Browse Items (2150 total)
Sort by:
-
Smart detection of rice purity and its grading
The main food in India is Rice. Be it the breakfast, lunch, dinner or some snacks, for everything the most preferred ingredient in Rice. In compared with north Indians, Rice is most used by South Indians. Today's youngsters from villages are migrating to cities in search of jobs after their education. Even farmers have stopped their cultivation and are working towards different business. So, the yield of rice is reduced in India. One more reason for this is because of the poor monsoon. Government is finding it challenging to supply rice to all its consumers. It is expected, because for Rice the consumers are more compared to its production. Government has decided to import the rice from the neighboring countries. This neighboring country knows the demand of rice in India and started supplying contaminated rice. Currently our Government has no technology to check the quality of the rice which they are getting imported, so the result is plastic rice arrived in India. Indirectly, India is in huge loss in terms of money and damages for its citizens health. So, there is a need of automated system to detect the quality of the rice that are imported. Another use of such automated system is that most of the people are not able to identify the type of the rice and the quality of the rice. This system helps even common man a facility in identifying the type and quality of rice. 2017 IEEE. -
A Self-Attention Bidirectional Long Short-Term Memory for Cold Start Movie Recommendation Models
Movie recommendation systems are useful tools that help users find relevant results and prevent information overload. On the other hand, the user cold-start issue has arisen because the system lacks sufficient user data. Furthermore, they are not very scalable for use in extensive real-world applications. One of the key strategies to address the sparsity and cold-start problems is to leverage other sources of information, including item or user profiles or user reviews. Processing client feedback is typically a challenging process that involves challenging the interpretation and analysis of the textual data. Thus, this research implements an efficient deep learning-based recommendation architecture. Following the acquisition of textual data from the Amazon product reviews database, stop word removal, lemmatization, and stemming techniques are applied to the data pre-processing which eliminate inconsistent and redundant data, facilitating the process of interpreting and utilising data. Then, the Term Frequency-Inverse Document Frequency (TF-IDF) method is applied to extract the feature values from the pre-processed text data. The extracted feature values are fed to the Self-Attention Bidirectional Long Short-Term Memory (SA-BiLSTM) that utilises the matrix factorization method framework's information sources. The SA-BiLSTM model obtained 95.93% of recall, 94.76% of precision, and 97.84% of accuracy on the amazon product reviews database. 2023 IEEE. -
An Abstractive Text Summarization Using Decoder Attention with Pointer Network
Nowadays, large amounts of unstructured data are currently trending on social media and the Web. Text summarising is the process of extracting pertinent information in a concise manner without altering the content's core meaning. Summarising text by hand requires a lot of time, money, and effort. Although deep learning algorithms are commonly applied in abstractive text summarization, further research is clearly needed to fully understand their conjunction with semantic-based or structure-based approaches. The resume dataset is taken for this research work, which is gathered from Kaggle and the dataset includes 1,735 Resumes. This paper presents a unique framework based on the combination of semantic data transformations and deep learning approaches for improving abstractive text summarization. In an attempt to tackle the problem of unregistered words, a solution called Decoder Attention with Pointer Network (DA-PN) has been introduced. This method incorporates the use of a coverage mechanism to prevent word repetition in the generated text summaries. DA-PN is utilized for protecting the spread of increasing errors in generated text summaries. The performance of the proposed method is estimated using the evaluation indicator Recall Oriented Understudy for Gisting Evaluation (ROUGE) and attains an average of 26.28 which is comparatively higher than existing methods. 2023 IEEE. -
Examining the Partnerships between AI and Business Technologies in the Contemporary Environment
In the last 20 years, businesses and individuals have undergone significant changes. Firstly, people's lives have changed due to the availability of intelligent artificial intelligence (AI) devices, and businesses have begun to use these devices to generate revenue. Secondly, as technology advances, businesses are adopting new technologies and growing more reliant on them in order to increase revenue and better understand their clientele. In the current era of business, companies are dealing with significant environmental changes, such as technology advancements, public regulations, competitive advantages, and structural changes in the competitive market. Their business strategies are converted as a result of the aforementioned ecosystem changes, and they go on to overcome these environmental changes. The primary goal of the work is to more accurately analyze different AI-enabled business models for data analytics. In the era of artificial intelligence, it also discusses secure commercial transactions and platform learning business strategies. Its goal is to investigate the different business models that are in use in the market today and to give readers a better knowledge of these models by shedding light on their characteristics. 2024 IEEE. -
Utilizing Machine Learning for Advanced Natural Language Processing and Sentiment Analysis in Social Media Platforms
