Deep Convolutional Neural Network Architecture Research Articles

Optimized deep learning networks for accurate identification of cancer cells in bone marrow

Radiologists utilize pictures from X-rays, magnetic resonance imaging, or computed tomography scans to diagnose bone cancer. Manual methods are labor-intensive and may need specialized knowledge. As a result, creating an automated process for distinguishing between malignant and healthy bone is essential. Bones that have cancer have a different texture than bones in unaffected areas. Diagnosing hematological illnesses relies on correct labeling and categorizing nucleated cells in the bone marrow. However, timely diagnosis and treatment are hampered by pathologists' need to identify specimens, which can be sensitive and time-consuming manually. Humanity's ability to evaluate and identify these more complicated illnesses has significantly been bolstered by the development of artificial intelligence, particularly machine, and deep learning. Conversely, much research and development is needed to enhance cancer cell identification—and lower false alarm rates. We built a deep learning model for morphological analysis to solve this problem. This paper introduces a novel deep convolutional neural network architecture in which hybrid multi-objective and category-based optimization algorithms are used to optimize the hyperparameters adaptively. Using the processed cell pictures as input, the proposed model is then trained with an optimized attention-based multi-scale convolutional neural network to identify the kind of cancer cells in the bone marrow. Extensive experiments are run on publicly available datasets, with the results being measured and evaluated using a wide range of performance indicators. In contrast to deep learning models that have already been trained, the total accuracy of 99.7% was determined to be superior.

Synergistic application of digital outcrop characterization techniques and deep learning algorithms in geological exploration

In order to meet the needs of geologists for the analysis of data characterizing field outcrops (rock sections or formations exposed on the ground surface), this study developed a field digital outcrop visualization platform based on Cesium (a 3D geospatial visualization technology) digital outcrop characterization technology. The platform was developed based on WebGL (a protocol for rendering interactions on web pages), which overcame the shortcomings of traditional software in terms of visualization, cross-device, cross-platform, and ease of use. Firstly, UAV inclined photography is used for data collection, which transforms a large amount of geological data into an intuitive 3D geological model, while the visualization platform provides rich measurement and mapping tools for the identified features, which more intuitively displays the outcrop information, helps geological explorers to understand the geological conditions in the field more quickly and comprehensively, and improves the analysis efficiency and ease-of-use of outcrop characterization data. Combined with the improved VGG19 (a deep convolutional neural network architecture) algorithm model, it has excellent performance in dealing with the fine texture and complex structure of rocks, which significantly improves the accuracy of lithology identification. The synergistic application of this technology provides geologists with a faster and more comprehensive means to understand the geological conditions in the field. The reliability of combining the Cesium digital outcrop characterization technology with the VGG19 lithology identification algorithm in geological exploration is verified through case studies. The synergistic application of this technology will greatly enhance the efficiency and ease of analysis of outcrop characterization in the field, and provide new perspectives for future research in geosciences.

Application of a deep-learning marker for morbidity and mortality prediction derived from retinal photographs: a cohort development and validation study

