Browse Items (16488 total)
Sort by:
-
Engagement Detection through Facial Emotional Recognition Using a Shallow Residual Convolutional Neural Networks
Online teaching and learning has recently turned out to be the order of the day, where majority of the learners undergo courses and trainings over the new environment. Learning through these platforms have created a requirement to understand if the learner is interested or not. Detecting engagement of the learners have sought increased attention to create learner centric models that can enhance the teaching and learning experience. The learner will over a period of time in the platform, tend to expose various emotions like engaged, bored, frustrated, confused, angry and other cues that can be classified as engaged or disengaged. This paper proposes in creating a Convolutional Neural Network (CNN) and enabling it with residual connections that can enhance the learning rate of the network and improve the classification on three Indian datasets that predominantly work on classroom engagement models. The proposed network performs well due to introduction of Residual learning that carries additional learning from the previous batch of layers into the next batch, Optimized Hyper Parametric (OHP) setting, increased dimensions of images for higher data abstraction and reduction of vanishing gradient problems resulting in managing overfitting issues. The Residual network introduced, consists of a shallow depth of 50 layers which has significantly produced an accuracy of 91.3% on ISED & iSAFE data while it achieves a 93.4% accuracy on the Daisee dataset. The average accuracy achieved by the classification network is 0.825 according to Cohens Kappa measure. 2020, Intelligent Engineering & System. All rights reserved. -
Engaging Adolescents With ASD in Animal-Assisted Therapy: Benefits of Human-Animal Bond
Adolescents with autism spectrum disorder lack social competence. Considering the chronic nature of the disorder, it becomes essential to focus on this critical developmental phase. For people with ASD, animal- assisted interventions appear to help enhance social functioning. This chapter aimed to explore whether therapy animals could help adolescents with ASD become more socially adept through research utilizing an AB single- case experimental design with two adolescents. The participants were measured on social competence, attention, and memory. Over a month, the intervention was given twice a week for 45-60 minutes, resulting in 8 therapy sessions. With the assistance of a trained dog, a licensed clinical psychologist delivered the AAT sessions. Results show that AAT helps improve social competence alongside fostering better attention and memory. The chapter highlights the role of human- animal interactions in the developmental period of adolescence with ASD. 2025 by IGI Global Scientific Publishing. All rights reserved. -
Engine behavior analysis on a conventional diesel engine combustion mode powered by low viscous cedarwood oil/waste cooking oil biodiesel/diesel fuel mixture An experimental study
Binary biofuel is the best alternative source that completely replaces petroleum-based fuel. In this study, we have experimented with the waste cooking oil and cedarwood oil as biofuel in a DI CI engine for various proportions and related its combustion, emission, and performance characteristics to those of base diesel. This study aims to eliminate the utilization of fossil fuel in a diesel engine by introducing green binary fuel (low viscous fuel resulting from the blending of cedarwood oil with WCO biodiesel) successfully. The objective of the study is to convert cedarwood WCO into green binary fuel and investigate its performance, emission, and combustion properties. The transesterification process is utilized for the enhancement of WCO as biodiesel. It occasioned a reduction in brake thermal efficiency as the addition of waste cooking oil in the blend increased. At the same time, the maximum value of BTE of 27.8% was attained for B10C90 (10% transesterified waste cooking oil and 90% cedarwood oil in volume), whereas it was 28.1% for diesel at maximum load conditions. The BSEC was 15.4 MJ/kW-hr for B10C90 and 12.8 MJ/kWhr for diesel. The emission characteristics, CO, HC, NOx, CO2, and smoke for B10C90 were 17.93 g/kWhr, 0.55 g/kWhr., 20.09 g/kWhr, 2210.9 g/kWhr, and 25.55%. Combustion features such as NHRR, burn duration, MPRR, combustion efficiency, Ignition delay, and coefficient of variance for B10C90 were 53.74 bar, 29.38 CAD, 4.71 bar/CAD, 99.7%, 7.01 CAD, and 4.73% respectively. It showed that B10C90 had comparable performance (BTE) and combustion values to mineral diesel with better emission characteristics. 2024 The Institution of Chemical Engineers -
Engineered biocorona on microplastics as a toxicity mitigation strategy in marine environment: Experiments with a marine crustacean Artemia salina
