Browse Items (16481 total)
Sort by:
-
Multimodal Learning Using Heterogeneous Data
Multimodal Learning Using Heterogeneous Data is a comprehensive guide to the emerging field of multimodal learning, which focuses on integrating diverse data types such as text, images, and audio within a unified framework. The book delves into the challenges and opportunities presented by multimodal data and offers insights into the foundations, techniques, and applications of this interdisciplinary approach. It is intended for researchers and practitioners interested in learning more about multimodal learning and is a valuable resource for those working on projects involving data analysis from multiple modalities. The book begins with a comprehensive introduction, focusing on multimodal learning's foundational principles and the intricacies of heterogeneous data. It then delves into feature extraction, fusion techniques, and deep learning architectures tailored for multimodal data. It also covers transfer learning, pre-processing challenges, and cross-modal information retrieval. The book highlights the application of multimodal learning in specialized contexts such as sentiment analysis, data generation, medical imaging, and ethical considerations. Real-world case studies are woven into the narrative, illuminating the applications of multimodal learning in diverse domains such as natural language processing, multimedia content analysis, autonomous systems, and cognitive computing. The book concludes with an insightful exploration of multimodal data analytics across social media, surveillance, user behavior, and a forward-looking examination of future trends and practical implementations. As a collective resource, Multimodal Learning Using Heterogeneous Data illuminates the powerful utility of multimodal learning to elevate machine learning tasks while also highlighting the need for innovative solutions and methodologies. The book acknowledges the challenges associated with deep learning and the growing importance of ethical considerations in the collection and analysis of multimodal data. Overall, Multimodal Learning Using Heterogeneous Data provides an expansive panorama of this rapidly evolving field, its potential for future research and application, and its vital role in shaping machine learning's evolution. 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies. -
Multimodal data analytics for climate and water resources management
The incorporation of multimodal data analytics into climate and water resource management has become a groundbreaking strategy for tackling intricate environmental issues. This chapter examines the importance of integrating various data sourcesincluding satellite imagery, weather sensors, textual reports, and social media feedsto develop a comprehensive perspective on climate and water systems. It addresses key challenges such as data heterogeneity, computational demands, and potential biases while showcasing the significant benefits of multimodal data in enhancing predictive modeling and decision-making. The discussion extends to advanced methodologies for data acquisition, integration, and feature extraction, with a focus on machine learning and deep learning techniques. Additionally, real-world applications in climate prediction, drought and flood forecasting, and water quality assessment are explored. The chapter also considers ethical concerns and future advancements in multimodal analytics, emphasizing the importance of responsible data utilization and innovative research to strengthen climate adaptation and water resource management efforts. 2026 Elsevier Inc. All rights reserved. -
P type copper doped tin oxide thin films and p-n homojunction diodes based on them
P-type copper doped tin oxide (SnO2:Cu) thin films were prepared by chemical spray pyrolysis method on glass substrates for different doping concentrations. Their structural, optical, surface morphological, elemental and electrical studies were investigated. We fabricated two transparent homojunction diodes using optimized sample of SnO2:Cu which are p- SnO2:Cu/n-SnO2 and p-SnO2:Cu/n- SnO2:F.These diodes are reported for the first time by this method. 2021 Elsevier B.V. -
Tailoring the properties of tin dioxide thin films by spray pyrolysis technique
Nanostructured transparent conducting SnO2 thin films have been grown on glass substrates via an environmentally benign chemical route viz spray pyrolysis. All samples were grown for various concentrations of precursor solution with the substrate kept at 350 C maintaining a spray rate of 10 mL/min. The characterizations revealed orthorhombic crystal structure with preferential growth in (112) plane for all samples. Ellipsometric analysis confirmed the good quality of the films. The sample prepared at 0.2 M concentration of precursor solution showed average transmission of 60% in the visible region with maximum conductivity of 24.86 S/cm. As synthesized samples exhibited overall Photoluminescence (PL) emission colours of green, greenish white and bluish white depending on the intensities of excitonic and oxygen vacancy defect level emissions. 2021 Elsevier B.V. -
Movie Success Prediction from Movie Trailer Engagement and Sentiment Analysis
