Browse Items (2150 total)
Sort by:
-
A Pre-trained YOLO-v5 model and an Image Subtraction Approach for Printed Circuit Board Defect Detection
Almost every electronic product used regularly contains printed circuit boards, which in addition to being used for business purposes are also used for security applications. Manual visual inspection of anomalies and faults in circuit boards during manufacture and usage is extremely challenging. Due to a shortage of training data and the uncertainty of new abnormalities, identifying undiscovered flaws continues to be complicated. The YOLO-v5 technique on a customized PCB dataset is used in the study to incorporate computer vision to detect six potential PCB defects. The algorithm is designed to be feasible, deliver precise findings, and operate at a considerable pace to be effective. A technique of image subtraction is also implemented to detect flaws in printed circuit boards. The structural similarity index, a perception-based method, gauges how similar non-defective and defective PCB images are to one another. 2023 IEEE. -
Impact ofFeature Selection Techniques forEEG-Based Seizure Classification
A neurological condition called epilepsy can result in a variety of seizures. Seizures differ from person to person. It is frequently diagnosed with fMRI, magnetic resonance imaging and electroencephalography (EEG). Visually evaluating the EEG activity requires a lot of time and effort, which is the usual way of analysis. As a result, an automated diagnosis approach based on machine learning was created. To effectively categorize epileptic seizure episodes using binary classification from brain-based EEG recordings, this study develops feature selection techniques using a machine learning (ML)-based random forest classification model. Ten (10) feature selection algorithms were utilized in this proposed work. The suggested method reduces the number of features by selecting only the relevant features needed to classify seizures. So to evaluate the effectiveness of the proposed model, random forest classifier is utilized. The Bonn Epilepsy dataset derived from UCI repository of Bonn University, Germany, the CHB-MIT dataset collected from the Childrens Hospital Boston and a real-time EEG dataset collected from EEG clinic Bangalore is accustomed to the proposed approach in order to determine the best feature selection method. In this case, the relief feature selection approach outperforms others, achieving the most remarkable accuracy of 90% for UCI data and 100% for both the CHB-MIT and real-time EEG datasets with a fast computing rate. According to the results, the reduction in the number of feature characteristics significantly impacts the classifiers performance metrics, which helps to effectively categorize epileptic seizures from the brain-based EEG signals into binary classification. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Hybrid Convolutional Neural Network and Extreme Learning Machine for Kidney Stone Detection
When it comes to diagnosing structural abnormalities including cysts, stones, cancer, congenital malformations, swelling, blocking of urine flow, etc., ultrasound imaging plays a key role in the medical sector. Kidney detection is tough due to the presence of speckle noise and low contrast in ultrasound pictures. This study presents the design and implementation of a system for extracting kidney structures from ultrasound pictures for use in medical procedures such as punctures. To begin, a restored input image is used as a starting point. After that, a Gabor filter is used to lessen the impact of the speckle noise and refine the final image. Improving image quality with histogram equalization. Cell segmentation and area based segmentation were chosen as the two segmentation methods to compare in this investigation. When extracting renal regions, the region-based segmentation is applied to obtain optimal results. Finally, this study refines the segmentation and clip off just the kidney area and training the model by using CNN-ELM model. This method produces an accuracy of about 98.5%, which outperforms CNN and ELM models. 2023 IEEE. -
Effect of VR Technological Development in the Age of AI on Business Human Resource Management
Human resource management (HRM) strategies are increasingly using AI and other AI-based technologies for managing employees in both local and foreign enterprises. An exciting new field of study has emerged in the last decade on topics like the media interaction of AI and robotics, the possessions of AI acceptance on independence and consequences, and the evaluation of AI-enabled HRM practices due to the proliferation of AI-based implementations in the HRM function. The use of these technologies has influenced the way work is organized in both domestic and global corporations, presenting new possibilities for better resource management, faster decision-making, and more creative issue resolution. Research on AI-based solutions for HRM is scarce and dispersed, despite a growing interest in academia. Human resource management (HRM) roles and human-AI interactions in major multinational corporations disseminating such advances need more study. As computing and networking infrastructure has advanced rapidly, so has the era of artificial intelligence. Now that in the age of AI, virtual reality technology has found many applications beyond gaming. Human resource management has emerged as a hot topic, with interest coming from both large businesses and government agencies. Many studies have been conducted on HRM in the business world, but in order to stay up with the trends, HRM must be constantly updated. This article does a demand analysis, and sets up and tests a fully-featured VR business human resource management system, all against the backdrop of the age of artificial intelligence and the present popularity of VR technology. 2023 IEEE. -
Automated Contactless Continuous Temperature Monitoring System for Pandemic Disease Controlling Infrastructures
