on the processed grayscale images. We develop and train a CNN on the processed image data, implementing dropout, batch normalization, and L2 regularization to reduce overfitting. The ideal hyperparameters are determined through trial and error, and the model's performance is evaluated. The proposed model achieves a recognition accuracy of 99.38%, with the confusion matrix, recall, precision, F1 score, and processing time further quantifying its performance characteristics. The model's generalization performance is assessed using images from the Warsaw Set of Emotional Facial Expression Pictures (WSEFEP) and Extended Cohn-Kanade Database (CK+) datasets. The results demonstrate the efficiency and usability of our proposed approach, contributing valuable insights into real-time visual emotion recognition.

A Sparse CNN Accelerator for Eliminating Redundant Computations in Intra- and Inter-Convolutional/Pooling Layers

Neural network pruning, which can be divided into unstructured pruning and structured pruning strategies, has been proven to be an efficient method to substantially reduce the number of computations of convolutional neural networks (CNNs). However, it remains difficult to combine the advantages of these two pruning strategies. This article proposes a high-performance accelerator for unstructured sparse CNNs. First, a convolution-based filter selection and clustering method (FSCM) is proposed to reorder unstructured sparse filters into uniform-size dense filters, eliminating redundant computations in the convolutional layers while maintaining a regular structure. In addition, a convolution and pooling calculation method (CPCM) is presented to reduce interlayers’ computational redundancy. Third, a hardware accelerator with high digital signal processing (DSP) efficiency is designed to take advantage of FSCM and CPCM. The proposed accelerator is implemented on a Xilinx XCVU9P platform at 300 MHz. With different CNN configurations, the performance and DSP efficiency for LeNet, AlexNet, and VGG16 are 1490.53 GOPS and 3.882, 913.85 GOPS and 1.785, and 862.16 GOPS and 1.68, respectively. Compared to previous field-programmable gate array (FPGA) and application-specific integrated circuit (ASIC) designs, the accelerator achieves up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$15.43\times $ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$7.73\times $ </tex-math></inline-formula> speedup in terms of performance and DSP efficiency.

Image Recovery from Synthetic Noise Artifacts in CT Scans Using Modified U-Net.

Computed Tomography (CT) is commonly used for cancer screening as it utilizes low radiation for the scan. One problem with low-dose scans is the noise artifacts associated with low photon count that can lead to a reduced success rate of cancer detection during radiologist assessment. The noise had to be removed to restore detail clarity. We propose a noise removal method using a new model Convolutional Neural Network (CNN). Even though the network training time is long, the result is better than other CNN models in quality score and visual observation. The proposed CNN model uses a stacked modified U-Net with a specific number of feature maps per layer to improve the image quality, observable on an average PSNR quality score improvement out of 174 images. The next best model has 0.54 points lower in the average score. The score difference is less than 1 point, but the image result is closer to the full-dose scan image. We used separate testing data to clarify that the model can handle different noise densities. Besides comparing the CNN configuration, we discuss the denoising quality of CNN compared to classical denoising in which the noise characteristics affect quality.

Abnormality classification and localization using dual-branch whole-region-based CNN model with histopathological images

The task of classification and localization with detecting abnormalities in medical images is considered very challenging. Computer-aided systems have been widely employed to address this issue, and the proliferation of deep learning network architectures is proof of the outstanding performance reported in the literature. However, localizing abnormalities in regions of images that can support the confidence of classification continues to attract research interest. The difficulty of using digital histopathology images for this task is another drawback, which needs high-level deep learning models to address the situation. Successful pathology localization automation will support automatic acquisition planning and post-imaging analysis. In this paper, we address issues related to the combination of classification with image localization and detection through a dual branch deep learning framework that uses two different configurations of convolutional neural networks (CNN) architectures. Whole-image based CNN (WCNN) and region-based CNN (RCNN) architectures are systematically combined to classify and localize abnormalities in samples. A multi-class classification and localization of abnormalities are achieved using the method with no annotation-dependent images. In addition, seamless confidence and explanation mechanism is provided so that outcomes from WCNN and RCNN are mapped together for further analysis. Using images from both BACH and BreakHis databases, an exhaustive set of experiments was carried out to validate the performance of the proposed method in achieving classification and localization simultaneously. Obtained results showed that the system achieved a classification accuracy of 97.08%, a localization accuracy of 94%, and an area under the curve (AUC) of 0.10 for classification. Further findings from this study revealed that a multi-neural network approach could provide a suitable method for addressing the combinatorial problem of classification and localization anomalies in digital medical images. Lastly, the study's outcome offers means for automating the annotation of histopathology images and the support for human pathologists in locating abnormalities.

