MSRNet: Multiclass Skin Lesion Recognition Using Additional Residual Block Based Fine-Tuned Deep Models Information Fusion and Best Feature Selection.

Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin cancer, particularly melanoma, is becoming a severe health problem due to its rising prevalence. The considerable death rate linked with melanoma requires early detection to receive immediate and successful treatment. Lesion detection and classification are more challenging due to many forms of artifacts such as hairs, noise, and irregularity of lesion shape, color, irrelevant features, and textures. In this work, we proposed a deep-learning architecture for classifying multiclass skin cancer and melanoma detection. The proposed architecture consists of four core steps: image preprocessing, feature extraction and fusion, feature selection, and classification. A novel contrast enhancement technique is proposed based on the image luminance information. After that, two pre-trained deep models, DarkNet-53 and DensNet-201, are modified in terms of a residual block at the end and trained through transfer learning. In the learning process, the Genetic algorithm is applied to select hyperparameters. The resultant features are fused using a two-step approach named serial-harmonic mean. This step increases the accuracy of the correct classification, but some irrelevant information is also observed. Therefore, an algorithm is developed to select the best features called marine predator optimization (MPA) controlled Reyni Entropy. The selected features are finally classified using machine learning classifiers for the final classification. Two datasets, ISIC2018 and ISIC2019, have been selected for the experimental process. On these datasets, the obtained maximum accuracy of 85.4% and 98.80%, respectively. To prove the effectiveness of the proposed methods, a detailed comparison is conducted with several recent techniques and shows the proposed framework outperforms.

A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI.

Skin cancer is a serious disease that affects people all over the world. Melanoma is an aggressive form of skin cancer, and early detection can significantly reduce human mortality. In the United States, approximately 97,610 new cases of melanoma will be diagnosed in 2023. However, challenges such as lesion irregularities, low-contrast lesions, intraclass color similarity, redundant features, and imbalanced datasets make improved recognition accuracy using computerized techniques extremely difficult. This work presented a new framework for skin lesion recognition using data augmentation, deep learning, and explainable artificial intelligence. In the proposed framework, data augmentation is performed at the initial step to increase the dataset size, and then two pretrained deep learning models are employed. Both models have been fine-tuned and trained using deep transfer learning. Both models (Xception and ShuffleNet) utilize the global average pooling layer for deep feature extraction. The analysis of this step shows that some important information is missing; therefore, we performed the fusion. After the fusion process, the computational time was increased; therefore, we developed an improved Butterfly Optimization Algorithm. Using this algorithm, only the best features are selected and classified using machine learning classifiers. In addition, a GradCAM-based visualization is performed to analyze the important region in the image. Two publicly available datasets-ISIC2018 and HAM10000-have been utilized and obtained improved accuracy of 99.3% and 91.5%, respectively. Comparing the proposed framework accuracy with state-of-the-art methods reveals improved and less computational time.

Dynamics of chaotic system based on circuit design with Ulam stability through fractal-fractional derivative with power law kernel.

In this paper, the newly developed Fractal-Fractional derivative with power law kernel is used to analyse the dynamics of chaotic system based on a circuit design. The problem is modelled in terms of classical order nonlinear, coupled ordinary differential equations which is then generalized through Fractal-Fractional derivative with power law kernel. Furthermore, several theoretical analyses such as model equilibria, existence, uniqueness, and Ulam stability of the system have been calculated. The highly non-linear fractal-fractional order system is then analyzed through a numerical technique using the MATLAB software. The graphical solutions are portrayed in two dimensional graphs and three dimensional phase portraits and explained in detail in the discussion section while some concluding remarks have been drawn from the current study. It is worth noting that fractal-fractional differential operators can fastly converge the dynamics of chaotic system to its static equilibrium by adjusting the fractal and fractional parameters.

iELMNet: Integrating Novel Improved Extreme Learning Machine and Convolutional Neural Network Model for Traffic Sign Detection.

Traffic sign detection (TSD) in real-time environment holds great importance for applications such as automated-driven vehicles. Large variety of traffic signs, different appearances, and spatial representations causes a huge intraclass variation. In this article, an extreme learning machine (ELM), convolutional neural network (CNN), and scale transformation (ST)-based model, called improved extreme learning machine network, are proposed to detect traffic signs in real-time environment. The proposed model has a custom DenseNet-based novel CNN architecture, improved version of region proposal networks called accurate anchor prediction model (A2PM), ST, and ELM module. CNN architecture makes use of handcrafted features such as scale-invariant feature transform and Gabor to improvise the edges of traffic signs. The A2PM minimizes the redundancy among extracted features to make the model efficient and ST enables the model to detect traffic signs of different sizes. ELM module enhances the efficiency by reshaping the features. The proposed model is tested on three publicly available data sets, challenging unreal and real environments for traffic sign recognition, Tsinghua-Tencent 100K, and German traffic sign detection benchmark and achieves average precisions of 93.31%, 95.22%, and 99.45%, respectively. These results prove that the proposed model is more efficient than state-of-the-art sign detection techniques.