People are being thermally screened in hospitals and in such facilities, all the data collected must be stored and displayed. The person responsible for keeping track of people's body temperatures must put in more time and effort. This approach is a tedious task, especially during times of dealing with the pandemic diseases like Covid-19. Hence, in this paper, an automated contactless continuous temperature monitoring system is designed to eliminate this time-consuming process. If a person's temperature is too high, that is, higher than the usual temperature range, the system records it and monitors it continuously via a mobile application. In this paper, we present the development of an Automated contactless continuous body temperature monitoring system using a Raspberry Pi camera and mobile application. 2023 IEEE. -
Text-Based Sentimental Analysis to Understand User Experience Using Machine Learning Approaches
Data Analysis is turning into a driving force in every industry. It is a process in which data is analyzed in multiple ways to come to certain conclusions for the given situation. Sentiment analysis can be said to be a sub-section of data analysis where analysis is carried out on the emotions and opinions of the text. Social media has a plethora of sentiment data in various forms such as tweets, updates on the status, and so forth. Sentiment analysis on the huge volume of data can help in identifying the opinions of the general mass.The primary goal is to find the opinion of customers on the services of the Bangalore airport and to enhance the nature of these services according to the feedback provided. In this paper, we aim to measure customer opinion on services provided by Bangalore Airport through sentiment. Data is collected by a python-based scraper. The tweets are processed to determine whether they are of positive or negative opinion. These opinions are then analyzed to determine the factors which cause the negative opinions and the airport staff are alerted about the same. Various algorithms were used as part of the experimental analysis. LSTM produces more accuracy compared with existing approaches. 2023 IEEE. -
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. -
An Analysis of Word Sense Disambiguation (WSD)
Word sense disambiguation (WSD) is the method of using computer algorithms to determine the sense of arguments in the background. As a result of its difficult nature, WSD has measured an AI-complete problem, i.e., a problem whose key is as minimum as difficult as those posed by artificial intelligence. This article describes the task and introduces motives to resolve the ambiguity of words discussed throughout the text. This article summarizes supervised, unsupervised, and knowledge-based solutions. Senseval/semeval campaigns are described in relation to the assessment of WSDs, with the aim of an unbiased assessment of schemes working on numerous disambiguation errands. Finally, future directions, requests, open difficulties, and open problems are discoursed. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
The Role of Machine Learning Analysis and Metrics in Retailing Industry by using Progressive Analysis Pattern Technique
Analyzing customer purchasing data has been a challenging task for data analyzers. Even though lots of methods are introduced in this kind of research but still many barriers are there to finding the optimal pattern. Consider customer buying data is used to examine the types of parameters which is influence the customer. In this proposed work, Progressive Analysis Pattern Technique (PAPT) to predict future customer buying patterns in online shopping. We incorporated dynamic data handling prior to the proposed methodology. It will give ample purpose for the organization's perspective because the proposed work primarily focused on customer features related to the number of product quantities and product price variations of the previous purchase. Marketing strategies are most effective if they are focused to the exact client requirements. A Significant mission in campaign planning is deciding which customer to target. This research paper focusses on empirical targeting models. 2023 IEEE. -
Data science: simulating and development of outcome based teaching method
The educational researcher has a wealth of options to apply analytics to extract meaningful insights to improve teaching and learning due to the growing availability of educational data. Teaching analytics, in contrast to learning analytics, examines the quality of the classroom environment and the efficacy of the instructional methods used to improve student learning. To investigate the potential of analytics in the classroom without jeopardizing students' privacy, we suggest a data science strategy that uses simulated data using pseudocode to build test cases for educational endeavors. Hopefully, this method's findings will contribute to creating a teaching outcome model (TOM) that can be used to motivate and evaluate educator performance. In Splunk, the study's simulated methodology was carried out. Splunk is a real-time Big Data dashboard that can gather and analyze massive amounts of machine-generated data. We provide the findings as a set of visual dashboards depicting recurring themes and developments in classroom effectiveness. Our study's overarching goal is to help bolster a culture of data-informed decision-making at academic institutions by applying a scientific method to educational data. 2023 IEEE. -
Stock Market Prediction Techniques Using Artificial Intelligence: A Systematic Review
This paper systematically reviews the literature related to stock price prediction systems. The reviewers collected 6222 research works from 12 databases. The reviewers reviewed the full-text of 10 studies in preliminary search and 70 studies selected based on PRISMA. This paper uses the PRISMA-based Python framework systematic-reviewpy to conduct this systematic review and browser-automationpy to automate downloading of full-texts. The programming code with comprehensive documentation, citation data, input variables, and reviews spreadsheets is provided, making this review replicable, open-source, and free from human errors in selecting studies. The reviewed literature is categorized based on type of prediction systems to demonstrate the evolution of techniques and research gaps. The reviewed literature is 7 % statistical, 9% machine learning, 23% deep learning, 20% hybrid, 25% combination of machine learning and deep learning, and 14% studies explore multiple categories of techniques. This review provides detailed information on prediction techniques, competitor techniques, performance metrics, input variables, data timing, and research gap to enable researchers to create prediction systems per technique category. The review showed that stock trading data is most used and collected from Yahoo! Finance. Studies showed that sentiment data improved stock prediction, and most papers used tweets from Twitter. Most of the reviewed studies showed significant improvements in predictions to previous systems. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Design and Implementation of Machine Learning-Based Hybrid Model for Face Recognition System