The diverse movie industry faces many challenges in the promotion of the product across different demographics. Movie trailer engagements provide valuable information about how the audience perceives the movie. This information can be used to predict the success of the upcoming movie before it gets released. The previous research works were mainly concentrating on Hindi language movies to predict success. The current research paper includes the success prediction of movies other than Hindi. This paper aims to analyze various Machine Learning models performance and select the best performing model to predict movie success. The developed model can efficiently classify successful and unsuccessful movies. For the current research, the data is collected from various sources through web scrapping and API calls in Sacnilk, The Movie Database (TMDB), YouTube, and Twitter. Different machine learning classification models such as Random Forest, Logistic Regression, KNN, and Gaussian Nae Bayes are tested to develop the best-performing prediction model. This research can help moviemakers to understand the popularity of the movie among the viewers and decide on an efficient promotional strategy to make the movie more successful. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
FACVO-DNFN: Deep learning-based feature fusion and Distributed Denial of Service attack detection in cloud computing
Cloud computing offers a broad range of resource pools for conserving a huge quantity of information. Due to the intrusion of attackers, the information that exists in the cloud is threatened. Distributed Denial of Service (DDoS) attack is the main reason for attacks in the cloud. In this study, a Fractional Anti Corona Virus Optimization-based Deep Neuro-Fuzzy Network (FACVO-based DNFN) is devised for detecting DDoS in the cloud. The production of log files, feature fusion, data augmentation, and DDoS attack detection is the processing stages involved in this phase of the DDoS attack detection process. The feature fusion is carried out by RV coefficient and Deep Quantum Neural Network (Deep QNN), and the data augmentation is performed. Then, the Anti Corona Virus Optimization (ACVO) method and Fractional Calculus (FC) are both incorporated to create the FACVO algorithm. The DNFN is trained by the created FACVO algorithm, which identifies the DDoS attack. The proposed approach achieved testing accuracy, TPR, TNR, and precision values of 0.9304, 0.9088, 0.9293, and 0.8745 for using the NSL-KDD dataset without attack, and 0.9200, 0.8991, 0.9015, and 0.8648 for using the BoT-IoT dataset without attack. 2022 Elsevier B.V. -
Ar-HGSO: Autoregressive-Henry Gas Sailfish Optimization enabled deep learning model for diabetic retinopathy detection and severity level classification
Diabetic Retinopathy (DR) is one the most important problems of diabetics and it directs to the main cause of blindness. When proper treatment is afforded for DR patients, almost 90% of patients are protected from visual damage. DR does not produce any symptoms at the initial phase of the disease, thus various physical assessments, namely pupil dilation, visual acuity test, and so on are needed for DR disease detection. It is more complex to detect the DR during manual testing, because of the variations and complications of DR. The early detection and appropriate treatment assist to prevent vision loss for DR patients. Thus, it is very indispensable to categorize the levels and severity of DR for recommendation of essential treatment. In this paper, Autoregressive-Henry Gas Sailfish Optimization (Ar-HGSO)-based deep learning technique is proposed for DR detection and severity level classification of DR and Macular Edema (ME) based on color fundus images. The segmentation process is more essential for proper detection and classification process, which segments the image into various subgroups. The Deep Learning approach is utilized for effective identification of DR and severity classification of DR and ME. Moreover, the deep learning technique is trained by the designed Ar-HGSO scheme for obtaining better performance. The performance of the devised technique is evaluated using the IDRID dataset and DDR dataset. The introduced Ar-HGSO-based deep learning approach obtained better performance than other existing DR detection and classification techniques with regards to testing accuracy, sensitivity, and specificity of 0.9142, 0.9254, and 0.9142 using the IDRID dataset. 2022 Elsevier Ltd -
Analysis of Challenges Experienced by Students with Online Classes During the COVID-19 Pandemic
In the current context of the COVID-19 pandemic, due to restrictions in mobility and the closure of schools, people had to shift to work from home. India has the worlds second-largest pool of internet users, yet half its population lacks internet access or knowledge to use digital services. The shift to online mediums for education has exposed the stark digital divide in the education system. The digitization of education proved to be a significant challenge for students who lacked the devices, internet facility, and infrastructure to support the online mode of education or lacked the training to use these devices. These challenges raise concerns about the effectiveness of the future of education, as teachers and students find it challenging to communicate, connect, and assess meaningful learning. This study was conducted at one of the universities in India using a purposive sampling method to understand the challenges faced by the students during the online study and their satisfaction level. This paper aims to draw insight from the survey into the concerns raised by students from different backgrounds while learning from their homes and the decline in the effectiveness of education. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Some New Results on ?(k) -Coloring of Graphs
