Browse Items (14421 total)
Sort by:
-
Smart Facial Expression Analysis: Fuzzy Extreme Learning Machine in Emotion Detection
The immense academic and economic potential of facial emotion recognition (FER) has made it a crucial field in computer vision and artificial intelligence. Because of the fundamental role that facial expressions play in interpersonal communication; face photographs are vital for analysing human emotions within the context of Smart Facial Expression Analysis. This research provides a successful pipeline for emotion identification and examines FER methods that rely just on face pictures. Preprocessing, segmentation, feature extraction, and training the model are the steps that make up the suggested method's organised procedure. Face detection using the Viola-Jones technique is the first step in the preprocessing phase. Four rectangular characteristics are used for segmentation, with greyscale conversion being a necessity. In order to train a fuzzy -ELM model, feature extraction uses HOS and LBP. Emotions are better understood with this method. The suggested fuzzy-ELM approach outperforms two state-of-the-art models, ELM and CNN. With an accuracy of 98.33 %, the experimental findings show a substantial improvement in precision. A dependable and high-performing method for emotion recognition using just facial imaging, these findings highlight the usefulness of the suggested approach for Smart Facial Expression Analysis. 2025 IEEE. -
Efficacy of AI for Three-Dimensional Point Cloud Semantic Segmentation of Heritage Data for XR Environments
In heritage documentation, three-dimensional (3D) models created using Scan-to-BIM processes are essential for interpreting and presenting historic structures. Point cloud data derived from 3D laser scanning and photogrammetry facilitate realistic digital models used for immersive experiences. For this, raw point clouds, which are unstructured, are processed, semantically classified, and segmented to create parametric architectural objects in modeling platforms. Three-Dimensional Point Cloud Semantic Segmentation (3DPCSS) refers to segmenting point clouds into classes like walls, columns, etc. Automating 3DPCSS using Artificial Intelligence (AI) has gained importance in current research activities because of its versatility and efficiency over manual segmentation. However, implementing it solely with AI presents various operational and conceptual challenges, particularly for XR models in digital heritage. Automated segmentation often fails to capture the unique characteristics and intricate geometries, leading to misrepresentations or oversimplifications. Selecting an appropriate algorithmic framework for automating 3DPCSS is essential to address this gap. This paper aims to understand the efficacy of AI algorithms in recent research for 3DPCSS, particularly those tailored for 3D modeling. A study of Dwarakadesh Haveli, Ahmedabad, India, highlights the workflow and challenges of integrating point clouds into 3D models. The findings indicate the need for a detailed approach tailored to the projects specific characteristics, emphasizing the importance of systematic algorithm ensemble experimentation to refine segmentation, leading to the development of 3D parametric objects. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Stress mindset as a mediator between self-efficacy and coping styles
Stress mindset is a lens through which one views stress and its consequences as beneficial or harmful for them. It is a distinct variable that differs from frequency, amount, and intensity of stress. The literature review indicated that stress mindset could mediate the link between self-efficacy and coping style, which was previously not tested. Hence, the study aimed; 1) to examine the relationship between self-efficacy, stress mindset, and coping style; 2) to investigate the influence of stress mindset and self-efficacy on coping styles; 3) to find whether stress mindset mediates the association between self-efficacy and coping styles. The study employed a correlational research design, whereby through multi-phase sampling recruited 727 participants (male = 300, female = 427, mean age = 16.26) studying in 11th and 12th standard. The researchers administered validated stress mindset, self-efficacy, and coping style and performed a multiple correlational and regression analysis. They computed mediation analysis using Hayes model 4 in Process Macro. The finding indicated that the association between self-efficacy and self-controlling coping style is mediated by stress mindset. Furthermore, it mediated the connection between some sub-domains of self-efficacy and coping styles. The data were evident to infer that individual with high self-efficacy can interpret social stressors as beneficial and improve their coping skills. 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. -
Efficiency Enhancement using Least Significant Bits Method in Image Steganography