Biological ageing markers are useful to risk stratify morbidity and mortality more precisely than chronological age. In this study, we aimed to develop a novel deep-learning-based biological ageing marker (referred to as RetiPhenoAge hereafter) using retinal images and PhenoAge, a composite biomarker of phenotypic age. We used retinal photographs from the UK Biobank dataset to train a deep-learning algorithm to predict the composite score of PhenoAge. We used a deep convolutional neural network architecture with multiple layers to develop our deep-learning-based biological ageing marker, as RetiPhenoAge, with the aim of identifying patterns and features in the retina associated with variations of blood biomarkers related to renal, immune, liver functions, inflammation, and energy metabolism, and chronological age. We determined the performance of this biological ageing marker for the prediction of morbidity (cardiovascular disease and cancer events) and mortality (all-cause, cardiovascular disease, and cancer) in three independent cohorts (UK Biobank, the Singapore Epidemiology of Eye Diseases [SEED], and the Age-Related Eye Disease Study [AREDS] from the USA). We also compared the performance of RetiPhenoAge with two other known ageing biomarkers (hand grip strength and adjusted leukocyte telomere length) and one lifestyle factor (physical activity) for risk stratification of mortality and morbidity. We explored the underlying biology of RetiPhenoAge by assessing its associations with different systemic characteristics (eg, diabetes or hypertension) and blood metabolite levels. We also did a genome-wide association study to identify genetic variants associated with RetiPhenoAge, followed by expression quantitative trait loci mapping, a gene-based analysis, and a gene-set analysis. Cox proportional hazards models were used to estimate the hazard ratios (HRs) and corresponding 95% CIs for the associations between RetiPhenoAge and the different morbidity and mortality outcomes. Retinal photographs for 34 061UK Biobank participants were used to train the model, and data for 9429participants from the SEED cohort and for 3986participants from the AREDS cohort were included in the study. RetiPhenoAge was associated with all-cause mortality (HR 1·92 [95% CI 1·42-2·61]), cardiovascular disease mortality (1·97 [1·02-3·82]), cancer mortality (2·07 [1·29-3·33]), and cardiovascular disease events (1·70[1·17-2·47]), independent of PhenoAge and other possible confounders. Similar findings were found in the two independent cohorts (HR 1·67 [1·21-2·31] for cardiovascular disease mortality in SEED and 2·07 [1·10-3·92] in AREDS). RetiPhenoAge had stronger associations with mortality and morbidity than did hand grip strength, telomere length, and physical activity. We identified two genetic variants that were significantly associated with RetiPhenoAge (single nucleotide polymorphisms rs3791224 and rs8001273), and were linked to expression quantitative trait locis in various tissues, including the heart, kidneys, and the brain. Our new deep-learning-derived biological ageing marker is a robust predictor of mortality and morbidity outcomes and could be used as a novel non-invasive method to measure ageing. Singapore National Medical Research Council and Agency for Science, Technology and Research, Singapore.

Identifying Mergers in the Legacy Surveys with Few-shot Learning

Galaxy mergers exert a pivotal influence on the evolutionary trajectory of galaxies and the expansive development of cosmic structures. The primary challenge encountered in machine learning–based identification of merging galaxies arises from the scarcity of meticulously labeled data sets specifically dedicated to merging galaxies. In this paper, we propose a novel framework utilizing few-shot learning techniques to identify galaxy mergers in the Legacy Surveys. Few-shot learning enables effective classification of merging galaxies even when confronted with limited labeled training samples. We employ a deep convolutional neural network architecture trained on data sets sampled from Galaxy Zoo Decals to learn essential features and generalize to new instances. Our experimental results demonstrate the efficacy of our approach, achieving high accuracy and precision in identifying galaxy mergers with few labeled training samples. Furthermore, we investigate the impact of various factors, such as the number of training samples and network architectures, on the performance of the few-shot learning model. The proposed methodology offers a promising avenue for automating the identification of galaxy mergers in large-scale surveys, facilitating the comprehensive study of galaxy evolution and structure formation. In pursuit of identifying galaxy mergers, our methodology is applied to analyze the Data Release 9 of the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys. As a result, we have unveiled an extensive catalog encompassing 648,183 galaxy merger candidates. We publicly release the catalog alongside this paper.

Tuning parameters of deep neural network training algorithms pays off: a computational study

AbstractThe paper aims to investigate the impact of the optimization algorithms on the training of deep neural networks with an eye to the interaction between the optimizer and the generalization performance. In particular, we aim to analyze the behavior of state-of-the-art optimization algorithms in relationship to their hyperparameters setting to detect robustness with respect to the choice of a certain starting point in ending on different local solutions. We conduct extensive computational experiments using nine open-source optimization algorithms to train deep Convolutional Neural Network architectures on an image multi-class classification task. Precisely, we consider several architectures by changing the number of layers and neurons per layer, to evaluate the impact of different width and depth structures on the computational optimization performance. We show that the optimizers often return different local solutions and highlight the strong correlation between the quality of the solution found and the generalization capability of the trained network. We also discuss the role of hyperparameters tuning and show how a tuned hyperparameters setting can be re-used for the same task on different problems achieving better efficiency and generalization performance than a default setting.

