Search

Epilepsy, a highly prevalent neurological disorder, profoundly impacts the lives of patients with periodic and unexpected seizures that lead to serious injury or death. This research work introduces a Siamese Convolutional Fire Hawk Sparse Autoencoder Network (SCFHSAN) to detect different states of the epileptic seizures. Initially, the EEG signals are gathered from two datasets including TUH EEG and UoB datasets. Then, artifacts removal is performed by multi-resolutional analysis and adaptive filtering technique. After that, dandelion tunable Q-wavelet transform is used to decompose signals into frequency sub-bands. Following that, the feature extraction and feature selection are processed using several techniques. Finally, Siamese convolutional sparse autoencoder network is proposed for epileptic seizure detection and fire hawk optimization algorithm is employed to optimize the weight parameter of the network. The results indicate that the introduced approach achieves an accuracy 99.95% and 98.78% on UoB and TUH EEG datasets, respectively. Analysis determines that the introduced SCFHSAN scheme would help neuro-experts in diagnosing epileptic behavior by analyzing seizure details from various brain regions using multichannel EEG signals. [ABSTRACT FROM AUTHOR]

Next generation wireless communication (WC) needs high-performance which assist high-speed data transmission while meeting the requirements for low profile, weight and cost. Several researchers introduce graphene-based circular, triangular, square and hexagonal antenna for WC in the terahertz (THz) resonant frequency (RF). This research work introduces a deep graphene based reconfigurable circularly polarized star-shaped microstrip antenna at 2.98 THz frequency for biomedical application. Graphene has been applied in the structure of star-shaped microstrip antenna. This reconfigurable circularly polarized graphene-based antenna is obtained on a SiO2 substrate. The introduced circularly polarized antenna has a single feed and an easy design. The major objective of this research work is to propose graphene material as an efficient solution in designing antenna for organizing and adjusting its polarization. Because of the complexity of the structure of graphene antenna, enhanced scalable graph random improved Fick's law neural networks is applied for predicting the antenna parameters. This proposed method is a combination of enhanced scalable graph random neural network (ESGRNN) and an improved Fick's law optimization which is used to optimize the prediction error of the proposed ESGRNN. To prevent premature incomplete convergence in the traditional Fick's law algorithm, a dynamic lens-imaging learning strategy is incorporated. Finally, the achieved prediction accuracy is 98%, the mean square error is 2%, minimal return loss (S11) is − 55.98 dB, impedance bandwidth is 800 GHz, gain is 9.8 dB, and voltage standing wave ratio is 1.011 at 2.98 THz RF. As a result, the designed antenna is well-suitable for biomedical applications like riboflavin detection. [ABSTRACT FROM AUTHOR]

Lymph node metastasis detections are more clinically significant task associated with the presence and reappearance of lung cancer. The development of the computer-assisted diagnostic approach has greatly supported the diagnosis of human disorders in the field of medicine including lung cancer. Lung cancer treatment is possible if it is detected at the initial stage. Radiologists have great difficulty identifying and categorizing lung cancers in the initial phase. So, several methods were used to predict the lung cancer but does not provide accurate solutions with increased error rate. To overcome these issues, a Deep Volcanic Residual U-Net (DVR U-Net) for nodal metastasis is proposed in this manuscript which identifies the LC accurately in the early stage. Initially, the input images are taken from two datasets. After that, these input data are pre-processed using Anisotropic Diffusion Filter with a Fuzzy based Contrast-Limited Adaptive Histogram Equalization (ADFFCLAHE) method. Then the pre-processed images are given to the DVR U-Net to segment and extract the volume of interest for estimating the nodal stage of each volume of interest. Finally, DVR U-Net effectively detects and classifies the N + (nodal metastasis) or N- (non-nodal metastasis). The introduced method attains 99.9% higher accuracy as compared with the existing methods. Also, the statistical analysis of the Shapiro–Wilk test, Friedman test and Wilcoxon Signed-Rank test are executed to prove the statistical effectiveness of the implemented method. [ABSTRACT FROM AUTHOR]

