Browse Items (16488 total)
Sort by:
-
Early strength of concrete amended with waste foundry sand - A potential for early open to traffic (EOT) pavements
The most predominant and widely practiced methods for waste disposal are Landfill, Incineration, and composting. There is a scarcity of land for waste disposal and because of increasing land cost, recycling and utilization of industrial by-products and waste materials has become an attractive proposition to waste disposal. There are several types of industrial by-products and waste materials. The utilization of such materials in concrete not only decreases the overall cost of construction but also helps in reducing disposal concerns. One such industrial by-product is waste foundry sand (WFS). The annual production is about 3 million tons from different industries in India. In the metal casting process, foundry industries dispose of huge quantities of waste sand into landfills, causing a harmful impact on the environment. The silica-based spent foundry sands from iron, steel, and aluminum foundries are evaluated in the risk assessment. This paper mainly focuses on achieving concrete for EOT (Early Open to Traffic) rigid pavements with WFS along with the use of accelerator and super-plasticizer. Effects of WFS on concrete properties such as compressive strength and split tensile strength are presented. Two types of mix proportions were investigated in this study. FDOT (Florida Department of transportation) and IRC (Indian Road Congress) recommendations were adopted for mix proportions using 5% & 10% of WFS replaced partially for M-Sand. 1-day compressive strength for FDOT mix with 10% WFS was 30MPa & for IRC mix with 10%, WFS was 20?MPa. The 3-days strength for mixtures with 10% WFS was 45MPa & 47MPa for FDOT & IRC mix proportions, respectively. Though the strength decreased with the inclusion of WFS, the 1-day and 3-days strength achieved for mixtures with 10% WFS surpassed the minimum strength requirements as per the slab replacement guidelines. Normally the pavement will be open to traffic after three to four days of laying asphalt, this method of using foundry sand enables the pavements to be open to traffic inless than a day. 2023 Author(s). -
Early stage detection of osteoarthritis of the joints (hip and knee) using machine learning
This study explores the developing relationship between health care and technology, with a special emphasis on the use of machine learning (ML) algorithms to detect early stage osteoarthritis (OA) in the hip and knee joints. OA, a substantial worldwide health problem, requires improved diagnosis techniques. In this analysis, we illuminate the limitations of traditional methods, emphasizing the inherent subjectivity of clinical assessments and the delay in detection using routine imaging techniques. The research investigates the potential of ML to bring about significant changes. It focuses on combining various algorithms with extensive datasets and highlights the need to select relevant features and prepare the data to improve the accuracy of the models. The use of ML is closely connected to ethical issues, which include the protection of data privacy and the capacity to comprehend the models used. To bridge the gap between theory and practice, the chapter presents concrete examples of ML's practical use in detecting OA, opening possibilities for customized therapy and enhanced patient results. The chapter also highlights potential areas for future study, emphasizing the urgent requirement for additional progress in ML-based early detection techniques to alleviate the worldwide impact of OA. 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies. -
Early Sepsis Prediction using Hybrid LightGBM and LSTM Model
Sepsis is a critical organ malfunction that results from an abnormal response of the body to infection and might be lethal. The early detection of sepsis is essential for the patient's life. However, the traditional clinical diagnostic systems are not capable of analyzing the complicated changes in the patient's vitals over time. Therefore, a hybrid predictive framework that merges Light Gradient Boosting Machine (LightGBM) and Long Short-Term Memory (LSTM) networks for fast and accurate sepsis detection in real-time using freely accessible MIMIC-III data, has been proposed in this research. Using LightGBM, the nonlinear relationships among the features are learnt very fast and efficient, while the LSTM gives the temporal dependencies in the sequence of the patient vital signs. The combined output of the two models is said to be more sensitive and robust than that of the single models. A Streamlit-based clinical dashboard is being provided, allowing for real-time predictions and visualization for healthcare professionals. The proposed system has shown a considerable increase in the accuracy of early sepsis detection and offers a non-restricted method for AI-assisted ICU monitoring. 2025 IEEE. -
Early Prediction of Plant Disease Using AI Enabled IOT
