Search

Abstract This study attempts to accelerate the learning ability of an artificial electric field algorithm (AEFA) by attributing it with two mechanisms: elitism and opposition-based learning. Elitism advances the convergence of the AEFA towards global optima by retaining the fine-tuned solutions obtained thus far, and opposition-based learning helps enhance its exploration ability. The new version of the AEFA, called elitist opposition leaning-based AEFA (EOAEFA), retains the properties of the basic AEFA while taking advantage of both elitism and opposition-based learning. Hence, the improved version attempts to reach optimum solutions by enabling the diversification of solutions with guaranteed convergence. Higher-order neural networks (HONNs) have single-layer adjustable parameters, fast learning, a robust fault tolerance, and good approximation ability compared with multilayer neural networks. They consider a higher order of input signals, increased the dimensionality of inputs through functional expansion and could thus discriminate between them. However, determining the number of expansion units in HONNs along with their associated parameters (i.e., weight and threshold) is a bottleneck in the design of such networks. Here, we used EOAEFA to design two HONNs, namely, a pi-sigma neural network and a functional link artificial neural network, called EOAEFA-PSNN and EOAEFA-FLN, respectively, in a fully automated manner. The proposed models were evaluated on financial time-series datasets, focusing on predicting four closing prices, four exchange rates, and three energy prices. Experiments, comparative studies, and statistical tests were conducted to establish the efficacy of the proposed approach.

The present study aimed to investigate pathological epidemiology and molecular confirmation of Ehrlichia canis among pet dogs in Bhubaneswar, Odisha, a state in eastern India. A total of 178 dogs were screened for Ehrlichiosis based on history, clinical signs, blood, and buffy coat smear examination, resulting in only 56 dogs (31.46%) screening positive. The epidemiological study recorded a non-significant (p ≥ 0.05) increase in incidences among male dogs (68%), German Shepherds (25%), dogs more than 20 kg body weight (75%), in the summer months (55%), and dogs housed in pukka houses with exposure to the outside (59%). The majority of the infected dogs had a history of tick infestation (79%) at some point in their lives. Clinical signs showed non-typical manifestations like fever, lethargy, diarrhoea, epistaxis, hind limb edema, and corneal opacity. Haematological studies revealed anaemia and thrombocytopenia along with neutrophilia with relative lymphopenia and monocytosis. A decreasing trend was observed in the levels of total protein and albumin, with an increase in the levels of globulin, alanine aminotransferase, alanine aminotransferase, aspartate aminotransferase, blood urea nitrogen, and creatinine. The ultrasonography studies revealed hepatosplenomegaly along with hyper-echogenicity in various organs. Proteinuria and haematuria were consistent, along with the presence of bile salts in the urine of affected dogs. Molecular confirmation from n-type PCR data using Ehrlichia-specific primers targeting the p28 gene (843 bp) was done, and the identified gene sequences submitted to NCBI databases have accession numbers OQ383671-OQ383674 and OP886674-OP886677. Ticks collected from dogs were identified morphologically through microscopy and scanning electron microscopy as Rhipicephalus sanguineus.

Compressive strength (CS) has been considered as the utmost critical parameter while designing concrete structures. Usually, it is determined through laboratory tests, which are expensive, time consuming, and requires consumptions of materials. Therefore, correct prediction of CS before actual placement of concrete is highly desirable. The relationship among the constituent materials that forms concrete structures is highly nonlinear and necessitates application of intelligent methods. Though a few such methods like artificial neural network (ANN) based models are available in the literature; their performance in the context is limited to certain extent and they have their own merits and demerits. Hence, to address some of the limitations of ANN (non-higher order Neural Network) based models, this contribution proposed a hybrid model in which a flat network i.e., a type of higher order neural network- functional link artificial neural network (FLANN) is used as the base structure and genetic algorithm (GA) is employed to find out the optimal FLANN parameters (i.e., GA + FLANN). The training process comprises selection of connection weights, bias, as well as optimal number of basis functions of FLANN by GA rather fixing them earlier. Thus, an optimal FLANN is crafted on fly from exploitation of training data. The proposed model is used to assess the CS of concrete cements from datasets available in the literature considering samples of curing age at 3, 7, 14, 28, 56, and 91 days. A rolling window is used for input selection and five evaluation metrics are used for performance evaluation. On an average, the GA + FLANN obtained 0.477052 MAPE (mean absolute percentage of error), 0.598067 ARV (average relative variance), 0.593862 UT (U of Theil’s statistic), 0.551452 NMSE (normalized mean squared error), and 0.206135 SD (standard deviation) values which are the lowest compared to others. The superiority of the model is established through comparative studies and statistical significance tests.

