Browse Items (16481 total)
Sort by:
-
A deep learning approach in early prediction of lungs cancer from the 2d image scan with gini index
Digital Imaging and Communication in Medicine (DiCoM) is one of the key protocols for medical imaging and related data. It is implemented in various healthcare facilities. Lung cancer is one of the leading causes of death because of air pollution. Early detection of lung cancer can save many lives. In the last 5years, the overall survival rate of lung cancer patients has increased, due to early detection. In this paper, we have proposed Zero-phase Component Analysis (ZCA) whitening and Local Binary Pattern (LBP) to enhance the quality of lung images which will be easy to detect cancer cells. Local Energy based Shape Histogram (LESH) technique is used to detect lung cancer. LESH feature extracts a suitable diagnosis of cancer from the CT scans. The Gini coefficient is used for characterizing lung nodules which will be helpful in Computed Tomography (CT) scan. We propose a Convolutional Neural Network (CNN) algorithm to integrate multilayer perceptron for image segmentation. In this process, we combined both traditional feature extraction and high-level feature extraction to classify lung images. The convolutional neural network for feature extraction will identify lung cancer cells with traditional feature extraction and high-level feature extraction to classify lung images. The experiment showed a final accuracy of about 93.27%. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Mining Heterogeneous Lung Cancer from Computer Tomography (CT) Scan with the Confusion Matrix
Early detection of any sort of cancer, particularly lung cancer, which is one of the worlds most lethal illnesses, can save many lives. Life expectancy can be improved and the degree of mortality reduced by adopting the early forecast. While there are different methods like X-ray and CT scans to detect lung cancer cells, CT images resulted as more favored. The 2D images are used for more accurate medical results, such as CT scans. The proposed approach here will address how to interpret the CT images for the Mining Heterogeneous Lung Cancer from Computer Tomography (CT) Scan with the Confusion Matrix. This research will explore how the image conversion can be achieved through different methods of image processing to obtain better results from CT images. The Confusion Matrix helps to estimate inequality in a picture pattern. After the evaluation of the processed images by Confusion Matrix, a final accuracy with a result of 93% is obtained. 2023 Scrivener Publishing LLC. -
Early prediction of lungs cancer by deep learning algorithms from the CT images with LBP features
The early prediction of the any type of cancer can save the lives of many especially if it is lung cancer which is one of the deadly diseases in the world. Thus the early prediction is implemented we can increase life expectancy and bring the mortality level low. Although there are various methods to detect the lung cancer cells by X-ray and CT scans, however the CT images are more preferred. The 2D images like CT scans are used to get medical results more accurate. The proposed method here will discuss how the LBP features are used to analyze the CT images with the support of Deep Learning methods. In this research work we will discuss how the image manipulation can be done to achieve better results from the CT images through various image processing methods. LBP features helps in estimating the distribution of local binary pattern of an image. A final result with 93% is achieved after the training of the processed images by LBP features. 2020 SERSC. -
Cop-edge critical generalized Petersen and Paley graphs
Cop Robber game is a two player game played on an undirected graph. In this game, the cops try to capture a robber moving on the vertices of the graph. The cop number of a graph is the least number of cops needed to guarantee that the robber will be caught. We study cop-edge critical graphs, i.e. graphs G such that for any edge e in E(G) either c(G?e) < c(G) or c(G?e) > c(G). In this article, we study the edge criticality of generalized Petersen graphs and Paley graphs. 2023 Azarbaijan Shahid Madani University. -
3-Sequent achromatic sum of graphs
Three vertices x,y,z in a graph G are said to be 3-sequent if xy and yz are adjacent edges in G. A 3-sequent coloring (3s coloring) is a function ?: V (G) ?{1, 2,...,k} such that if x,y and z are 3-sequent vertices, then either ?(x) = ?(y) or ?(y) = ?(z) (or both). The 3-sequent achromatic number of a graph G, denoted ?3s(G), equals the maximum number of colors that can be used in a coloring of the vertices' of G such that if xy and yz are any two sequent edges in G, then either x or z is colored the same as y. The 3-sequent achromatic sum of a graph G, denoted a'3s(G), is the greatest sum of colors among all proper 3s-coloring that requires ?3s(G) colors. This research initiates the study of 3-sequent achromatic sum and finds the exact values of this parameter for some known graphs. Furthermore, we calculate the a'3s(G) of corona product, Cartesian product of the graphs and some important results have been proved and a comparative study is carried out. 2021 World Scientific Publishing Company. -