India is an industrialized country, and about 70% of the residents rely on agriculture. Leaves are damaged by chemicals, and climates issues. An unknown illness is found on plants leads to the lowering of quality of produced. Internet of Things is a practice of reinventing the wheel agriculture by enabling farmers to tackle the problems in the industry with practical farming techniques. IoT helps to inform knowledge about factors like weather, and moisture condition. We proposed IoT, ML, and image processing based method to identify the infection. IOT enabled camera to capture the image then required region of interest is extracted. After ROI extraction, image is enhanced to remove the unwanted details form the image and to improve image quality. We compute image features. At the end we do the classification which is a twostep process training and testing and done by SVM. Our proposed method gives 92% accuracy. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Early prediction of lungs cancer by deep learning algorithms from the CT images with LBP features
The early prediction of the any type of cancer can save the lives of many especially if it is lung cancer which is one of the deadly diseases in the world. Thus the early prediction is implemented we can increase life expectancy and bring the mortality level low. Although there are various methods to detect the lung cancer cells by X-ray and CT scans, however the CT images are more preferred. The 2D images like CT scans are used to get medical results more accurate. The proposed method here will discuss how the LBP features are used to analyze the CT images with the support of Deep Learning methods. In this research work we will discuss how the image manipulation can be done to achieve better results from the CT images through various image processing methods. LBP features helps in estimating the distribution of local binary pattern of an image. A final result with 93% is achieved after the training of the processed images by LBP features. 2020 SERSC. -
Early life adversity: Impact on the neuroimmune network and long-term health outcomes
A life that begins in a healthy environment is a precursor to the evolution of a beautiful narrative. In its course, adversities can manifest in various forms ranging from psychosocial factors to environmental toxins. The current understanding of these adverse events is largely limited to a unidimensional perspective. However, it is to be noted that the nature of the impact is not isolated, but interconnected, also emphasizing the neurobehavioral effects caused by the combination of different types of adversities in varied contexts and time frames. Hence, this chapter investigates the cumulative/interactive effect of early life adversity on the neuroimmune network and its long-term consequences to health. It proposes that by fostering environments where children are more likely to develop in healthy, supportive settings, we can create a foundation for social change, leading to physically, psychologically and socially healthier communities. Such a development would contribute to individual well-being, with a potential to create healthy and resilient societies. 2025 by IGI Global Scientific Publishing. All rights reserved. -
Early Identification and Detection of Driver Drowsiness by Hybrid Machine Learning
Drunkenness or exhaustion is a leading cause of car accidents, with severe implications for road safety. More fatal accidents could be avoided if fatigued drivers were warned ahead of time. Several drowsiness detection technologies to monitor for signs of inattention while driving and notifying the driver can be adopted. Sensors in self-driving cars must detect if a driver is sleepy, angry, or experiencing extreme changes in their emotions, such as anger. These sensors must constantly monitor the driver's facial expressions and detect facial landmarks in order to extract the driver's state of expression presentation and determine whether they are driving safely. As soon as the system detects such changes, it takes control of the vehicle, immediately slows it down, and alerts the driver by sounding an alarm to make them aware of the situation. The proposed system will be integrated with the vehicle's electronics, tracking the vehicle's statistics and providing more accurate results. In this paper, we have implemented real-time image segmentation and drowsiness using machine learning methodologies. In the proposed work, an emotion detection method based on Support Vector Machines (SVM) has been implemented using facial expressions. The algorithm was tested under variable luminance conditions and outperformed current research in terms of accuracy. We have achieved 83.25 % to detect the facial expression change. 2013 IEEE. -
Early Disaster Detection and Monitoring Using Text Analysis and Levy Flight-based Particle Swarm Optimization Algorithm