In this work, we present a novel clustering approach which is inheriting the best characteristics of Unsupervised Functional Link Artificial Neural Network (UFLANN) and Genetic Algorithms (GAs) for uncovering clusters embedded in dataset represented through $(X)_{Nxd}$ , where X consists of $N$ data points with $d$ -dimensions. With an aim to realize natural clusters in a linear space UFLANN mapped the input vectors from lower dimension to higher dimension with a greater hope to achieve linearity in higher dimensional space. As a result, UFLANN introduces the problem of curse of dimensionality in the given datasets. However, it has been realized that the problems like sparse data and distance concentration associated with curse of dimensionality cast this problem to again a very complex problem. Hence to address some of the issues of curse of dimensionality, we have used GAs for selecting optimal number of features in the higher dimension for UFLANN to discover clusters embedded in the dataset. The proposed approach herein after named as GAUFLANN has been experimentally evaluated by using the metrics like (i) Davies-Bouldin Index, ii) Silhouette Score, and iii) Completeness score on different synthetic and real datasets. Our experimental study confirms that GAUFLANN is evidently scoring better in DB-index, Silhouette score, and Completeness score than the clustering methods like K-means, Hierarchical-Agglomerative (Average Linkage), and UFLANN across the datasets like Circles, Moons, Iris, and CORD-19.

Cryptocurrencies have carved out a significant presence in financial transactions during the past few years. Cryptocurrency market performs similarly to other financial markets with considerable nonlinearity and volatility and its prediction is a growing research area. It is challenging to capture the inherent uncertainties connected with cryptocurrency using the currently used conventional methodologies. The popularity of random vector functional link networks (RVFLN) is attributed to its simple structural layout, quick rate of learning, and enhanced generalization ability. It computes the output layer weights using non-iterative techniques like least square methods or iterative techniques like gradient methods, and assigns hidden neuron parameters at random. Random initialization of non-optimal hidden neuron settings, however, degrades the performance. Population-based metaheuristics are a superior option to random initialization for determining the ideal parameters and avoiding the problem of local optima stagnation. In the current article, an elitist artificial electric field algorithm (eAEFA) for training RVFLN is proposed. Here, eAEFA is utilized to create an ideal RVFLN by determining the weights and biases of the hidden layer connections. The elitism method is used by AEFA to maximize its strength. Here, the most suitable entities are directly inserted to create the population of the following generation. By predicting the closing values of six widely used cryptocurrencies, including Bitcoin, Litecoin, Ethereum, ZEC, XLM, and Ripple, one may determine how well the eAEFA+RVFLN model is performing. For comparison study, models including ARIMA, multi-layer perceptron (MLP), basic RVFLN, support vector regression (SVR), LSTM, GA trained RVFLN, and AEFA trained RVFLN are also constructed concurrently. In terms of performance and statistical significance testing, the suggested eAEFA+RVFLN findings outperform the comparator models. On an average, it achieves a MAPE (mean absolute percentage of error) value of 0.0573, R2 (coefficient of determination) of 0.9589, POCID (prediction of change in direction) of 0.9676, RMSE (root mean squared error) of 0.0685, MAE (mean absolute error) of 0.0727 and an average rank of 1.346; as a result, it is possible to recommend it as a useful financial forecasting tool.

This work presents a novel approach by considering teaching learning based optimization (TLBO) and radial basis function neural networks (RBFNs) for building a classifier for the databases with missing values and irrelevant features. The least square estimator and relief algorithm have been used for imputing the database and evaluating the relevance of features, respectively. The preprocessed dataset is used for developing a classifier based on TLBO trained RBFNs for generating a concise and meaningful description for each class that can be used to classify subsequent instances with no known class label. The method is evaluated extensively through a few bench-mark datasets obtained from UCI repository. The experimental results confirm that our approach can be a promising tool towards constructing a classifier from the databases with missing values and irrelevant attributes.

