Browse Items (16488 total)
Sort by:
-
Gray Level Co-occurrence Matrix based Fully Convolutional Neural Network Model for Pneumonia Detection
This study presents a new method to improve the detection ability of a convolutional neural network (CNN) in pneumonia detection using chest X-ray images. Using Gray-Level Co-occurrence Matrix (GLCM) analysis, additional channels are added to the original image data provided by Guangzhou Children's Hospital in Guangzhou, China. The main goal is to design a lightweight, fully convolution network and increase its available information using GLCM. Performance analysis is performed on the new CNN model and GLCM-enhanced CNN model, and results are compared with Transfer Learning approaches. Various evaluation metrics, including accuracy, precision, recall, F1 score, and AUC-ROC, are used to evaluate the improved analysis performance of CNN. The results showed a significant increase in the ability of the model to detect pneumonia, with an accuracy of 99.57%. In addition, the study evaluates the descriptive properties of the CNN model by analyzing its decision process using Grad-CAM. 2024, J.J. Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology. All rights reserved. -
DEVELOPMENT AND EVALUATION OF PNEUMFC NET: A NOVEL AUTOMATED LIGHTWEIGHT FULLY CONVOLUTIONAL NEURAL NETWORK MODEL FOR PNEUMONIA DETECTION
The aim of this study is to address the challenges of pneumonia diagnosis under constraint resources and the need for quick decision making. We present the PneumFC Net, a novel architectural solution where our approach focuses on minimizing the number of trainable parameters by incorporating transition blocks that efficiently manage channel dimensions and reduce number of channels. In contrast to using fully connected layers, which disregard the spatial structure of feature maps and substantially increase parameter counts, we exclusively employ only convolutional layer approach. In the study, X-ray image dataset is used to train and evaluate the proposed Convolutional Neural Network model. By carefully designing the architecture, the model achieves a balance between parameters and accuracy while maintaining comparable performance to pre-trained models. The results demonstrate the model's effectiveness in detecting pneumonia images reliably. In addition, the study examines the decision-making process of the model using Grad-CAM, which helps to identify important aspects of radiographic images that contribute to the positive pneumonia prediction. Furthermore, the study shows that the proposed model, Pneum FC Net not only has the highest accuracy of 98%, but the total trainable model parameters is only 0.02% of the next best model VGG-16, thus establishing the potential of this new robust Deep Learning model. This research primarily addresses concerns related to mitigating significant computational requirements, with a specific focus on implementing lightweight networks. The contribution of this work involves the development of resource-efficient and scalable solution for pneumonia detection. 2024 Little Lion Scientific. All rights reserved. -
Comparison of Augmentation and Preprocessing Techniques for Improved Generalization Performance in Deep Learning based Chest X-Ray Classification
Convolutional Neural Network (CNN) models are well known for image classification; however, the downside of CNN is the ineffectiveness to generalize and inclination towards over-fitting in case of a small train dataset. A balanced and sufficient data is thus essential to effectively train a CNN model, but this is not always possible, especially in the case of medical imaging data, as often patients with the same disease are not always available. Image augmentation addresses the given issue by creating new data points artificially with slight modifications. This study, investigates ten different methods with various parameters and probability and their combined effect on the test dataset's generalization performance and F1 Score. For the study, three pre-Trained CNN models, namely ResNetl8, ResNet34, and ResNet50, are fine tuned on a small training dataset of 500 Pneumonia and 160 Non-Pneumonia(Normal) Images for each augmentation setting. The test accuracy, F1 Score, and generalization performance were calculated for a test dataset consisting of 50 Pneumonia and 16 Non-Pneumonia(Normal) Images. 2022 IEEE. -
Detection and Classification of Thoracic Diseases in Medical Images using Artificial Intelligence Techniques: A Systematic Review
Artificial Intelligence is at the leading edge of innovation and is developing very fast. In recent studies, it has played a progressive and vital role in Computer-Aided Diagnosis. The chest is one of the large body parts of human anatomy and contains several vital organs inside the thoracic cavity. Furthermore, chest radiographs are the most commonly ordered and globally used by physicians for diagnosis. An automated, fast, and reliable detection of diseases based on chest radiography can be a critical step in radiology workflow. This study presents the conduction and results of a systematic review investigating Artificial Intelligence Techniques to identify Thoracic Diseases in Medical Images. The systematic review was performed according to PRISMA guidelines. The research articles published in English were filtered based on defined inclusion and exclusion criteria. The Electrochemical Society -
Nutraceuticals to prevent and manage cardiovascular diseases