This paper aims to understand the impact of big data analytics on the retail supply chain. For doing so, we set our context to select the best big data practices amongst the available alternatives based on retail supply chain performance. We have applied TODIM (an acronym in Portuguese for Interactive Multi-criteria Decision Making) for the selection of the best big data analytics tools among the identified nine practices (data science, neural networks, enterprise resource planning, cloud computing, machine learning, data mining, RFID, Blockchain and IoT and Business intelligence) based on seven supply chain performance criteria (supplier integration, customer integration, cost, capacity utilization, flexibility, demand management, and time and value). One of the intriguing understandings from this paper is that most of the retail firms are in a dilemma between customer loyalty and cost while implementing the big data practices in their organization. This study analyses the dominance of the big data practices at the retail supply chain level. This helps the newly emerging retail firms in evaluating the best big data practice based on the importance and dominance of supply chain performance measures. [ABSTRACT FROM AUTHOR]

In this modern world, people move fast and most people are very busy in their daily scheduled lives. In such a scenario, E-commerce online shopping is a great time-saver. In general, ladies clothing has numerous characteristics that are hard to designate such as texture, shape, color, print, and length. Moreover, accurate extraction of product features is critical in the analysis of fashion images for product search, and texture detection based on the query images remains a more challenging task. To overcome the aforementioned challenges, a novel deep learning-based saree texture detection network (STD-Net) has been proposed for the rapid classification of saree tactile textures based on the user query. The research work is conducted in three phases: (1) Indian Saree Dataset creation and Pre-processing phase (2) Patch generation phase (3) Texture detection of the query image. Initially, the input images are denoised using SCRAB (scalable range-based adaptive bilateral filter). Afterward, a region-based convolutional neural network (RCNN) is used for segmenting the region of interest viz, the field part of a saree into patches with the augmented and annotated dataset of sarees. Finally, the Modified EfficientNet-B3 which is integrated with the squeeze and excitation attention (SEA) module is used to classify the texture of the sarees. The experimental results disclose that the proposed STD-Net attains a better testing accuracy of 99.1% for the texture classification of saree images. [ABSTRACT FROM AUTHOR]

Autism spectrum disorder (ASD) is one of the major problems, which manifests at a young age and is hard to identify in the early stages. Typically, it affects the interaction skills and social behavior in children aged 6–17 years old. Autism is caused by both genetic and environmental factors. Autism can manifest itself in children as a lack of communication, social interaction, and limited interest behaviors, among other symptoms. ASD is a mild retardation, in which many people on ASD have incredible talents and abilities. Approximately 40% are academically above average and possess a special ability to view the world with joy from a unique viewpoint. This paper developed the ASD classification using deep Q learning network (DQN), and SpinalNet, wherein these network's hyperparameters are trained by the proposed driving training political optimizer (DTPO). The initial stage of this processing starts with the acquisition of an image from the dataset, and further preprocessing is carried out by an adaptive Wiener filter, and this filtered image is sent to regions of interest (ROI) extraction. After that, extraction of the nub region is done by the proposed DTPO, from which the classification process is done by considering extracted features. Moreover, the classification performance of ASD is performed, and the output of DQN and SpinalNet is subjected to a fusion process to provide the classification of ASD with the help of Czekanowski similarity. Furthermore, the classification is based on three metrics like accuracy, sensitivity, specificity, mean-squared error, root-mean-squared error, R, and mean absolute error, with superior values of 0.907, 0.958, 0.936, 0.536, 0.732, 0.488, and 0.409, respectively. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) is a non-invasive medical tool that divulges the rhythm and function of the human heart. This is broadly employed in heart disease detection including arrhythmia. Arrhythmia is a general term for abnormal heart rhythms that can be identified and classified into many categories. Automatic ECG analysis is provided by arrhythmia categorization in cardiac patient monitoring systems. It aids cardiologists to diagnose the ECG signal. In this work, an Ensemble classifier is proposed for accurate arrhythmia detection using ECG Signal. Input data are taken from the MIT-BIH arrhythmia dataset. Then the input data was pre-processed using Python in Jupyter Notebook which run the code in an isolated manner and was able to keep code, formula, comments, and images. Then, Residual Exemplars Local Binary Pattern is applied for extracting statistical features. The extracted features are given to ensemble classifiers, like Support vector machines (SVM), Naive Bayes (NB), and random forest (RF) for classifying the arrhythmia as normal (N), supraventricular ectopic beat (S), ventricular ectopic beat (V), fusion beat (F), and unknown beat (Q). The proposed AD-Ensemble SVM-NB-RF method is implemented in Python. The proposed AD-Ensemble SVM-NB-RF method is 44.57%, 52.41%, and 29.49% higher accuracy; 2.01%, 3.33%, and 3.19% higher area under the curve (AUC); and 21.52%, 23.05%, and 12.68% better F-Measure compared with existing models, like multi-model depending on the ensemble of deep learning for ECG heartbeats arrhythmia categorization (AD-Ensemble CNN-LSTM-RRHOS), ECG signal categorization utilizing VGGNet: a neural network based classification method (AD-Ensemble CNN-LSTM) and higher performance arrhythmic heartbeat categorization utilizing ensemble learning along PSD based feature extraction method (AD-Ensemble MLP-NB-RF). [ABSTRACT FROM AUTHOR]