Chemical reaction optimization (CRO) algorithm is a robust metaheuristic by simulating the process of natural chemical reaction and has been applied for solving numerous realistic problems. However, it is suffering from low population diversity, slow convergence, and deprived from local search ability. To boost the search operation of CRO, this article proposes an improved CRO method termed as ICRO. We achieve the improvements in two phases. First, to start the search operation with a better-quality population, we propose a new method to initialize population which helps in enhancing diversification of the search space. Second, to intensify the local search ability we integrate Nelder-Mead simplex method with CRO. The ICRO is then evaluated on a few benchmark functions for optimization and found apposite. Dendritic neuron model (DNM) using additive and multiplicative-based aggregation functions has been emerging as a machine learning approach and found successful in many engineering applications. This study attempts to advance the predictive accuracy of DNM through maintaining a decent steadiness between exploitation and exploration of its search space with the proposed ICRO, termed as ICRO-DNM. The powerful global search ability of ICRO synergies with better approximation capability of DNM thus, able to overcome the limitations of conventional back propagation learning based DNM. ICRO-DNM is evaluated on closing price prediction for four stock index and net asset values of four mutual fund datasets and found efficient. The consequences of this attempt are: 1) Proposed ICRO shows robust parameter optimization ability for benchmark functions and DNM compared to basic CRO, particle swarm optimization (PSO), and genetic algorithm (GA) and 2) The learning paradigm formed due to reasonable amalgamation of ICRO and DNM is pretty able to capture the underlying uncertainties coupled with financial data, produces more precise and steady predictions and significantly different from other forecasts.

This work presents an integrated framework for imputation of missing values and prediction of class label of unseen samples by using the best features of rule based inductive decision tree (DT) and Support Vector Machine (SVM) classifier (DT-SVM). In this work, the decision tree is used for imputation of missing values of the datasets containing both categorical and numerical valued attributes. In addition, some of the other popular and simple missing value imputation techniques like drop, mean, median, mode, and k-nearest neighbor (kNN) are used for a comparative analysis. The imputed datasets are then classified using SVM. The performance of the proposed integrated novel framework DT-SVM has been compared with Drop-SVM, Mean-SVM, Median-SVM, Mode-SVM, and kNN-SVM and it is found that DT-SVM outperforms others. Further, a new variant of kNN named it as approximated kNN (A-kNN) has been proposed to overcome some of the shortcomings of canonical kNN while learning from a training set imputed by DT. Unlike canonical kNN, A-kNN does not scan the entire training set. Instead, it processes some of the representative instances from the training dataset to identify the nearest neighbor. The class centroid approach is adopted to find the representative instances of the training set. The effectiveness in term of accuracy as well as computational time of A-kNN is examined by comparing with canonical kNN. It is found that computational time of the proposed A-kNN is drastically reduced as compared to canonical kNN without compromising with the classification accuracy.

Biogeography Based Optimization (BBO) is a population based metaheuristic algorithm using the idea of migration and mutation operation of species for solving complex optimization problems. BBO has demonstrated good performance on various unconstrained and constrained benchmark functions. It has also been applied to real world optimization problems of type linear or nonlinear, nominal or ordinal as well as mixed variables. But, it is realized that adaptation of the intensification and diversification for solving complex optimization problems are challenging tasks. To cope with these challenges, we develop a novel migration model for BBO which inherits features of the nearest neighbour of the local best individual to be migrated along with a global best individual of the pool. Furthermore to select the local best individual for the habitat to be migrated an adaptive local topological structure has been used. We name it as “Adaptive Neighbourhood for Locally and Globally Tuned Biogeography Based Optimization algorithm (ANLGBBO)”. This maintains the balance between intensification and diversification i.e., improve solution by exploiting the accumulated search space and exploring the large space by identifying regions with high quality solutions. We have carried out an extensive numerical evaluation and comparisons for experimental tests using twenty benchmark functions with different features to measure the efficiency of the algorithm. The experimental study confirms ANLGBBO draws clear line of other variants of BBO algorithms in terms of population diversity and establish the accuracy of global optimal solution.

