Browse Items (9795 total)
Sort by:
-
Developing the assessment questions automatically to determine the cognitive level of the e-learner using NLP techniques
The key objective of the teaching-learning process (TLP) is to impart the knowledge to the learner. In the digital world, the computer-based system emphasis teaching through online mode known as e-learning. The expertise level of the learner in learned subjects can be measured through e-assessment in which multiple choice questions (MCQ) is considered to be an effective one. The assessment questions play the vital role which decides the ability level of a learner. In manual preparation, covering all the topics is difficult and time consumable. Hence, this article proposes a system which automatically generates two different types of question helps to identify the skill level of a learner. First, the MCQ questions with the distractor set are created using named entity recognizer (NER). Further, based on blooms taxonomy the Subjective questions are generated using natural language processing (NLP). The objective of the proposed system is to generate the questions dynamically which helps to reduce the occupation of memory concept. 2020, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. -
Group Movie Recommendations via Content Based Feature Preferences
International Journal of Scientific & Engineering Research Vol. 4, Issue 2, pp.1-5 ISSN No. 2229-5518 -
Improved Collaborative Filtering using Evolutionary Algorithm based Feature Extraction
International Journal of Computer Applications Vol.64,No.20, pp.20-26 ISSN No. 0975-8887 -
Feature Extraction for Collaborative Filtering: A Genetic Programming Approach
International Journal of Computer Science Issues, Vol. 9, Issue, 5, No. 1, pp. 348-354, ISSN No. 1694-0814 -
Comparative Analysis of Different Machine Learning Prediction Models for Seasonal Rainfall and Crop Production in Cultivation
Agriculture is one of the strengths of India, from the last few years, gradually the agriculture growth is going downwards in other side the population growth is upwards. Reason for agricultural downward growth depends on so many parameters. The rainfall is one of the main parameters which affects the crop yield. Because of this, the farmers are also facing the loss. If they know this information in prior, the farmers can plan accordingly the type of crop suited for the particular season and it helps the farmer to get good profit out of it. Machine learning scientific and statistical methods are used for predicting the rain fall and crop yield. Kharif and Rabi are two seasons taken for analysis. The regressor predicting models are constructed to predict the seasonal rainfall and crop yield. This study primarily focuses on seasonal crop production prediction, which is dependent on rainfall. The different types of machine learning regression method are used to achieve better results. The performance of comparison models is evaluated using different metrics. Finally, the linear regression and Bayesian linear regression models comparatively produce the best result in terms of accuracy for rainfall prediction. The boosted decision tree regression model is achieving the better result for crop prediction. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Specialized CNN Architectures for Enhanced Image Classification Performance
Image classification is one of the important tasks in computer vision, with a greater number of applications from facial recognition, medical imaging, object recognition and many more. Convolutional Neural Networks (CNNs) have developed as the foundation for image all classification tasks, showcasing the capacity to learn the hierarchical features automatically. In this study proposed three custom CNN models and its comprehensive analysis for the image classification tasks. The models are evaluated using CIFAR-10 dataset to assess the performance and efficiency. The experimental results shows that the proposed custom CNN Model-3 performance is better than the other two models. Our findings demonstrate that Model 3, featuring with the global average pooling, achieves the highest overall accuracy of 94 % with competitive computational efficiency. This suggests that global average pooling is the valuable technique for balanced and accurate image classification. 2024 IEEE. -
Deep Belief Network-Based User and Entity Behavior Analytics (UEBA) for Web Applications
Machine learning (ML) is currently a crucial tool in the field of cyber security. Through the identification of patterns, the mapping of cybercrime in real time, and the execution of in-depth penetration tests, ML is able to counter cyber threats and strengthen security infrastructure. Security in any organization depends on monitoring and analyzing user actions and behaviors. Due to the fact that it frequently avoids security precautions and does not trigger any alerts or flags, it is much more challenging to detect than traditional malicious network activity. ML is an important and rapidly developing anomaly detection field in order to protect user security and privacy, a wide range of applications, including various social media platforms, have incorporated cutting-edge techniques to detect anomalies. A social network is a platform where various social groups can interact, express themselves, and share pertinent content. By spreading propaganda, unwelcome messages, false information, fake news, and rumours, as well as by posting harmful links, this social network also encourages deviant behavior. In this research, we introduce Deep Belief Network (DBN) with Triple DES, a hybrid approach to anomaly detection in unbalanced classification. The results show that the DBN-TDES model can typically detect anomalous user behaviors that other models in anomaly detection cannot. 2024 World Scientific Publishing Company. -
