3D Semantic Deep Learning Networks for Leukemia Detection

White blood cells (WBCs) are a vital part of the immune system that protect the body from different types of bacteria and viruses. Abnormal cell growth destroys the body’s immune system, and computerized methods play a vital role in detecting abnormalities at the initial stage. In this research, a deep learning technique is proposed for the detection of leukemia. The proposed methodology consists of three phases. Phase I uses an open neural network exchange (ONNX) and YOLOv2 to localize WBCs. The localized images are passed to Phase II, in which 3D-segmentation is performed using deeplabv3 as a base network of the pre-trained Xception model. The segmented images are used in Phase III, in which features are extracted using the darknet-53 model and optimized using Bhattacharyya separately criteria to classify WBCs. The proposed methodology is validated on three publically available benchmark datasets, namely ALL-IDB1, ALL-IDB2, and LISC, in terms of different metrics, such as precision, accuracy, sensitivity, and dice scores. The results of the proposed method are comparable to those of recent existing methodologies, thus proving its effectiveness.     

Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification

Sentiment Analysis (SA) is one of the subfields in Natural Language Processing (NLP) which focuses on identification and extraction of opinions that exist in the text provided across reviews, social media, blogs, news, and so on. SA has the ability to handle the drastically-increasing unstructured text by transforming them into structured data with the help of NLP and open source tools. The current research work designs a novel Modified Red Deer Algorithm (MRDA) Extreme Learning Machine Sparse Autoencoder (ELMSAE) model for SA and classification. The proposed MRDA-ELMSAE technique initially performs preprocessing to transform the data into a compatible format. Moreover, TF-IDF vectorizer is employed in the extraction of features while ELMSAE model is applied in the classification of sentiments. Furthermore, optimal parameter tuning is done for ELMSAE model using MRDA technique. A wide range of simulation analyses was carried out and results from comparative analysis establish the enhanced efficiency of MRDA-ELMSAE technique against other recent techniques.     

Deep Learning-Based Hookworm Detection in Wireless Capsule Endoscopic Image Using AdaBoost Classifier

Hookworm is an illness caused by an internal sponger called a roundworm. Inferable from deprived cleanliness in the developing nations, hookworm infection is a primary source of concern for both motherly and baby grimness. The current framework for hookworm detection is composed of hybrid convolutional neural networks; explicitly an edge extraction framework alongside a hookworm classification framework is developed. To consolidate the cylindrical zones obtained from the edge extraction framework and the trait map acquired into the hookworm scientific categorization framework, pooling layers are proposed. The hookworms display different profiles, widths, and bend directions. These challenges make it difficult for customized hookworm detection. In the proposed method, a contourlet change was used with the development of the Hookworm detection. In this study, standard deviation, skewness, entropy, mean, and vitality were used for separating the highlights of the each form. These estimations were found to be accurate. AdaBoost classifier was utilized to characterize the hookworm pictures. In this paper, the exactness and the territory under bend examination in identifying the hookworm demonstrate its scientific relevance.     

Gastric Tract Disease Recognition Using Optimized Deep Learning Features

Artificial intelligence aids for healthcare have received a great deal of attention. Approximately one million patients with gastrointestinal diseases have been diagnosed via wireless capsule endoscopy (WCE). Early diagnosis facilitates appropriate treatment and saves lives. Deep learning-based techniques have been used to identify gastrointestinal ulcers, bleeding sites, and polyps. However, small lesions may be misclassified. We developed a deep learning-based best-feature method to classify various stomach diseases evident in WCE images. Initially, we use hybrid contrast enhancement to distinguish diseased from normal regions. Then, a pretrained model is fine-tuned, and further training is done via transfer learning. Deep features are extracted from the last two layers and fused using a vector length-based approach. We improve the genetic algorithm using a fitness function and kurtosis to select optimal features that are graded by a classifier. We evaluate a database containing 24,000 WCE images of ulcers, bleeding sites, polyps, and healthy tissue. The cubic support vector machine classifier was optimal; the average accuracy was 99%.     

Modeling and numerical analysis of nanoliquid (titanium oxide,graphene oxide) flow viscous fluid with second order velocity slip and entropy generation

The prime objective of the present communication is to examine the entropy-optimized second order velocity slip Darcy–Forchheimer hybrid nanofluid flow of viscous material between two rotating disks.Electrical conducting flow is considered and saturated through Darcy–Forchheimer relation. Both the disks are rotating with different angular frequencies and stretches with different rates. Here graphene oxide and titanium dioxide are considered for hybrid nanoparticles and water as a continuous phase liquid. Joule heating, heat generation/absorption and viscous dissipation effects are incorporated in the mathematical modeling of energy expression. Furthermore, binary chemical reaction with activation energy is considered. The total entropy rate is calculated in the presence of heat transfer irreversibility, fluid friction irreversibility,Joule heating irreversibility, porosity irreversibility and chemical reaction irreversibility through thermodynamics second law. The nonlinear governing equations are first converted into ordinary differential equations through implementation of appropriate similarity transformations and then numerical solutions are calculated through Built-in-Shooting method. Characteristics of sundry flow variables on the entropy generation rate, velocity, concentration, Bejan number, temperature are discussed graphically for both graphene oxide and titanium dioxide hybrid nanoparticles. The engineering interest like skin friction coefficient and Nusselt number are computed numerically and presented through tables. It is noticed from the obtained results that entropy generation rate and Bejan number have similar effects versus diffusion parameter. Also entropy generation rate is more against the higher Brinkman number.     