Factorizers for distributed sparse block codes

Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however is to disentangle, or factorize, the distributed representation of data structures into their constituent elements without having to search through all possible combinations. This factorization becomes more challenging when SBCs vectors are noisy due to perceptual uncertainty and approximations made by modern neural networks to generate the query SBCs vectors. To address these challenges, we first propose a fast and highly accurate method for factorizing a more flexible and hence generalized form of SBCs, dubbed GSBCs. Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an ℓ ∞ -based similarity metric. Its random sampling mechanism, in combination with the search in superposition, allows us to analytically determine the expected number of decoding iterations, which matches the empirical observations up to the GSBC’s bundling capacity. Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs). This facilitates its application in replacing the large fully connected layer (FCL) in CNNs, whereby C trainable class vectors, or attribute combinations, can be implicitly represented by our factorizer having F-factor codebooks, each with C F fixed codevectors. We provide a methodology to flexibly integrate our factorizer in the classification layer of CNNs with a novel loss function. With this integration, the convolutional layers can generate a noisy product vector that our factorizer can still decode, whereby the decoded factors can have different interpretations based on downstream tasks. We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets. In all use cases, the number of parameters and operations are notably reduced compared to the FCL.

Detecting COVID-19 from chest X-ray images using machine learning and deep convolutional neural networks

<p>The world was affected by a novel coronavirus in December 2019 that changed human life. Several types of research have been done, substantial scientific advances have been made, and millions of dollars have been spent on bringing scholars and scientists to one platform to end this critical pandemic. Ascertaining COVID-19 diagnoses in the initial stage of the pandemic was critical, specifically for patients with no manifestations. In this case, artificial intelligence-based systems were proposed to identify the virus at an earlier phase. Thus, the present study suggests a machine vision scheme to identify COVID-19 from chest X-ray images. Three machine learning approaches, such as logistic regression (LR), decision tree (DT), and random forest (RF), were implemented with more than 95% accuracy. The deep convolutional neural network (CNN) architecture was also proposed and implemented with a 99.99% detection rate. Therefore, the present work can effectively detect COVID-19 cases in the early stages.</p>

DeepOpt: a deep learning optimized privacy preservation framework for cyber-physical systems

Privacy preservation and security enhancement are the key components of any network architecture due to advanced attack procedures. Cyber-Physical Systems (CPS) also need a mitigation and prevention strategy to deal with cyber threats. The existing approaches majorly deal with attack detection and focus on one or two attacks at a time. With this focus and demand of the CPS, this work proposes a deep learning optimized privacy preservation framework called DeepOpt. This proposed framework prevents the network from attackers and maintains security by classifying multiple attackers simultaneously using deep learning architecture. The proposed framework initializes privacy preservation using the trust-based approach and a hybrid optimization algorithm. In this, the network is divided into different zones, and each zone is secured using trust parameters with additional verification by secure hash function. The hybrid optimization selects the communication path using trust and energy that returns the attack-free path. This proposed architecture is simulated over different network scenarios with or without attacker nodes, and their traces are labeled to train the proposed deep convolutional neural network architecture. Finally, these models are integrated, and their performance is analyzed in different network scenarios and the presence of five different attackers such as blackhole, wormhole, man-in-the-middle attack, spoofing, and distributed denial of service. The simulation results, with improvement in detection accuracy, packet delivery ratio, and other performance factors, indicate the effectiveness of the proposed framework for both prevention and mitigation. Hence, this overall architecture preserves the privacy of CPS even in multifarious dynamic network scenarios.