Let ? be the minimum number of distinct resources or equipment such as channels, transmitters, antennas and surveillance equipment required for a system's stability. These resources are placed on a system. The system is stable only if the resources of the same type are placed far away from each other or, in other words, they are not adjacent to each other. Let these distinct resources represent different colors assigned on the vertices of a graph G. Suppose the available resources, denoted by k, are less than ?. In that case, placing k resources on the vertices of G will make at least one equipment of the same type adjacent to each other, which thereby make the system unstable. In ?(k)-coloring, the adjacency between the resources of a single resource type is tolerated. The remaining resources are placed on the vertices so that no two resources of the same type are adjacent to each other. In this paper, we discuss some general results on the ?(k)-coloring and the number of bad edges obtained from the same for a graph G. Also, we determine the minimum number of bad edges obtained from ?(k)-coloring of few derived graph of graphs. The number of bad edges which result from a ?(k)-coloring of G is denoted by bk(G). 2023 World Scientific Publishing Company. -
On ?(k)-colouring of Some Wheel Related Graphs
The question on how to colour a graph G when the number of available colours to colour G is less than that of the chromatic number ?(G), such that the resulting colouring gives a minimum number of edges whose end vertices have the same colour, has been a study of great interest. Such an edge whose end vertices receives the same colour is called a bad edge. In this paper, we use the concept of ?(k)-colouring, where 1 ? k ? ?(G) ? 1, which is a near proper colouring that permits a single colour class to have adjacency between the vertices in it and restricts every other colour class to be an independent set, to find the minimum number of bad edges obtained from the same for some wheel related graphs. The minimum number of bad edges obtained from ?(k)-colouring of any graph G is denoted by bk(G). 2024 the Author(s), licensee Combinatorial Press. -
On (k) -coloring of generalized Petersen graphs
The chromatic number, ?(G) of a graph G is the minimum number of colors used in a proper coloring of G. In an improper coloring, an edge uv is bad if the colors assigned to the end vertices of the edge is the same. Now, if the available colors are less than that of the chromatic number of graph G, then coloring the graph with the available colors leads to bad edges in G. In this paper, we use the concept of (k)-coloring and determine the number of bad edges in generalized Petersen graph (P(n,t)). The number of bad edges which result from a (k)-coloring of G is denoted by bk(G). 2022 World Scientific Publishing Company. -
On ?(k)-coloring of powers of helm and closed helm graphs
If the availability of colors to color a graph G is less than that of the chromatic number ?(G) of the graph, then coloring the graph with available colors, say k colors, where 1 ? k ? ?(G)-1, will cause the end vertices of at least one edge to be colored with same color. Such an edge whose end vertices receive a same color is called as a bad edge. A coloring that restricts few color classes to have adjacency between the elements in it so as to minimize the number of bad edges obtained from it in a graph G is called as a near proper coloring and a near proper coloring that uses k colors where 1 ? k ? ?(G)-1 to color a graph G by permitting only one color class to have adjacency among the elements in it and thereby minimize the number of bad edges resulting from the permitted color class is called as a ?(k)-coloring of the graph G. In this paper, we determine the number of bad edges of powers of helm graphs H1,nr and powers of closed helm graphs CH1,nr. 2022 World Scientific Publishing Company. -
A note on ?(k)-colouring of the Cartesian product of some graphs
The chromatic number, x(G) of a graph G is the minimum number of colours used in a proper colouring of G. In an improper colouring, an edge uv is bad if the colours assigned to the end vertices of the edge is the same. Now, if the available colours are less than that of the chromatic number of graph G, then colouring the graph with the available colours lead to bad edges in G. The number of bad edges resulting from a ? (k)-colouring of G is denoted by bk(G). In this paper, we use the concept of (k)-colouring and determine the number of bad edges in Cartesian product of some graphs. 2022 by the authors. -
On ?(k)-coloring of graph products
An edge which is incident on two vertices that are assigned the same color is called a bad edge. A near proper coloring is a coloring that minimises the number of bad edges in a graph G, by permitting few color classes to have adjacency between the elements in it. A near proper coloring, that uses k colors where 1 ? k ? ?(G) ? 1, which allows at most one color class to be a non independent set to minimise the number of bad edges resulting from the same is called a ?(k)-coloring. In this paper, we determine the minimum number of bad edges, bk(G), resulting from a ?(k)- coloring of some graph products viz. direct product of two graphs G H and corona product of two graphs G?H, for all different possible values of k by investigating an optimal ?(k)-coloring that results in minimum number of bad edges. (2023), (Institute of Combinatorics and its Applications). All Rights Reserved. -