Zero forcing number of degree splitting graphs and complete degree splitting graphs
A subset Z V(G) of initially colored black vertices of a graph G is known as a zero forcing set if we can alter the color of all ver- tices in G as black by iteratively applying the subsequent color change condition. At each step, any black colored vertex has exactly one white neighbor, then change the color of this white vertex as black. The zero forcing number Z(G), is the minimum number of vertices in a zero forcing set Z of G (see [11]). In this paper, we compute the zero forcing num- ber of the degree splitting graph (DS-Graph) and the complete degree splitting graph (CDS-Graph) of a graph. We prove that for any simple graph, Z[DS(G)] k + t, where Z(G) = k and t is the number of newly introduced vertices in DS(G) to construct it. 2019 Sciendo. All rights reserved. -
Advanced Malware Analysis and Detection Using Deep Neural Networks
Malware is malicious software that is used to cause harm to the computer systems, networks or users across several operating systems, such as Windows, macOS, iOS, Android and Linux. The identification and categorisation of malware is a difficult subject with no one-size-fits-all solution due to the constant evolution of the malware and lack of standardised detection frameworks. The use of deep learning models in cybersecurity encourages the growth of Explainable Artificial Intelligence (XAI) and Interpretable Machine Learning (IML) techniques. The goal of this research is to automate the way of analysing malware using a simple framework without the need of complex software. This article focuses on the application of Neural Networks, a deep learning model in detecting and analysing the behavior of malware. The model performed better when compared to other techniques by achieving an accuracy of 99.43%, precision of 99.05% and a F1 score of 0.99, which was trained on a large dataset containing 1,38,048 samples. 2025 IEEE. -
Advanced Malware Analysis and Detection Using Deep Neural Networks
Malware is malicious software that is used to cause harm to the computer systems, networks or users across several operating systems, such as Windows, macOS, iOS, Android and Linux. The identification and categorisation of malware is a difficult subject with no one-size-fits-all solution due to the constant evolution of the malware and lack of standardised detection frameworks. The use of deep learning models in cybersecurity encourages the growth of Explainable Artificial Intelligence (XAI) and Interpretable Machine Learning (IML) techniques. The goal of this research is to automate the way of analysing malware using a simple framework without the need of complex software. This article focuses on the application of Neural Networks, a deep learning model in detecting and analysing the behavior of malware. The model performed better when compared to other techniques by achieving an accuracy of 99.43%, precision of 99.05% and a F1 score of 0.99, which was trained on a large dataset containing 1,38,048 samples. 2025 IEEE. -
Smart Finances: A Web-Based System for Personalized Financial Management
Smart Finances is a dynamic and user-friendly web application designed to assist users in managing and understanding their personal finances with ease. Built using HTML, CSS, JavaScript, and PHP with MySQL for backend functionality and data persistence, the platform offers a suite of tools, including an interest calculator, investment calculator, budget manager, and interactive spending analysis. The intuitive interface enhances usability and promotes financial literacy, especially among students and individuals new to personal finance. The application supports both guest and registered user modes, offering tiered access to features based on authentication. Smart Finances aims to make money management more approachable and insightful through accessible design and practical functionality. Initial user testing with 20 participants indicated a 30% improvement in budgeting accuracy and a high satisfaction rate (88%) with the usability of the interface. These results validate the systems impact on financial literacy and user engagement. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Analysis of Online In-Destination Booking Service Processes in the Travel Industry: A Case Study