DUNET D UNET Dilated UNET for Brain Tumor Sub Region Segmentation using MRI Images

The precise diagnosis and treatment planning of brain tumors significantly rely on the accurate segmentation of sub-regions from Magnetic Resonance Imaging (MRI) data. In this research, we propose a framework, D-UNET (Dilated-UNET), which enhances the traditional UNET architecture by incorporating dilated convolutions. UNET is the deep CNN architecture widely adopted for biomedical image segmentation tasks. D-UNET is specifically designed for brain tumor sub-region segmentation from multi-modal (T1, T2, T1ce, Flair) MRI images in nifti file format, each comprising 155 slices. The framework comprises of four distinct steps viz. data collection, data preprocessing, model training, and outcome evaluation. D-UNET employs two key modules during training, the dilated encoding module and the dilated decoding module. These modules enable the model to efficiently capture multi-scale contextual information, facilitating better representation learning for complex and varied tumor sub[1]regions. We evaluated the performance of D-UNET using Intersection over Union and Dice Coefficient metrics. The experimental results demonstrate that D-UNET outperforms the traditional UNET and other benchmark models in terms of segmentation accuracy. Notably, D-UNET excels in capturing finer details and intricate shapes of tumor sub-regions, contributing to its superiority in brain tumor segmentation. The ability to precisely delineate tumor sub-regions from different modalities provides crucial insights for medical professionals in treatment planning and decision-making.

Deep convolutional neural network for Lampung character recognition

Recognition of document based, and handwritten characters has recently emerged as highly relevant field of study in the field of digital image processing. The ability to read and write Lampung script is a crucial competency as it helps preserve the language, which is a part of Indonesian culture. This research utilizes data obtained from classified documents and handwritten samples, categorized into eight types. To recognize Lampung characters, deep convolutional neural network (DCNN) architecture is proposed. The novelty of this architecture lies in optimizing document-based and handwritten character recognition to achieve the best performance in terms of accuracy and execution time. The proposed architecture will be compared to principal component analysis (PCA) combined with support vector machine (SVM) to evaluate its results. Experimental results using the DCNN architecture show an average accuracy of 99.3% and an execution time of 283 seconds for all data, while PCA and SVM exhibit an average accuracy of 92.9%. Furthermore, the recognition results for all data from documents and handwritten samples yield satisfactory accuracy of 98.6%. These results make the DCNN architecture suitable for use in recognizing Lampung characters and are expected to make it easier for Lampung people to recognize Lampung character.

Result and Analysis of Soft Computing Techniques for Diagnosis of Skin Diseases

Abstract: A prevalent bodily issue that has a significant impact on people's lives is skin disease. An early and precise identification of the condition can assist patients in receiving proper care, hastening their recovery. Convolutional neural networks (CNN) powered by deep learning have recently made major advancements that have greatly increased the accuracy of illness categorization. This led to the motivation for this work, which used deep CNN architectures to identify two different skin conditions—eczema and psoriasis. Ten fold cross validation has been utilized to examine the performance of five distinct cutting-edge CNN architectures. With the Adam optimizer, the Inception ResNet v2 architecture achieves a maximum validation accuracy of 97.1%. The results of the performance matrices suggest that the model performs remarkably well in terms of diagnosing skin disorders. Additionally, the study demonstrates two approaches for the practical application of the implemented model. (i) CNN Approach ii) PCA Approach.