The marine environment has become a major sink for microplastics (MPs) wastes. When MPs interact with biological macromolecules, the biocorona forms on their surface, which can alter their biological reactivity and toxicity. In this study, we investigated the impact of biocorona formation on the toxicity of aminated (NH2) and carboxylated (COOH) polystyrene MPs towards the marine crustacean Artemia salina. Biocoronated MPs were prepared using cell-free extracts (CFEs) from microalgae Chlorella sp. (phytoplankton) and the brine shrimp Artemia salina (zooplankton). The results revealed that biocorona formation effectively reduced the toxicity of MPs. Pristine NH2-MPs exhibited higher reactive oxygen species production (ROS) (182%) compared to COOH-MPs (162%) in Artemia salina. Notably, NH2-MPs coronated with brine shrimp CFE exhibited a substantial reduction in ROS production (127%) than those coronated with algal CFE, with COOH-MPs showing a similar trend (120%). Biocorona formation also significantly decreased malondialdehyde (MDA) levels and antioxidant activity compared to pristine MPs. Molecular docking and dynamics simulations demonstrated a strong binding between polystyrene and acetylcholinesterase (AChE). In vitro studies indicated that pristine NH2-MPs exhibited more reduction in AChE activity (84%) compared to COOH-MPs (95%). However, no significant reduction in AChE activity was observed upon exposure to MPs coronated with either algal or brine shrimp cell-free extracts. Independent action modeling indicated an antagonistic interaction for MPs coronated with both the CFEs. Pearson correlation and cluster heatmap analysis suggested that the toxicity reduction in Artemia salina might be driven by decreased oxidative stress followed by the corona formation. Overall, this study provides valuable insights into the potential of biomolecules from phytoplankton and zooplankton to reduce MPs toxicity in Artemia salina, while highlighting their role in modulating the toxicity of other marine pollutants. 2024 The Author(s) -
Engineered biocorona on microplastics as a toxicity mitigation strategy in marine environment: Experiments with a marine crustacean Artemia salina
The marine environment has become a major sink for microplastics (MPs) wastes. When MPs interact with biological macromolecules, the biocorona forms on their surface, which can alter their biological reactivity and toxicity. In this study, we investigated the impact of biocorona formation on the toxicity of aminated (NH2) and carboxylated (COOH) polystyrene MPs towards the marine crustacean Artemia salina. Biocoronated MPs were prepared using cell-free extracts (CFEs) from microalgae Chlorella sp. (phytoplankton) and the brine shrimp Artemia salina (zooplankton). The results revealed that biocorona formation effectively reduced the toxicity of MPs. Pristine NH2-MPs exhibited higher reactive oxygen species production (ROS) (182%) compared to COOH-MPs (162%) in Artemia salina. Notably, NH2-MPs coronated with brine shrimp CFE exhibited a substantial reduction in ROS production (127%) than those coronated with algal CFE, with COOH-MPs showing a similar trend (120%). Biocorona formation also significantly decreased malondialdehyde (MDA) levels and antioxidant activity compared to pristine MPs. Molecular docking and dynamics simulations demonstrated a strong binding between polystyrene and acetylcholinesterase (AChE). In vitro studies indicated that pristine NH2-MPs exhibited more reduction in AChE activity (84%) compared to COOH-MPs (95%). However, no significant reduction in AChE activity was observed upon exposure to MPs coronated with either algal or brine shrimp cell-free extracts. Independent action modeling indicated an antagonistic interaction for MPs coronated with both the CFEs. Pearson correlation and cluster heatmap analysis suggested that the toxicity reduction in Artemia salina might be driven by decreased oxidative stress followed by the corona formation. Overall, this study provides valuable insights into the potential of biomolecules from phytoplankton and zooplankton to reduce MPs toxicity in Artemia salina, while highlighting their role in modulating the toxicity of other marine pollutants. 2024 The Author(s) -
Engineered core-shell nanocomposite fibres incorporating bio-ceramics and bioactive molecules for wound repair
Skin plays a major role in protecting the body from external injuries and contaminants. Despite the self-healing mechanisms of the body, wound healing has several limitations, such as being time-consuming, leading to scar formation, and susceptibility to infections. In this study, a novel coreshell nanofibre membrane was designed to protect wounds and prevent secondary trauma, thereby enhancing the wound healing process. A coreshell nanofibre membrane was prepared using polycaprolactone (PCL) as the core polymer loaded with astaxanthin (ASTX) and bioglass (BG), while the shell was made from polylactic acid (PLA) containing nanohydroxyapatite (nHA) to support faster wound healing. The surface structure, morphology, and hydrophilicity of the fibres were extensively characterised. The analysis revealed uniform, well-organised, interconnected coreshell nanocomposite fibres ideal for cell adhesion and growth. In vitro studies have demonstrated enhanced cell viability and wound closure in mouse L929 fibroblast cells. Immune response studies on test membranes loaded with ASTX, BG, and nHA revealed strong anti-inflammatory and antibacterial activities against Gram-positive and Gram-negative bacteria. In vivo studies indicated favourable cellular responses and superior wound healing potential of membranes incorporated with ASTX, BG and a higher concentration of nHA. These findings highlight the potential of coreshell nanofibre membranes as an innovative wound dressing for full-thickness skin injuries, showing significant promise for biomedical applications, especially in wound healing treatments. 2025 -