Unhealthy lifestyle and diet are the key risk factors to cardiovascular diseases. A healthy cardiac and vascular system can prevent cardiovascular-related diseases like hypertension, atherosclerosis, and heart stroke. Identifying pharmacologically important metabolites had paved the way to contemporary medicine. People are more attracted to them as they are majorly plant-based metabolites such as polysaccharides, polyphenols, polysterols, and vitamins as cardio-protectors. Preclinical, clinical, and animal studies provide substantial data confirming nutraceuticals as a promising therapeutic agent in curing cardiovascular diseases. This chapter summarizes on major bioactive molecules as nutraceuticals with preclinical and clinical studies, emphasising their cardiovascular protective roles. 2023 Elsevier Inc. All rights reserved. -
A Comparative Evaluation of Standalone LLMs and Retrieval-Augmented Generation Models Using Hypothetical Gemini Systems
This study assesses the efficacy of two theoretical language models; Gemini Standalone LLM and Gemini RAG (Retrieval Augmented Generation) across diverse natural language inquiries. The assessment centers on three principal metrics: precision, pertinence, and inference duration. The experiment utilizes a controlled simulation to illustrate the benefits and drawbacks of independent language creation versus retrieval augmented generation strategies. The results demonstrate that RAG at trains superior accuracy and relevance by integrating retrieved context, albeit it incurs longer inference durations. This comparative analysis seeks to assist researchers in comprehending the ramifications of including retrieval methods into big language models. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Market Reaction to Dividend Announcements During Pandemic: An Event Study
This study analyses the difference in stock market reactions to dividend announcement during the pandemic. The thirty constituent stocks of Sensex, the index of Bombay Stock Exchange (BSE), is used for analysis. This allows cross-industry comparison of the market reaction. The study examines stock market reactions covering 44 days around the dividend announcement dates. The primary objective of this study is to understand whether the price adjustment linked to the dividend announcement news during the pandemic was different from the earlier years. This empirical study employs the conventional event study methodology using abnormal returns (ARs) to examine the stock market reaction to dividend announcement. The market reaction to dividend announcement was increasingly positive during the pandemic, compared to previous years. The statistical pooled t-tests showed there was a significant relationship between the pandemic and ARs. The findings also indicate that the difference in the market reaction to dividend announcement was more prominent in services stocks than that in manufacturing. Further, the results also verify the weak-form of efficiency of Indian stock exchange. 2025 MDI. -
Artificial Intelligence and Human-AI Driven Accreditation System for Higher Education Quality Assurance
This study introduces the Artificial Intelligence and Human-AI powered Accreditation System, which is meant to transform quality assurance in higher education. The suggested framework will combine human knowledge and smart automation to guarantee transparency, scalability and reliability of accreditation assessments. The data processing algorithm is based on Robust Principal Component Analysis of noise elimination and data normalization and then on the minimum-Redundancy Maximum-Relevancefeature selection algorithm. The fundamental classifier is a Graph Attention Network developed on PyTorch and PyTorch Geometric that is able to capture all the relations between institutional characteristics to make explainable judgments. A blockchain ledger is incorporated to record accreditation results to achieve security and traceability. The experimental simulations show excellent performance with high accuracy, evaluation times, and fairness than the traditional models. The system offers a strong, smart and open accreditation system that facilitates continuous improvement and accountability in the higher education system. 2025 IEEE. -
INTRODUCTION TO NEUROCOGNITIVE REHABILITATION
This chapter offers a comprehensive examination of the historical development, theoretical foundations, and contemporary directions in neurocognitive rehabilitation. Beginning with early clinical observations, including the cases of Phineas Gage and Alexander Lurias wartime studies, the narrative traces the evolution of the field from anecdotal case reports to empirically validated interventions. The discussion delineates core principles that underpin effective rehabilitation practice, including individualization and person-centered planning, goal-directed and functionally relevant interventions, evidence-based methodologies, interdisciplinary collaboration, and ecological validity. Established frameworks such as the cognitive neuropsychological model and the information processing model are critically appraised alongside the biopsychosocial perspective and holistic neuropsychological rehabilitation approaches. Particular attention is given to emerging trends, including the integration of advanced technologies such as virtual reality, tele-rehabilitation, and adaptive computerized training as well as their implications for accessibility, scalability, and equity in service delivery. The chapter further considers the relevance of these paradigms to forensic psychology and legal scholarship, highlighting their role in capacity assessment and the determination of criminal responsibility. Drawing upon recent systematic reviews and high-quality empirical studies, this synthesis underscores the necessity of combining scientific rigor with ethically grounded, person-centered care. While artificial intelligence tools supported aspects of drafting, the content has been critically curated and adapted to reflect current scholarship and clinical expertise. The chapter concludes by emphasizing the imperative for rehabilitation professionals to engage in lifelong learning and innovation to meet the evolving needs of individuals with acquired brain injury. 2026 selection and editorial matter, K. Jayasankara Reddy; individual chapters, the contributors. All rights reserved. -