Over the years, there has been a tremendous growth in the field of steganography. Steganography is a technique of hidden message passing i.e. transferring a message which is not visible to human eyes, through some media such as an image, music, games etc. In this particular article we focus on Image steganography which has its own advantages and has undergone a lot of improvements in the past years. The most basic image steganography can be achieved by changing the LSBs (Least Significant Bits) of the image pixels. These bits can usually be called the redundant bits. However, changing a large numbers of LSBs of an image can distort the image to an extent where it would be easily noticeable that the image maybe carrying a hidden message rendering it useless. These LSBs are changed according to the message bits allowing the person to hide their data which can be decoded later by reading the LSBs of image pixels. This paper introduces and explains a method to improve the efficiency of LSB method. 2022 IEEE -
A Narrative Review on Experience and Expression of Anger Among Infertile Women
Infertility is stressful among women though there are several technological advancements in treating infertility. Anger is a powerful emotion resulting due to stigma and oppression due to infertility, especially among women. Studies have also proven that women have a poor quality of life in the context of infertility. Women are prone to suppressing anger rather than dealing with anger in the present. Psychosocial intervention and psychoeducation help women manage anger and maintain healthy quality of life. Springer Nature Switzerland AG 2023. -
Statistical Analysis of Ecological Mathematical Model Based on Data Warehouse
Persistence of ecosystems, existence and stability of periodic and almost periodic solutions, and global attractiveness are important research contents in ecological mathematical theory. This article takes the ocean as an example to illustrate. The marine ecological model management system integrates marine technology, Internet technology and database technology. The purpose is to collect, organize and analyze mathematical models related to marine ecosystems, integrate them according to certain classification principles, and store them in the form of text. In the database, the query of the database according to the important parameters in the mathematical model or the classification of the mathematical model is provided on the Internet, and the queried mathematical model is displayed on the screen through the browser. This paper adopts the method of data warehouse. How to effectively use resources is an important aspect of whether to take the initiative in competition. Data warehouse can play the characteristics of information processing and has broad application prospects in the face of competition in the field of telecommunications. 2023 IEEE. -
Predicting Wind Energy: Machine Learning from Daily Wind Data
This paper offers a comprehensive review of the advancements in the realm of renewable energy, specifically focusing on solid oxide fuel cells and electrolysers for green hydrogen production. The review delves into the significance of wind energy as a pivotal renewable energy source and underscores the importance of precise forecasting for efficient energy management and distribution. The integration of machine learning-based approaches, such as Support Vector Regression and Random Forest Regression, has shown promising results in enhancing the accuracy of wind energy production forecasts. Furthermore, the paper explores the broader landscape of renewable energy generation forecasting, emphasizing the rising prominence of machine learning and deep learning techniques. As the penetration of renewable energy sources into the electricity grid intensifies, the need for accurate forecasting becomes paramount. Traditional methods, while valuable, have encountered limitations, paving the way for advanced algorithms capable of deciphering intricate data relationships. The review also touches upon the inherent challenges and prospective research avenues in the domain, including addressing uncertainties in renewable energy generation, ensuring data availability, and enhancing model interpretability. The overarching goal remains the seamless integration of renewable sources into the grid, propelling us towards a greener future. The Authors, published by EDP Sciences, 2024. -
Stress Level Detection in Continuous Speech Using CNNs and a Hybrid Attention Layer
This paper mainly targets stress detection by analyzing the audio signals obtained from human beings. Deep learning is used to model the levels of stress pertaining to this whole paper followed by an analysis of the Mel spectrogram of the audio signals is done. A hybrid attention model helps us achieve the required result. The dataset that has been used for this article is the DAIC-WOZ dataset containing continuous speech files of conversations between a patient and a virtual assistant who is controlled by a human counselor from another room. The best results obtained were a 78.7% accuracy on the classification of the stress levels. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024. -
Lane Detection using Kalman Filtering
Autonomous vehicles are the future of transportation. Modern high-tech vehicles use a sequence of cameras and sensors and in order to assess their atmosphere and aid to the driver by generating various alerts. While driving, it is always a challenging task for drivers to notice lane lines on the road, especially at night time, it becomes more difficult. This research proposes a novel way to recognize lanes in a variety of environments, including day and night. First various pre-processing techniques are used to improve and filter out the noise present in the video frames. Then, a sequence of procedure with respect to lane detection is performed. This stable lane detection is achieved by Kalman filter, by removing offset errors and predict future lane lines. 2023 Elsevier B.V.. All rights reserved. -
