Browse Items (16481 total)
Sort by:
-
A Frame Work For Continous Indian Sign Language Recognition Using Computer Vision
Sign language is a non-vocal, visually oriented natural language used by the hearing newlineimpaired and the hard-for-hearing part of society. It combines multiple modalities newlinelike hand movements, facial expressions and body poses. Static gestures involve basic finger movements such as numbers and alphabets, dynamic signs include words, and a sign sentence consists of grammatically connected and meaningful dynamic words. Sign Language Translation (SLT) models have been an actively evolving research topic under computer vision. One of the most challenging aspects in earlier iterations of SLTs was accurately capturing the intricate and constantly changing hand movements and facial expressions characteristic of sign language. newlineHowever, the advent of deep learning models has facilitated significant advancements in the field, particularly in the realm of continuous sign language translation. newlineThe research endeavours to develop a lightweight deep-learning framework newlinespecifically tailored for the translation of Indian Sign Language (ISL) into text and newlineaudio. The proposed framework introduces two collaborative deep-learning components that extract and classify features synergistically. The ISL video sequence serves as the input, which undergoes feature extraction utilizing the Inception V3 architecture, enabling the extraction of features from each frame. Classification models tend to be bulky and intricate, consuming substantial memory space and requiring extended training periods. This challenge has been addressed by introducing a lightweight LSTM model, which effectively utilizes the feature map generated by the Inception model for accurate classification. It is important to note that each sign possesses unique characteristics yet exhibits similar feature maps. The performance of the framework is assessed based on the speed and accuracy achieved in converting the input video into text and audio formats. -
Catalytic performance and SERS substrate efficiency of PdNPs@GOQDs
Graphene Oxide Quantum Dots (GOQDs) have received significant attention for diverse applications owing to their unique physical and chemical properties. Herein, yellow luminescent graphene oxide quantum dots are achieved via hydrothermal pathway and are characterized using different analytical methods. GOQDs, noted for their reducing character, are utilized for the synthesis of palladium nanoparticles (PdNPs). PdNPs@GOQDs obtained are explored for their catalytic efficiency and SERS substrate performance. The combined effect of electromagnetic enhancement and chemical enhancement factors make the composite a good SERS substrate, as exemplied using Rhodamine B molecule. PdNPs@GOQDs exhibited catalytic activity that effectively promoted the reduction of several functionalized aromatic nitroarenes. Notably, sensitive groups like nitrile and ester were well-tolerant under the reaction conditions, warranting the potential of the system in synthesising amines of industrial and environmental significance with high selectivity. This journal is The Royal Society of Chemistry, 2026 -
A Mixed methods study of psyhosocial factors in career decision making in adolescents
Career choice is an important developmental task in adolescence and is influenced by many factors. Using a mixed methods research design, this study aimed to understand career decision making and factors influencing the same in adolescents. In the quantitative phase the relationship between career maturity and perceived parenting style, personality traits, metacognition, socio- economic status, gender, college type, stream of study and decision status was studied in students studying in II Year Pre- University in Bangalore, India. Career decisions, personal and family factors in career decision making were explored in the qualitative phase. Informed consent was obtained from the participants and parents of the participants of the study. newlineQuantitative data was collected from 548 students studying in Arts, Science and Commerce stream in second year Pre- University in Bangalore. Students from eight private and seven government colleges were recruited for the study. Quantitative data was collected using a socio- demographic data sheet, Career Maturity Inventory, Parental Authority Questionnaire, Neo Five Factor Inventory and Metacognitive Awareness Inventory. The scales were translated to Kannada and back translated. In the qualitative phase, data was collected through a semi- structured interview schedule designed for this study. 30 students who were a part of the quantitative phase took part in this phase. The interviews were audio-recorded and transcribed for analysis. Statistical analysis was done to analyze quantitative data. Descriptive statistics, correlation, regression analysis, t tests and one-way ANOVA was done. Qualitative data was analyzed by template analysis and themes were derived from the data. The results revealed associations between personality traits neuroticism, openness and conscientiousness and specific aspects of career maturity attitude and competence. -
Enhancing red wine quality prediction through Machine Learning approaches with Hyperparameters optimization technique