Hypocalcaemia As A Rare Reversible Cause Of Dilated Cardiomyopathy.

Dilated cardiomyopathy is characterized by dilation and enlargement of one or both ventricles with reduced systolic function. Calcium plays a key role in myocardial contraction. Hypocalcaemia can lead to a decrease in contraction, left ventricular systolic dysfunction, and heart failure with reduced ejection fraction (EF). Hypocalcaemia is a rare reversible cause of dilated cardiomyopathy. The author presents a case who presented with complaints of shortness of breath on exertion, orthopnoea, paroxysmal nocturnal dyspnoea, numbness and crampy muscular pains. He had a high JVP, systolic murmur on auscultation, hepatomegaly, pedal oedema and crackles on chest auscultation. His ECG showed sinus rhythm with prolonged QT interval. His echocardiography showed dilated cardiomyopathy with reduced ejection fraction, moderate mitral regurgitation and mild tricuspid regurgitation. His Calcium levels and PTH levels were both low. He was treated with ionotrophes, diuretics, vitamin D and calcium supplements, including both intravenous and oral. With the correction of calcium levels, he was weaned off the ionotrophic support and his ejection fraction improved. Calcium levels if low should be corrected in patients with dilated cardiomyopathy.

MHD flow of time-fractional Casson nanofluid using generalized Fourier and Fick's laws over an inclined channel with applications of gold nanoparticles.

Gold nanoparticles are commonly used as a tracer in laboratories. They are biocompatible and can transport heat energy to tumor cells via a variety of clinical techniques. As cancer cells are tiny, properly sized nanoparticles were introduced into the circulation for invasion. As a result, gold nanoparticles are highly effective. Therefore, the current research investigates the magnetohydrodynamic free convection flow of Casson nanofluid in an inclined channel. The blood is considered as a base fluid, and gold nanoparticles are assumed to be uniformly dispersed in it. The above flow regime is formulated in terms of partial differential equations. The system of derived equations with imposed boundary conditions is non-dimensionalized using appropriate dimensionless variables. Fourier's and Fick's laws are used to fractionalize the classical dimensionless model. The Laplace and Fourier sine transformations with a new transformation are used for the closed-form solutions of the considered problem. Finally, the results are expressed in terms of a specific function known as the Mittag-Leffler function. Various figures and tables present the effect of various physical parameters on the achieved results. Graphical results conclude that the fractional Casson fluid model described a more realistic aspect of the fluid velocity profile, temperature, and concentration profile than the classical Casson fluid model. The heat transfer rate and Sherwood number are calculated and presented in tabular form. It is worth noting that increasing the volume percentage of gold nanoparticles from 0 to 0.04 percent resulted in an increase of up to 3.825% in the heat transfer rate.

Intelligent Tracking of Mechanically Thrown Objects by Industrial Catching Robot for Automated In-Plant Logistics 4.0.

Industry 4.0 smart manufacturing systems are equipped with sensors, smart machines, and intelligent robots. The automated in-plant transportation of manufacturing parts through throwing and catching robots is an attempt to accelerate the transportation process and increase productivity by the optimized utilization of in-plant facilities. Such an approach requires intelligent tracking and prediction of the final 3D catching position of thrown objects, while observing their initial flight trajectory in real-time, by catching robot in order to grasp them accurately. Due to non-deterministic nature of such mechanically thrown objects' flight, accurate prediction of their complete trajectory is only possible if we accurately observe initial trajectory as well as intelligently predict remaining trajectory. The thrown objects in industry can be of any shape but detecting and accurately predicting interception positions of any shape object is an extremely challenging problem that needs to be solved step by step. In this research work, we only considered spherical shape objects as their3D central position can be easily determined. Our work comprised of development of a 3D simulated environment which enabled us to throw object of any mass, diameter, or surface air friction properties in a controlled internal logistics environment. It also enabled us to throw object with any initial velocity and observe its trajectory by placing a simulated pinhole camera at any place within 3D vicinity of internal logistics. We also employed multi-view geometry among simulated cameras in order to observe trajectories more accurately. Hence, it provided us an ample opportunity of precise experimentation in order to create enormous dataset of thrown object trajectories to train an encoder-decoder bidirectional LSTM deep neural network. The trained neural network has given the best results for accurately predicting trajectory of thrown objects in real time.

