VGG16 Network Research Articles

Dynamic Load Reactive Power Optimization Based on Convolutional Neural Network VGG16 Model

<p>In reactive power optimization of distribution network, in most cases, the processing of load data is often only for the specific data under a certain operation condition, so it is difficult to classify and process the data of multiple working conditions in a certain operation stage. To solve the above problems, an optimization method basedon convolutional neural network VGG16 (visual geometry group network) is proposed. Firstly, it is classified according to the capacity proportion of transformer in the station area, and three kinds of scenes of light, medium and high are obtained. Then, particle swarm optimization algorithm is used to optimize each kind of scene, and the corresponding optimization strategy is obtained. The effectiveness of this method to solve the problem of dynamic reactive power and voltage in the substation area is verified by simulation.</p>

Optimized Ensemble Approach for Multi-model Event Detection in Big data

Event detection acts an important role among modern society and it is a popular computer process that permits to detect the events automatically. Big data is more useful for the event detection due to large size of data. Multimodal event detection is utilized for the detection of events using heterogeneous types of data. This work aims to perform for classification of diverse events using Optimized Ensemble learning approach. The Multi-modal event data including text, image and audio are sent to the user devices from cloud or server where three models are generated for processing audio, text and image. At first, the text, image and audio data is processed separately. The process of creating a text model includes pre-processing using Imputation of missing values and data normalization. Then the textual feature extraction using integrated N-gram approach. The Generation of text model using Convolutional two directional LSTM (2DCon_LSTM). The steps involved in image model generation are pre-processing using Min-Max Gaussian filtering (MMGF). Image feature extraction using VGG-16 network model and generation of image model using Tweaked auto encoder (TAE) model. The steps involved in audio model generation are pre-processing using Discrete wavelet transform (DWT). Then the audio feature extraction using Hilbert Huang transform (HHT) and Generation of audio model using Attention based convolutional capsule network (Attn_CCNet). The features obtained by the generated models of text, image and audio are fused together by feature ensemble approach. From the fused feature vector, the optimal features are trained through improved battle royal optimization (IBRO) algorithm. A deep learning model called Convolutional duo Gated recurrent unit with auto encoder (C-Duo GRU_AE) is used as a classifier. Finally, different types of events are classified where the global model are then sent to the user devices with high security and offers better decision making process. The proposed methodology achieves better performances are Accuracy (99.93%), F1-score (99.91%), precision (99.93%), Recall (99.93%), processing time (17seconds) and training time (0.05seconds). Performance analysis exceeds several comparable methodologies in precision, recall, accuracy, F1 score, training time, and processing time. This designates that the proposed methodology achieves improved performance than the compared schemes. In addition, the proposed scheme detects the multi-modal events accurately.

DDLSNet: A Novel Deep Learning-Based System for Grading Funduscopic Images for Glaucomatous Damage

To report an image analysis pipeline, DDLSNet, consisting of a rim segmentation (RimNet) branch and a disc size classification (DiscNet) branch to automate estimation of the disc damage likelihood scale (DDLS). Retrospective observational. RimNet and DiscNet were developed with 1208 and 11536 optic disc photographs (ODPs), respectively. DDLSNet performance was evaluated on 120 ODPs from the RimNet test set, for which the DDLS scores were graded by clinicians. Reproducibility was evaluated on a group of 781 eyes, each with 2 ODPs taken within 4years apart. Disc damage likelihood scale calculation requires estimation of optic disc size, provided by DiscNet (VGG19 network), and the minimum rim-to-disc ratio (mRDR) or absent rim width (ARW), provided by RimNet (InceptionV3/LinkNet segmentation model). To build RimNet's dataset, glaucoma specialists marked optic disc rim and cup boundaries on ODPs. The "ground truth" mRDR or ARW was calculated. For DiscNet's dataset, corresponding OCT images provided "ground truth" disc size. Optic disc photographs were split into 80/10/10 for training, validation, and testing, respectively, for RimNet and DiscNet. DDLSNet estimation was tested against manual grading of DDLS by clinicians with the average score used as "ground truth." Reproducibility of DDLSNet grading was evaluated by repeating DDLS estimation on a dataset of nonprogressing paired ODPs taken at separate times. The main outcome measure was a weighted kappa score between clinicians and the DDLSNet pipeline with agreement defined as ± 1 DDLS score difference. RimNet achieved an mRDR mean absolute error (MAE) of 0.04 (± 0.03) and an ARW MAE of 48.9 (± 35.9) degrees when compared to clinician segmentations. DiscNet achieved 73% (95% confidence interval [CI]: 70%, 75%) classification accuracy. DDLSNet achieved an average weighted kappa agreement of 0.54 (95% CI: 0.40, 0.68) compared to clinicians. Average interclinician agreement was 0.52 (95% CI: 0.49, 0.56). Reproducibility testing demonstrated that 96% of ODP pairs had a difference of 1 DDLS score. DDLSNet achieved moderate agreement with clinicians for DDLS grading. This novel approach illustrates the feasibility of automated ODP grading for assessing glaucoma severity. Further improvements may be achieved by increasing the number of incomplete rims sample size, expanding the hyperparameter search, and increasing the agreement of clinicians grading ODPs.