In light of the intricacy of the winemaking process and the wide variety of elements that could affect the taste and quality of the finished product, predicting red wine quality is difficult. ML methods have been widely used in forecasting red wine quality from its chemical characteristics in recent years. This Paper evaluated the comparison of classification and regression methods to predict the quality of red wine and performed the initial data analysis and exploratory data analysis on the data. This study implemented different Classifiers and Regressors that were trained and tested. Contrasted and Comparative analysis of the accuracies of eight models with hyperparameter tuning optimization, including Logistic Regression, Gradient Boosting, Extra Tree, Ada Boost, Random Forest, Support Vector Classifier, and Decision Tree, Knn and measured the classification report with F1, Accuracy, and Recall Scores. For Imbalance data, SMOTE Classifier was used. This study performed the Cross-validation technique, such as Grid search and with the best hyperparameters tuning. The study's findings demonstrated that the Gradient Boosting technique accurately predicted red wine quality. This research shows the promising results of Gradient Boosting for predicting red wine quality and adds important context to the usage of machine learning classifiers for this challenge. 2023 IEEE. -
Unraveling Campus Placement Success Integrating Exploratory Insights with Predictive Machine Learning Models
The dynamics of campus placements have garnered considerable attention in recent years, with educational institutions, students, and employers all keenly invested in understanding the factors that drive successful recruitment. This surge in interest stems from the potential implications for academic curricula, student preparation, and hiring strategies. In this study, we aimed to unravel the myriad factors that influence a student's placement success, drawing from a comprehensive dataset detailing a range of academic and demographic attributes. Our methodology combined thorough exploratory data analysis with advanced predictive modeling. The exploratory phase unveiled notable patterns, particularly highlighting the roles of gender, academic performance analysis, Degree and MBA specialization in placement outcomes. In the predictive modeling phase, the spotlight was on state-of-the-art machine learning models, with a particular emphasis on their capacity to forecast placement success. Notably, algorithms like Logistic Regression and Support Vector Machines not only confirmed the insights from our exploratory analysis but also showcased remarkable predictive prowess, with accuracy scores nearing perfection. These findings not only demonstrate the capabilities of machine learning in the academic and recruitment spheres but also emphasize the enduring importance of core academic achievements in influencing placement outcomes. As a prospective direction, future research might benefit from examining how placement trends evolve over time and integrating qualitative insights to provide a holistic view of the campus recruitment process. 2023 IEEE. -
Exploring Machine Learning Models to Predict the Diamond Price: A Data Mining Utility Using Weka
In contrast to gold and platinum, whose values may be fairly determined, determining a diamond's worth involves a far more complex set of considerations. The appropriate rate is based on many factors, not just one of the stones. Diamonds are graded based on their appearance, carat weight, cut quality, and how well they have presented dimensions like a table's surface, depth, and breadth. In order to accurately forecast diamond prices, this study seeks to develop the most effective approaches possible. Different machine learning classifiers are trained on the diamond dataset to forecast diamond prices based on the features. This article shows how to analyze diamond prices using WEKA's data mining software. Diamond data have been utilized for this study. These methods include M5P, Random Forest, Multilayer perceptron, Decision Stump, REP Trees, and M5Rules. For the purpose of estimating the cost of a diamond, different Machine Learning classifiers are compared and contrasted. Performance measures and analysis showed that Random Forest was the best-performing classifier. Experimental findings show, as shown by the coefficient of correlation that Random Forest is better than other classification methods. 2023 IEEE. -
Insider attack detection using deep belief neural network in cloud computing
Cloud computing is a high network infrastructure where users, owners, third users, authorized users, and customers can access and store their information quickly. The use of cloud computing has realized the rapid increase of information in every field and the need for a centralized location for processing efficiently. This cloud is nowadays highly affected by internal threats of the user. Sensitive applications such as banking, hospital, and business are more likely affected by real user threats. An intruder is presented as a user and set as a member of the network. After becoming an insider in the network, they will try to attack or steal sensitive data during information sharing or conversation. The major issue in today's technological development is identifying the insider threat in the cloud network. When data are lost, compromising cloud users is difficult. Privacy and security are not ensured, and then, the usage of the cloud is not trusted. Several solutions are available for the external security of the cloud network. However, insider or internal threats need to be addressed. In this research work, we focus on a solution for identifying an insider attack using the artificial intelligence technique. An insider attack is possible by using nodes of weak users systems. They will log in using a weak user id, connect to a network, and pretend to be a trusted node. Then, they can easily attack and hack information as an insider, and identifying them is very difficult. These types of attacks need intelligent solutions. A machine learning approach is widely used for security issues. To date, the existing lags can classify the attackers accurately. This information hijacking process is very absurd, which motivates young researchers to provide a solution for internal threats. In our proposed work, we track the attackers using a user interaction behavior pattern and deep learning technique. The usage of mouse movements and clicks and keystrokes of the real user is stored in a database. The deep belief neural network is designed using a restricted Boltzmann machine (RBM) so that the layer of RBM communicates with the previous and subsequent layers. The result is evaluated using a Cooja simulator based on the cloud environment. The accuracy and F-measure are highly improved compared with when using the existing long short-term memory and support vector machine. 2022 CRL Publishing. All rights reserved. -