Prediction of currency exchange rate becomes highly desirable due to its greater role in financial and managerial decision making process. The fluctuations in exchange rate affect the economy of a country. Hence, over the years different types of neural network models along with statistical models are developed to predict the currency exchange rates of different countries with varying parameters. In this paper, we divide our effort into two parts. In first part, we have reviewed a few selected models of neural networks and statistics including fundamental and technical aspects of currency exchange rate prediction. Additionally, a thorough and careful experimental result analysis has been conducted on the models reviewed in part one. A committee machine has been proposed in part two to address the shortcomings of both neural networks and statistical models in the context of exchange rate prediction. Our study reveals that the currency exchange rates with multi-layer neural networks having Bayesian learning predictive accuracy is better than multi-layer neural networks with back-propagation learning. However, in the case of higher-order neural network multi-stage radial basis function network is predicting better than single stage radial basis function network. In the case of statistical models, it is drawn that under the umbrella of root mean square error measure, random walk is predicting better than other models of this category, whereas variance based model predicts better than rest of the models grouped under normalized mean square error measure. On the other hand, the integrated model is performing better than its counterpart like models with stand-alone mode. Moreover, our newly proposed committee machine is drawing a clear line over all the models while predicting exchange rate of GBP/USD.

In this paper, we propose a novel method of cluster analysis called unsupervised functional link artificial neural networks (UFLANNs), which inherit the best characteristics of functional link artificial neural networks and self-organizing feature maps (SOFMs). UFLANNs adopt three types of basis functions such as Chebyshev, Legendre orthogonal polynomials, and power series for mapping the input data into a new feature space with higher dimensions, where the objects are clustered based on the principle of competitive learning of SOFMs. The effectiveness of this algorithm has been tested with various artificial and real-life datasets including remote sensing images. A thorough comparison with other popular clustering algorithms shows that the proposed method is promising in revealing clusters from many complex datasets.

Background: The incidence of pregnancy associated breast cancers is on the rising trend in different parts of the world. There are occasional studies dealing with the fine needle aspiration cytology (FNAC) and clinicopathological characteristics of these tumors. Objectives: To study the cytomorphology and clinicopathological characteristics of pregnancy associated breast cancers and review the existing literature on the pathological characteristics. Methods: This is a retrospective study which includes cases of breast cancer which were diagnosed during peripartum period. FNAC was performed for all the cases from primary and metastatic sites along with correlation of the clinicopathological characteristics. Results: In the study group, 4 cases were lactating at the time of diagnosis, 1 patient presented at 37 weeks of her pregnancy and another patient presented 1 week after ruptured tubal ectopic pregnancy. Histologically two cases of infiltrating duct carcinoma -not otherwise specified (IDC-NOS), one case of invasive duct carcinoma with mucinous differentiation, one case of invasive duct carcinoma with concomitant lactating adenoma and one case each of metaplastic carcinoma and malignant phyllodes tumor. Only a single case was found to be positive for both the estrogen and progesterone receptors and another case only for estrogen receptors. None of the cases were found to positive for Her -2 neu. Conclusion: FNAC still serves as a reliable diagnostic measure inspite of the close mimics, especially when combined with cell block preparation. Further documentation of the clinicopathological features is essential for establishing the prognostic parameters and treatment guidelines for these peripartum breast cancers.

Radiation induced sarcomas (RIS) on cytology is rare however need to be reported as they are histologically distinct from the primary tumor and arise years after completion of the radiotherapy. Fine needle aspiration cytology is mostly indicated in cancer patients suspected of recurrence/metastasis and rarely in secondary tumors post therapy or irradiation. Depending on the morphology and site of occurrence of RIS they can cause diagnostic difficulty with the primary carcinoma or sarcoma that was irradiated. Here we discuss a 49 yr old lady, known and treated case of carcinoma cervix who presented with multiple nodular swellings in the lower back and gluteal region and had clinical impression of metastatic carcinoma. The fine needle aspiration cytology smears revealed pleomorphic spindle shaped cells with abundant mitotic figures. Extensive immunocytochemical work up was done on the smear and cell block which helped to make a final conclusion of radiation induced pleomorphic sarcoma. The diagnosis of a tumor in a proven case of previous malignancy needs consideration of tumors secondary to therapy as well, along with the diagnostic differentials of metastasis or recurrence.