Texture-Based DNN for Pneumonia in Thorax X-Rays
This paper introduces an innovative methodology for identifying pneumonia in thoracic X-ray images through the application of neural network classifiers. In our experiment, we employed a comprehensive training regimen involving multiple neural network classifiers, each trained on distinct sets of texture features meticulously extracted from thoracic X-ray images. Four different gray-level matrices and a neighboring gray-tone difference matrix (NGTDM) were used to generate these input features, guaranteeing a reliable depiction of the textural properties found in the X-ray pictures. We carried out an extensive evaluation utilizing a number of performance criteria to gauge the trained classifiers' efficacy. Classifying the thoracic X-ray pictures into two groups pneumonia and healthy state was the assignment assigned to the classifiers. A thorough study of the classifiers' performance was provided by our assessment measures, which comprised accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). The experimental findings showed that the suggested method accomplished a remarkable 91% overall test categorization accuracy, which was encouraging. This degree of precision highlights how well our approach works to accurately diagnose pneumonia from thoracic X-ray images. Furthermore, the consistent performance across different metrics highlights the robustness and generalizability of the proposed strategy. 2025, Iquz Galaxy Publisher. All rights reserved. -
A critical analysis of the law relating to elementary education in India viz-a-viz minimum level of learning /
The “demand for free and compulsory education” started in the British period. The framers directed that the object of Article 45 must be achieved within ten years of the commencement of the constitution. After several judicial strictures the Constitutional (Eighty Sixth) Amendment Act 2002 (Amendment Act, 2002) declared ‘education’ as a fundamental right. -
A Critical analysis of the law relationg to elementary education in india Viz-A-Viz Minimum level of learning
The demand for free and compulsory education started in the British period. newlineThe framers directed that the object of Article 45 must be achieved within ten years newlineof the commencement of the constitution. After several judicial strictures the newlineConstitutional (Eighty Sixth) Amendment Act 2002 (Amendment Act, 2002) declared education as a fundamental right. To execute this mandate the Children Right to Free and Compulsory Education Act 2009 (RTE Act, 2009) was passed. However, the government has failed to fulfil the mandate of giving quality education in terms of minimum level of learning under the RTE Act. One of the newlineparameters of the Quality Monitoring Tool under Sarva Shiksha Abhiyan (SSA) is newlineto give quality education in terms of minimum level of learning. But, when it was newlinerealized that the children from Government schools are completing their primary newlineeducation without minimum level of learning, three amendments had been made to the RTE Act 2009, i.e., during 2012, 2015 and 2019. Yet, the latest Annual Survey on Education Report shows that there is poor minimum level of learning among children who have completed their primary education in government primary newlineschools. Thus, the purpose of this research is to critically analyse the RTE Act 2009 newlineand the subsequent amendments to the Act of 2009 and to study various policies and schemes under SSA, to explore the reasons for low level of learning in government primary school and to make suggestion to improve the minimum level of learning. -
Finding a New Life Through Adaptive Reuse for the Old Railway Terminus Complex, Kochi, Kerala
The research article, titled Finding a New Life through adaptive reuse for the Old Railway Terminus Complex, Kochi, Kerala, examines the historical and cultural importance of the original and still existing railway station complex in Ernakulam. This station, which symbolized the arrival of the initial train to Cochin, was constructed during the zenith of the Kochi kingdom in partnership with the British, making a substantial contribution to the regions progress. Over time, the stations original role steadily diminished, leading to its abandonment and subsequent deterioration. The aim of the study is to assess the effectiveness of adaptive reuse as a strategy for conserving this valuable urban asset. The objective of the research is to reuse these neglected structures with the goal of reintegrating them into the vibrant urban landscape of Kochi, thus ensuring a sustainable and environmentally conscious future for the city. The approach involves a thorough analysis of the historical context, current condition, and potential utilization of the precinct. The main findings emphasize that adaptive reuse is an effective method for optimizing space to meet modern requirements while maintaining the historical essence of the built environment. The study highlights the significance of preserving cultural assets by creatively repurposing decommissioned railway historical structures, demonstrating their potential to contribute to sustainable urban development. The research highlights the importance of finding a balance between preserving historical elements and incorporating modern practicality. It provides a framework that can be used by other communities dealing with similar challenges. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Static perfect fluid space-Time and paracontact metric geometry