Disasters can strike unexpectedly and leave a trail of destruction, causing immense suffering and loss of life while disrupting entire communities. These events can be natural, such as floods, earthquakes, hurricanes, wildfires, or man-made, including industrial accidents and technological failures. This study investigates a hybrid approach that uses text analysis, natural language processing, and optimization techniques to identify and monitor disaster-related events. The methodology of this paper involves collecting and analyzing text, focusing on sentiment and keywords associated with disaster-related text. Various aspects of text patterns are examined to enhance the models performance. The proposed model uses a Levy flight-based Particle Swarm Optimization algorithm to select optimal features from a vector set. It uses Text Blob for sentiment analysis, cosine similarity to classify each tweet as a disaster, Count Vectorizer for feature extraction, and XGBoost machine learning algorithm for classification. The significance of this model is that it provides early warning and insight for any disaster based on text analysis and classification. The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2026. -
Early diagnosis of COVID-19 patients using deep learning-based deep forest model
Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%. 2022 Informa UK Limited, trading as Taylor & Francis Group. -
Early Detection of Plant Diseases Using IoT Sensors and Machine Learning Algorithms
Agriculture is one of the most important and necessitates of the world. This paper is a study to detect plant diseases using IoT sensors and ML Algorithms for early detection of plant diseases using IoT sensors and machine learning algorithms. A primary dataset from Indian Agricultural Research Institute (ICAR) was used for the research. The dataset comprised the following features: temperature, humidity, soil moisture, leaf wetness, and dew point. Five different machine learning algorithms were explored for the implementation: Logistic Regression, Random Forest, XGBoost, CatBoost, and LightGBM. Upon comparative analysis, it was found that the LightBGM model performed the best with an accuracy of 93.4 % using cross-validation, implying remarkable performance for real-time plant disease monitoring. 2025 IEEE. -
Early detection of mental health disorders using machine learning models: An analysis based on behavioral and voice data
Mental illnesses are to be detected promptly and correctly to intervene effectively and in time. In this paper, a multi-stage NeuroVibeNet model of early mental disorders detection based on multimodal behavioral and voice data is proposed. It starts with the preprocessing of data that is high-quality and consistent, such as mean imputation, min-max normalization, outlier detection, noise reduction, and short-time energy extraction. The majority of the advanced methods employed in extracting temporal, spectral, and complex features include multiscale entropy, soft dynamic time warping, spectral contrast analysis, formant frequency analysis, and a one-dimensional convolutional neural network autoencoder. The feature selection is done via a sparse autoencoder that is used to maximize relevance and minimize redundancy. The chosen features are fed into the NeuroVibeNet architecture, where TabNet is used to process behavioral data, and Capsule Networks are used to process voice data to allow learning representations with attention and hierarchy. Lastly, a voting-based ensemble classifier uses the two modalities to combine the predictions to make strong classification decisions. The structure is coded in Python and tested on three benchmark datasets with the accuracy of 0.9839, 0.9856, and 0.9855, which is better than the current approaches. Copyright 2026. Published by Elsevier Ltd. -
Early Detection of Cyber Threats in EVCS Using Machine Learning: A Focus on Reconnaissance Attacks
There is a significant rise in electric vehicle adoption and robust and secure electric vehicle charging station infrastructure to meet this increasing demand. However, advanced technology is vulnerable to several cyber threats. Primarily starting with reconnaissance attacks, attackers gather information about the system to plan greater attacks. This can further lead to several kinds of attacks such as Denial of Service and Host Attacks where the attacker can bypass firewalls, create false traffic and disrupt service for the users. Thus, it is important to detect and prevent these attacks at an early stage. This paper presents a robust machine learning model in order to detect reconnaissance attacks. To the best of our knowledge, there have not been enough studies that focus on specific attack categories for early detection of cyber threats. The ensemble model used in the study demonstrates an impressive accuracy of 97.71% with a good balance between precision and recall. Moreover, variables related to power consumption which are harder to manipulate are used as features. This approach contributes towards more secure EVCS, fosters user trust and promotes adoption of electric vehicles at large. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Early Detection of Cervical Cancer using Machine Learning Classifiers for Improved Diagnosis in Underserved Regions