This article presents a comprehensive analysis of the online in-destination booking service processes within the dynamic landscape of the travel industry. Utilizing a case study approach, the research investigates the various stages involved in providing travel-related services, focusing on the key players. The study employs a quantitative method to assess the information quality, system quality, service quality, customer satisfaction, and purchase intention of online in-destination booking. The research highlights the investigation of the usability of online travel booking systems and identifies the purchase intention of customers towards online travel booking websites. To address the research objectives, the participants are selected using a nonprobability sampling method. The sample size of the study is 225 from in and around Coimbatore. The sampling procedure used is convenience sampling. The sampling is selected based on convenience and accessibility to the residents. The findings reveal that there exists a significant difference in respondents opinions on quality criteria: system quality and service quality. Additionally, the study finds that the loading time of online travel booking websites is positively correlated with quality criteria and features of travel apps. By examining a specific case within the travel sector, this study contributes valuable insights that can inform strategic decision-making for businesses operating in the online in-destination booking space. The results aim to guide industry players in enhancing their operational efficiency, leveraging technology advancements, and aligning their services with evolving customer expectations, ultimately fostering sustainable growth in the competitive travel market. 2024, Bentham Books imprint. -
Effectiveness of Learning Management System (LMS) in Sustainable Learning and Development among Bank Employees
Learning Management Systems in the form of E-Learning platform is currently an evolving scenario for the primary means of delivering various courses across educational, business, industries and vocational learning environments in the form of Learning and Development activities in all the sectors. LMS is a challenging and resource-intensive task requires demanding substantial knowledge, time, and effort. Consequently, there emerged a necessity in both research and practical applications to establish the personalized usage process of an LMS. Despite its significant impact on the outcomes of such an Information System (IS), the usage process has to be analysed. The researcher developed a conceptual model to delineate with set of factors to influence LMS course in Learning and Development Practices in industry context. Researcher revealed specific set of factors such as interface design, content presentation format, transfer of learning, and feedback mechanisms significantly impact learner satisfaction among Bank employees in their Learning and Development activities. Moreover, learner satisfaction depends on the application platform and content. The findings offer a valuable insight to design a corporate education system, with the quality content delivery and practical delivery. By considering these results, designers can develop more integrated and effective LMS to cater the needs and satisfaction of Learning and Development activities among Bank employees. 2024, Creative Publishing House. All rights reserved. -
Phytofabricated Silver Nanoparticles Derived from Leea crispa Leaf Extract: Antituberculosis and Anticancer Activities
Aqueous extracts of Leea crispa used for producing silver nanoparticles (AgNPs) with the supplementation of the external capping substance, were determined by UV-Visible spectroscopy. The synthesized nanoparticles were examined for their antituberculosis and anticancer activities. The presence of phytoconstituents available for reducing silver ions and to form the AgNPs was confirmed using FTIR analysis. The XRD and TEM examination validated the AgNPs spherical particle shape and size of 15 to 85 nm and their face-centered cubic crystal form. Additionally, the FTIR spectrum revealed variation in the band values in the range 1384.0 to 3419.4 cm-1, respectively, and the EDX noted a strong band at 3 keV induced the presence of metallic silver. The AgNPs exhibited comparatively potential anti-tuberculosis activity (0.2 to 100 g/mL) respectively. Alternatively, various doses of AgNPs, 12.5 to 400 g/mL documented considerable activity towards the human breast cancer cell lines. The percentage of cell viability increased at 12.5g/mL and declined at 400 ng/mL concentrations of AgNPs solution. The AgNPs synthesized from L. crispa exhibited potential activity against life-threatening tuberculosis and cancer cells. 2025, North Carolina State University. All rights reserved. -
Novel Approach for Osteoporosis Classification Using X-ray Images
This research delves into the technical advancements of image segmentation and classification models, specifically the refined Pix2Pix and Vision Transformer (ViT) architectures, for the crucial task of osteoporosis detection using X-ray images. The improved Pix2Pix model demonstrates noteworthy strides in image segmentation, achieving a specificity of 97.24% and excelling in the reduction of false positives. Simultaneously, the modified ViT models, especially the MViT-B/16 variant, exhibit superior accuracy at 96.01% in classifying osteoporosis cases, showcasing their proficiency in identifying critical medical conditions. These models are poised to revolutionize osteoporosis diagnosis, providing clinicians with accurate tools for early detection and intervention. The synergies between the Pix2Pix and ViT models open avenues for nuanced approaches in automated diagnostic systems, with the potential to significantly improve clinical results and contribute to the broader landscape of medical image analysis. As osteoporosis remains a prevalent and often undiagnosed condition, the technical insights from this study hold substantial importance in advancing the field, emphasizing the critical role of accurate diagnostic tools in improving patient care and health outcomes. 2025 Oriental Scientific Publishing Company. All rights reserved. -