Engineered MOF-199 Modified Electrodes for Enhanced Electrochemical Immunosensing of Lactoferrin via Signal Amplification
The detection of lactoferrin (LF), an essential immunological and nutritional biomarker, demands highly sensitive analytical platforms for low-level detection. In this study, a label-free electrochemical immunosensing platform was constructed by immobilizing anti-lactoferrin antibodies (Anti-LF-Ab) on a multiwalled carbon nanotube and a metalorganic framework (MWCNT/MOF-199) nanocomposite-modified glassy carbon electrode (GCE). The synergy between MWCNTs and MOF-199 provided abundant active sites for antibody immobilization and enhanced electron transfer, yielding an eightfold current increase compared to bare GCE. Electrochemical analyses confirmed efficient charge transfer and stable antibody binding. Under optimized conditions, the immunosensor exhibited exceptional analytical performance with a low detection limit of 5.24 ng ml?1 and a quantification limit of 17.46 ng ml?1 across a wide detection range of 050 ng ml?1. The platform demonstrated strong analytical reliability, including excellent repeatability (RSD < 5%), reproducibility and operational stability over multiple measurement cycles for LF detection in food diagnostics. In addition, Monte Carlo simulations confirmed the stability of the layer-by-layer assembly, supporting the robustness of the engineered sensing interface. 2025 The Author(s). Published on behalf of The Electrochemical Society by IOP Publishing Limited. -
Engineering a low-cost diatomite with Zn-Mg-Al Layered triple hydroxide (LTH) adsorbents for the effectual removal of Congo red: Studies on batch adsorption, mechanism, high selectivity, and desorption
In this work, naturally occurring, low-cost diatomite (De) or diatomaceous earth (DE) adsorbent was treated with various molar concentrations (0.05, 0.1, and 0.2 M) of Zn-Mg-Al layered triple hydroxide (LTH) using a co-precipitation approach. The DE-modified samples were named 0.05 LDE, 0.1 LDE, and 0.2 LDE and employed to remove Congo Red (CR) dye from an aqueous solution. The adsorbents were examined using XRD, BET-N2 adsorption-desorption method, ATR-IR, FESEM-EDX, and XPS, and also analyzed for zeta potentials of adsorbents at pH values between 5 and 11 to observe their surface charges. The removal efficiencies of CR were 96.5%, 99.7%, and 94.5% for 20 mg of 0.05 LDE, 0.1 LDE, and 0.2 LDE, respectively, at pH 7. A bare DE, however, showed a removal efficiency of only 7.4%. After CR adsorption, the maximum adsorption capacities (qmax) of the adsorbents were examined using the Langmuir isotherm, and the results showed that 0.1 LDE-CR (44.0 mgg?1) had a higher qmax than 0.05 LDE-CR (35.6 mgg?1), 0.2 LDE-CR (27.9 mgg?1), and DE-CR (0.9 mgg?1). The optimal adsorbent of 0.1 LDE was utilized for the selectivity and salt effects based on the investigation's efficiency in removing contaminants. 0.1 LDE has been studied for reusability of up to five cycles and can remove CR up to three cycles with 77.7% and 79.9% efficiency using NaCl and NaOH, respectively. The adsorbents may therefore be particularly effective at removing CR from water and beneficial in industrial settings where dye is often used. 2023 Elsevier B.V. -
Engineering applications of artificial intelligence
Artificial intelligence (AI) has evolved rapidly over the past few decades, permeating various aspects of our lives and transforming industries. This chapter explores the emerging applications of AI across diverse fields, including healthcare, finance, transportation, education, and entertainment. In healthcare, AI is revolutionizing diagnostics, drug discovery, personalized medicine, and patient care. In finance, AI-powered algorithms are enhancing trading strategies, risk assessment, fraud detection, and customer service. The transportation sector is witnessing advancements in autonomous vehicles, traffic management, and logistics optimization through AI technologies. AI is also reshaping education with adaptive learning platforms, personalized tutoring, and educational analytics. Moreover, in the entertainment industry, AI is driving content creation, recommendation systems, and virtual experiences. Despite the remarkable progress, challenges such as ethical concerns, bias mitigation, data privacy, and regulatory frameworks need to be addressed for the responsible deployment of AI. 2024, IGI Global. All rights reserved. -
Engineering applications of blockchain in this smart era