An integrated framework for COVID-19 classification based on classical and quantum transfer learning from a chest radiograph.

COVID-19 is a quickly spreading over 10 million persons globally. The overall number of infected patients worldwide is estimated to be around 133,381,413 people. Infection rate is being increased on daily basis. It has also caused a devastating effect on the world economy and public health. Early stage detection of this disease is mandatory to reduce the mortality rate. Artificial intelligence performs a vital role for COVID-19 detection at an initial stage using chest radiographs. The proposed methods comprise of the two phases. Deep features (DFs) are derived from its last fully connected layers of pre-trained models like AlexNet and MobileNet in phase-I. Later these feature vectors are fused serially. Best features are selected through feature selection method of PCA and passed to the SVM and KNN for classification. In phase-II, quantum transfer learning model is utilized, in which a pre-trained ResNet-18 model is applied for DF collection and then these features are supplied as an input to the 4-qubit quantum circuit for model training with the tuned hyperparameters. The proposed technique is evaluated on two publicly available x-ray imaging datasets. The proposed methodology achieved an accuracy index of 99.0% with three classes including corona virus-positive images, normal images, and pneumonia radiographs. In comparison to other recently published work, the experimental findings show that the proposed approach outperforms it.

Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition.

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. Results obtained on the retinal fundus images, which are prone to adversarial attacks, are 99% accurate and prove that the proposed defensive model is robust.

From ECG signals to images: a transformation based approach for deep learning.

Provocative heart disease is related to ventricular arrhythmias (VA). Ventricular tachyarrhythmia is an irregular and fast heart rhythm that emerges from inappropriate electrical impulses in the ventricles of the heart. Different types of arrhythmias are associated with different patterns, which can be identified. An electrocardiogram (ECG) is the major analytical tool used to interpret and record ECG signals. ECG signals are nonlinear and difficult to interpret and analyze. We propose a new deep learning approach for the detection of VA. Initially, the ECG signals are transformed into images that have not been done before. Later, these images are normalized and utilized to train the AlexNet, VGG-16 and Inception-v3 deep learning models. Transfer learning is performed to train a model and extract the deep features from different output layers. After that, the features are fused by a concatenation approach, and the best features are selected using a heuristic entropy calculation approach. Finally, supervised learning classifiers are utilized for final feature classification. The results are evaluated on the MIT-BIH dataset and achieved an accuracy of 97.6% (using Cubic Support Vector Machine as a final stage classifier).

An Optimized Approach for Breast Cancer Classification for Histopathological Images Based on Hybrid Feature Set.

BACKGROUND: Breast cancer is considered as one of the most perilous sickness among females worldwide and the ratio of new cases is increasing yearly. Many researchers have proposed efficient algorithms to diagnose breast cancer at early stages, which have increased the efficiency and performance by utilizing the learned features of gold standard histopathological images. OBJECTIVE: Most of these systems have either used traditional handcrafted or deep features, which had a lot of noise and redundancy, and ultimately decrease the performance of the system. METHODS: A hybrid approach is proposed by fusing and optimizing the properties of handcrafted and deep features to classify the breast cancer images. HOG and LBP features are serially fused with pre-trained models VGG19 and InceptionV3. PCR and ICR are used to evaluate the classification performance of the proposed method. RESULTS: The method concentrates on histopathological images to classify the breast cancer. The performance is compared with the state-of-the-art techniques, where an overall patient-level accuracy of 97.2% and image-level accuracy of 96.7% is recorded. CONCLUSION: The proposed hybrid method achieves the best performance as compared to previous methods and it can be used for the intelligent healthcare systems and early breast cancer detection.

Pearson Correlation-Based Feature Selection for Document Classification Using Balanced Training.

Documents are stored in a digital form across several organizations. Printing this amount of data and placing it into folders instead of storing digitally is against the practical, economical, and ecological perspective. An efficient way of retrieving data from digitally stored documents is also required. This article presents a real-time supervised learning technique for document classification based on deep convolutional neural network (DCNN), which aims to reduce the impact of adverse document image issues such as signatures, marks, logo, and handwritten notes. The proposed technique's major steps include data augmentation, feature extraction using pre-trained neural network models, feature fusion, and feature selection. We propose a novel data augmentation technique, which normalizes the imbalanced dataset using the secondary dataset RVL-CDIP. The DCNN features are extracted using the VGG19 and AlexNet networks. The extracted features are fused, and the fused feature vector is optimized by applying a Pearson correlation coefficient-based technique to select the optimized features while removing the redundant features. The proposed technique is tested on the Tobacco3482 dataset, which gives a classification accuracy of 93.1% using a cubic support vector machine classifier, proving the validity of the proposed technique.