One of the incurable diseases that affect women is cervical cancer. It is brought on by a protracted infection of the skin and the vaginal mucous membrane cells. The Human Papilloma Virus (HPV), is the main factor causing aberrant cell proliferation in the area around the cervix. There are no symptoms present when the illness first appears. Early detection of this malignancy may be used to prevent death. People in less developed countries cannot afford to periodically examine themselves due to a lack of awareness, poor medical infrastructure, and expensive medication. The EDA technique is applied to examine the data and understand its characteristics. Machine Learning algorithm has been used to diagnose cervical cancer. In order to spot the existence of cervical cancer, five machine learning classifiers are utilized, the algorithms to begin earlier. The Logistic Regression classifier's results validate the correct stage prediction. 2023 IEEE. -
Early detection of breast cancer using ER specific novel NIR fluorescent dye conjugate: A phantom study using FD-f-DOT system
Fluorescence diffuse optical tomography (f-DOT) is an imaging technique that can quantify the spatial distribution of fluorescent tracers in small animals and human soft tissues. Efficacy of f-DOT imaging can be improved by tagging a functional group to the dye. A novel estrogen receptor (ER) specific near-infrared (NIR) fluorescent dye conjugate was synthesized which can be effectively used for detecting breast cancer tissues at an early stage. Our novel dye, Near Infrared Dye Conjugate-2 (NIRDC-2), is a conjugate of 17?-estradiol with an analogue of Indocyanine Green dye, bis1,1-(4-sulfobutyl) indotricarbocyanine-5-carboxylic acid, sodium salt. Our present study focuses on imaging cylindrical silicone phantoms using Frequency Domain f-DOT system. Background absorption and scattering coefficients were 0.01mm-1 and 1mm-1 respectively. 10?M concentration of NIRDC-2 and Indocyanine Green (ICG) were administered separately into a cylindrical hole (target) of size 8mm diameter in the phantom. In-silico studies were performed to analyze the properties of dyes using experimental data. Absorption coefficient of 0.0002 mm-1 was recovered for the background. Fluorophore absorption coefficient at the target recovered were 0.000173 mm-1 and 0.000408 mm-1 for ICG and NIRDC-2 respectively. In comparison with ICG, our novel dye had a two fold higher target to background contrast. Recovered target position was accurate but size altered. In concurrence with the recovered fluorescent property and the cell lines studies carried out earlier, binding properties of NIRDC-2 makes it a potential probe for the early tumor detection using f-DOT system. COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. -
Early Detection and Analysis of Potato Leaf Diseases Using Deep Learning based CNN Models
Potato diseases pose a significant threat to global agricultural productivity, leading to severe economic losses. Early and accurate disease detection is crucial for effective disease management and improved crop yield. This research explores deep learning techniques for automated potato disease prediction using convolutional neural networks (CNNs). A large dataset of potato leaf images is used to train and validate the model, ensuring robustness and accuracy. The proposed deep learning model efficiently classifies common potato diseases, such as late blight and early blight, with high precision. Performance evaluation metrics, include accuracy, The integration of deep learning in disease prediction minimizes the reliance on manual inspection, providing farmers with a cost-effective and scalable solution. Additionally, we analyze the impact of transfer learning and data augmentation on model performance. The results highlight the potential of AI-driven approaches in precision agriculture, offering real-time disease diagnosis and early intervention strategies. This research contributes to the advancement of smart farming technologies, ensuring sustainable crop protection and food security. Future work will focus on optimizing the model for real-world deployment through mobile applications and IoT-based systems. 2025 IEEE. -
Early CKD Prediction Using Ensemble and Basic Machine Learning Models
Chronic kidney disease (CKD) is a progressive illness that often remains undiagnosed until advanced stages and represents a significant global health burden. Proper and timely diagnosis of CKD can significantly improve patient prognosis and reduce treatment costs. This study evaluates several machine learning (ML) models, including support vector machine (SVM), random forest (RF), gradient boosting (GB), Nae Bayes (NB), AdaBoost, and a multilayer perceptron (MLP) neural network. Additionally, it proposes a stacking ensemble model combining RF and GB for accurate CKD prediction using a publicly available Kaggle dataset. Missing value handling and feature normalisation are performed during data preprocessing, and model performance is evaluated using an 80:20 traintest split with metrics such as the area under the curve (AUC), classification accuracy (CA), F1-score, precision, recall, and Matthews Correlation Coefficient (MCC). Experimental results indicate that RF and GB achieve the strongest individual performance, while the proposed stacking ensemble attains the highest CA of 99.4%. These findings highlight the potential of artificial intelligence (AI)-driven predictive models to support proactive CKD diagnosis and enhance clinical decision-making in healthcare systems. 2026 by the authors of this article. Published under CC-BY. -