Exploratory Architectures Analysis of Various Pre-trained Image Classification Models for Deep Learning
The image classification is one of the significant applications in the area of Deep Learning (DL) with respective to various sectors. Different types of neural network architectures are available to perform the image classification and each of which produces the different accuracy. The dataset and the features used are influence the outcome of the model. The research community is working towards the generalized model at least to the domain specific. On this gesture the contemporary survey of various Deep Learning models is identified using knowledge information management methods to move further to provide optimal architecture and also to generalized Deep Learning model to classify images narrow down to the sector specific. The study systematically presents the different types of architecture, its variants, layers and parameters used for each version of Deep Learning model. Domain specific applications and limitations of the type of architecture are detailed. It helps the researchers to select appropriate Deep Learning architecture for specific sector. 2024 by the authors. -
The influence of social environment on children of a commercial sex worker
The case study aims to understand the influence of social environment on the course of life of children of a commercial sex worker. The participants of the study were two sons of a commercial sex worker who grew up in different environments. The older sibling who is 19 years of age (case 1) lives with his mother, whereas the younger sibling who is 17 years of age (case 2) lives in a hostel distant from everyday influence of a brothel. The study adopts multiple case study design and in-depth interviews were conducted to gather data. The obtained data were subjected to thematic analysis. Each case was analyzed individually, and then cross comparison of the themes derived was carried out. The themes derived on analyzing case 1 were social categorization, mercenary activity, substance aficionado, complacency in life, and compliance with life while the themes derived on analyzing case 2 were disgust toward commercial sex work, feeling of precariousness, antipathy toward home environment, irrational thoughts and anticipation of a better future. The only overlapping issue that emerged in both cases was being protective about their mother. It was concluded that environmental variance contributes to the difference in experience and perception of the situation and society. Indian Journal of Social Psychiatry. All Rights Reserved. -
Performance Analysis of Deep Learning Pretrained Image Classifiation Models
Convolutional Neural Networks (CNNs) is revolutionized in the field of computer vision, with the high accuracy and capability to learn features from raw data. In this research work focused on a comparative analysis of two popular CNN architectures, VGG16 and VGG19. The CIFAR dataset consists of 60,000 images, each with a resolution of 32x32 and it's belong to one of the 10 classes. Experimental results are compared with VGG16 and VGG19 in terms of their accuracy and training time, and to identify any differences in their ability to learn features from the CIFAR-10 dataset. The results of this research can aid in directing the choice of appropriate architectures for image classification tasks as well as the advantages of optimisation strategies for enhancing the efficiency of deep learning models. In order to enhance the performance of these structures, more optimisation methods and datasets may be investigated in subsequent research. 2023 IEEE. -
Hereditary factor-based multi-featured algorithm for early diabetes detection using machine learning
Today's advent in the medical industry have given numerous chances to improve the quality of detection and reporting the diseases at the early stages for a better diagnosis. Modern day datasets generate fruitful information for timely and periodic monitoring of patients' health conditions. Such information is hidden to a naked eye or hidden in multiple track records of highly affected population. Diabetes mellitus is one such disease which is predominant among a global population which ultimately leads to blindness and death in some cases. The model proposed in this system attempts to design and deliver an intelligent solution for predicting diabetes in the early stages and address the problem of late detection and diagnosis. Intensive research is carried out in many tropical countries for automating this process through a machine learning model. The accuracy of machine learning algorithms is more than satisfactory in the detection of Type 2 diabetes from the dataset of PIMA Indians Diabetes Dataset. An additional feature of hereditary factor is implemented to the existing multiple objective fuzzy classifiers. The proposed model has improved the accuracy to 83% in the training and tested datasets when compared to NGSA model of prediction. 2022 Scrivener Publishing LLC. -
An intelligent inventive system for personalised webpage recommendation based on ontology semantics