The main purpose of this paper is to study and explore some characteristics of static perfect fluid space-Time on paracontact metric manifolds. First, we show that if a K-paracontact manifold M2n+1 is the spatial factor of a static perfect fluid space-Time, then M2n+1 is of constant scalar curvature-2n(2n + 1) and squared norm of the Ricci operator is given by 4n2(2n + 1). Next, we prove that if a (?,?)-paracontact metric manifold M2n+1 with ? >-1 is a spatial factor of static perfect space-Time, then for n = 1, M2n+1 is flat, and for n > 1, M2n+1 is locally isometric to the product of a flat (n + 1)-dimensional manifold and an n-dimensional manifold of constant negative curvature-4. Further, we prove that if a paracontact metric 3-manifold M3 with Q? = ?Q is a spatial factor of static perfect space-Time, then M3 is an Einstein manifold. Finally, a suitable example has been constructed to show the existence of static perfect fluid space-Time on paracontact metric manifold. 2022 World Scientific Publishing Company. -
The zamkovoy canonical paracontact connection on a para-kenmotsu manifold
The object of the paper is to study a type of canonical linear connection, called the Zamkovoy canonical paracontact connection on a para-Kenmotsu manifold. 2021 D. G. Prakasha et al. -
On (?)-Lorentzian para-Sasakian Manifolds
The object of this paper is to study (?)-Lorentzian para-Sasakian manifolds. Some typical identities for the curvature tensor and the Ricci tensor of (?)-Lorentzian para-Sasakian manifold are investi-gated. Further, we study globally ?-Ricci symmetric and weakly ?-Ricci symmetric (?)-Lorentzian para-Sasakian manifolds and obtain interesting results. 2022 Academic Center for Education, Culture and Research TMU. -
h-almost Ricci Solitons on Generalized Sasakian-space-forms
The aim of this article is to study the h-almost Ricci solitons and h-almost gradient Ricci solitons on generalized Sasakian-space-forms. First, we consider h-almost Ricci soliton with the potential vector field V as a contact vector field on generalized Sasakian-space-form of dimension greater than three. Next, we study h-almost gradient Ricci solitons on a three-dimensional quasi-Sasakian generalized Sasakian-space-form. In both the cases, several interesting results are obtained Kyungpook Mathematical Journal -
Invariant Submanifolds of (?)-Sasakian Manifolds
In this paper, we consider invariant submanifolds of an (?)-Sasakian manifolds. We show that if the second fundamental form of an invariant submanifold of a (?)-Sasakian manifold is recurrent then the submanifold is totally geodesic. We also prove that, invariant submanifolds of an Einstein (?)-Sasakian manifolds satisfying the conditions (Formula presented) (X, Y) ? = 0 and (Formula presented)(X, Y) (Formula presented)? = 0 with ?r ? n(n 1) are also totally geodesic. 2020. All Rights Reserved. -
A Novel Approach for Fractional (1 + 1 ) -Dimensional BiswasMilovic Equation
In this paper, we find the solution for (1 + 1 ) -dimensional fractional Biswas-Milovic (FBM) equation using the q-homotopy analysis transform method (q-HATM). The Biswas-Milovic equation is a generalization of the nonlinear Schringer (NLS) equation. The future scheme is the elegant mixture of q-homotopy analysis scheme with Laplace transform technique and fractional derivative considered in Caputo sense. To validate and illustrate the competence of the method, we examine the projected model in terms of arbitrary order. Moreover, the nature of the attained results have been presented in 3D plots and contour plots for different value of the order. The gained consequences show that, the hired algorithm is highly accurate, easy to implement, and very operative to investigate the nature of complex nonlinear models ascended in science and engineering. 2021, The Author(s), under exclusive licence to Springer Nature India Private Limited. -
ON 3-DIMENSIONAL QUASI-PARA-SASAKIAN MANIFOLDS AND RICCI SOLITONS
The purpose of this paper is to study 3-dimensional quasi-para-Sasakian manifolds and Ricci solitons. First, we prove that a 3-dimensional non-paracosymplectic quasi-para-Sasakian manifold is an ?-Einstein manifold if and only if the structure function ? is constant. Further, it is shown that a Ricci soliton on a 3-dimensional quasi-para-Sasakian manifold with ?=constant is expanding. Moreover, we show that if a 3-dimensional quasi-para-Sasakian manifold admits a Ricci soliton, then the flow vector field V is Killing, and the quasi-para-Sasakian structure can be obtained by a homothetic deformation of a para-Sasakian structure. Besides, we study gradient Ricci solitons and prove that if a 3-dimensional non-paracosymplectic quasi-para-Sasakian manifold with ?=constant admits a gradient Ricci soliton, then the manifold is an Einstein one. Also, a suitable example of a 3-dimensional quasi-para-Sasakian manifold is constructed to verify our results. 2022 A. Razmadze Mathematical Institute of Iv. Javakhishvili Tbilisi State University. All rights reserved.