Intelligent Data Processing for Alzheimer's Disease Using Deep Learning

Background: With the advancement in Alzheimer's disease (AD) brain, cells start to deteriorate, which eventually creates physical dependency and mental instability that interferes with daily living. Presently, this disease is immedicable. Therefore, the only suitable treatment is early detection and prevention. Although many studies have investigated the usefulness of deep learning in AD detection, relatively few have focused on the necessary image preprocessing processes, which are essential to any computer-aided diagnostic system. Furthermore, an optimal classification strategy that takes into account a diverse handful of prominent features is required. Method: This paper focuses on improving MRI-based AD detection by incorporating image enhancement approaches and deep hybrid learning into a fused framework to harness the power of multiple Deep Learning (DL) architectures and Machine Learning (ML) classifiers. The deep features extracted from three heterogeneous CNN architectures, namely, VGG16, DensetNet169, and MobileNetV1, are fused to produce a more informative and discriminative hybrid feature. Furthermore, the mRMR approach was used to optimise the acquired features, followed by classification via a stack of multiple ML classifiers to predict the target class. Results: The proposed architecture based on feature fusion strategy and ensemble learning resulted in 99.53%(Accuracy), 99.73%(Precision),99.70%(Recall), and 99.72% (F1 score). The presented model outperformed individual deep CNN architectures. Conclusion: Lastly, we present a sobol-based sensitivity analysis that illustrates the concentration of the presented technique upon significant regions of the image and can assist medical professionals in decoding the decisions. The presented technique exeplifies the potency and constancy of categorizing Alzheimer's disease.

Comparison of data fusion strategies for automated prostate lesion detection using mpMRI correlated with whole mount histology

BackgroundIn this work, we compare input level, feature level and decision level data fusion techniques for automatic detection of clinically significant prostate lesions (csPCa).MethodsMultiple deep learning CNN architectures were developed using the Unet as the baseline. The CNNs use both multiparametric MRI images (T2W, ADC, and High b-value) and quantitative clinical data (prostate specific antigen (PSA), PSA density (PSAD), prostate gland volume & gross tumor volume (GTV)), and only mp-MRI images (n = 118), as input. In addition, co-registered ground truth data from whole mount histopathology images (n = 22) were used as a test set for evaluation.ResultsThe CNNs achieved for early/intermediate / late level fusion a precision of 0.41/0.51/0.61, recall value of 0.18/0.22/0.25, an average precision of 0.13 / 0.19 / 0.27, and F scores of 0.55/0.67/ 0.76. Dice Sorensen Coefficient (DSC) was used to evaluate the influence of combining mpMRI with parametric clinical data for the detection of csPCa. We compared the DSC between the predictions of CNN’s trained with mpMRI and parametric clinical and the CNN’s trained with only mpMRI images as input with the ground truth. We obtained a DSC of data 0.30/0.34/0.36 and 0.26/0.33/0.34 respectively. Additionally, we evaluated the influence of each mpMRI input channel for the task of csPCa detection and obtained a DSC of 0.14 / 0.25 / 0.28.ConclusionThe results show that the decision level fusion network performs better for the task of prostate lesion detection. Combining mpMRI data with quantitative clinical data does not show significant differences between these networks (p = 0.26/0.62/0.85). The results show that CNNs trained with all mpMRI data outperform CNNs with less input channels which is consistent with current clinical protocols where the same input is used for PI-RADS lesion scoring.Trial registrationThe trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under proposal number Nr. 476/14 & 476/19.

ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing.

Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.

Using Machine Learning to Identify Diseases and Perform Sorting in Apple Fruit

Fruit diseases play a major role in global agriculture, leading to substantial crop losses and influencing food production and economic stability. In this age of Industry 4.0 the fruit sorting is an important part in the food processing wherein this work plays a vital role. In this study, a solution for the detection and classification of apple fruit diseases is proposed and experimentally validated. Deep learning models offer promise for automating disease identification using fruit images, but encounter obstacles such as therequirement for extensive training data, computational complexity, and the risk of overfitting. This study introduces an innovative convolutional neural network (CNN) architecture aimed at addressing these challenges by incorporating a reduced number of layers, thus alleviating computational burdens while maintaining performance. Additionally, augmentation techniques such as shift, shear, scaling, zoom, and flipping are employed to diversify the training set without additional image acquisition. Our CNN model is specifically trained to identify common apple crop diseases like Scab, Rot, and Blotch. Rigorous experimental evaluation demonstrates the effectiveness ofour model, achieving a remarkable classification accuracy of 95.37%. Significantly, our model demonstrates reduced storage requirements and faster execution times compared to existing deep CNN architectures, enabling deployment on handheld devices and resource-limited environments. While other CNN models may offer similar accuracy levels, our approach emphasizes efficiency and resource optimization, rendering it practical for real-world applications in agriculture. Furthermore, our CNN model exhibits resilience to environmental variations and imaging parameters, enhancing its applicability across diverse agricultural settings. By leveraging advanced machine learning techniques, the approach developed in this experimental work contributes to modernizing fruits and vegetables sorting operations in food processing, crop management practices thus promoting agricultural sustainability. The scalability and portability of our model make it suitable for deployment in both small-scale farms and large-scale agricultural operations.