Face recognition technologies must be able to recognize users faces in a chaotic environment. Facial detection is a different issue from facial recognition in that it requires reporting the position and size of every face in an image, whereas facial recognition does not allow for this. Due to their general similarity in look, the photographs of the same face have several alterations, which makes it a challenging challenge to solve. Face recognition is an extremely challenging process to do in an uncontrolled environment because the lighting, perspective, and quality of the image to be identified all have a significant impact on the process's output. The paper proposed a hybrid model for the face recognition using machine learning. Their performance is calculated on the basis of value derived for the FAR, FRR, TSR, ERR. At the same time their performance is compared with some existing machine learning model. It was found that the proposed hybrid model achieved the accuracy of almost 98%. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Comprehensive Review onCrop Disease Prediction Based onMachine Learning andDeep Learning Techniques
Leaf diseases cause direct crop losses in agriculture, and farmers cannot detect the disease early. If the diseases are not detected early and correctly, the farmer must undergo huge losses. It may lead to the wrong pesticide or over pesticide, directly affect crop productivity and economy, and indirectly affect human health. Sensitive crops have various leaf diseases, and early prediction of these diseases remains challenging. This paper reviews several machine learning (ML) and deep learning (DL) methods used for different crop disease segmentation and classification. In the last few years, computer vision and DL techniques have made tremendous progress in object detection and image classification. The study summaries the available research on different diseases on various crops based on machine learning (ML) and deep learning (DL) techniques. It also discusses the data sets used for research and the accuracy and performance of existing methods. It does mean that the methods and available data sets presented in this paper are not projected to replace published solutions for crop disease identification, perhaps to enhance them by finding the possible gaps. Seventy-five articles are analysed and reviewed to find essential issues that involve additional study for future research in this domain to promote continuous progress for data sets, methods, and techniques. It mainly focuses on image segmentation and classification techniques used to solve agricultural problems. Finally, this paper provides future research scope and challenges, limitations, and research gaps. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Mathematical Model to Explore the Details in an Image with Local Binary Pattern Distribution (LBP)
Mathematical understanding is required to prove the completeness of any research and scientific problem. This mathematical model will help to understand, explain and verify the results obtained in the experiment. The model in a way will portray the mathematical approach of the entire research process. This paper discusses the mathematical background of proposed prediction of lung cancer with all the parameters. Processes involved analyzing the 2D images, basic quantitative method, from, related equation and fundamental algorithmic understanding with slightly modified versions of prediction are represented in the below section with how the local binary pattern distribution can be modified so that we get reduced run time and better accuracy in the final result. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Self-adaptive Butterfly Optimization for Simultaneous Optimal Integration of Electric Vehicle Fleets and Renewable Distribution Generation
Fuel prices and environmental concerns have prompted an increase in the use of electric vehicle (EV) technology in recent years. Charging stations (CSs) are a great way to support this shift to sustainability. This has increased the demand for EV charging on electrical distribution networks (EDNs). However, optimal EV charging stations along with renewable energy sources (RES) integration can maintain EDN performance. This paper proposes a novel hybrid approach based on self-adaptive butterfly optimization algorithm (SABOA) for optimal integration of EV CSs and RES problems under various EV load growth scenarios. A multi-objective function is created from distribution losses, GHG emissions, and VSI. The ideal locations for CSs and RES are found using SABOA while minimizing the proposed multi-objective function. The simulation results on IEEE 33-bus EDN validate the suggested technique's superiority in terms of global optima. This type of hybrid strategy is required for optimal real-time integration of EV CSs and RES, taking into account emerging high EV load penetrations. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Are Women Employees in Engineering Institutions Suffer from the Stress: An Investigation Approach