Social media is increasingly regarded as one of the most abundant online resources for information gathering and knowledge exchange. Among the most widely used social media sites is Twitter available today. When attempting to comprehend the information in any unknown word-based data (such as social media), natural language processing (NLP) techniques are crucial since they help remove noise from data, identify stem words, etc. It also helps with comprehension of the sentiment or semantic contents. Using social media, we apply machine learning techniques (clustering and classification) to determine the viewpoint's polarity in the information. Several classifiers and clusters, including SVM, RF, Naive Byes, and KNN, are used to detect content on social media. Sentiment analysis is the process of automatically classifying user-generated content as neutral, negative, or positive. It is possible to utilize the text, sentence, feature, or aspect as criteria to group feelings into distinct categories. This study demonstrates the application of machine learning techniques to the analysis of emotions expressed on the Twitter network. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Development of Enhance-Net Deep Learning Approach for Performance Boosting on Medical Images
Only a few clinical procedures include the use of clinical methods for the early detection, observing, evaluation, and treatment evaluation of a range of medical illnesses. Knowing the analysis of medical images in computer vision necessitates being acquainted with the core concepts and uses of deep learning and artificial neural networks. The A rapidly expanding area of study is the Deep Learning Approach (DLA) in medical image processing. DLA is often used in medical imaging to determine if an ailment is present or not. By producing speedier, more accurate results in real time, deep learning algorithms may make the jobs of radiologists and orthopaedic surgeons easier. But the standard deep learning approach has reached its efficiencies. While offering an ideal solution known as boost-Net, we study numerous optimization strategies to increase the effectiveness of deep neural networks in this research. From a selection of well-known deep learning models, Champion-Net was selected as the deep learning model. The musculoskeletal radiograph-bone classification (MURA-BC) dataset is used in this investigation. Utilizing the train and test datasets, Enhance-Net's classification precision was evaluated. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancement of coal nanostructure and investigation of its novel properties
Coal is a mineral and is extensively used as a solid fuel in developing nations and has a sizeable share in the global fossil fuel reserve. Utilization of this resource generates excess spoil and large volume of low grade waste to the environment. In recent years there have been serious research on enhancing its value and exploring the utility of this carbonaceous material to novel carbon materials. The Minerals, Metals & Materials Society 2018. -
Raman spectrum of graphite layers in Indian coal
Two Indian coals of different rank (bituminous and subbituminous coal) have been demineralized by chemical method. Fourier transform Raman spectroscopy studies have been performed to study the changes in functional groups. Well resolved G peak is observed at 1605 cm-1 and 1590 cm-1 both in bituminous coal and subbituminous coal. With HF leaching, this doublet is reduced to a singlet along with reduction of frequency to 1585 cm -1 in subbituminous coal, where as in bituminous coal the absorption become very distinct. Bituminous coal is showing more intense absorption with HF leaching in this region where as subbituminous coal is shown a reduction in intensity. G' band is observed at ? 2700 cm-1 with almost the same intensity as that of G band. This confirms the presence of multilayer formation of graphite layer. The defect band at 1355 cm-1 is due to benzene or condensed benzene rings present in amorphous carbon. This band is weak in the present study. This is mainly due to immature nature of subbituminous coal than the higher rank bituminous coal. Graphite structure is remained behind after chemical leaching liberated oxygenated functional groups and mineral groups. The decrease of ID/IG ratio indicates that graphitization is increased in bituminous coal. 2011 American Institute of Physics. -
Structural characterization of graphene layers in various Indian coals by X-Ray Diffraction technique
The results of the structural investigation of three Indian coals showed that, the structural parameters like fa & Lc increased where as interlayer spacing d002 decreased with increase in carbon content, aromaticity and coal rank. These structural parameters change just opposite with increase in volatile matter content. Considering the 'turbostratic' structure for coals, the minimum separation between aromatic lamellae was found to vary between 3.34 to 3.61 A for these coals. As the aromaticity increased, the interlayer spacing decreased an indication of more graphitization of the sample. Volatile matter and carbon content had a strong influence on the aromaticity, interlayer spacing and stacking height on the sample. The average number of carbon atoms per aromatic lamellae and number of layers in the lamellae was found to be 16-21 and 7-8 for all the samples. Published under licence by IOP Publishing Ltd. -
Cyber-Secure Framework for the Insecure Designs in Healthcare Industry
Sensitive data protection has been a top priority in the healthcare industry. This has led to the investigation of safe data storage and transaction. Despite various attempts to address this issue, data breaches continue to plague the healthcare industry. This study aims to investigate prevalent storage practices and security methodologies in the healthcare, recognizing the need for a robust framework. The work further extends with design of new security framework for healthcare industry. This framework identifies critical data and implement measures to prevent unauthorized access and data tempering. The industrial hype towards the implementation of adaptive machine learning craves the need for hybrid machine learning approaches to be adapted in the cyber secure framework. In order to improve security and confidentiality in the healthcare sector. Blockchain is used in the proposed cyber secure framework promising integrity of data with the features of immutability. This proposal aims to provide a comprehensive solution to the ongoing problem of protecting medical data. Grenze Scientific Society, 2024. -