In this paper, fractional order internal model control technique is formulated for non-ideal dc–dc buck and boost converter. The fractional order internal model control approach integrates the concept of Commande Robuste d’Ordre Non Entier principle for tuning a fractional order filter with internal model control scheme. The final controller can be expressed as a series combination of proportional integral derivative controller and a fractional order low pass filter. To assess the robustness of the proposed fractional order internal model control scheme, both the servo response and regulatory response of the dc–dc converters are investigated in the presence of disturbances. The efficacy of fractional order internal model control technique is demonstrated via comparison with 2 degrees of freedom internal model control scheme. Furthermore, an experimental validation of fractional order internal model control is conducted on laboratory setup, and a dSPACE 1104 microcontroller is used for hardware implementation. The simulation results and the hardware validation are a testimony to the effectiveness of fractional order internal model control technique.

Primary carcinosarcoma of the ovary is a rare, challenging malignancy of the female genital tract. Preoperative diagnosis of this tumor is seldom made as it mimics epithelial ovarian tumors. We report a case of 45 years multiparous lady who underwent staging laparotomy to disclose smooth surface left ovarian cystic mass with minimal solid areas. Histopathologically a biphasic tumor with malignant epithelial and mesenchymal component was seen. Explicit diagnosis of primary ovarian carcinosarcoma was established using immunohistochemical marker study. Primary mixed Mullerian tumor of the ovary has to be considered in the differential diagnosis of predominantly cystic ovarian lesion with minimal solid areas. Regular followup and close monitoring of the patient is required to understand the behavior of this exceptional tumor.

Introduction The COVID-19 outbreak has posed a major challenge to healthcare providers. Due to its communicable nature, very stringent public health interventions have been put in place worldwide; yet, it still poses new emerging challenges, one of the most recent being a multisystem inflammatory condition with clinical features resembling Kawasaki-like disease and toxic shock syndrome in children and adolescents. The data on this novel condition are scarce which need to be reported to identify its clinico-epidemiological and geographical distribution. There is an urgent need to generate evidence for diagnosis and management of this condition in the midst of a pandemic.Methods and analysis This systematic review will be conducted using Medline database searched through PubMed, Embase, Ovid; and Google Scholar, ProQuest and EBSCO databases will also be searched along with grey literature with the aim to identify the clinical features, aetiopathology, laboratory findings, treatment modes and outcomes of Kawasaki-like disease among paediatric patients suffering from COVID-19. Original articles reporting Kawasaki-like disease in paediatric patients with COVID-19 will be retrieved after screening by two independent reviewers. Data will be extracted in a specially designed form and studies will be assessed independently for risk of bias. Data will be extracted for the following: author, journal title, publication year, study design, study setting, demographic characteristics, sample size, clinical features, aetiopathology, laboratory findings, modes and doses of treatment given, strength and weakness of studies. A descriptive and quantitative analysis will be completed.Ethics and dissemination This is a literature-based review study with no ethical concerns. We will publish the results in a peer-reviewed journal and present at a conference.PROSPERO registration number CRD42020187427.

Aim: The effects of N-P-K fertilizers in the form of urea, single super phosphate and muriate of potash on development of free-living stages of Haemonchus contortus were studied. Materials and Methods: Five parasite free experimental plots of 1 mx1 m area, each of paddy leaves (15-day-old) and an equal number of Cynodon dactylon grass were infested with about 10x104 eggs/ml phosphate buffer saline along with the application of the calculated amount of fertilizers solution. On the 10th day of posttreatment, the pasture was cut, processed, larvae recovered by Baermann method and counted, which was expressed as number of L3 per kg dry matter (DM) of pasture. Results: The average recovered population of L3 of H. contortus per kg DM varied significantly (p0.05). Conclusion: This study shown that when N-P-K fertilizers administered at recommended level, significantly reduced larval translation of H. contortus minimizing pasture infectivity for the free range grazing animals.