Detection of solar panel defects based on separable convolution and convolutional block attention module

ABSTRACT The share of renewable energy in the electricity market is increasing year by year. It is necessary to identify damage of solar panels in a timely manner, as solar panels are important components in photovoltaic power generation. In this paper, a lightweight solar panel fault diagnosis system based on image pre-processing and an improved VGG-19 network is proposed to address the problem of blurred solar panel field images, which are not easy for defects detection. First, we use Daubechies 4(DB4) wavelet and morphology-based enhancements to improve the quality of solar panel images. Then, conventional convolutional layers in the VGG-19 are replaced with separable convolutional layers to reduce the number of network parameters and improve training efficiency. Finally, the Convolutional Block Attention Module (CBAM) is introduced to improve the accuracy of solar panel defects’ detection. A dataset consisting of 3344 images of solar panels was used to evaluate the performance of the proposed method in defect detection. The experimental results show that the method has an accuracy of 87.8% and a detection speed of 0.047 s per image. The proposed model has higher accuracy and more stable performance than other conventional networks with a lightweight structure, demonstrating the reliability of the improved VGG-19 in detecting solar panel defects in practical applications.

State Identification of Power System Based on Visual Geometric Group Network

Accurate and timely identification of power system operation states are requisite for taking control strategies and ensuring power system security. With the high grid penetration of renewable energy generation and wide application of power electronic equipment, power system is becoming more complicated and facing more uncertainties. Traditional model based power system state identification methods are faced with challenges and data driven methods have great prospects. This paper proposes a new data-driven method for identifying power system operating states based on visual geometric group network VGG16 (16-layer Visual Geometry Group (VGG16). Firstly, the Lasso algorithm is used to select the operating state features of the power system to realize the features dimensionality reduction. Then, the weights of the loss functions are adjusted according to the difficulty of model for identifying power system states. Finally, the IEEE39 node system is used as an example, the effectiveness and robustness of the proposed method is verified.

Weakly Supervised Breast Lesion Detection in Dynamic Contrast-Enhanced MRI.

Currently, obtaining accurate medical annotations requires high labor and time effort, which largely limits the development of supervised learning-based tumor detection tasks. In this work, we investigated a weakly supervised learning model for detecting breast lesions in dynamic contrast-enhanced MRI (DCE-MRI) with only image-level labels. Two hundred fifty-four normal and 398 abnormal cases with pathologically confirmed lesions were retrospectively enrolled into the breast dataset, which was divided into the training set (80%), validation set (10%), and testing set (10%) at the patient level. First, the second image series S2 after the injection of a contrast agent was acquired from the 3.0-T, T1-weighted dynamic enhanced MR imaging sequences. Second, a feature pyramid network (FPN) with convolutional block attention module (CBAM) was proposed to extract multi-scale feature maps of the modified classification network VGG16. Then, initial location information was obtained from the heatmaps generated using the layer class activation mapping algorithm (Layer-CAM). Finally, the detection results of breast lesion were refined by the conditional random field (CRF). Accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were utilized for evaluation of image-level classification. Average precision (AP) was estimated for breast lesion localization. Delong's test was used to compare the AUCs of different models for significance. The proposed model was effective with accuracy of 95.2%, sensitivity of 91.6%, specificity of 99.2%, and AUC of 0.986. The AP for breast lesion detection was 84.1% using weakly supervised learning. Weakly supervised learning based on FPN combined with Layer-CAM facilitated automatic detection of breast lesion.