Mysterious outbreaks of gastrointestinal illness associated with burritos supplied through school lunch programs

From October 1997 through March 1998, three outbreaks of gastrointestinal illness among school children were linked to company A burritos. In September 1998, a similar outbreak occurred in three North Dakota schools following lunches that included company B burritos. We conducted an investigation to determine the source of the North Dakota outbreak, identify other similar outbreaks, characterize the illness, and gather evidence about the cause. The investigation included epidemiologic analyses, environmental investigation, and laboratory analyses. In North Dakota, a case was defined as nausea, headache, abdominal cramps, vomiting, or diarrhea after lunch on 16 September 1998. Case definitions varied in the other states. In North Dakota, 504 students and staff met the case definition; predominant symptoms were nausea (72%), headache (68%), abdominal cramps (54%), vomiting (24%), and diarrhea (16%). The median incubation period was 35 min and median duration of illness was 6 h. Eating burritos was significantly associated with illness (odds ratio, 2.6; 95% confidence interval, 1.6 to 4.2). We identified 16 outbreaks that occurred in seven states from October 1997 through October 1998, affecting more than 1,900 people who ate burritos from two unrelated companies. All tortillas were made with wheat flour, but the fillings differed, suggesting that tortillas contained the etiologic agent. Results of plant inspections, tracebacks, and laboratory investigations were unrevealing. More than two million pounds of burritos were recalled or held from distribution. The short incubation period, symptoms, and laboratory data suggest that these outbreaks were caused by an undetected toxin or an agent not previously associated with this clinical syndrome. Mass psychogenic illness is an unlikely explanation because of the large number of sites where outbreaks occurred over a short period, the similarity of symptoms, the common food item, the lack of publicity, and the link to only two companies. A network of laboratories that can rapidly identify known and screen for unknown agents in food is a critical part of protecting the food supply against natural and intentional contamination.     

Measurements of solar flux density distribution on a plane receiver due to a flat heliostat

An experimental facility is designed and manufactured to measure the solar flux density distribution on a central flat receiver due to a single flat heliostat. The tracking mechanism of the heliostat is controlled by two stepping motors, one for tilt angle control and the other for azimuth angle control. A x-y traversing mechanism is also designed and mounted on a vertical central receiver plane, where the solar flux density is to be measured. A miniature solar sensor is mounted on the platform of the traversing mechanism, where it is used to measure the solar flux density distribution on the receiver surface. The sensor is connected to a data acquisition card in a host computer. The two stepping motors of the heliostat tracking mechanism and the two stepping motors of the traversing mechanism are all connected to a controller card in the same host computer. A software “TOWER” is prepared to let the heliostat track the sun, move the platform of the traversing mechanism to the points of a preselected grid, and to measure the solar flux density distribution on the receiver plane. Measurements are carried out using rectangular flat mirrors of different dimensions at several distances from the central receiver. Two types of images were identified on the receiver plane—namely, apparent (or visible) and mirror-reflected radiation images. Comparison between measurements and a mathematical model validates the mathematical model.     

Arithmetic Optimization with Ensemble Deep Transfer Learning BasedMelanoma Classification

Melanoma is a skin disease with high mortality rate while early diagnoses of the disease can increase the survival chances of patients. It is challenging to automatically diagnose melanoma from dermoscopic skin samples. Computer-Aided Diagnostic (CAD) tool saves time and effort in diagnosing melanoma compared to existing medical approaches. In this background, there is a need exists to design an automated classification model for melanoma that can utilize deep and rich feature datasets of an image for disease classification. The current study develops an Intelligent Arithmetic Optimization with Ensemble Deep Transfer Learning Based Melanoma Classification (IAOEDTT-MC) model. The proposed IAOEDTT-MC model focuses on identification and classification of melanoma from dermoscopic images. To accomplish this, IAOEDTT-MC model applies image preprocessing at the initial stage in which Gabor Filtering (GF) technique is utilized. In addition, U-Net segmentation approach is employed to segment the lesion regions in dermoscopic images. Besides, an ensemble of DL models including ResNet50 and ElasticNet models is applied in this study. Moreover, AO algorithm with Gated Recurrent Unit (GRU) method is utilized for identification and classification of melanoma. The proposed IAOEDTT-MC method was experimentally validated with the help of benchmark datasets and the proposed model attained maximum accuracy of 92.09% on ISIC 2017 dataset.