Intelligent microscopic approach for identification and recognition of citrus deformities.

Plant diseases are accountable for economic losses in an agricultural country. The manual process of plant diseases diagnosis is a key challenge from last one decade; therefore, researchers in this area introduced automated systems. In this research work, automated system is proposed for citrus fruit diseases recognition using computer vision technique. The proposed method incorporates five fundamental steps such as preprocessing, disease segmentation, feature extraction and reduction, fusion, and classification. The noise is being removed followed by a contrast stretching procedure in the very first phase. Later, watershed method is applied to excerpt the infectious regions. The shape, texture, and color features are subsequently computed from these infection regions. In the fourth step, reduced features are fused using serial-based approach followed by a final step of classification using multiclass support vector machine. For dimensionality reduction, principal component analysis is utilized, which is a statistical procedure that enforces an orthogonal transformation on a set of observations. Three different image data sets (Citrus Image Gallery, Plant Village, and self-collected) are combined in this research to achieving a classification accuracy of 95.5%. From the stats, it is quite clear that our proposed method outperforms several existing methods with greater precision and accuracy.

Experiments in globalisation, food security and land use decision making.

The globalisation of trade affects land use, food production and environments around the world. In principle, globalisation can maximise productivity and efficiency if competition prompts specialisation on the basis of productive capacity. In reality, however, such specialisation is often constrained by practical or political barriers, including those intended to ensure national or regional food security. These are likely to produce globally sub-optimal distributions of land uses. Both outcomes are subject to the responses of individual land managers to economic and environmental stimuli, and these responses are known to be variable and often (economically) irrational. We investigate the consequences of stylised food security policies and globalisation of agricultural markets on land use patterns under a variety of modelled forms of land manager behaviour, including variation in production levels, tenacity, land use intensity and multi-functionality. We find that a system entirely dedicated to regional food security is inferior to an entirely globalised system in terms of overall production levels, but that several forms of behaviour limit the difference between the two, and that variations in land use intensity and functionality can substantially increase the provision of food and other ecosystem services in both cases. We also find emergent behaviour that results in the abandonment of productive land, the slowing of rates of land use change and the fragmentation or, conversely, concentration of land uses following changes in demand levels.

Acute-stage transmission of HIV: effect of volatile contact rates.

BACKGROUND: The role of acute-stage transmission in sustaining HIV epidemics has been difficult to determine. This difficulty is exacerbated by a lack of theoretical understanding of how partnership dynamics and sexual behavior interact to affect acute-stage transmission. We propose that individual-level variation in rates of sexual contact is a key aspect of partnership dynamics that can greatly increase acute-stage HIV transmission. METHODS: Using an individual-based stochastic framework, we simulated a model of HIV transmission that includes individual-level changes in contact rates. We report both population-level statistics (such as prevalence and acute-stage transmission rates) and individual-level statistics (such as the contact rate at the time of infection). RESULTS: Volatility increases both the prevalence of HIV and the proportion of new cases from acute-stage infectors. These effects result from 1) a relative reduction in transmission rate from chronic but not acute infectors and 2) an increase in the availability of high-risk susceptibles. CONCLUSIONS: The extent of changes in individual-level contact rates in the real world is unknown. Aggregate or strictly cross-sectional data do not reveal individual-level changes in partnership dynamics and sexual behavior. The strong effects presented in this article motivate both continued theoretical exploration of volatility in sexual behavior and collection of longitudinal individual-level data to inform more realistic models.

Detectable signals of episodic risk effects on acute HIV transmission: strategies for analyzing transmission systems using genetic data.

Episodic high-risk sexual behavior is common and can have a profound effect on HIV transmission. In a model of HIV transmission among men who have sex with men (MSM), changing the frequency, duration and contact rates of high-risk episodes can take endemic prevalence from zero to 50% and more than double transmissions during acute HIV infection (AHI). Undirected test and treat could be inefficient in the presence of strong episodic risk effects. Partner services approaches that use a variety of control options will be likely to have better effects under these conditions, but the question remains: What data will reveal if a population is experiencing episodic risk effects? HIV sequence data from Montreal reveals genetic clusters whose size distribution stabilizes over time and reflects the size distribution of acute infection outbreaks (AIOs). Surveillance provides complementary behavioral data. In order to use both types of data efficiently, it is essential to examine aspects of models that affect both the episodic risk effects and the shape of transmission trees. As a demonstration, we use a deterministic compartmental model of episodic risk to explore the determinants of the fraction of transmissions during acute HIV infection (AHI) at the endemic equilibrium. We use a corresponding individual-based model to observe AIO size distributions and patterns of transmission within AIO. Episodic risk parameters determining whether AHI transmission trees had longer chains, more clustered transmissions from single individuals, or different mixes of these were explored. Encouragingly for parameter estimation, AIO size distributions reflected the frequency of transmissions from acute infection across divergent parameter sets. Our results show that episodic risk dynamics influence both the size and duration of acute infection outbreaks, thus providing a possible link between genetic cluster size distributions and episodic risk dynamics.