Damage Detection and Localization of Bridge Deck Pavement Based on Deep Learning.

Bridge deck pavement damage has a significant effect on the driving safety and long-term durability of bridges. To achieve the damage detection and localization of bridge deck pavement, a three-stage detection method based on the you-only-look-once version 7 (YOLOv7) network and the revised LaneNet was proposed in this study. In stage 1, the Road Damage Dataset 202 (RDD2022) is preprocessed and adopted to train the YOLOv7 model, and five classes of damage were obtained. In stage 2, the LaneNet network was pruned to retain the semantic segmentation part, with the VGG16 network as an encoder to generate lane line binary images. In stage 3, the lane line binary images were post-processed by a proposed image processing algorithm to obtain the lane area. Based on the damage coordinates from stage 1, the final pavement damage classes and lane localization were obtained. The proposed method was compared and analyzed in the RDD2022 dataset, and was applied on the Fourth Nanjing Yangtze River Bridge in China. The results shows that the mean average precision (mAP) of YOLOv7 on the preprocessed RDD2022 dataset reaches 0.663, higher than that of other models in the YOLO series. The accuracy of the lane localization of the revised LaneNet is 0.933, higher than that of instance segmentation, 0.856. Meanwhile, the inference speed of the revised LaneNet is 12.3 frames per second (FPS) on NVIDIA GeForce RTX 3090, higher than that of instance segmentation 6.53 FPS. The proposed method can provide a reference for the maintenance of bridge deck pavement.

SFincBuster: Spoofed fingerprint buster via incremental learning using leverage bagging classifier

The fingerprint presentation attack detection (PAD) studies are extensively explored by investigators to augment the security aspects of human authentication in biometric systems. Although existing approaches yield promising results while evaluated on data having same distribution as the training data, but their performance is declined in scenarios when data is gathered from unknown environment. In these situations model is learned with the new type of fake samples by re-training the entire model. Nevertheless, it has been a non-trivial concern to re-train the entire system to tackle the newly created fake samples as unseen artifacts are generated continuously in real-time scenarios. In this work, we expound a novel incremental learning-based approach namely; SFincBuster that can work effectively in the challenging real-time scenarios and can handle both new data as well as new observations from old classes. We train a leveraging bagging ensemble (LBE) in incremental fashion regardless of the extracted deep-level features (using pre-trained VGG19 network) being too large to accommodate into system memory, it is still possible to train our model effectively. Furthermore, the LBE integrates the simplicity of classical bagging with augmented randomization to the input and outcome of the base classifiers. To tackle the issue of change in distribution that arises with gradual changes from learned fakes to entirely new fingerprint artifacts, the SFincBuster employs LBE with ADWIN (Adaptive WINDowing) technique that continuously evaluate the performance of underlying base model and whenever a change is detected the weakest classifier is substituted with a new one. Our approach achieves high classification accuracy, even though it is not prerequisite to access all features at once. The SFincBuster is trained and evaluated on LivDet 2009, LivDet 2011, LivDet 2013, LivDet 2015 and LivDet 2021 benchmark datasets and yields maximum average classification accuracy (ACA) of 98.65% on LivDet 2013 and LivDet 2015 datasets. The model exhibits stupendous generalization capabilities with an average classification error rate (ACER) of 1.39% for known fakes (KF) and 2.84% for unknown fakes (UF). Finally, the comparable investigation perceives that the SFincBuster model demonstrates a noteworthy performance gain over the similar state-of-the-art (SOTA) approaches and achieve an improved benchmark for real-time cross-sensor, cross-material and cross-dataset scenarios.