Mosquito larvicidal property of Citrus species
Mosquitoes and their larvae have several detrimental effects on humans, animals and the environment.. Their bites cause itching, allergic reactions and skin irritation. Mosquito larvae thrive in stagnant water, polluting water sources and creating breeding grounds for further infestations. Large mosquito populations negatively impact agriculture and livestock by transmitting diseases to animals. Additionally, their presence reduces outdoor activities, affecting tourism and economic productivity in affected regions. The review focuses on the Culicidae mosquito genera Anopheles, Aedes and Culex, including many species in each. The papers show that Clevenger and Soxhlet apparatus methods maintain high-quality and quantity oils because of their unique properties. These methods are cost-effective and environmentally friendly since chloroform, carbon tetrafluoride and other similar pollutants are not used, which causes severe health issues.Future research will examine how oil release from plant parts varies with age and how this relates to mosquito mortality. Different plant parts may yield varying quantities of oil at different stages, which can be considered as a point of discussion. The present findings supportthe efficiency of certain Citrus species in the Rutaceae family to eradicate mosquitoes and its larvae. The Author(s). -
Evidence of microRNAs origination from chloroplast genome and their role in regulating Photosystem II protein N (psbN) mRNA
The microRNAs are endogenous, regulating gene expression either at the DNA or RNA level. Despite the availability of extensive studies on microRNA generation in plants, reports on their abundance, biogenesis, and consequent gene regulation in plant organelles remain naVve. Building on previous studies involving pre-miRNA sequencing in Abelmoschus esculentus, we demonstrated that three putative microRNAs were raised from the chloroplast genome. In the current study, we have characterized the genesis of these three microRNAs through a combination of bioinformatics and experimental approaches. The gene sequence for a miRNA, designated as AecpmiRNA1 (A. esculentus chloroplast miRNA), is potentially located in both the genomic DNA, i.e., nuclear and chloroplast genome. In contrast, the gene sequences for the other two miRNAs (AecpmiRNA2 and AecpmiRNA3) are exclusively present in the chloroplast genome. Target prediction revealed many potential mRNAs as targets for AecpmiRNAs. Further analysis using 5N RACE-PCR determined the AecpmiRNA3 binding and cleavage site at the photosystem II protein N (psbN). These results indicate that AecpmiRNAs are generated from the chloroplast genome, possessing the potential to regulate mRNAs arising from chloroplast gene(s). On the other side, the possibility of nuclear genome-derived mRNA regulation by AecpmiRNAs cannot be ruled out. 2024, Termedia Publishing House Ltd.. All rights reserved. -
Medicinal plants, phytochemicals, and herbs to combat viral pathogens including sars-cov-2
The coronavirus disease 2019 (COVID-19) pandemic, caused by severe acute respiratory syndrome corona virus-2 (SARS-CoV-2), is the most important health issue, internationally. With no specific and effective antiviral therapy for COVID-19, new or repurposed antiviral are urgently needed. Phytochemicals pose a ray of hope for human health during this pandemic, and a great deal of research is concentrated on it. Phytochemicals have been used as antiviral agents against several viruses since they could inhibit several viruses via different mechanisms of direct inhibition either at the viral entry point or the replication stages and via immunomodulation potentials. Recent evidence also suggests that some plants and its components have shown promising antiviral properties against SARS-CoV-2. This review summarizes certain phytochemical agents along with their mode of actions and potential antiviral activities against important viral pathogens. A special focus has been given on medicinal plants and their extracts as well as herbs which have shown promising results to combat SARS-CoV-2 infection and can be useful in treating patients with COVID-19 as alternatives for treatment under phytotherapy approaches during this devastating pandemic situation. 2021 by the authors. Licensee MDPI, Basel, Switzerland. -
Evolutionary algorithm based feature extraction for enhanced recommendations
A major challenge to Collaborative Filtering systems is high dimensional and sparse data which they have to deal with. Feature selection techniques partly address this problem by reducing the feature space and retaining only a representative subset of features. However these techniques do not address the sparsity problem which affects both quality and quantity of recommendations. A more promising direction would be to construct/extract new features which are low dimensional, dense and have more discriminative power. Content based construction of features has been explored in the past. This work proposes a evolutionary algorithm based feature extraction techniques which discover hidden features with high discriminative capacity. Such an approach offers the advantage of discovering features even in the absence of additional information such as item contents etc. The proposed approach is contrasted with content based feature extraction techniques through experiments and the ability of the new approach in discovering interesting and useful features is established. -