A new multi-objective hyperparameter optimization algorithm for COVID-19 detection from x-ray images

The coronavirus occurred in Wuhan (China) first and it was declared a global pandemic. To detect coronavirus X-ray images can be used. Convolutional neural networks (CNNs) are used commonly to detect illness from images. There can be lots of different alternative deep CNN models or architectures. To find the best architecture, hyper-parameter optimization can be used. In this study, the problem is modeled as a multi-objective optimization (MOO) problem. Objective functions are multi-class cross entropy, error ratio, and complexity of the CNN network. For the best solutions to the objective functions, multi-objective hyper-parameter optimization is made by NSGA-III, NSGA-II, R-NSGA-II, SMS-EMOA, MOEA/D, and proposed Swarm Genetic Algorithms (SGA). SGA is a swarm-based algorithm with a cross-over process. All six algorithms are run and give Pareto optimal solution sets. When the figures obtained from the algorithms are analyzed and algorithm hypervolume values are compared, SGA outperforms the NSGA-III, NSGA-II, R-NSGA-II, SMS-EMOA, and MOEA/D algorithms. It can be concluded that SGA is better than others for multi-objective hyper-parameter optimization algorithms for COVID-19 detection from X-ray images. Also, a sensitivity analysis has been made to understand the effect of the number of the parameters of CNN on model success.

DCNN for Pig Vocalization and Non-Vocalization Classification: Evaluate Model Robustness with New Data.

Since pig vocalization is an important indicator of monitoring pig conditions, pig vocalization detection and recognition using deep learning play a crucial role in the management and welfare of modern pig livestock farming. However, collecting pig sound data for deep learning model training takes time and effort. Acknowledging the challenges of collecting pig sound data for model training, this study introduces a deep convolutional neural network (DCNN) architecture for pig vocalization and non-vocalization classification with a real pig farm dataset. Various audio feature extraction methods were evaluated individually to compare the performance differences, including Mel-frequency cepstral coefficients (MFCC), Mel-spectrogram, Chroma, and Tonnetz. This study proposes a novel feature extraction method called Mixed-MMCT to improve the classification accuracy by integrating MFCC, Mel-spectrogram, Chroma, and Tonnetz features. These feature extraction methods were applied to extract relevant features from the pig sound dataset for input into a deep learning network. For the experiment, three datasets were collected from three actual pig farms: Nias, Gimje, and Jeongeup. Each dataset consists of 4000 WAV files (2000 pig vocalization and 2000 pig non-vocalization) with a duration of three seconds. Various audio data augmentation techniques are utilized in the training set to improve the model performance and generalization, including pitch-shifting, time-shifting, time-stretching, and background-noising. In this study, the performance of the predictive deep learning model was assessed using the k-fold cross-validation (k = 5) technique on each dataset. By conducting rigorous experiments, Mixed-MMCT showed superior accuracy on Nias, Gimje, and Jeongeup, with rates of 99.50%, 99.56%, and 99.67%, respectively. Robustness experiments were performed to prove the effectiveness of the model by using two farm datasets as a training set and a farm as a testing set. The average performance of the Mixed-MMCT in terms of accuracy, precision, recall, and F1-score reached rates of 95.67%, 96.25%, 95.68%, and 95.96%, respectively. All results demonstrate that the proposed Mixed-MMCT feature extraction method outperforms other methods regarding pig vocalization and non-vocalization classification in real pig livestock farming.