Episodic HIV Risk Behavior Can Greatly Amplify HIV Prevalence and the Fraction of Transmissions from Acute HIV Infection.

A deterministic compartmental model was explored that relaxed the unrealistic assumption in most HIV transmission models that behaviors of individuals are constant over time. A simple model was formulated to better explain the effects observed. Individuals had a high and a low contact rate and went back and forth between them. This episodic risk behavior interacted with the short period of high transmissibility during acute HIV infection to cause dramatic increases in prevalence as the differences between high and low contact rates increased and as the duration of high risk better matched the duration of acute HIV infection. These same changes caused a considerable increase in the fraction of all transmissions that occurred during acute infection. These strong changes occurred despite a constant total number of contacts and a constant total transmission potential from acute infection. Two phenomena played a strong role in generating these effects. First, people were infected more often during their high contact rate phase and they remained with high contact rates during the highly contagious acute infection stage. Second, when individuals with previously low contact rates moved into an episodic high-risk period, they were more likely to be susceptible and thus provided more high contact rate susceptible individuals who could get infected. These phenomena make test and treat control strategies less effective and could cause some behavioral interventions to increase transmission. Signature effects on genetic patterns between HIV strains could make it possible to determine whether these episodic risk effects are acting in a population.

Heterogeneity in Number and Type of Sexual Contacts in a Gay Urban Cohort.

HIV transmission models include heterogeneous individuals with different sexual behaviors including contact rates, mixing patterns, and sexual practices. However, heterogeneity can also exist within individuals over time. In this paper we analyze a two year prospective cohort of 882 gay men with observations at six month intervals focusing on heterogeneity both within and between individuals in sexual contact rates and sexual roles. The total number of sexual contacts made over the course of the study (mean 1.55 per month) are highly variable between individuals (standard deviation 9.82 per month) as expected. At the individual level, contacts were also heterogeneous over time. For a homogeneous count process the variance should scale with the mean; however, at the individual level the variance scaled with the square root of the mean implying the presence of heterogeneity within individuals over time. We also observed a high level of movement between dichotomous sexual roles (insertive/receptive, protected/unprotected, anal/oral, and HIV status of partners). On average periods of exclusively unprotected sexual contacted lasted 16 months. Our results suggest that future HIV models should consider heterogeneities both between and within individuals in sexual contact rates and sexual roles.

Dynamic sex roles among men who have sex with men and transmissions from primary HIV infection.

BACKGROUND: Previous studies estimating the fraction of transmissions from persons with primary HIV have not focused on the effects of switching sex role in male homosexual populations. Such behavioral fluctuations can increase the contribution of primary HIV in the overall population. METHODS: We modeled HIV transmission with 8 compartments defined by 4 behavioral groups, with different anal-insertive and anal-receptive combinations, and 2 stages of infection. We explored the effects of fluctuating behavioral categories on endemic prevalence and the fraction of transmissions from primary HIV. We varied transition rates to develop the theory on how behavioral fluctuation affects infection patterns, and we used the transition rates in a Netherlands cohort to assess overall effects in a real setting. RESULTS: The dynamics of change in behavior-group status over time observed in the Netherlands cohort amplifies the prevalence of infection and the fraction of transmissions from primary HIV, resulting in the highest proportions of transmissions being from people with primary HIV. Fluctuation between dual- or receptive-role periods and no-anal-sex periods mainly determines this amplification. In terms of the total transmissions, the dual-role risk group is dominant. Fluctuation between insertive and receptive roles decreases the fraction of transmissions from primary HIV, but such fluctuation is infrequently observed. CONCLUSION: The fraction of transmissions from primary HIV is considerably raised by fluctuations in insertive and receptive anal sex behaviors. This increase occurs even when primary HIV or later infection status does not influence risk behavior. Thus, it is not simply biology but also behavior patterns and social contexts that determine the fraction of transmissions from primary HIV. Moreover, each primary HIV transmission has a larger population effect than each later infection transmission because the men to whom one transmits from primary HIV carry on more chains of transmissions than the men to whom one transmits later in infection. Reducing transmissions from primary HIV should be a primary focus of HIV control efforts.