Harnessing Digital Marketing for Promoting Green Finance: A Strategic Approach to Building Climate Resilience
The study intents to utilize digital marketing strategies in order to foster green finance and influence climate-resilient?financial practices. Utilizing 250 survey respondents, the paper investigates how digital marketing intensity, content quality and platform interactiveness influence critical psychological dimensions (perceived green?value perception, trust in green finance and perceived transparency). SEM analysis shows that digital marketing exerts a significant positive effect on these?mediators, and the aforementioned mediators significantly affect individual green financial product investment intention. Furthermore, investment intention is found to be the most significant predictor of climate-resilient financial behavior, suggesting that behavioral pathways are instrumental to understanding the?digital engagementsustainable finance value chain. The findings provide an insight to the importance of transparent, trustworthy and engaging digital communication as a strategy for reducing information?asymmetry and building consumer trust towards green finance offering. Drawing on literature in sustainable finance, behavioral economics and digital communication, this contribution to a nascent literature on the use of digital tools to strengthen climate resilience?presents opportunities associated with each. The research also has practical implications for policy makers and financial institutions that wish to promote pro-environmental behaviour in the financing sphere with digital?means. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Mental health literacy and happiness among university students: a social work perspective to promoting well-being
The present study tried to assess university students mental health literacy (MHL) and happiness levels and whether a relationship existed between these. The study used a descriptive quantitative methodology, utilizing Likert-type scales to collect data. A private university in Istanbuls Faculty of Health Sciences had a sample of 443 students. Information was collected using a Personal Data Collection PR Form, the Oxford Happiness Questionnaire Short Form (OHQ-SF), and the Mental Health Literacy Scale (MHLS). Descriptive statistics and one-way analysis of variance (ANOVA) were used to analyze the data. The participants mean MHLS score was 23.00 4.70, and the OHQ-SF score was 23.50 4.70. We detected a significant difference in the MHL subscale owing to age, gender, department, class, maternal education, maternal employment status, income level, academic success, family attitude, smoking status, and exercise status. There were also differences in OHQ-SF scores by students department, class level, mothers education level, fathers income level, academic success status, resident status, family attitude type smoking status, health perception of chronic illness, family history of chronic illness, exercise habit, nutritional status psychological problems, and family mental illness history. Knowledge-oriented and belief-oriented MHL subscales were weak but significantly negatively related, according to the findings. A weak correlation but a significant one was found for subscale Resource-Oriented MHL with happiness level and MHL Total. According to the above-stated research, people who can access mental health resources are more likely to be happy. These findings highlight how making mental health resources available could improve peoples mental well-being with a prolonged social work perspective. As happiness is a primary goal of life, more research contributing to our understanding of it is essential. The mental health literacy indicators for university students relate to realizing happiness and fostering well-being. Copyright 2025 Elkin, Mohammed, K?l?nl, Soydan, Tanr?ver, lik and Ranganathan. -
Screens and scars: SEM analysis of the relationship between childhood trauma, emotion regulation, and social media addiction
Background: Addiction is an increasingly significant global public health concern, affecting individuals across diverse age groups and demographics. With the rapid rise of digital technology, social media addiction has emerged as a growing behavioral issue, impacting mental health, interpersonal relationships, and daily functioning. Methods: This study employed an online cross-sectional self-report questionnaire, with university students aged 1635?years as the target population. Data were collected using Google Forms questionnaires, accessible via the university registration system, and sent to the participating students smart phones. The data collection instruments included the Social Media Addiction Scale (SMAS), the Childhood Trauma Scale (CTS), and the Difficulty in Emotion Regulation Scale (DERS). Results: Data from 318 university students were analyzed. The analysis of sociodemographic data revealed a mean participant age of 21.2?years, with 87.3% being female. An analysis of the relationship between social media addiction and childhood trauma revealed that participants with childhood trauma had higher social media addiction. The linear regression model, including childhood traumas and emotion regulation difficulties for social media addiction scores, was statistically significant. A positive correlation was observed between social media addiction and difficulty in emotion regulation. Conclusion: These findings suggest that individuals who struggle with emotion regulation tend to use social media more frequently. Furthermore, the negative effects of childhood trauma on emotion regulation capabilities during adulthood contribute to the development of social media addiction. Copyright 2025 Elkin, Mohammed Ashraf, K?l?nl, K?l?nL, Ranganathan, Sakarya and Soydan. -