One of the essential elements of the cyber-physical system is the wireless sensor network (WSN), which is a multi-hop, self-organizing wireless network made up of numerous stationary or moving sensors. It collaborates, collects, processes and transmits the information of objects sensed in the geographic area enclosed by the network, and transmits this data to the network user. Several common WSN attacks exist, including Blackhole, Gray hole, Flooding, and Scheduling, which can quickly harm the WSN system. Owing to sensor node's constrained resources, extensive redundancy, and strong correlation of network data, the intrusion detection schemes for WSN have low detection rate, high rates of false alarms, and substantial calculation overhead. To overwhelm these issues, an Enhanced Elman Spike Neural Network fostered Intrusion detection framework (IDS-WSN-EESNN) is proposed in this manuscript. First, the Balancing Composite Motion Optimization Algorithm (BCMOA) is employed to lessen the data dimension and computational overhead in original traffic data's feature space. Then, EESNN is applied to identify different network attacks. WSN-DS dataset based the experimental results prove that the proposed IDS-WSN-EESNN approach attains 30.42%, 28.24%, 23.03% and 32.63% higher accuracy, 95.02%, 91.52%, 92.67% and 92.9% lower error rate and 25.13%, 21.75%, 27.54% and 23.08% lower computation time compared with the existing methods. [ABSTRACT FROM AUTHOR]

The year 2020 can be earmarked as the year of global supply chain disruption owing to the outbreak of the coronavirus (COVID-19). It is however not only because of the pandemic that supply chain risk assessment (SCRA) has become more critical today than it has ever been. With the number of supply chain risks having increased significantly over the last decade, particularly during the last 5 years, there has been a flurry of literature on supply chain risk management (SCRM), illustrating the need for further classification so as to guide researchers to the most promising avenues and opportunities. We therefore conduct a bibliometric and network analysis of SCRA publications to identify research areas and underlying themes, leading to the identification of three major research clusters for which we provide interpretation and guidance for future work. In doing so we focus in particular on the variety of parameters, analytical approaches, and characteristics of multi-criteria decision-making techniques for assessing supply chain risks. This offers an invaluable synthesis of the SCRA literature, providing recommendations for future research opportunities. As such, this paper is a formidable starting point for operations researchers delving into this domain, which is expected to increase significantly also due to the current pandemic. [ABSTRACT FROM AUTHOR]