Performance comparison of CNNs on high-resolution multispectral dataset applied to land cover classification problem

Multispectral images acquired by satellites have been used in many fields such as agriculture, urban change detection, finding fire-hazardous forest areas, and real-time surface monitoring. The central issue in remote sensing analysis is land use and land cover classification. Land use and land cover classification (LULC) is the process of classification into meaningful classes based on the spectral characteristics of remote sensing data. Land use and land cover classification is a challenging task due to the complex nature of the Earth's surface. The accuracy of solving the issue using deep learning approaches depends on the quality of the remote sensing data, the choice of the classification algorithm. The ability to obtain high-resolution multispectral images periodically could dramatically improve remote sensing solutions. In this study, we propose a solution for the land cover and land classification problem of high-resolution remote sensing data by applying deep learning methods using EuroPlanet geo-referenced high-quality images with four bands and pixel resolution of 204x204 per image, and acquired by Planet platform in 2020-2022 years. The dataset consists of 25911 images with spatial resolution up to 3.125 meters per pixel and 10 different classes. In the past decade, artificial neural networks have shown great performance in solving complex image classification tasks. For the dataset evaluation, we have taken advantage of state-of-art pretrained convolutional neural network models ResNet50v2, EfficientNetV2, Xception, VGG-16, and DenseNet201 with fine tuning. It has been established that DenseNet201 pretrained neural network outperformed other models. The accuracy of the test data was 92.01 % and the F1 metric was 91.63 %. In addition, bands evaluation for the dataset was carried out. Overall classification accuracy of 93.83 % and F1 score of 93.56 % were achieved by DenseNet201 model. The results could be used for area verification, real-time monitoring, and surface change detection. Nowadays, this is very helpful for Ukrainian territory because of the Russian invasion and the country's recovery in the future.

Human Action Behavior Recognition in Still Images with Proposed Frames Selection Using Transfer Learning

One of the most difficult challenges is recognizing human actions., especially in still images where there isn't much movement. Therefore, Using the transfer learning strategy, we suggested a technique for identifying human action., which consists of training some of the layers of deep learning techniques while freezing others. Also presented a way for data split, which is to choose some frames because we are working on a large dataset such as ucf-101, and this method is summarized by discovering the features for each frame, then clustering the elements, and then choosing a percentage of each cluster for training and test data. We used three techniques. They are vgg16, inceptionv3, and xception. The proposed models have been implemented on UCF-101 Dataset. Depending on three data split methods with the dataset, the random split method, and the proposed split method, the inceptionv3 achieved the highest accuracy. In contrast, the vgg16 achieved the least accuracy, and the accuracy of the xception was close to that of the inceptionv3. By comparing the size of the dataset, the proposed methods achieved good results: the vgg16 in the proposed split attained an accuracy of 92.5%, the inception v3 in the proposed split attained an accuracy of 98.12%, and the xception in the proposed split attained an accuracy of 95.16%. The VGG16 network is simple, so the VGG16 is less accurate. While the network in inceptionv3, xception, is more extensive and complex, the learning space is more significant, although the network size is more prominent in inceptionv3, xception. We only trained some blocks in the top layer

Identification of Rice Freshness Using Terahertz Imaging and Deep Learning

Retention of rice freshness is highly dependent on storage temperature. Timely and accurate identification of rice freshness is critical to ensure food security. Here, we characterize the freshness of rice in reference to storage temperature. Terahertz reflection imaging is a non-destructive and deeply penetrating technique that can be used for detecting rice freshness. Due to the shortcomings of traditional machine learning, such as limited processing of nonlinear problems and insufficient computing power. Deep learning has the advantages of strong learning ability and high portability. Therefore, for rice freshness identification, the VGG19 network and the Inception-ResNet-v2 network were used in this paper. Moreover, we propose an improved 1D-VGG19-Inception-ResNet-A network. This network possesses the advantages of low time consumption from the 1D-VGG19 network and high classification accuracy from the 1D-Inception-ResNet-V2 network. Compared with the traditional algorithms, the accuracy of the proposed network is significantly improved, with the rice freshness recognition accuracy of 99.80%. The experimental results indicate that terahertz spectral imaging and deep learning algorithms are viable tools for monitoring rice freshness.