Owing to the information diversity in the web and its dynamically changing contents, extraction of relevant information from the web is a huge challenge. With the World Wide Web transforming into a more organised semantic web, the incorporation of semantic techniques to retrieve relevant information is highly necessary. In this paper, a dynamic ontology alignment technique for recommending relevant webpages is proposed. The strategy focuses on knowledge tree construction by computing the semantic similarity between the query terms as well as the ontological entities. Furthermore, the semantic similarity is again computed between nodes of the constructed knowledge tree and URLs in the URL repository to recommend relevant webpages. The dynamic ontology alignment by computing their respective semantic similarity constitutes Ontology Semantics. Personalisation is achieved by prioritisation of webpages by content-based analysis of the users web usage data. An overall accuracy of 87.73% is achieved by the proposed approach. Copyright 2019 Inderscience Enterprises Ltd. -
Descriptive Answer Evaluation using NLP Processes Integrated with Strategically Constructed Semantic Skill Ontologies
The world is moving towards an online methodology of education. One of the key challenges is the assessment of questions which do not have a definite answer and have several correct answers. To solve this problem, and for quality evaluation of descriptive answers online, an automatic evaluation methodology is proposed in this work. A language model is modelled from the expected answer key, and entity graphs are generated from the ontology modelled using the input answer to be evaluated. Natural Language Processing (NLP) techniques like Stemming, Summarization, and Polarity Analysis are integrated in this work with Ontologies for the efficient evaluation of descriptive answers. Several challenges which come across evaluating descriptive answers are discussed in this chapter, and they have been solved in order to obtain a dynamic and robust evaluating system. Finally, the system is evaluated using a user-feedback methodology comprising a panel of 100 students and 100 professors. 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) -
ATRSI: Automatic Tag Recommendation for Videos Encompassing Semantic Intelligence
There is a requirement for an automatic semantic-oriented framework for Web video tagging in the epoch of Web 3.0, as Web 3.0 is much denser, intelligent, but more cohesive compared to Web 2.0. This paper proposes the ATRSI framework which is the Automatic Tag Recommender framework which encompasses the semantic-oriented Artificial Intelligence that outgrows the dataset by making the use of informative terms using TF-IDF and bag of words model to build the intermediate semantic network which is further organized using an Lin similarity measure and is optimized using red deer optimization by encompassing the entities from the World Wide Web to focused crawling. RNN is a classifier that is used for the classification of the dataset, it is a strong deep-learning classifier. Semantic-oriented Intelligence is achieved using the CoSim rank and Morisita's overlap index. The bag of lightweight graphs is obtained from the semantic network which is an intermediate knowledge representation mechanism that is further embedded in the intrinsic model. A semantically consistent system for video recommendation, ATRSI outperforms the other baseline models in terms of average accuracy, average precision and F-measure for a variety of recommendations. 2024 IEEE. -
JRHDLSI: An Approach Towards Job Recommendation Hybridizing Deep Learning and Semantic Intelligence
The requirement of the job for people and employees for employers are al-ways in demand. This is due to the lack of proper infrastructure to reduce the unmatching job application for employers and inappropriate job recommendations for people. This chapter proposes a strategic framework with machine learning and knowledge integration to increase accuracy in the provided recommendations and increase the chance of getting a job offer. The usage of'user's search data intends job recommended more in liking of the users, and the machine learning helps in finding the accurate job recommendation. The machine learning technique used here is Radial Basis Function Neural Net-work for the classification and Knowledge Integrated using Analysis of Variance - Web Point Wise Mutual Information and Kullback Leibler (KL) divergence. All the job providers ads are retrieved from the top websites using beautiful soup. The proposed JRHDLSI architecture achieved an accuracy of 94.99% which outperformed the baseline models and was much superior. 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) -
A hybrid semantic algorithm for web image retrieval incorporating ontology classification and user-driven query expansion
There is always a need to increase the overall relevance of results in Web search systems. Most existing web search systems are query-driven and give the least preferences to the users needs. Specifically, mining images from the Web are a highly cumbersome task as there are so many homonyms and canonically synonymous terms. An ideal Web image recommendation system must understand the needs of the user. A system that facilitates modeling of homonymous and synonymous ontologies that understands the users need for images is proposed. A Hybrid Semantic Algorithm that computes the semantic similarity using APMI is proposed. The system also classifies the ontologies using SVM and facilitates a homonym lookup directory for classifying the semantically related homonymous ontologies. The users intentions are dynamically captured by presenting images based on the initial OntoPath and recording the user click. Strategic expansion of OntoPath based on the users choice increases the recommendation relevance. An overall accuracy of 95.09% is achieved by the proposed system. 2018, Springer Nature Singapore Pte Ltd. -
A hybridized semantic trust-based framework for personalized web page recommendation