In signal analysis, various filters, devices, or algorithms are utilized to process signals, selectively permitting or blocking frequencies to induce desired changes in signal properties. Speech analysis faces challenges dealing with accent, dialect, pitch, and non-stationary features. Filters are crucial in modifying frequency components, reducing noise impact, enhancing robustness, and improving efficiency in speech analyses. To tackle speech analysis challenges, a proposed solution involves a low power, area efficient 2D Finite Impulse Response (FIR) filter, utilizing optimized multipliers and adders. The design integrates the Hybrid Mountaineering Team Bowerbird Optimization Algorithm (HMTBOA) to optimize filter coefficients, minimizing switching activities while considering ripple contents, transition width parameters, and power requirements. Additionally, High Speed Approximate Parallel Prefix Adders (HSAPPA) and the adaptive banyan tree growth optimization algorithm aim to reduce path delay, enhance area efficiency, and lower design complexity and power consumption in approximate adder design and error efficient posit logarithm approximate multiplier. The suggested method achieves outstanding results, with a 3.05ns delay, 0.101mW power consumption, and a 26.36dB signal-to-noise ratio, highlighting its robustness and effectiveness in addressing signal analysis challenges. [ABSTRACT FROM AUTHOR]

A wealth of microarray and RNA-seq data for studying abiotic stress tolerance in rice exists but only limited studies have been carried out on multiple stress-tolerance responses and mechanisms. In this study, we identified 6657 abiotic stress-responsive genes pertaining to drought, salinity and heat stresses from the seedling stage microarray data of 83 samples and used them to perform unweighted network analysis and to identify key hub genes or master regulators for multiple abiotic stress tolerance. Of the total 55 modules identified from the analysis, the top 10 modules with 8–61 nodes comprised 239 genes. From these 10 modules, 10 genes common to all the three stresses were selected. Further, based on the centrality properties and highly dense interactions, we identified 7 intra-modular hub genes leading to a total of 17 potential candidate genes. Out of these 17 genes, 15 were validated by expression analysis using a panel of 4 test genotypes and a pair of standard check genotypes for each abiotic stress response. Interestingly, all the 15 genes showed upregulation under all stresses and in all the genotypes, suggesting that they could be representing some of the core abiotic stress-responsive genes. More pertinently, eight of the genes were found to be co-localized with the stress-tolerance QTL regions. Thus, in conclusion, our study not only provided an effective approach for studying abiotic stress tolerance in rice, but also identified major candidate genes which could be further validated by functional genomics for abiotic stress tolerance. [ABSTRACT FROM AUTHOR]

The genus Rosa is one of the most important genera of ornamental plants comprising of more than 120 species of which only eight were involved in the development of modern roses. Proper characterization and identification of the species require an accurate and reliable method that discriminates the different species. In the present study, 56 Simple Sequence Repeat (SSR) markers were used to identify and discriminate the 21 cultivated and four wild species of rose. Among the 56 SSR markers, 24 exhibited polymorphism giving a total of 47 alleles across the 28 rose species. The number of alleles ranged from 1 to 3 per marker locus with an average of 1.42. The polymorphism information content for 24 SSR markers ranged from 0.102 (Rw5G14) to 0.87 (Rw60A16) with an average of 0.365. Maximum dissimilarity was observed between R. tomentosa and R. slancensis with similarity coefficient of 0.33. In UPGMA based clustering, R. brunonii was placed along with R. dumalis and similarly R. tomentosa and R. damascena cv. Jwala were placed together, though, they were placed distinctly but on the same coordinates by the principal component analysis. The higher degree of similarity between R. brunonii and R. dumalis was supported by both molecular and morpholgical data while that of between R. macrophylla and R. hybrida cv. Rose Sherbet and wild species as shown in the present study could not be supported by the morphological data based on Distinctness, Uniformity and Stability descriptors. Hence, Simple Sequence Repeat markers proved useful in identifying and assessing genetic relationships among cultivated species of rose, whereas, wild species need more robust dataset with still higher number of markers. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to find out the development team structure and work division at the onsite and offshore location for development, re-engineering and maintenance projects in Indian outsourcing software industry. This study employs expert interview approach in Indian software industry to find out team structure and work division between onsite and offshore locations. The requisite data were collected through focus group meeting, expert interviews and direct observations. The study found that the development projects require higher onsite presence in comparison to re-engineering and maintenance projects and offshore team involved in coding and testing work. The role and responsibilities of team members at onsite and offshore location varies drastically for different kinds of projects in an outsourcing environment. The software project manager can use the findings to get more insight into the project and divide the software team between onsite and offshore location. The study is novel as there is little attempt at finding the team structure to execute various kinds of business software development in outsourcing environment in the context of India. [ABSTRACT FROM AUTHOR]