Game Rules Prediction Winning Strategies Using Decision Tree Algorithms
With the availability of extensive data spanning over the years, sports have become an emerging field of research. The application of analytics in cricket has become prominent over the years. Cricket, the most loved sport in India, draws the attention of fans worldwide. The Indian Premier League is no exception. Created in 2008, this franchise-based T20 format of cricket has gripped the attention of cricket enthusiasts. With ardent fans cheering for their favorite teams, teams have mounting pressure to maintain their winning streak. One such team is the beloved Chennai Super Kings. Statistical techniques for winner prediction have become popular over the last decade. In this study, we try to frame decision rules for IPL teams to win a series using the CART algorithm. By considering Chennai Super Kings, this study aims to understand the criteria for winning and identify potential weaknesses, allowing the team to predict the likelihood of winning the IPL series. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Machine Learning based Candidate Recommendation System using Bayesian Model
Online websites that recommend books, music, movies, and other media are becoming increasingly prevalent because of collaborative filtering. This online websites are using many algorithms to provide the better recommendation to attract the customer. Bayesian statistics, which is based on Bayes' theorem, is a technique for data analysis in which observable data are used to update the parameters of a statistical model. To discuss a strategy called item-based collaborative filtering, which bases predictions on the similarities between the said objects. This uses Machine Learning based Candidate Recommendation System which uses Bayesian Model database to assess the proposed method. The actual results show that for collaborative filtering which is based on correlation, the Bayesian techniques we have proposed outperform traditional algorithms. Also discuss a technique for improving prediction accuracy that combines the Simple Bayesian Classifier with user- and item-based collaborative filtering. The user-based recommendation is then applied to the matrix once the user-item rating matrix has been filled out with pseudo-scores produced by the item-based filter. This model is demonstrated that the combined approach outperforms the individual collaborative recommendation approach. The creation of UI based web application will help Students to manage achievement details. Job seekers and admin will be given a separately formatted version of the application where, students can upload and view their certificate, wherein admin can access student achievement details categorized by different parameters. This proposed model is developed under the service learning scheme to benefit both job seeker and recruiter. 2023 IEEE. -
Partial load shedding using ant colony algorithm in smart grid environment
Effective power distribution methodology is one of the basic necessities to meet the increasing power demand in any power system. Load shedding is done when power demand is more than power generation, to sustain the power system stability. Load shedding methods followed today shed a particular load completely, neglecting the critical consumers within the system. Controlling the loads at individual utility level in smart grid system enables us to put a maximum power limit on utility. Hence by partially shedding the load, demand can be reduced. The technique used here utilizes ant colony algorithm to choose a maximum power limit for each load dynamically based on the importance and priority of load. This method forces the consumer to manage his load internally based on criticality. It also effectively makes use of availability based tariff schemes. 2015 IEEE. -
Design and implementation of Adaptive PI control based dynamic voltage restorer for solar based grid integration
This paper introduces an innovative approach to address voltage fluctuations in solar-based grid integration by implementing an adaptive PI control-based Dynamic Voltage Restorer (DVR). This DVR is engineered to counteract voltage disruptions resulting from grid disturbances and the intermittent nature of solar energy generation. To achieve optimal performance in diverse operating conditions, the adaptive PI controller dynamically adjusts its parameters, adapting to changes in load and solar generation. The system is realized on a digital signal processor (DSP) and evaluated within a laboratory-scale solar-based grid integration setup. The findings reveal that the proposed system effectively mitigates voltage fluctuations, ensuring a stable integration of solar energy into the grid. The adaptive PI control-based DVR outperforms traditional PI control-based DVRs, particularly when dealing with variable solar energy generation. This approach holds significant potential for practical applications in solar-based grid integration systems. 2024 IEEE. -
Demand response for residential loads using artificial bee colony algorithm to minimize energy cost
Power performance expectations are increasing, impacting designs and requiring advanced technology to improve system reliability. Demand Response (DR) is a highly flexible customer driven program in which customer voluntarily changes his energy usage patterns during the peak demand to maintain the system stability and reliability and thereby improves the performance of the gird. This paper proposes a novel algorithm for optimization of the DR schedule of the residential loads for various hours of the day using Artificial Bee Colony (ABC) algorithm. Here, the objective function is subjected to the constraints like cost constraints, time constraints and load demand. The results show that the proposed approach enhances potential in solving problems with good reliability compared with existing approaches. 2015 IEEE. -