Assesment of bone mineral density in X-ray images using image processing
X-ray application in medical fields has given rise to various research challenges related to bone, due to its wide usage in finding out the disease related to human anatomy. It has lot of research challenges to solve using available wide application of medical imaging techniques and inspired by this, a novel X-ray images based survey was conducted to understand the role of Xray images in medical field. Bone mass density identification is the standard procedure to monitor the risk of fracture in bone using DEXA. Lot of research has been carried out to calculate BMD using X-ray images and it provided prominent results. Since Xray is economically affordable and very economical compared to DEXA, we have decided to work on X-ray images. This paper explains us about various current advancements and disadvantages with respect to X-ray image in medical sector and various techniques related to BMD calculation. X-ray images characteristics and its fundamentals in the medical field for identifying bone related diseases are also discussed. 2021 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth. -
Diagnosis of Osteoporosis from X-ray Images using Automated Techniques
Osteoporosis is Bone Disease most commonly seen in aged people due to various food habits and life style habits. The bone becomes so brittle and weak which may break just from a fall. So, it is required to attend this Issue as there are various challenges faced by medical domain to identify and treat Osteoporosis. In this paper we focus on identifying and detecting osteoporosis using X-ray images using modified U-net Architecture using Residual Block and skip connections and done comparison study with existing models, as per state-of-art our model outcomes issues in existing model and obtain better accuracy. 2022 IEEE. -
Transfer Learning-Based Osteoporosis Classification Using Simple Radiographs
Osteoporosis is a condition that affects the entire skeletal system, resulting in a decreased density of bone mass and the weakening of bone tissues micro-architecture. This leads to weaker bones that are more susceptible to fractures. Detecting and measuring bone mineral density has always been a critical area of focus for researchers in the diagnosis of bone diseases such as osteoporosis. However, existing algorithms used for osteoporosis diagnosis encounter challenges in obtaining accurate results due to X-ray image noise and variations in bone shapes, especially in low-contrast conditions. Therefore, the development of efficient algorithms that can mitigate these challenges and improve the accuracy of osteoporosis diagnosis is essential. In this research paper, a comparative analysis was conducted Assessing the accuracy and efficiency of the latest deep learning CNN model, such as VGG16, VGG19, DenseNet121, Resnet50, and InceptionV3 in detecting to Classify Normal and Osteoporosis cases. The study employed 830 X-ray images of the Spine, Hand, Leg, Knee, and Hip, comprising Normal (420) and Osteoporosis (410) cases. Various performance metrics were utilized to evaluate each model. The findings indicate that DenseNet121 exhibited superior performance with an accuracy rate of 93.4% Achieving an error rate of 0.07 and a validation loss of only 0.57 compared with other models considered in this study. 2023, International journal of online and biomedical engineering. All Rights Reserved. -
Grey Wolf Optimization Guided Non-Local Means Denoising for Localizing and Extracting Bone Regions from X-Ray Images
The key focus of the current study is implementation of an automated semantic segmentation model to localize and extract bone regions from digital X-ray images. Methods: The proposed segmentation framework uses a pre-processing stage which follows convolutional neural network (CNN) obtained segmentation stage to extract the bone region from X-ray images, mainly for diagnosing critical conditions such as osteoporosis. Since the presence of noise is critical in image analysis, the X-ray images are initially processed with a grey wolf optimization (GWO) guided non-local means (NLM) denoising. The segmentation stage uses a Multi-Res U-Net architecture with attention modules. Findings: The proposed methodology shows superior results while segmenting bone regions from real X-ray images. The experiments include an ablation study that substantiates the need for the proposed denoising approach. Several standard segmentation benchmarks such as precision, recall, Dice-score, specificity, Intersection over Union (IOU), and total accuracy have been used for a comprehensive study. The proposed architectural has good impact compared to the state-of-the-art bone segmentation models and is compared both quantitatively and qualitatively. Novelty: The denoising using GWO-NLM adaptively chose the denoising parameters based on the required conditions and can be reused in other medical image analysis domains with minimal finetuning. The design of the proposed CNN model also aims at better performance on the target datasets. 2023 Biomedical & Pharmacology Journal. -