Deeper Rooting 1 (DRO1) gene identified from a major QTL on chromosome 9 increases the root growth angle (RGA) and thus facilitates survival under drought and hence is an excellent candidate for rice improvement. Twenty-four major Indian upland and lowland genotypes including the 'yield under drought' (DTY) QTL donors were subjected to allele mining of DRO1 (3058 bp) using four pairs of overlapping primers. A total of 216 and 52 SNPs were identified across all genotypes in the gene and coding region (756 bp) respectively with transversions 3.6 fold more common than transitions in the gene and 2.5 times in the CDS. In 251 amino acid long protein, substitutions were found in 19 positions, wherein change in position 92 was the most frequent. Based on allele mining, the 24 genotypes can be classified into 16 primary structure variants ranging from complete functional allele (Satti, IR36 and DTY 3.1 donor, IR81896-B-B-195) to truncated non-functional alleles in PMK2, IR64, IR20 and Swarna. All the DTY donors, other than IR81896-B-B-195, and most of the upland drought tolerant cultivars (Nagina 22, Vandana and Dhagaddeshi) had accumulated 6–19 SNPs and 4–8 amino acid substitutions resulting in substantial differences in their protein structure. The expression analysis revealed that all the genotypes showed upregulation under drought stress though the degree of upregulation varied among genotypes. The information on structural variations in DRO1 gene will be very useful for the breeders, especially in the light of recent breeding programmes on improving drought tolerance using several DTY donors and upland accessions. [ABSTRACT FROM AUTHOR]

This investigation pertains to the bitumen production using component blending. During the manufacture of blended bitumen, the proportion of the constituents, the temperature during blending, and the duration of blending are selected to meet the penetration at 25°C and the absolute viscosity at 60°C as per the Indian specifications. The choices of the blend parameters become challenging when the constituents from multiple crudes are blended to produce different paving grades. Two constituent and three constituent blends for four different grades of bitumen were prepared in a laboratory blending facility from four different crude sources. A design of experiments framework was used to develop prediction models for penetration and viscosity. Simulations were carried out to suggest blending schemes to manufacture all the viscosity grades from different crude sources. Correspondence between the viscosity grade and high-temperature performance grade was observed for blend parameters for the crude sources investigated in this study. [ABSTRACT FROM AUTHOR]

Since 1990s, the world has seen a lot of advances in providing humanitarian aid through sophisticated logistics operations. The current consensus seems to be that humanitarian relief organizations (HROs) can improve their relief operations by collaborating with logistics service providers (CLSPs) in the commercial sector. The question remains: how can HROs select the most appropriate CLSP for disaster preparation? Despite its practical significance, no explicit effort has been done to identify the criteria/factors in prioritizing and selecting a CLSP for disaster relief. The present study aims to address this gap by consolidating the list of criteria from a socio-technical systems (STS) perspective. Then, to handle the interdependence among the criteria derived from the STS, we develop a hybrid multi-criteria decision making model for CLSP selection in the disaster preparedness stage. The proposed model is then evaluated by a real-life case study, providing insights into the decision-makers in both HROs and CLSPs. [ABSTRACT FROM AUTHOR]