A Review of Algorithms for Mental Stress Analysis Using EEG Signal
Mental stress is an enduring problem in human life. The level of stress increases exponentially with an increase in the complexity of work life. Hence, it is imperative to understand the causes of stress, a prerequisite of which is the ability to determine the level of stress. Electroencephalography (EEG) has been the most widely used signal for understanding stress levels. However, EEG signal is useful only when appropriate algorithms can be used to extract the properties relevant to stress analysis. This paper reviews algorithms for preprocessing, feature extraction and learning, and classification of EEG, and reports on their advantages and disadvantages for stress analysis. This review will help researchers to choose the most effective pipeline of algorithms for stress analysis using EEG signals. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Synthesis and Characterization of Carbon Nanomaterial Derived from Anthracite
Among various storage devices, carbon based supercapacitors grabs the recent trends in the electronic devices. The present research work describes the synthesis of carbon nanomaterials derived from anthracite by using staudenmaier method. Anthracite was used as a precursor because of its high carbon content. The structural and chemical complex formation carried out by using XRD and FTIR confirms the formation of CNT's. The calculated value obtained from the XRD peaks confirms the formation of multilayer carbon nano-materials. The electrode was prepared by coating synthesized CNT on copper rod. The electrochemical performance of prepared working electrode was carried out by using cyclic voltammetric performance. Electrode characterization was performed for different scan rates 10, 20, 30 and 50 mV/sec in a potential window from-0.08 to 0.2V. The CV curves represents symmetric nature which imply that electrode material have stable capacitive process. 2019 Elsevier Ltd. -
Factors Effecting on Work Values Towards Career Choices Among University Students
The pandemic effect of COVID-19 triggered a global recession in the year 2020. The unpredictability that surrounds the coronavirus is the most challenging problem that many people must confront, particularly in terms of making decisions regarding their careers, considering the significant shift in employment opportunities. The purpose of this research is to investigate the influence anxiety and the Covid-19 pandemic have on work values and the reality of career choices among university students. A quantitative research methodology was applied to 110 respondents from a nearby institution to achieve the study's objective. This was done through online surveys and the snowball sampling technique. In order to acquire the findings, a data analysis using SPSS and PLS-SEM was carried out. It is evident from the study's findings that students work values are impacted by anxiety and the COVID-19 pandemic. Moreover, the findings support the hypothesis that anxiety and the COVID-19 pandemic influence students employment decisions. The findings of the study provide insight into the body of knowledge. The influence of anxiety and the COVID-19 pandemic on current work values among university students about career choices are examined, and recommendations are made to various stakeholders, such as policymakers, university management, and career counselors. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Artificial Intelligence in Fostering Sustainable Development
Sustainable development is vital to mankind. The world is finding a growing effort of Artificial Intelligence (AI) towards sustainability, and we made an attempt to address the development in sustainability using AI systems. Sustainable development has three pillars of sustainability (i.e. social, economic, environment), and as such, the pillars of sustainable AI. The entire Life cycle of AI products can foster change in the movement of sustainability from which greater integrity and social justice can be achieved. Sustainable AI helps us to address the whole socio-technical system more than AI applications. This paper tried to address the positive impacts of AI on sustainable indicators in terms of Environmental, Societal and Economy factors. This paper is prepared to make readers, policymakers, AI ethicists and AI developers to inspire and connect with the environment for the current and future generations as there are few AI costs to be made compatible with the environment. 2023 American Institute of Physics Inc.. All rights reserved. -
Unveiling the Future: Exploring Stock Price Prediction in the Finance Sector through Machine Learning and Deep Learning - A Comprehensive Bibliometric Analysis
The investigation of predicting share prices is a captivating and beneficial area of study within the realm of economic research. precise projections and findings can potentially benefit shareholders by reducing the risk of making suboptimal investment selections. The objective of this investigation is to examine the present state of research pertaining to the prognostication of share price predictions through the utilization of Machine Learning (ML) and Deep Learning techniques. The present study examined the existing body of scientific works on methods involving DL and ML in the context of predicting the value of stocks. This study presents a comprehensive overview of research trends, methodologies, and applications in a particular field by conducting a bibliometric analysis of publications indexed in the Scopus database. Drawing from the presented data, recommendations for optimal methodologies can be formulated. The data was visually represented through the utilization of the R programming language and Vos Viewer software. The investigation additionally discerns the primary authors, institutions, and nations that are making contributions to this particular field of research. The outcomes of this investigation possess the potential to guide future research trajectories and offer significant perspectives for professionals and policymakers who are keen on utilizing machine learning and deep learning in the financial sector. 2024 IEEE.