Hybrid computer aided diagnostic system designs for screen film mammograms using DL‐based feature extraction and ML‐based classifiers

AbstractMammography is most popular imaging method used often in predicting breast cancer within women above age of 38 years. Various computer‐assisted algorithms have been employed for classifying breast masses as normal or malignant using screen film mammographic (SFM) images. In present research work, exhaustive experimentations have been carried out with nine deep learning‐based convolutional neural networks (CNNs) belonging to the three different categories of CNN architectures including (a) simple convolution‐based series models, that is VGG16 and VGG19 (b) simple convolution‐based directed acyclic graph (DAG) model, that is GoogleNet and (c) dilated convolution‐based DAG models, that is ResNet18, ResNet50, Inceptionv3, XceptionNet, ShuffleNet and MobileNet‐V2, for binary classification of the mammographic masses with SFM images. The experimental work has been carried out using 518 mammographic images taken from DDSM dataset with 208 images ϵ benign class and 310 images ϵ malignant class, respectively. The encoder‐decoder based semantic segmentation network model, that is ResNet50 has been used for the segmentation of mammographic masses from SFM images. The segmented masses images obtained from the ResNet50 model are subjected to classification experiments. To design a robust hybrid classifier design, that is, deep learning (DL)‐based feature extraction and machine learning (ML)‐based classification, the first step is to obtain an optimal DL‐based feature extractor for classification task. The optimal feature set obtained by the best performing CNN Model, that is, VGG 19 has been subjected to correlation‐based feature extraction and ML‐based classifiers including (i) adaptive neuro fuzzy classifier‐linguistic hedges (ii) principal component analysis‐ support vector machine classifier and (iii) GA‐SVM classifier to yield an optimal hybrid computer aided diagnostic (CAD) system design. It is found that hybrid CAD system using VGG19 as feature extractor and ANFC‐LH as classifier yields 96% the highest classification accuracy. The other performance parameters yield values, that is 96% sensitivity, 96% specificity, 96% F‐score, 96% precision and 92% MCC, which indicates a best prediction of binary classification. The test images which were misclassified by these hybrid CAD system designs were analysed subjectively by experienced participating radiologist. The results obtained by present work suggests that proposed hybrid CAD system with VGG19 Network model acting as feature extractor and ANFC‐LH classifier can be employed for the differential diagnosis of benign as well as malignant mammographic masses using SFM images in a routine clinical setting.

On-Device Deep Multi-Task Inference via Multi-Task Zipping

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of deep models needs to be trimmed down to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme that induces a minimal change in the error function. MTZ inherits information from eachmodel and demands light retraining to re-boost the accuracy of individual tasks. MTZ supports typical network layers and applies to inference tasks with different input domains. Evaluations show that MTZ can fully merge the hidden layers of two VGG-16 network. Moreover, MTZ can effectively merge nine residual networks for diverse inference tasks and models for different input domains. Withthe joint model merged by MTZ, the latency to switch between these tasks on memory-constrained devices is reduced by 8.71.

Lung Image Classification Based On Long-Short Term Memory recurrent neural network

Due to various factors such as complicated lung imaging and rapidly growing amount of data, the task for imaging technicians is arduous. The emergence of artificial intelligence assisted diagnosis technology comes just in time.To effectively classify lung partial images and alleviate the burden of medical application, a deep learning method based on attention mechanism is therefore developed. The proposed model uses deep learning as the basic integrates Long-Shot term memory (LSTM) the recurrent neural network (RNN). Technology for lung imaging diagnosis based on artificial intelligence has evolved through time from combined diagnosis of multiple diseases to the diagnosis of a single specific disease. The suggested network’s overall classification accuracy, according to experiments, is 95.93%, which is 1.019% greater than that of the deep learning basic network. It also outperforms the VGG16 and VGG19 networks in terms of classification performance. Finally, the benefits and drawbacks of the suggested algorithm are explored, as well as the future development path.