The key objective of this study is to develop a tool (hybridization or integration of different techniques) for locating the temporary blood banks during and post-disaster conditions that could serve the hospitals with minimum response time. We have used temporary blood centers, which must be located in such a way that it is able to serve the demand of hospitals in nearby region within a shorter duration. We are locating the temporary blood centres for which we are minimizing the maximum distance with hospitals. We have used Tabu search heuristic method to calculate the optimal number of temporary blood centres considering cost components. In addition, we employ Bayesian belief network to prioritize the factors for locating the temporary blood facilities. Workability of our model and methodology is illustrated using a case study including blood centres and hospitals surrounding Jamshedpur city. Our results shows that atleast six temporary blood facilities are required to satisfy the demand of blood during and post-disaster periods in Jamshedpur. The results also show that that past disaster conditions, response time and convenience for access are the most important factors for locating the temporary blood facilities during and post-disaster periods. [ABSTRACT FROM AUTHOR]

Background: Increased water and labour scarcity in major rice growing areas warrants a shift towards direct seeded rice cultivation under which management of weeds is a major issue. Use of broad spectrum non-selective herbicides is an efficient means to manage weeds. Availability of rice genotypes with complete tolerance against broad-spectrum non-selective herbicides is a pre-requisite for advocating use of such herbicides. In the present study, we developed an EMS induced rice mutant, 'HTM-N22', exhibiting tolerance to a broad spectrum herbicide, 'Imazethapyr', and identified the mutations imparting tolerance to the herbicide. Results: We identified a stable and true breeding rice mutant, HTM-N22 (HTM), tolerant to herbicide, Imazethapyr, from an EMS-mutagenized population of approximately 100,000 M plants of an upland rice variety, Nagina 22 (N22). Analysis of inheritance of herbicide tolerance in a cross between Pusa 1656-10-61/HTM showed that this trait is governed by a single dominant gene. To identify the causal gene for Imazethapyr tolerance, bulked segregant analysis (BSA) was followed using microsatellite markers flanking the three putative candidate genes viz., an Acetolactate Synthase (ALS) on chromosome 6 and two Acetohydroxy Acid Synthase (AHAS) genes, one on chromosomes 2 and another on chromosome 4. RM 6844 on chromosome 2 located 0.16 Mbp upstream of AHAS (LOC_Os02g30630) was found to co-segregate with herbicide tolerance. Cloning and sequencing of AHAS (LOC_Os02g30630) from the wild type, N22 and the mutant HTM and their comparison with reference Nipponbare sequence revealed several Single Nucleotide Polymorphisms (SNPs) in the mutant, of which eight resulted in non-synonymous mutations. Three of the eight amino acid substitutions were identical to Nipponbare and hence were not considered as causal changes. Of the five putative candidate SNPs, four were novel (at positions 30, 50, 81 and 152) while the remaining one, S627D was a previously reported mutant, known to result in Imidazolinone tolerance in rice. Of the novel ones, G152E was found to alter the hydrophobicty and abolish an N myristoylation site in the HTM compared to the WT, from reference based modeling and motif prediction studies. Conclusions: A novel mutant tolerant to the herbicide 'Imazethapyr' was developed and characterized for genetic, sequence and protein level variations. This is a HTM in rice without any IPR (Intellectual Property Rights) infringements and hence can be used in rice breeding as a novel genetic stock by the public funded organizations in the country and elsewhere. [ABSTRACT FROM AUTHOR]

In this paper, we propose a framework for performing allocation, assignment and admission control (AAA) in next generation cellular networks. A novel heuristic method for resource allocation is proposed. The allocation is done in a semi-distributed manner consisting of central allocation and local allocation. The role of the assignment module is to estimate the amount of resources needed by a user in order to satisfy the quality of service (QoS) requirements of the application. To that end, a Markov based approach which calculates the dropping probability of packets by considering the effects of queuing in the medium access control layer and the adaptive modulation and coding in the physical layer is presented. In order to estimate the required resources, the predicted throughput and delay are calculated based on the dropping probability and the predicted values are mapped to the required ones. The admission control module is responsible for admitting or rejecting a new or handoff user and is based on a mean resource calculation. The calculation takes into account the mean number of resources used by existing users as well as the buffer conditions of the individual users. By combining the three novel contributions on AAA into the AAA framework the overall network as well as the cell-edge throughput have been improved and the number of admitted users have been increased while still guaranteeing QoS for new users as well as existing users. [ABSTRACT FROM AUTHOR]