Early bruise detection, classification and prediction in strawberry using Vis-NIR hyperspectral imaging
The most frequent kind of damage to strawberries is bruising. However, most of the bruises are so barely perceptible at an early stage on the surface, that detection of them with the human eye is quite challenging. This study proposes a method for accurately detecting and classifying the damage using reflectance imaging spectroscopy. In order to carry out the study, an experiment was devised to artificially induce bruises and a dataset was generated at different bruise intervals. A model for detecting and classifying bruises at their latent stage was developed using machine learning classifiers, including support vector machines (SVM), k-nearest neighbors (KNN), linear discriminant analysis (LDA), random forest (RF), and decision tree (DT), to investigate the changes over time after bruise occurrence on the detection performance. Regression models for the prediction of bruising time were developed using partial least square regression (PLSR), RF, gradient boosting (GB), support vector regression (SVR), and DT. Among the compared models, both SVM and LDA could achieve 99.99 % classification accuracy. RF was regarded as being the most advisable for detection and prediction jobs due to its high performance. It achieved MSE of 0.052 and R2 of 0.989 for prediction. 2024 Elsevier Ltd -
Early bruise detection, classification and prediction in strawberry using Vis-NIR hyperspectral imaging
The most frequent kind of damage to strawberries is bruising. However, most of the bruises are so barely perceptible at an early stage on the surface, that detection of them with the human eye is quite challenging. This study proposes a method for accurately detecting and classifying the damage using reflectance imaging spectroscopy. In order to carry out the study, an experiment was devised to artificially induce bruises and a dataset was generated at different bruise intervals. A model for detecting and classifying bruises at their latent stage was developed using machine learning classifiers, including support vector machines (SVM), k-nearest neighbors (KNN), linear discriminant analysis (LDA), random forest (RF), and decision tree (DT), to investigate the changes over time after bruise occurrence on the detection performance. Regression models for the prediction of bruising time were developed using partial least square regression (PLSR), RF, gradient boosting (GB), support vector regression (SVR), and DT. Among the compared models, both SVM and LDA could achieve 99.99 % classification accuracy. RF was regarded as being the most advisable for detection and prediction jobs due to its high performance. It achieved MSE of 0.052 and R2 of 0.989 for prediction. 2024 Elsevier Ltd -
Earliness of SME internationalizationand performance: Analyzing the role of CEO attributes
Purpose: The purpose of this paper is to understand the mediating effects of Chief Executive officer (CEO) attributes on the earliness of internationalization and performance in context of Indian small and medium enterprises (SMEs). Design/methodology/approach: The proposed framework is tested through analysis of a sample of 102 internationalized SMEs of the engineering industry in the Bangalore city region of India. Findings: Results highlight that CEOs age and educational background moderates between early internationalization and performance in the Indian SME context. Practical implications: Overall results facilitate in leveraging the decision-makers capabilities to successfully formulate and strategize their international marketing efforts to achieve higher performance. Originality/value: The study enriches the importance of CEO attributes in influencing the early internationalization and degree of internationalization in the context of an emerging economy where studies are limited. 2019, Emerald Publishing Limited. -
Earlier Stage Identification of Bone Cancer with Regularized ELM
A major focus of current research in the field of image processing is the application of such methods to the field of medical imaging. While dealing with biological issues like fractures, canoers, ulcers, etc., image processing facilitated pinpointing the precise cause and tailoring a remedy. In the field of tumor identification, medical imaging has set a new standard by overcoming a number of challenges. Medical imaging is the practice of generating images of the human body for diagnostic or exploratory purposes. Because of its high image quality, MRI is the method of choice for detecting tumors. This research study proposes the integration of RLM to detect tumors and presents an automatic bone cancer detection system to assist oncologists in making early diagnosis of bone malignancies, which in turn allows patients to receive treatment as soon as possible. This research work also proposes to detect bone tumors by using a combination of the RELM based M3 filtering, Canny Edge segmentation, and the Enhanced Harris corner approach. When compared to other models like CNN, ELM, and RNN, the suggested technique achieves an accuracy of around 97.55%. 2023 IEEE.