The brain signals usually generate certain electrical signals that can be recorded and analyzed for detection in several brain disorder diseases. These small signals are expressly called as Electroencephalogram (EEG) signals. This research work analyzes the epileptic disorder in human brain through EEG signal analysis by integrating the best attributes of Artificial Bee Colony (ABC) and radial basis function networks (RBFNNs). We have used Discrete Wavelet Transform (DWT) technique for extraction of potential features from the signal. In our study, for classification of these signals, in this paper, the RBFNNs have been trained by a modified version of ABC algorithm. In the modified ABC, the onlooker bees are selected based on binary tournament unlike roulette wheel selection of ABC. Additionally, kernels such as Gaussian, Multi-quadric, and Inverse-multi-quadric are used for measuring the effectiveness of the method in numerous mixtures of healthy segments, seizure-free segments, and seizure segments. Our experimental outcomes confirm that RBFNN with inverse-multi-quadric kernel trained with modified ABC is significantly better than RBFNNs with other kernels trained by ABC and modified ABC.

Most of the available feature selection techniques in the literature are classifier bound. It means a group of features tied to the performance of a specific classifier as applied in wrapper and hybrid approach. Our objective in this study is to select a set of generic features not tied to any classifier based on the proposed framework. This framework uses attribute clustering and feature ranking techniques in pipeline in order to remove redundant features. On each uncovered cluster, signal-to-noise ratio, t-statistics and significance analysis of microarray are independently applied to select the top ranked features. Both filter and evolutionary wrapper approaches have been considered for feature selection and the data set with selected features are given to ensemble of predefined statistically different classifiers. The class labels of the test data are determined using majority voting technique. Moreover, with the aforesaid objectives, this paper focuses on obtaining a stable result out of various classification models. Further, a comparative analysis has been performed to study the classification accuracy and computational time of the current approach and evolutionary wrapper techniques. It gives a better insight into the features and further enhancing the classification accuracy with less computational time.

The electroencephalogram (EEG) is a low amplitude signal generated in the brain, as a result of information flow during the communication of several neurons. Hence, careful analysis of these signals could be useful in understanding many human brain disorder diseases. One such disease topic is epileptic seizure identification, which can be identified via a classification process of the EEG signal after preprocessing with the discrete wavelet transform (DWT). To classify the EEG signal, we used a radial basis function neural network (RBFNN). As shown herein, the network can be trained to optimize the mean square error (MSE) by using a modified particle swarm optimization (PSO) algorithm. The key idea behind the modification of PSO is to introduce a method to overcome the problem of slow searching in and around the global optimum solution. The effectiveness of this procedure was verified by an experimental analysis on a benchmark dataset which is publicly available. The result of our experimental analysis revealed that the improvement in the algorithm is significant with respect to RBF trained by gradient descent and canonical PSO. Here, two classes of EEG signals were considered: the first being an epileptic and the other being non-epileptic. The proposed method produced a maximum accuracy of 99% as compared to the other techniques. Keywords: Electroencephalography, Radial basis function neural network, Particle swarm optimization, Discrete wavelet transform, Machine learning

Radial basis function networks (RBFNs) have gained widespread appeal amongst researchers and have shown good performance in a variety of application domains. They have potential for hybridization and demonstrate some interesting emergent behaviors. This paper aims to offer a compendious and sensible survey on RBF networks. The advantages they offer, such as fast training and global approximation capability with local responses, are attracting many researchers to use them in diversified fields. The overall algorithmic development of RBF networks by giving special focus on their learning methods, novel kernels, and fine tuning of kernel parameters have been discussed. In addition, we have considered the recent research work on optimization of multi-criterions in RBF networks and a range of indicative application areas along with some open source RBFN tools.

Aim: Studies on the prevalence of gastrointestinal helminths infection in Banaraja fowls of Mayurbhanj district in Odisha with respect to semi-intensive system of rearing. Materials and Methods: A total of 160 Banaraja birds (30 males and 130 females) belonging to two age groups (below 1 month age and above 1 month) were examined for the presence of different species of gastrointestinal helminth infection over a period of 1-year. The method of investigation included collection of fecal sample and gastrointestinal tracts, examination of fecal sample of birds, collection of parasites from different part of gastrointestinal tract, counting of parasites, and examination of the collected parasites by standard parasitological techniques followed by morphological identification as far as possible up to the species level. Results: Overall, 58.75% birds were found infected with various gastrointestinal helminths. Total five species of parasites were detected that included Ascaridia galli (25.63%), Heterakis gallinarum (33.75%), Raillietina tetragona (46.25%), Raillietina echinobothrida (11.87%), and Echinostoma revolutum (1.87%). Both single (19.15%) as well as mixed (80.85%) infection were observed. Highest incidence of infection was observed during rainy season (68.88%) followed by winter (66.66%) and least in summer season (41.81%). Sex-wise incidence revealed slightly higher occurrence among females (59.23%) than males (56.67%). Age-wise prevalence revealed that chicks were more susceptible (77.77%) than adults (51.30%) to gastrointestinal helminths infection. Conclusions: Present study revealed that mixed infection with gastrointestinal helminths of different species was more common than infection with single species and season-wise prevalence was higher in rainy season followed by winter and summer. Chicks were found to be more prone to this parasitic infection and a slight higher prevalence among female birds was observed.