In this paper we present a framework, called Futon, which provides a platform to integrate heterogeneous radio access networks. Futon is a hybrid fibre-radio network that replaces legacy base stations with simple remote antenna units, which are connected to a central unit. As a part of the Futon framework, a generic middleware architecture is discussed in detail, which provides interoperability, cooperative management and service provisioning to both underlying radio access networks (RANs) and IP layer for a heterogeneous network scenario. One of the middleware's functionality is to provide vertical handover between heterogeneous IP-based radio access technologies and to ensure seamless mobility and service continuity, which is implemented on top of an IPv4/IPv6 Mobile IP (MIP) core. In this paper, the Futon framework and a generic middleware architecture as a part of Futon framework for heterogeneous RANs is discussed. The main modules of the middleware, namely common radio resource management (CRRM), media independent handover, Service/Connection Manager and link selection are explained in detail. Radio over fibre (RoF) Manager is an important part of Central unit, which does performance, fault and security management of network elements. RoF manager helps middleware during handoff, by providing the status of fibre optic links. The implementation of Security management module as a part of RoF manager, and results of authentication with AAA protocol are explained. The CRRM as part of middleware is simulated and the results of experimental evaluation are presented. [ABSTRACT FROM AUTHOR]

Maastrichtian–Danian strata of the Cauvery basin as well as selected sections of NE-Mexico, Guatemala and Israel record Ba anomalies, away from the Cretaceous/Tertiary boundary (KTB) in addition to common occurrences of geochemical and stable isotopic anomalies across the KTB. Ba anomalies were recorded in monotonous shallow marine sandstones of the Cauvery basin (south India) which contain minor amounts of Ba-orthoclase. Barium anomalies were observed also in shallow marine carbonates in sections of Israel, NE-Mexico and Guatemala. Calculation of excess Ba with reference to PAAS (Post-Archaen Average Australian Shale), comparison of coeval geochemical anomalies, depositional pattern and associated petrographic and mineralogical features of the Cauvery basin revealed that while a first Ba peak was related to detrital influx, the second Ba peak was coincident with sea level fall which in turn may have been influenced by emission of volatile hydrocarbons and resultant climatic changes. In view of intrinsic involvement of Ba in various geochemical processes and occurrence of Ba anomalies in K/T sites distributed around the world (NE-Mexico, Guatemala and Israel), it is suggested that probable causes of such widespread Ba-anomalies should be taken into consideration while analyzing end Cretaceous events. These observations support the views espoused by many workers who have stated that the K/T boundary was also accompanied by many non-catastrophic events that might have contributed to environmental stress on marine fauna, as a result of which selective multi-stage extinctions occurred. [ABSTRACT FROM AUTHOR]

Classification of cardiac diseases from electrocardiogram signals is essential for enhancing patient results to minimize healthcare costs, early detection and accurate diagnosis. This research investigates the integration of dimensionality reduction methods with various deep learning classifiers to improve the accuracy and efficient classification of cardiac disease. Uniform Manifold Approximation and Projection combined with Principal Component Analysis is used for dimensionality reduction, that captures both global and local data structures. Deep learning classifiers with convolutional neural networks, capsule networks, recurrent neural networks, graph neural networks, deep long short-term memory and automatical attention-based convolutional neural networks are employed for classification. The Adaptive spiral Flying Sparrow Search algorithm optimizes classifier parameters for enhance accuracy. Performance is evaluated through various metrics, with area under the receiver operating characteristic curve, accuracy, F1-Score, precision and recall. The proposed method's outcomes are compared with and without optimization to demonstrate the efficiency and attains 92.16%, 96.15%, 91.95%, 94.65%, 91.45% and 92.85% accuracy respectively for each classification method. [ABSTRACT FROM AUTHOR]