Ultrasonic evaluation of fetal lung development using deep learning with graph

BackgroundThe neonatal respiratory morbidity that was primarily caused by the immaturity of the fetal lung is an important clinical issue in close relation to the morbidity and mortality of the fetus. In clinics, the amniocentesis has been used to evaluate the fetal lung maturity, which is time-consuming, costly and invasive. As a non-invasive means, ultrasonography has been explored to quantitatively examine the fetal lung in the past decades. However, existing studies required the contour of the fetal lung which was delineated manually. This may lead to significant inter- and intra-observer variations. MethodsWe proposed a deep learning model for automated fetal lung segmentation and measurement, which was constructed combined U-Net with Graph model and pre-trained Vgg-16 network. The graph connection would extract stable feature for final segmentation and pre-trained method could speed up convergence.The model was trained with 3500 datasets augmented from 250 ultrasound images with both the fetal lung and heart delineated manually, and tested on 50 ultrasound images. In addition, the correlation between the size of fetal lung/heart as delineated by the model with gestational age was analyzed. ResultsThe fetal lung and cardiac area were segmented automatically with the accuracy, average Intersection over Union(IoU), sensitivity and precision being 0.991, 0.818, 0.909 and 0.888, respectively. In addition, the size of fetal lung/heart was well correlated with the gestational age, demonstrating good potentials for assessing the fetal development. ConclusionsThis study proposed a new robust method for automatic fetal lung segmentation in ultrasound images using Vgg16-GCN-UNet. Our proposed method could be utilized potentially not only to improve existing research in quantitative analyzing the fetal lung using ultrasound imaging technology, but also to alleviate the labor of the clinicians in routine measurement of the fetal lung/cardiac.

Tactile recognition technology based on Multi-channel fiber optical sensing system

In order to achieve efficient and high-accuracy tactile sensing recognition of objects in complex industrial environments, this paper builds a multi-channel fiber optic tactile sensing system which is based on recurrence plot(RP) and VGG network. We design and build a bionic three-fingers tactile sensing system with fiber bragg grating(FBG) for acquiring signals. Three fiber Bragg gratings are pasted on the inside of an industrial three-finger flexible mechanical claw using an epoxy resin. After test,the packaged FBG still has good linear sensing characteristics, and its strain sensitivity is 0.51 pm/με. For solving the fusion problem of three-finger tactile signals, this paper proposes an improved RP algorithm to encode multi-channel one-dimensional tactile sensing signals into images, which not only reveals deeper temporal correlation of sensing signals, but also has higher robustness to noise. We use the VGG network to accurately classify the grasped objects. Six visually similar classes of fruits and vegetables are selected for tactile sensing. The results show that the accuracy of the system can reach 99.204%, the recognition time of each object can be as low as 0.29 s, which almost meets the industry standard of real-time sorting.

An Intelligent and Precise Agriculture Model in Sustainable Cities Based on Visualized Symptoms

Plant diseases represent one of the critical issues which lead to a major decrease in the quantity and quality of crops. Therefore, the early detection of plant diseases can avoid any losses or damage to these crops. This paper presents an image processing and a deep learning-based automatic approach that classifies the diseases that strike the apple leaves. The proposed system has been tested using over 18,000 images from the Apple Diseases Dataset by PlantVillage, including images of healthy and affected apple leaves. We applied the VGG-16 architecture to a pre-trained unlabeled dataset of plant leave images. Then, we used some other deep learning pre-trained architectures, including Inception-V3, ResNet-50, and VGG-19, to solve the visualization-related problems in computer vision, including object classification. These networks can train the images dataset and compare the achieved results, including accuracy and error rate between those architectures. The preliminary results demonstrate the effectiveness of the proposed Inception V3 and VGG-16 approaches. The obtained results demonstrate that Inception V3 achieves an accuracy of 92.42% with an error rate of 0.3037%, while the VGG-16 network achieves an accuracy of 91.53% with an error rate of 0.4785%. The experiments show that these two deep learning networks can achieve satisfying results under various conditions, including lighting, background scene, camera resolution, size, viewpoint, and scene direction.