Exploring graph-based global similarity estimates for quality recommendations
Data sparsity or the insufficiency of past user preferences in predicting future user needs continues to be a major challenge for RS engines. We propose a solution to the sparsity problem by exploring similarity measures that capture the global patterns of commonality between users or items by leveraging on indirect ways of connecting users (items) through a user (item) graph. Entities (users or items) sharing common features are connected to each other by edges weighted by their proximity or distance. Graph-based techniques, for estimating transitive similarity between entities not directly connected, are exploited to bring the entities closer thus facilitating collaboration. Furthermore, we also propose a combined user-item graph approach for exploiting the similarity between users preferring similar items (and vice versa). In this work, we have suggested alternatives to the already existing global similarity assessment and we aim to investigate the appropriateness of the proposed techniques under differing data features. 2014 Inderscience Enterprises Ltd. -
Folksonomy-based fuzzy user profiling for improved recommendations
Genre is a major factor influencing user decisions to peruse an item in domains such as movies, books etc. Recommender systems, generally have, at their disposal, information regarding genres/categories that a movie/book belongs to. However, the degree of membership of the objects in these categories is typically unavailable. Such information, if available, would provide a better description of items and consequently lead to quality recommendations. In this paper, we propose an approach to infer the degree of genre presence in a movie by examining the various tags conferred on them by various users. Tags are user-defined metadata for items and embed abundant information about various facets of user likes, their opinion on the quality and the type of object tagged. Leveraging on tags to guide the genre degree determination exploits crowd sourcing to enrich item content description. Fuzzy logic naturally models human logic allowing for the nuanced representation of features of objects and thus is utilized to derive such gradual representation as well as for modeling user profiles. To the best of our knowledge ours is one of the first approaches to utilize such folksonomy information to infer genre degrees subsequently used for recommendations. The proposed method has the twin advantages of utilizing enriched content information for recommendation as well as squeezing the information from the user-item-tag and user-item ratings spaces and condensing them into fuzzy user profiles. The fuzzy user and object representations are leveraged both for the design of content-based as well as collaborative recommender systems. Experimental evaluations establish the effectiveness of the proposed approaches as compared to other baselines. 2013 Elsevier Ltd. All rights reserved. -
User profiling based on keyword clusters for improved recommendations
Recommender Systems (RS) have risen in popularity over the years, and their ability to ease decision-making for the user in various domains has made them ubiquitous. However, the sparsity of data continues to be one of the biggest shortcomings of the suggestions offered. Recommendation algorithms typically model user preferences in the form of a profile, which is then used to match user preferences to items of their interest. Consequently, the quality of recommendations is directly related to the level of detail contained in these profiles. Several attempts at enriching the user profiles leveraging both user preference data and item content details have been explored in the past. We propose a method of constructing a user profile, specifically for the movie domain, based on user preference for keyword clusters, which indirectly captures preferences for various narrative styles. These profiles are then utilized to perform both content-based (CB) filtering as well as collaborative filtering (CF). The proposed approach scores over the direct keyword-matching, genre-based user profiling and the traditional CF methods under sparse data scenarios as established by various experiments. It has the advantage of a compact user model representation, while at the same time capturing the essence of the styles or genres preferred by the user. The identification of implicit genres is captured effectively through clustering without requiring labeled data for training. 2014 Springer International Publishing Switzerland. -
Impact of Blockchain Technology in the Healthcare Systems
The healthcare industry is one of the most important industries in the world which is in dire need of a restructuring process because of its poor and outdated techniques of data management. Healthcare system has adopted a centralized environment and deals with a lot of intermediaries which makes it prone to issues of single point of failure, lack of traceability of transactions, and privacy issues such as data leakage. Blockchain is a relatively new technology which is able to tackle the obsolete methods and practices existing in the healthcare industry. In this chapter, we analyzed the applications of blockchains in the healthcare industry which can solve the issues prevalent in the healthcare industry. The aim of this chapter is to reveal the potential benefits that comes from using blockchain technology in the healthcare industry and identify the various challenges that this technology has. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Bibliometric analysis of the impact of blockchain technology on the tourism industry