COVID-19 Effects on Learning Behaviour of Tourism Students for Sustainable Education: The Malaysian Context
According to the World Health Organization (WHO), the alarming spread of coronavirus (COVID-19) began to shock the world on 31 December 2019, and it was first detected in Wuhan, Hubei, in China when a patient presented with pneumonia. To date, the virus has recorded over 2,088,663 cases worldwide. The impact of COVID-19 would be precisely worrying as it aggravated not only tourism but also the learning behaviour of tourism students. What are the effects of the COVID-19 pandemic on the learning behaviour of tourism students? What lessons could be learned to make it more sustainable for the students? And finally, what would be the suggested resilient strategies for the tourism students in the post-pandemic era? There is no original study conducted to focalise investigation on revealing the negative characteristics of COVID-19 and the learning curve of university students in Malaysia. However, the main objectives of this chapter are to provide an overview of the effects of COVID-19 in the learning behaviour of tourism students for sustainable education and the factors that distress students minds and how these helped students to share the positive aspects with others. It is gradually visible that the effects of COVID-19 on learning behaviour and dangers to university students in Malaysia and their significance on students emotional change or learning behaviours are not well perceived. This chapter recommends that educational institutions produce studies to proliferate and document the pandemics impact on the educational system. It is crucial for tourism students for sustainable education in the current time. 2023 Priyakrushna Mohanty, Anukrati Sharma, James Kennell and Azizul Hassan. -
Diversifying investor's portfolio using bitcoin: An econometric analysis
Rational investors look into maximizing returns with minimal risk. Since this is highly unlikely, optimizing risk and return is a practical solution. Bitcoin is a new financial product that can be included in an investment portfolio. This paper looks at Bitcoins as a separate asset class and attempts to capture the volatility using the Exponential GARCH (E-GARCH) as well as to check if Bitcoins can be used as an optimal tool to hedge using the Dynamic Conditional Correlation GARCH against four traditional asset classes in the U.S. economy which includes the stock market (S&P 500 index), Bonds (U.S. Aggregate Bond Index), Gold and Crude Oil. The period of study is a little over 7 years. The results suggest that Bitcoin stands as a highly speculative class of asset with extremely high volatility and with respect to hedging, Bitcoin stands as a possible tool of hedge with the U.S. Aggregate Bond index and to a certain extent against Gold but fails to be an optimal hedge against the S&P 500 and Crude Oil in the U.S. economy between April 29, 2013 and October 31, 2019 due to its highly volatile nature. 2020 John Wiley & Sons, Ltd. -
KMSBOT: enhancing educational institutions with an AI-powered semantic search engine and graph database
In the rapidly evolving field of education, a semantic search engine is essential to efficiently retrieve knowledge experts data. Universities and colleges continuously generate a vast amount of educational and research data. A semantic search engine can assist students and staff in efficiently searching for required information in such a big data pool. The existing systems have limitations in providing personalized recommendations that align with the individual learning objectives of students and scholars, thus hindering their educational experience. To address this, this paper proposed a KMSBOT. This novel recommendation system effectively summarizes academic data and provides tailored information for students, research scholars, and faculty, enhancing educational experiences. This paper meticulously details the development of KMSBOT, which comprises a neo4j-based knowledge graph technique, the NLP method for data structuring, and the KNN machine learning model for classification. The system employs a three-module approach, utilizing data structuring, NLP processing, and semantic search engine integration. By leveraging Neo4j, NLTK, and BERT in Python, this proposed work ensures optimal performance metrics such as time, accuracy, and loss value. The proposed solution addresses traditional recommendation systems limitations and contributes to a brighter future, improving user satisfaction and engagement in academic environments. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. -
Smart Skin Cancer Diagnosis: Integrating SCA-RELM Method for Enhanced Accuracy