MRI-Based Brain Tumor Classification Using a Dilated Parallel Deep Convolutional Neural Network

Brain tumors are frequently classified with high accuracy using convolutional neural networks (CNNs) to better comprehend the spatial connections among pixels in complex pictures. Due to their tiny receptive fields, the majority of deep convolutional neural network (DCNN)-based techniques overfit and are unable to extract global context information from more significant regions. While dilated convolution retains data resolution at the output layer and increases the receptive field without adding computation, stacking several dilated convolutions has the drawback of producing a grid effect. This research suggests a dilated parallel deep convolutional neural network (PDCNN) architecture that preserves a wide receptive field in order to handle gridding artifacts and extract both coarse and fine features from the images. This article applies multiple preprocessing strategies to the input MRI images used to train the model. By contrasting various dilation rates, the global path uses a low dilation rate (2,1,1), while the local path uses a high dilation rate (4,2,1) for decremental even numbers to tackle gridding artifacts and to extract both coarse and fine features from the two parallel paths. Using three different types of MRI datasets, the suggested dilated PDCNN with the average ensemble method performs best. The accuracy achieved for the multiclass Kaggle dataset-III, Figshare dataset-II, and binary tumor identification dataset-I is 98.35%, 98.13%, and 98.67%, respectively. In comparison to state-of-the-art techniques, the suggested structure improves results by extracting both fine and coarse features, making it efficient.

VashaNet: An automated system for recognizing handwritten Bangla basic characters using deep convolutional neural network

Automated character recognition is currently highly popular due to its wide range of applications. Bengali handwritten character recognition (BHCR) is an extremely difficult issue because of the nature of the script. Very few handwritten character recognition (HCR) models are capable of accurately classifying all different sorts of Bangla characters. Recently, image recognition, video analytics, and natural language processing have all found great success using convolutional neural network (CNN) due to its ability to extract and classify features in novel ways. In this paper, we introduce a VashaNet model for recognizing Bangla handwritten basic characters. The suggested VashaNet model employs a 26-layer deep convolutional neural network (DCNN) architecture consisting of nine convolutional layers, six max pooling layers, two dropout layers, five batch normalization layers, one flattening layer, two dense layers, and one output layer. The experiment was performed over 2 datasets consisting of a primary dataset of 5750 images, CMATERdb 3.1.2 for the purpose of training and evaluating the model. The suggested character recognition model worked very well, with test accuracy rates of 94.60% for the primary dataset, 94.43% for CMATERdb 3.1.2 dataset. These remarkable outcomes demonstrate that the proposed VashaNet outperforms other existing methods and offers improved suitability in different character recognition tasks. The proposed approach is a viable candidate for the high efficient practical automatic BHCR system. The proposed approach is a more powerful candidate for the development of an automatic BHCR system for use in practical settings.

Ensemble of Deep CNN Models for Human Skin Disease Classification

ABSTRACTSkin diseases are among the leading causes of disability worldwide and are a significant cause of morbidity in sub‐Saharan Africa. It can be cured if identified early. Only an expert dermatologist can classify skin disease by examining clinical signs. Sometimes, it can happen that dermatologists do not correctly classify the Skin disease, and therefore prescribe inappropriate drugs to the patient. Various research has been done to automate skin disease classification. Almost all the studies were concentrated on classifying three to four types of skin diseases. Developing a model that can be used in real‐world practical AI applications is important. In this study, we present an ensemble model based on the hard‐voting scheme of three deep CNN architectures: SKDCNET, FVGG16, and InceptionV3 for automatic classification of the top eight skin diseases. The proposed model utilizes three architectural diversities: training from scratch, fine‐tuning, and transfer learning. We used median filter noise removal and data augmentation technique to increase the number of training datasets. The proposed ensemble model produces 98% of accuracy. As an outcome of this study, the proposed model has the potential to be used as a decision support method for dermatologists. It can also contribute to the early identification (treatment) of skin diseases to reduce their further spread.