A multi-variate heart disease optimization and recognition framework

Cardiovascular diseases (CVD) are the most widely spread diseases all over the world among the common chronic diseases. CVD represents one of the main causes of morbidity and mortality. Therefore, it is vital to accurately detect the existence of heart diseases to help to save the patient life and prescribe a suitable treatment. The current evolution in artificial intelligence plays an important role in helping physicians diagnose different diseases. In the present work, a hybrid framework for the detection of heart diseases using medical voice records is suggested. A framework that consists of four layers, namely “Segmentation” Layer, “Features Extraction” Layer, “Learning and Optimization” Layer, and “Export and Statistics” Layer is proposed. In the first layer, a novel segmentation technique based on the segmentation of variable durations and directions (i.e., forward and backward) is suggested. Using the proposed technique, 11 datasets with 14,416 numerical features are generated. The second layer is responsible for feature extraction. Numerical and graphical features are extracted from the resulting datasets. In the third layer, numerical features are passed to 5 different Machine Learning (ML) algorithms, while graphical features are passed to 8 different Convolutional Neural Networks (CNN) with transfer learning to select the most suitable configurations. Grid Search and Aquila Optimizer (AO) are used to optimize the hyperparameters of ML and CNN configurations, respectively. In the last layer, the output of the proposed hybrid framework is validated using different performance metrics. The best-reported metrics are (1) 100% accuracy using ML algorithms including Extra Tree Classifier (ETC) and Random Forest Classifier (RFC) and (2) 99.17% accuracy using CNN.

Classification of diffraction patterns using a convolutional neural network in single-particle-imaging experiments performed at X-ray free-electron lasers.

Single particle imaging (SPI) at X-ray free-electron lasers is particularly well suited to determining the 3D structure of particles at room temperature. For a successful reconstruction, diffraction patterns originating from a single hit must be isolated from a large number of acquired patterns. It is proposed that this task could be formulated as an image-classification problem and solved using convolutional neural network (CNN) architectures. Two CNN configurations are developed: one that maximizes the F1 score and one that emphasizes high recall. The CNNs are also combined with expectation-maximization (EM) selection as well as size filtering. It is observed that the CNN selections have lower contrast in power spectral density functions relative to the EM selection used in previous work. However, the reconstruction of the CNN-based selections gives similar results. Introducing CNNs into SPI experiments allows the reconstruction pipeline to be streamlined, enables researchers to classify patterns on the fly, and, as a consequence, enables them to tightly control the duration of their experiments. Incorporating non-standard artificial-intelligence-based solutions into an existing SPI analysis workflow may be beneficial for the future development of SPI experiments.

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data.

Convolutional neural networks (CNNs) are increasingly used to automate segmentation for radiotherapy planning, where accurate segmentation of organs-at-risk (OARs) is crucial. Training CNNs often requires large amounts of data. However, large, high quality datasets are scarce. The aim of this study was to develop a CNN capable of accurate head and neck (HN) 3D auto-segmentation of planning CT scans using a small training dataset (34 CTs). Elements of our custom CNN architecture were varied to optimise segmentation performance. We tested and evaluated the impact of: using multiple contrast channels for the CT scan input at specific soft tissue and bony anatomy windows, resize vs. transpose convolutions, and loss functions based on overlap metrics and cross-entropy in different combinations. Model segmentation performance was compared with the inter-observer deviation of two doctors' gold standard segmentations using the 95th percentile Hausdorff distance and mean distance-to-agreement (mDTA). The best performing configuration was further validated on a popular public dataset to compare with state-of-the-art (SOTA) auto-segmentation methods. Our best performing CNN configuration was competitive with current SOTA methods when evaluated on the public dataset with mDTA of mm for the brainstem, mm for the mandible, mm for the left parotid and mm for the right parotid. Through careful tuning and customisation we trained a 3D CNN with a small dataset to produce segmentations of HN OARs with an accuracy that is comparable with inter-clinician deviations. Our proposed model performed competitively with current SOTA methods.