One out of three cancers now is skin cancer, a figure that has exploded in the previous several decades. Melanoma is the worst kind of skin cancer and occurs in 4% of cases. It is also the most aggressive type. The health and economic impact of skin cancer is substantial, especially given its rising incidence and fatality rates. However, with early detection and treatment, the 5-year survival rate for skin cancer patients is much improved. As a result, a lot of money has gone into studying the disease and developing methods for early diagnosis in the hopes of stopping the rising tide of cancer cases and deaths, particularly melanoma. In order to enhance non-invasive skin cancer diagnosis, this research examines a range of optical modalities that have been utilized in recent years. The suggested system uses image processing to identify, remove, and categorize lesions from dermoscopy images; this system will greatly aid in the detection of melanoma, a type of skin cancer. A median filter is employed for preprocessing. Using watershed and clever edge detector, it can segment objects. The BOF plus SURF method is employed for feature extraction. It employs SCA-RELM, which performs better than the other two conventional approaches, to train the model. 2024 IEEE. -
Melanoma Skin Cancer Detection using a CNN-Regularized Extreme Learning Machine (RELM) based Model
Recent years have brought a heightened awareness of skin cancer as a potentially fatal type of human disease. While all three forms of skin cancer - Melanoma, Basal, and Squamous are terrifying, Melanoma is the most erratic. Melanoma cancer is curable if caught at an early stage. Multiple current systems have demonstrated that computer vision can play a significant role in medical image diagnosis. This study suggests a new approach to picture categorization that can help convolutional neural networks train more quickly (CNN). CNN has seen widespread use in multiclass image classification datasets, but its poor learning performance for huge volumes of data has limited its usefulness. On the other hand, whereas Regularized Extreme Learning Machine (RELM) are capable of rapid learning and have strong generalizability to improve their recognized accuracy quickly. This study introduces a novel CNN-RELM, a novel classifier that integrates convolutional neural networks with regularized extreme learning machines. CNN-RELM begins by training a Convolutional Neural Network (CNN) through the gradient descent technique until the desired learning and target accuracy is achieved. This approach outperforms the CNN and RELM model with an accuracy of around 98.6%. 2023 IEEE. -
Should Crypto Integrate Micro-Finance option?
Purpose - The purpose of the study is to identify the readiness or acceptance by the younger population specifically, the school and university students towards the investment in cryptocurrency if the micro-finance option is included in such new asset investments. Further to this the research also focusses on the mediating factor as trustworthiness to identify the impact or influence of the variable towards the acceptance of the new asset investment.Design/methodology/approach - The research conducted through relevant literature with sufficient variables measuring with five point Likert's scale. The research also tested with hypothesis on the relationship with variables. A total of 293 valid respondents data were collected and analysed through Structural Equation model.Findings - The analysis and results suggested that the perception, awareness and trustworthiness has positive impact towards the readiness towards crypto investments. Whereas, the investment behaviour has complex acceptability towards the readiness as it failed to accept the hypothesis.Research limitations/implications - the research is limited with the younger population however the research did not focusses on the economically challenged population as they may not be afford to invest in such platforms. The future studies can also be focussed on the same area with more towards the other factors that influence the economically challenged population and identify solution their economic growth. Furthermore, the study may be game changer for the policy makers in legalising the crypto investments in the country.Originality/value - According the wider background study and with substantial literature the research is of first in its kind as per the author's knowledge to integrate the micro finance concept in crypto investments to promote the investment habit among the younger population. 2024 IEEE. -
Channel Selection Using Stochastic Diffusion Search Algorithm for Classification in Brain-Computer Interface
Utilization of the Brain-Computer Interfaces (BCI) is done via Electroencephalogram (EEG) signals that provide several environmental interactions among individuals having restricted movements owing to neurodegenerative diseases or strokes. However, the BCI system was based on Motor Imagery (MI). It was not used for any form of real-life application owing to a decrease in the performance of various Common Spatial Pattern (CSP) algorithms, especially while the actual number of channels was high. A multi-channel structure of such EEG signals can increase cost and bring down speed. Due to this, a reduction in the system cost by the detection of active electrodes during the process can increase accessibility. This way, optimization techniques in choosing electrodes can be used to determine other effective channels by employing a method of random selection. For this work, a Stochastic Diffusion Search (SDS) algorithm based on herd optimization techniques was used with four different classifiers, which were the AdaBoost, the Classification and Regression Tree (CART), the Naive Bayes (NB) as well as the K-Nearest Neighbor (KNN). The channels that were chosen frequently were determined to improve the system performance with regard to accuracy and speed. The results proved that the approach proposed was successful in bringing down the channel number and run time without affecting the accuracy of classification. 2024 Seventh Sense Research Group. -