Anticorrosive studies of Chitosan/TiO2/g-C3N4 composite on mild steel in saline and acidic conditions
This work focuses on the synthesis of a nanocomposite coating that enhances the anticorrosive property of the metal. The nanocomposite under study is a synergistic blend of chitosan, titanium dioxide (TiO2), and graphitic carbon nitride (g-C3N4), effectively challenging the corrosion problem faced by various industries. The environment-friendly and natural properties of chitosan, the photocatalytic activity of TiO2 nanoparticles, and the efficient electrical conductivity of g-C3N4 make the composite an ideal material for studying anticorrosion activity. Experimental techniques like XPS, XRD, HR-TEM, FE-SEM, TGA, BET surface area, and FTIR analysis have been employed to characterize the nanocomposite. Weight loss studies indicate the efficacy of the nanocomposite on mild steel in 3.5 % NaCl and 1 M HCl. The corrosion behavior of the nanocomposite is examined by Tafel curves and electrochemical impedance analysis. The results indicate that the inhibition efficiency of chitosan/TiO2/g-C3N4 nanocomposite is 99 % with a charge transfer resistance value of 152.43 ?, which is more effective in the corrosion inhibition of mild steel than chitosan, TiO2, and g-C3N4 when taken separately. The anticorrosive coating prepared using this composite can be applied on different surfaces under various environmental conditions to reduce corrosion. 2025 Elsevier B.V. -
Child mental health: The role of different attributional styles
Background: High prevalence of mental health issues in the twenty-first century accounts for a lion share in the worldwide burden of disease. There is an alarming decrease in the onset of half of the mental health problems. Hence, it is necessary to explore the current situation and figure out the causes and preventive measures as well as the appropriate mental health enhancement measures. Individual characteristics, such as thinking patterns and perception, have an impact on the mental health. Attributional style is one source of cognitive vulnerability which influences mental health disorders. Therefore, the present study examines whether there are any variations in the mental health of children with different attributional styles. Methods: The current research adopted a cross-sectional research design and selected 150 school going students [74 males and 76 females] between 10-13 years of age as participants. The Child Attributional Style Questionnaire [CASQ], Satisfaction with Life Scale-Children [SWLS-C], Brief Resilience Scale, and Revised Child Anxiety and Depression Scale [RCADS] are used to gather information. Results: The results indicated that children with a pessimistic attributional style experienced more depression and generalized anxiety than children with other two attributional styles. In terms of gender differences in mental health, female students with pessimistic attributional style significantly differed from their counterparts on depression [?2 [2] = 10.131, p = 0.006] and separation anxiety [?2 [2] = 6.456, p = 0.040]. Conclusion: Attributional style seems to have a significant role in depression and anxiety in female children. Although male children did not show any statistically significant results, they were more likely to be pessimistic in terms of their attributional style, which makes them vulnerable to mental health issues. 2020, Indian Association for Child and Adolescent Mental Health. All rights reserved. -
Harnessing Machine Learning toOptimize Social Media Marketing
Machine learning (ML) has transformed the way digital advertising is done and analyzed by social media data. This paper explores ML in targeted advertising, including techniques such as supervised learning, neural networks, and NLP. While ML improves campaign precision and consumer engagement, it also presents challenges such as algorithmic bias, data privacy concerns, and computational scalability. This study is a synthesis of existing research and explores real-world applications, providing a critical analysis of MLs capacity to optimize social media advertising. It argues that while ML may provide exceptional possibilities for customization and engagement, its success can only be ensured through appropriate ethical practices, transparency, and innovation in technology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.