An ensemble method for the detection and classification of lung cancer using Computed Tomography images utilizing a capsule network with Visual Geometry Group

The five-year survival rate for lung cancer is among the lowest of all malignancies. Lung cancer possesses a high incidence of death per capita, therefore finding it early is crucial. To this end, Computed Tomography (CT) scans are often employed for the early identification of lung cancer, with clinical judgement serving as the current reference standard. Deep learning Convolutional Neural Networks (CNNs)have been used in end-to-end approaches for the detection of lung nodules. Capsule Networks are one of the numerous deep learning models that have been presented as a potential solution to the problems caused by the shortcomings of CNNs, such as the inability of CNNs to recognize fine-grained spatial correlations. As of now, capsule networks have shown to be effective in solving medical imaging challenges. To build on the previous work, Visual Geometry Group - Capsule Network (VGG-CapsNet) an innovative capsule network-based combination of VGG and Capsule Network is introduced. According to the findings, VGG-CapsNetis superior to using a basiccapsule network, or a combination ofCNNcapsule networks, with a 0.980 AUC and a 98.61 % F1-Score, a precision of 99.07 %, a recall of 98.16 %, a specificity of 99.07 %,and an accuracy of 98.61 % for LIDC-IDRI datasets, and 98.14 % precision, 99.16 specificity, 98.07 % accuracy, 0.98 AUC and 98.14 % F1-Score for Kaggle datasets.

Multi-modal IoT-based medical data processing for disease diagnosis using Heuristic-derived deep learning

Nowadays, the quick development of the Internet of Things (IoT) has changed our lifestyle. However, disease diagnosis is a difficult task owing to managing an enormous volume of data. Thus, in this research task, the latest IoT-assisted disease detection model for healthcare applications is developed. Initially, the patient data are taken from the IoT sensor devices in image, text, and signal data. The gathered patient data is further forward to the pre-processing phase. Accordingly, the images are gathered from patients’ data using IoT devices and forward to the feature extraction process. Feature extraction is done based on the IoT-collected images using VGG16 and Inception network. Moreover, the signals are garnered from the patient’s data and fed to the decomposition procedure. It is done by Empirical Mode Decomposition (EMD) technique. Then, the optimal feature selection of data, images, and signals is carried out by a hybrid algorithm termed Mating Probability-based Hybrid Strider Glowworm Swarm Optimization (MP-HSGSO). Finally, the Radial Basis Recurrent Neural Network (RBRNN) using MP-HSGSO is suggested to get the detected outcomes. Here, various brain diseases have been detected to classify the disease. This designed RBRNN method is utilized for efficient treatment, and also it provides the appropriate decision-making through processing various kinds of multimodal data. Throughout the simulation outcomes, the accuracy and precision of the offered method achieve 97 % and 96 %. Consequently, the simulation outcome of the offered method is proved that the designed model using a deep learning model shows enriched performance in clinical trial applications.

DeepBLS: Deep Feature-Based Broad Learning System for Tissue Phenotyping in Colorectal Cancer WSIs.

Tissue phenotyping is a fundamental step in computational pathology for the analysis of tumor micro-environment in whole slide images (WSIs). Automatic tissue phenotyping in whole slide images (WSIs) of colorectal cancer (CRC) assists pathologists in better cancer grading and prognostication. In this paper, we propose a novel algorithm for the identification of distinct tissue components in colon cancer histology images by blending a comprehensive learning system with deep features extraction in the current work. Firstly, we extracted the features from the pre-trained VGG19 network which are then transformed into mapped features space for nodes enhancement generation. Utilizing both mapped features and enhancement nodes, the proposed algorithm classifies seven distinct tissue components including stroma, tumor, complex stroma, necrotic, normal benign, lymphocytes, and smooth muscle. To validate our proposed model, the experiments are performed on two publicly available colorectal cancer histology datasets. We showcase that our approach achieves a remarkable performance boost surpassing existing state-of-the-art methods by (1.3% AvTP, 2% F1) and (7% AvTP, 6% F1) on CRCD-1, and CRCD-2, respectively.