Introduction: Neural tube defects (NTD) are a group of serious birth defects occurring due to defective closure of neural tube during embryonic development. It comprises of anencephaly, encephalocele and spina bifida. We conducted this prospective fetal autopsy series to study the rate and distribution of NTD, analyze the reproductive factors and risk factors, note any associated anomalies and evaluate the organ weights and their deviation from normal. Materials and Methods: This was a prospective study done over a period of 6 years from August, 2007 to July, 2013. All cases of NTDs delivered as abortion, still born and live born were included. The reproductive and risk factors like age, parity, multiple births, previous miscarriage, obesity, diabetes mellitus, socioeconomic status and use of folic acid during pregnancy were collected.Autopsy was performed according to Virchow′s technique. Detail external and internal examination were carried out to detect any associated anomalies. Gross and microscopic examination of organs were done. Results: Out of 210 cases of fetal and perinatal autopsy done, 72 (34.28%) had NTD constituting 49 cases of anencephaly, 16 spina bifida and 7 cases of encephalocele. The mothers in these cases predominantly were within 25-29 years (P = 0.02) and primy (P = 0.01). Female sex was more commonly affected than males (M:F = 25:47, P = 0.0005) There was no history of folate use in majority of cases. Organ weight deviations were >2 standard deviation low in most of the cases. Most common associated anomalies were adrenal hypoplasia and thymic hyperplasia. Conclusion: The authors have made an attempt to study NTD cases in respect to maternal reproductive and risk factors and their association with NTD along with the organ weight deviation and associated anomalies. This so far in our knowledge is an innovative study which was not found in literature even after extensive search.

Amelanotic signet ring cell melanoma is one of the rare variants of malignant melanoma. Here we are presenting a case of a 58- year-old female with chief complaints of swelling in the left sternal region/breast, and right cervical region. Contrast Enhanced CT scan showed the two well circumscribed lobular mass lesions with central necrosis in the left breast. The radiologist opined the lesions as intramammary nodes. Biopsy from the larger breast mass lesion showed a tumour with cells arranged in discohesive pattern less with hetrogenos morphology. These tumour cells had a predominantly signet ring morphology along with markedly pleomorphic tumour cells and giant cells. These tumour cells were negative for pan CK and positive for S100, HMB45. So the case was diagnosed as metastatic amelanotic malignant melanoma with signet ring morphology.

Paratesticular aggressive angiomyxoma is a very rare tumour in males. Most of documented cases of aggressive angiomyxomas have been seen in genital, perineal and pelvic regions in women of child bearing age. We report two cases of aggressive angiomyxomas in males who presented with inguinal swellings. A globular mass with greyish white, glistening cut surface was received after excision of the mass. Microscopic examination revealed a paucicellular tumour comprising of spindle shaped cells along with vessels of varying calibre. The accompanying stroma was myxocollagenous. In addition there was evidence of fat infiltration in one of the cases. Immunohistochemical staining showed CD34, desmin, vimetin positivity and negative staining for S100, actin, Estrogen Receptors (ER) and Progesterone Receptors (PR). The microscopic and immunohistochemical features favoured the diagnosis of aggressive angiomyxoma. This report of angiomyxoma in two cases of males assumes great significance in view of the extreme rarity of the tumour in males and its locally infiltrative nature.

Male breast can show almost all pathological entities described in female breast. Inflammatory conditions of the breast in male are not common; however, occasionally, it can be encountered in the form of an abscess. Clinically, gynecomastia always presents as a symmetric unilateral or bilateral lump in the retroareolar region, and any irregular asymmetric lump raises a possibility of malignancy. Radiology should be used as a part of the triple assessment protocol for breast lump along with fine-needle aspiration cytology for definite diagnosis and proper management.