The World Wide Web is constantly evolving and is the most dynamic information repository in the world that has ever existed. Since the information on the web is changing continuously and owing to the presence of a large number of similar web pages, it is very challenging to retrieve the most relevant information. With a large number of malicious and fake web pages, it is required to retrieve Web Pages that are trustworthy. Personalization of the recommendation of web pages is certainly necessary to estimate the user interests for suggesting web pages as per their choices. Moreover, the Web is tending towards a more organized Semantic Web which primarily requires semantic techniques for recommending the Web Pages. In this paper, a framework for personalized web page recommendation based on a hybridized strategy is proposed. Web Pages are recommended based on the user query by analyzing the Web Usage Data of the users. An array of strategies is intelligently integrated together to achieve an efficient Web Page Recommendation system. Latent Semantic Analysis is applied to the User-Term Matrix and the Term-Frequency Matrix that are built from the Web Usage Information to form a Term Prioritization Vector. Further, techniques like Latent Dirichlet Allocation for Topic-based Segregation of the URLs and Normalized Pointwise Mutual Information strategies are used for recommending web pages based on users queries. The Personalization is achieved by prioritizing the Web pages based on the Prioritization Vector. Also, a unique methodology is incorporated into the system to retrieve trustworthy websites. An overall Accuracy of 0.84 is achieved which is better than the existing strategies. 2018 Informa UK Limited, trading as Taylor & Francis Group. -
Longitudinal study on noncommunicable diseases using machine learning
This longitudinal case study thoroughly explores the intricate connection between body mass index (BMI) and four key factors: physical health, psychological well-being, lifestyle choices, and the impact of diet on health. Through the analysis of longitudinal data, notable trends emerge, revealing an increase in risk factors for noncommunicable diseases (NCDs) and unhealthy behaviors over time. This highlights the combined impact of these interconnected factors on health outcomes and the risk of developing NCDs like heart disease, diabetes, and cancer. Leveraging machine learning, the study effectively identifies individuals at elevated risk for NCDs and dispels common health misconceptions, underscoring the significance of holistic wellness approaches. Serving as a beacon for the next generation, this study provides insights that contribute to shaping a healthier future. 2025 selection and editorial matter, Arun Kumar Rana, Vishnu Sharma, Sanjeev Kumar Rana, and Vijay Shanker Chaudhary; individual chapters, the contributors. All rights reserved. -
Comic Memes and Sexist Humor in India: Tools for Reinforcement of Female Body-Image Stereotypes
Memes have been described as communicative and aesthetic practices that serve cultural, social, political purpose on a digital platform. Several studies, in the last decade, have attempted to study this digital aesthetic knowledge production as a powerful tool for political, racial, and gender-related discourses. Most often this knowledge is produced through comic multi-media texts. Many theorists believe that, digital media reinforces inequality, marginalization and such other social issues through the audio-visual-textual medium as much as it establishes the counter-discourses for equality, body activism, racial activism and the like. Speed and lack of censorship can be the cardinal reasons for the popularity of these memes. Among the mass-influencing gender-related memes are those encouraging fat-talk and body-image stereotypes. In the Indian context, 'Tag a Friend' memes is one such widely circulated meme which communicates body-shaming messages through sexist humor. It mainly targets the fat/colored/transgender women. The current study examines these memes using multimodal discourse analysis methodology. The paper attempts to investigate the revival/reproduction potential of color-shaming and body-shaming stereotypes via comic memes through Shiffman's memetic dimensions. The analysis establishes that memes can be a prominent site for the re-production of the problematic ideology of body/color shaming even in the 21st century. AesthetixMS 2021 -
Parametrical variation and its effects on characteristics of microstrip rectangular patch antenna
This paper represents a brief description about design of rectangular microstrip patch antenna and its parameter effects in size, efficiency and compactness and parametric analysis in terms of return loss, bandwidth, directivity and gain by using same and different dielectric substrate materials with same and different thickness of rectangular microstrip patch antenna. The important parameters of patch such as L, W, r and h has its own impact in antenna characteristics. This parametrical impact is studied and verified. As thickness of dielectric substrate increases, the gain & directivity of rectangular microstrip patch antenna decreases and bandwidth increases. As r increases, the size of the antenna decreases but when height of dielectric substrate increase antenna size also increases. There will be always a compromise between miniaturization and other antenna characteristics. This antenna is designed for microstrip feed line technique and with center frequency (f0) at 4GHz. The parametric analysis is obtained by comparing the simulated results of rectangular microstrip patch antenna for different cases. The proposed antenna is simulated using HFSS tool at resonance frequency of 4 GHz. 2017 IEEE.