Screens and scars: SEM analysis of the relationship between childhood trauma, emotion regulation, and social media addiction
Background: Addiction is an increasingly significant global public health concern, affecting individuals across diverse age groups and demographics. With the rapid rise of digital technology, social media addiction has emerged as a growing behavioral issue, impacting mental health, interpersonal relationships, and daily functioning. Methods: This study employed an online cross-sectional self-report questionnaire, with university students aged 1635?years as the target population. Data were collected using Google Forms questionnaires, accessible via the university registration system, and sent to the participating students smart phones. The data collection instruments included the Social Media Addiction Scale (SMAS), the Childhood Trauma Scale (CTS), and the Difficulty in Emotion Regulation Scale (DERS). Results: Data from 318 university students were analyzed. The analysis of sociodemographic data revealed a mean participant age of 21.2?years, with 87.3% being female. An analysis of the relationship between social media addiction and childhood trauma revealed that participants with childhood trauma had higher social media addiction. The linear regression model, including childhood traumas and emotion regulation difficulties for social media addiction scores, was statistically significant. A positive correlation was observed between social media addiction and difficulty in emotion regulation. Conclusion: These findings suggest that individuals who struggle with emotion regulation tend to use social media more frequently. Furthermore, the negative effects of childhood trauma on emotion regulation capabilities during adulthood contribute to the development of social media addiction. Copyright 2025 Elkin, Mohammed Ashraf, K?l?nl, K?l?nL, Ranganathan, Sakarya and Soydan. -
Integrating Traditional Healing Practices with Cognitive Therapy: Attitude, Preparedness and Perceived Effectiveness among Clients and Therapists
Mental health and well- being has become a serious concern in the Indian health setting. The mental health care has been rapidly increasing. The various approaches involved in mental health has been explored widely in the Indian mental health setting. This research study aims to explore the integrated approach which involves traditional healing practices and cognitive therapy. The aim of this research study is to understand the three main variables attitude, preparedness and perceived effectiveness in clients and therapists while integrating traditional healing practices with cognitive therapy. The traditional healing practices explored in this study are yoga, meditation and mindfulness. The attitude of the clients and therapists towards the integrated approach has been studied. The preparedness of the clients as well as the preparedness of the therapists toward the integrated approach is also the next set of objectives in the research study. The next two objectives have been to study the perceived effectiveness of this approach in clients and therapists. The research study is a qualitative study. The data for the research study has been collected using semi- structured interviews. The data has been analyzed using thematic content analysis. The sample for the study includes 5 therapists and 10 clients who have been involved in this therapeutic approach. The results of the study show that there are two types of attitude clients who have interviewed hold towards the integrated approach. The two types of attitude include positive attitude and apprehensive attitude. The attitude of the therapists towards the approach has been positive and the factors which have led to the positive attitude has been cultural factors, familial background and previous exposure. The apprehensive attitude in clients have been due to the forced participation and past negative experience. The positive attitude of the therapists has been due to prior training and prior positive results. The preparedness and perceived effectiveness observed in therapists and clients have also been studied at length in the research study. The preparedness observed in clients has been due to previous exposure and knowledge and in therapists it has been due to extensive practice and the perceived effectiveness seen in clients. The perceived effectiveness observed in clients have been at three levels. They are physiological well- being, psychological well- being and improved relationships in the family. The perceived effectiveness in therapists have been seen as increased emotional and physical well- being as well as increased competence in the profession.