Primary ovarian choriocarcinoma is a rare neoplasm that can be gestational and non-gestational in origin. It accounts for one in 369 million pregnancies. Both types present with similar clinical, histomorphological and ultrastructural findings. But, it is essential to differentiate the two because the gestational type has a better clinical course and responds to single-agent chemotherapy. Usually, the gestational ovarian choriocarcinoma is metastatic from uterine choriocarcinoma and follows antecedent pregnancy and is seen in females of 40 years or older. DNA polymorphism analysis showing the presence of paternal genes in the tumor establishes the gestational origin of choriocarcinoma. We present the intra-operative cytological findings of a case of primary ovarian choriocarcinoma in a 25-year-old lady arising from ectopic pregnancy with Ki67 immunostain.

This work presents an accurate and smooth functional link artificial neural network (FLANN) for classification of noisy database. The accuracy and smoothness of the network is taken birth by suitably tuning the parameters of FLANN using differential evolution and filter based feature selection. We use Qclean algorithm for identification of noise, information gain theory for filtering irrelevant features, and then supplied the remaining relevant attributes to the functional expansion unit of FLANN, which in turn map lower to higher dimensional feature space for constructing a smooth and accurate classifier. In specific, the differential evolution is used to fine tune the weight vector of this network and some trigonometric functions are used in functional expansion unit. The proposed approach is validated with a few benchmarking highly skewed and balanced dataset retrieved from University of California, Irvine (UCI) repository with a range of 5-20% noise. The insightful experimental study signifies the propensity of noise in the classification accuracy of a database with a range of noise from 5-20%. Moreover, our method suggests that noisy samples along with irrelevant set of attributes are deceptive and weakening the reliability of the classifier, therefore, it is required to reduce its effect before or during the process of classification.

This work presents a novel approach by considering teaching learning based optimization (TLBO) and radial basis function neural networks (RBFNs) for building a classifier for the databases with missing values and irrelevant features. The least square estimator and relief algorithm have been used for imputing the database and evaluating the relevance of features, respectively. The preprocessed dataset is used for developing a classifier based on TLBO trained RBFNs for generating a concise and meaningful description for each class that can be used to classify subsequent instances with no known class label. The method is evaluated extensively through a few bench-mark datasets obtained from UCI repository. The experimental results confirm that our approach can be a promising tool towards constructing a classifier from the databases with missing values and irrelevant attributes. [ABSTRACT FROM AUTHOR]

Compressive strength (CS) has been considered as the utmost critical parameter while designing concrete structures. Usually, it is determined through laboratory tests, which are expensive, time consuming, and requires consumptions of materials. Therefore, correct prediction of CS before actual placement of concrete is highly desirable. The relationship among the constituent materials that forms concrete structures is highly nonlinear and necessitates application of intelligent methods. Though a few such methods like artificial neural network (ANN) based models are available in the literature; their performance in the context is limited to certain extent and they have their own merits and demerits. Hence, to address some of the limitations of ANN (non-higher order Neural Network) based models, this contribution proposed a hybrid model in which a flat network i.e., a type of higher order neural network- functional link artificial neural network (FLANN) is used as the base structure and genetic algorithm (GA) is employed to find out the optimal FLANN parameters (i.e., GA + FLANN). The training process comprises selection of connection weights, bias, as well as optimal number of basis functions of FLANN by GA rather fixing them earlier. Thus, an optimal FLANN is crafted on fly from exploitation of training data. The proposed model is used to assess the CS of concrete cements from datasets available in the literature considering samples of curing age at 3, 7, 14, 28, 56, and 91 days. A rolling window is used for input selection and five evaluation metrics are used for performance evaluation. On an average, the GA + FLANN obtained 0.477052 MAPE (mean absolute percentage of error), 0.598067 ARV (average relative variance), 0.593862 UT (U of Theil's statistic), 0.551452 NMSE (normalized mean squared error), and 0.206135 SD (standard deviation) values which are the lowest compared to others. The superiority of the model is established through comparative studies and statistical significance tests. [ABSTRACT FROM AUTHOR]