A Framework for Enhancing Classification in BrainComputer Interface
Over the past twenty years, the various merits of braincomputer interface (BCI) have garnered much recognition in the industry and scientific institutes. An increase in the quality of life is the key benefit of BCI utilization. The majority of the published works are associated with the examination and assessment of classification algorithms due to the ever-increasing interest in electroencephalography-based (EEG) BCIs. Yet, another objective is to offer guidelines that aid the reader in picking the best-suited classification algorithm for a given BCI experiment. For a given BCI system, selecting the best-suited classifier essentially requires an understanding of the features to be utilized, their properties, and their practical uses. As a feature extraction method, the common spatial pattern (CSP) will project multichannel EEG signals into a subspace to highlight the variations between the classes and minimize the similarities. This work has evaluated the efficacy of various classification algorithms like Naive Bayes, k-nearest neighbor classifier, classification and regression tree (CART), and AdaBoost for the BCI framework. Furthermore, the work has offered the proposal for channel selection with recursive feature elimination. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Survey on Feature Selection, Classification, and Optimization Techniques for EEG-Based BrainComputer Interface
In braincomputer interface (BCI) systems, the electroencephalography (EEG) signal is extensively utilized, as the recording of EEG brain signals is having relatively low cost, the potentiality for user mobility, high time resolution, and non-invasive nature. The EEG features are extracted by the BCI to execute commands. In the feature set obtained, the computational complexity increases, and poor classifier generalization can be caused by the utilization of a lot of overlapping features. The irrelevant features accumulation could be avoided with the feature selection procedures application. The feature selection algorithms are utilized to select diverse features for each classifier. Classifiers are the algorithms that are run to attain the classification. The researchers have examined diverse classifier implementation techniques to identify the feature vectors class. A review of EEG-BCI techniques available in the literature for feature selection, classifiers, and optimization algorithms is presented in this work. The research challenges, gaps, and limitations are identified in this paper. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Deep Learning Method for Classification in Brain-Computer Interface
Neural activity is the controlling signal used in enabling BCI to have direct communication with a computer. An array of EEG signals aid in the selection of the neural signal. The feature extractors and classifiers have a specific pattern of EEG control for a given BCI protocol, which is tailor-made and limited to that specific signal. Although a single protocol is applied in the deep neural networks used in EEG-based brain-computer interfaces, which are being used in the feature extraction and classification of speech recognition and computer vision, it is unclear how these architectures find themselves generalized in other area and prototypes. The deep learning approach used in transferring knowledge acquired from the source tasks to the target tasks is called transfer learning. Conventional machine learning algorithms have been surpassed by deep neural networks while solving problems concerning the real world. However, the best deep neural networks were identified by considering the knowledge of the problem domain. A significant amount of time and computational resources have to be spent to validate this approach. This work presents a deep learning neural network architecture based on Visual Geometry Group Network (VGGNet), Residual Network (ResNet), and inception network methods. Experimental results show that the proposed method achieves better performance than other methods. 2023 IEEE. -
Smart medical sensor
Medical sensors facilitate health-care applications to save a patient's life by continuously monitoring the patient's health. The combined feature of medical sensors and the fastest growing techniques that are Internet of things improves the accuracy of treatment. Internet of things techniques serve the smart and very effective medical service. Early diagnosis of the symptoms helps the health-care provider to get success in the treatment to save a patient's life. Many medical sensors are available in the health-care application that can monitor continuously patient health. Medical sensors can be wearable and nonwearable. There are some common parameters such as body temperature and a heart rate that are used to monitor human activity. These parameters are measured by using wearable and body-embedded sensors. The data collected from these parameters are analyzed by the medical devices for early detection of disease. The advanced internet of things techniques help to connect the sensors, patients, hospitals, and other medical devices. In this chapter, we highlight the use of different types of sensors with advanced technology (internet of things). 2023 Elsevier Inc. All rights reserved.