Workplace stress could be detrimental to both the employer and its employees. The greatest ways to keep distress at bay in the workplace are via competent management and well-organized processes. Supervisors must recognize signs of staff distress and be prepared to provide assistance. Whenever an individual is confronted with job expectations and pressures exceeding their skillset and expertise, they experience stress connected to their employment. Workplace stress is common and could exacerbate stress when workers don't perceive they have the backing of management or coworkers in dealing with the challenges they face. The term 'stressed' is frequently used as a justification for ineffective management and inadequate supervision, even though it is typically caused by a misunderstanding of the difference between pressure and challenge. Stress and other forms of adversity are at an all-time high, both in the job and in personal life. Employee stress could be further exacerbated by things like job uncertainty, excessive hours, frequent changes, workload, and unattainable targets. The purpose of this article is to understand the variables that contribute to high-stress levels amongst female faculty members in engineering institutions strain in the job atmosphere. One's ability to manage stressful work situations, the amount of social help and assistance one receives, and the coping mechanisms one employs all play significant roles in how much stress one endures on the job. This research was done because it was necessary and important. In addition, women play a larger role in society than males do. This study suggests that women experience much high levels of stress than men do employment reasons, repercussions, roles and obligations of women faculty in engineering education, and possible remedies are all explored in this paper. 2023 IEEE. -
Empirical Study on Categorized Deep Learning Frameworks for Segmentation of Brain Tumor
In the medical image segmentation field, automation is a vital step toward illness detection and thus prevention. Once the segmentation is completed, brain tumors are easily detectable. Automated segmentation of brain tumor is an important research field for assisting radiologists in effectively diagnosing brain tumors. Many deep learning techniques like convolutional neural networks, deep belief networks, and others have been proposed for the automated brain tumor segmentation. The latest deep learning models are discussed in this study based on their performance, dice score, accuracy, sensitivity, and specificity. It also emphasizes the uniqueness of each model, as well as its benefits and drawbacks. This review also looks at some of the most prevalent concerns about utilizing this sort of classifier, as well as some of the most notable changes in regularly used MRI modalities for brain tumor diagnosis. Furthermore, this research establishes limitations, remedies, and future trends or offers up advanced challenges for researchers to produce an efficient system with clinically acceptable accuracy that aids radiologists in determining the prognosis of brain tumors. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Optimization in the Flow of Scientific Newspapers
The evolutions that occurred in the past decades have provoked variations in the market as well as academic and research. Given this scenario, the research explored in this article was aimed to analyze the contribution of the management of PMBOK methods for the optimization of Scientific Editorial Flow. The methodology used presented a quantitative approach, of descriptive character based on a survey, made available on social networks and Facebook groups, through the google forms platform. The sample is given by Snowball, this type of sampling enables the researcher to study specific groups and is difficult to reach. The analysis was by descriptive statistics, using the Likert scale, as well as the weighted average and fashion responses. It was identified that the Critical Success Factors of a Project that can contribute to the optimization of the editorial flow of a Scientific Periodical are efficient communication, empowerment, change management, client involvement, supplier involvement and conflict management. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Impact of Using Partial Gait Energy Images for Human Recognition by Gait Analysis
Gait analysis is a behavioral biometric that classifies human, based on how they walk and other variables involved in the forward movement. In this study, we have attempted to comprehend the significance of the upper portion of the body in gait analysis for human recognition. The data for this study came from the CASIA dataset, which was donated by the Chinese Academy of Sciences Institute of Automation. We began by extracting the gait energy image (GEI) from the dataset and employing principal component analysis to minimize the dimensionality (PCA). For classification, random forest, support vector machine (SVM), and convolution neural network (CNN) algorithms are implemented to recognize the human subjects. This paper provides experimental results to show the accuracy attained when classification is done on GEI of full-body images is higher than the accuracy attained when classification is done on GEI of the lower portion of the body only. It also shows the significance of the GEI of the upper portion of the body. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Improvement of Speech Emotion Recognition by Deep Convolutional Neural Network and Speech Features
Speech emotion recognition (SER) is a dynamic area of research which includes features extraction, classification and adaptation of speech emotion dataset. There are many applications where human emotions play a vital role for giving smart solutions. Some of these applications are vehicle communications, classification of satisfied and unsatisfied customers in call centers, in-car board system based on information on drivers mental state, human-computer interaction system and others. In this contribution, an improved emotion recognition technique has been proposed with Deep Convolutional Neural Network (DCNN) by using both speech spectral and prosodic features to classify seven human emotionsanger, disgust, fear, happiness, neutral, sadness and surprise. The proposed idea is implemented on different datasets such as RAVDESS, SAVEE, TESS and CREMA-D with accuracy of 96.54%, 92.38%, 99.42% and 87.90%, respectively, and compared with other pre-defined machine learning and deep learning methods. To test the real-time accuracy of the model, it has been implemented on the combined datasets with accuracy of 90.27%. This research can be useful for development of smart applications in mobile devices, household robots and online learning management system. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.