Recognition of emotional states using frequency effective connectivity maps through transfer learning approach from electroencephalogram signals

Convolutional Neural Networks (CNN) have been widely utilized in Emotion Recognition (ER) research due to their vast benefits. Designing specific CNN configuration and learning accurate parameters are provided through the Transfer Learning (TL) approach. A novel combined ER schema based on sophisticated Frequency Effective Connectivity (FEC) maps and transfer learned CNN models named FEC-CNN is proposed in this study. The EC measure estimates the information flow between brain channels in frequency bands regarding the volume conduction problem. Then, visualization of this information provides valuable and distinctive information for classifying emotional states. After preprocessing Electroencephalogram (EEG) signals, the Effective Connectivity maps were computed through the Partial Directed Coherence (PDC) measure from EEG channels at standard delta, theta, alpha, beta, and gamma frequency bands. Then, PDC maps were used to fine-tune six pre-trained CNN models, AlexNet, ResNet-18, DarkNet-19, ShuffleNet, Inception-v3, and Xception, and classify five emotional states toward the subject independent Leave-One-Subject-Out (LOSO) Cross-Validation criterion for MAHNOB-HCI, DEAP and DREAMER databases. The experimental results show that ResNet-18 achieved the highest average accuracy and F-score 94.27%, 94.74% for the DEAP database, and 95.25% and 95.33% for the MAHNOB-HCI database, and 96.00% and 96.77% for DREAMER database, to recognize five emotional states from PDC maps at alpha frequency bands. Comparison of the experimental results with recent researches showed the superiority of the proposed EC-based CNN model.This research introduced an interesting sight of deep learning applications in cognitive computation area by utilizing effective connectivity information flows to recognize emotional states from EEG signals.

Detection of Bow Echoes in Kilometer-Scale Forecasts Using a Convolutional Neural Network

Abstract Bow echoes (BEs) are bow-shaped lines of convective cells that are often associated with swaths of damaging straight-line winds and small tornadoes. This paper describes a convolutional neural network (CNN) able to detect BEs directly from French kilometer-scale model outputs in order to facilitate and accelerate the operational forecasting of BEs. The detections are only based on the maximum pseudoreflectivity field predictor (“pseudo” because it is expressed in mm h−1 and not in dBZ). A preprocessing of the training database is carried out in order to reduce imbalance issues between the two classes (inside or outside bow echoes). A CNN sensitivity analysis against a set of hyperparameters is done. The selected CNN configuration has a hit rate of 86% and a false alarm rate of 39%. The strengths and weaknesses of this CNN are then emphasized with an object-oriented evaluation. The BE largest pseudoreflectivities are correctly detected by the CNN, which tends to underestimate the size of BEs. Detected BE objects have wind gusts similar to the hand-labeled BE. Most of the time, false alarm objects and missed objects are rather small (e.g., &lt;1500 km2). Based on a cooperation with forecasters, synthesis plots are proposed that summarize the BE detections in French kilometer-scale models. A subjective evaluation of the CNN performances is also reported. The overall positive feedback from forecasters is in good agreement with the object-oriented evaluation. Forecasters perceive these products as relevant and potentially useful to handle the large amount of available data from numerical weather prediction models.

A Decision Support System for Face Sketch Synthesis Using Deep Learning and Artificial Intelligence.

The recent development in the area of IoT technologies is likely to be implemented extensively in the next decade. There is a great increase in the crime rate, and the handling officers are responsible for dealing with a broad range of cyber and Internet issues during investigation. IoT technologies are helpful in the identification of suspects, and few technologies are available that use IoT and deep learning together for face sketch synthesis. Convolutional neural networks (CNNs) and other constructs of deep learning have become major tools in recent approaches. A new-found architecture of the neural network is anticipated in this work. It is called Spiral-Net, which is a modified version of U-Net fto perform face sketch synthesis (the phase is known as the compiler network C here). Spiral-Net performs in combination with a pre-trained Vgg-19 network called the feature extractor F. It first identifies the top n matches from viewed sketches to a given photo. F is again used to formulate a feature map based on the cosine distance of a candidate sketch formed by C from the top n matches. A customized CNN configuration (called the discriminator D) then computes loss functions based on differences between the candidate sketch and the feature. Values of these loss functions alternately update C and F. The ensemble of these nets is trained and tested on selected datasets, including CUFS, CUFSF, and a part of the IIT photo–sketch dataset. Results of this modified U-Net are acquired by the legacy NLDA (1998) scheme of face recognition and its newer version, OpenBR (2013), which demonstrate an improvement of 5% compared with the current state of the art in its relevant domain.