The tourism sector is one of the world's fastest-expanding industries. Because of the benefits, it provides to individuals and organizations, the tourism sector has attracted a lot of attention throughout the years. But because of its poor and obsolete data management techniques, this industry is in desperate need of reform. Blockchain technology is one method for managing and exploring data relevant to the tourism industry. This study used bibliometric methods to analyze the impact of blockchain technology on the tourism sector from 2017 to 2022. The publications were extracted from the dimensions database, and the VOS viewer software was used to visualize research patterns. The findings provided valuable information on the publication year, authors, author's country, author's organizational affiliations, publishing journals, etc. Based on the findings of this analysis, researchers may be able to design their studies better and add more insights into their empirical studies. 2024 Srinesh Thakur, Anvita Electronics, 16-11-762, Vijetha Golden Empire, Hyderabad. -
Recurrent Neural Networks in Predicting the Popularity of Online Social Networks Content: A Review
An online social network is a web platform that individuals use to make social relationships with people who share similar interests, activities, connections, and backgrounds. All online social networks differ in the number of features they provide and their format. In recent years, drastic growth has been seen in the users of online social networks like Flickr, Instagram, Pinterest, Twitter, etc. Among all the features of online social networks, content sharing is the one being widely used by individual users and large organizations. Due to this, content popularity prediction has been extensively studied nowadays, considering various aspects related to it. The study throws light on the use of machine learning techniques in this field. Various algorithms have been used to handle popularity prediction, including classification, regression, and clustering techniques. It is feasible to extract the essential information from such content using machine learning algorithms and utilize the retrieved information in a variety of ways, the majority of which are commercial in nature. The goal of this study is to review and analyze various recurrent neural network (RNN) approaches for predicting the popularity of social media content. The Electrochemical Society -
Popularity Prediction of Online Social Media Content: A Bibliometric Analysis
An online social network is a platform that enables individuals to interact with others who have similar backgrounds, preferences, activities, and associations. The number of features available and the format of each online social network range widely. Users of online social networks, such as Twitter, Instagram, Flicker, and Pinterest, have increased dramatically in recent years. Content sharing is the most popular feature of online social networks, used by both specific users and big enterprises. This study has used bibliometric methods to analyze the growth of the social media popularity prediction on online social network content from 2013 to 2022. The publications have been extracted from the dimensions database, and the VOS viewer software was used to visualize research patterns. The finding provides valuable information on the publication year, authors, authors country, authors organizational affiliations, publishing journals, etc. Based on the findings of this analysis, researchers will be able to design their studies better and add more insights into their empirical studies. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A study on the relationship between internal branding and affective commitment of customer contact employees in multi-brand retail stores in Bangalore /
International Journal of Business and Administration Research, Vol.1, Issue 7, pp.189-197, ISSN No: 2348-0653. -
Studies on K X Ray fluorescence parameters of low and medium Z elements
K X-ray fluorescence parameters for pure elements have been determined using different single and double reflection geometry by several researchers over the years. Horakeri et al.have shown that the K X-ray fluorescence parameters can also be determined by a simple 2and#960;-geometrical configuration method and a NaI(Tl) detector spectrometer for high Z elements. newlineHowever, in order to study the K XRF parameters for low Z elements, high resolution detector spectrometers are required.But in high resolution detectors like HPGe and Si(Li), due to the gap between window and the active area of the detector, the solid angle subtended by the detector at the target is not 2and#960;. Hence a suitable geometry correction is required for accurate newlinemeasurement of incident photons and the emitted K X-ray photons in order to determine the K XRF parameters in low Z elements. In the present study, employing a nearly 2and#960;-geometrical configuration and applying suitable geometry correction, we have determined the K X-ray fluorescence parameters of a few low and medium Z elements in the range of 27 and#8804; Z and#8804; 30 and 42 and#8804; Z and#8804; 47 respectively. The elements were procured in the form of thin foils and were irradiated by a weak radioactive source. The emitted K X-ray photons were detected using a low energy high resolution HPGe detector spectrometer. The incident photons, emitted K X-ray photons and the transmitted photons at newlinethe incident energy is measured and were corrected for window attenuation, efficiency, self-attenuation and geometry correction newlineto obtain the true intensities of incident photons, emitted K Xray photons and the transmitted photons at the incident energy.