The advent of blockchain technology has revolutionized various industries, offering novel solutions to age-old problems. In this smart era, characterized by interconnected devices and burgeoning digital ecosystems, blockchain stands out as a transformative force. This chapter explores the emerging applications of blockchain technology in this paradigm shift towards smart systems. One prominent application of blockchain lies in the domain of decentralized finance (DeFi). Blockchain facilitates peer-to-peer transactions, eliminating the need for intermediaries like banks. Smart contracts, powered by blockchain, automate and execute agreements, enabling programmable finance, lending, and asset management. Moreover, blockchain's transparency and immutability enhance trust in financial transactions, fostering financial inclusion and security. In the realm of SCM, blockchain offers unprecedented transparency and traceability. By recording every transaction on an immutable ledger, blockchain enables users to track the journey of products from raw materials to end consumers. 2024, IGI Global. All rights reserved. -
Engineering CoMn2O? nanofibers: Enhancing one-dimensional electrode materials for high-performance supercapacitors
One-dimensional CoMn2O4 nanofibers were developed via the electrospinning method, offers a novel approach for designing electrode materials for energy storage device -supercapacitors. Field emission scanning electron microscopy (FESEM) with EDX confirmed the highly porous CoMn2O4 phase with desired composition. Elemental mapping studies confirmed uniform distribution of Co, Mn, and O elements throughout the nanofibers.Electrochemical studies underscored the crucial role of structural voids and spacing in enhancing energy storage capacity, establishing CoMn2O4 as a promising electrode material. Specific energy and power studies yielded remarkable results of 93.84 Whr/kg and 55.20 kW/kg, respectively. Additionally, specific capacitance determination returned 937.42 F/g, indicating exceptional charging and discharging performance over 1000 cycles with 93.3 % capacitance retention. Moreover, the flexible symmetric supercapacitor is expected to demonstrate exceptional flexibility and electrochemical stability, achieving a specific energy of 232 Wh/kg and a specific power of 84 kW/kg at a current density of 1 mA/cm. These findings advance our understanding of CoMn2O4 nanofibers and offer insights into developing efficient and stable energy storage systems for diverse applications. 2025 Elsevier B.V. -
Engineering CoMn2O? nanofibers: Enhancing one-dimensional electrode materials for high-performance supercapacitors
One-dimensional CoMn2O4 nanofibers were developed via the electrospinning method, offers a novel approach for designing electrode materials for energy storage device -supercapacitors. Field emission scanning electron microscopy (FESEM) with EDX confirmed the highly porous CoMn2O4 phase with desired composition. Elemental mapping studies confirmed uniform distribution of Co, Mn, and O elements throughout the nanofibers.Electrochemical studies underscored the crucial role of structural voids and spacing in enhancing energy storage capacity, establishing CoMn2O4 as a promising electrode material. Specific energy and power studies yielded remarkable results of 93.84 Whr/kg and 55.20 kW/kg, respectively. Additionally, specific capacitance determination returned 937.42 F/g, indicating exceptional charging and discharging performance over 1000 cycles with 93.3 % capacitance retention. Moreover, the flexible symmetric supercapacitor is expected to demonstrate exceptional flexibility and electrochemical stability, achieving a specific energy of 232 Wh/kg and a specific power of 84 kW/kg at a current density of 1 mA/cm. These findings advance our understanding of CoMn2O4 nanofibers and offer insights into developing efficient and stable energy storage systems for diverse applications. 2025 Elsevier B.V. -
Engineering Ru(ii) Schiff base complexes as biofunctional materials: cytotoxic and cell imaging perspectives
Four bromine-substituted Ru(ii)-arene Schiff base complexes derived from bromo-picolinaldehyde and 3-(1H-pyrazol-1-yl)propan-1-amine were examined for their cytotoxic behaviour toward cervical cancer (SiHa) and normal fibroblast (3T3-L1) cells using MTT-based in vitro assays. The ligands and complexes were comprehensively characterized by FTIR; 1H, 13C, and 19F NMR; and ESI-LCMS analyses. Single-crystal X-ray diffraction (SCXRD) confirmed the molecular structure of complex 3, while PXRD validated the crystalline nature of complexes 2 and 4. Density functional theory (DFT) calculations further supported the experimental data by revealing optimized geometries and key electronic descriptors. All complexes exhibited time- and dose-dependent anticancer effects, with complexes 24 showing the greatest cytotoxicity toward the SiHa cells (viability at 72 h: 20% 3%, 31% 3%, and 29% 3%, respectively) while maintaining high viability in normal fibroblasts (>90%). The IC50 values for complexes 14 were 19.54 2, 14.21 4, 12.43 4, and 12.43 4 M, respectively. Acridine orange (AO) and ethidium bromide (EtBr) staining and morphological analyses confirmed apoptosis as the primary mechanism of cell death, as evidenced by reduced adhesion, membrane blebbing, and cell rounding. The pronounced and selective cytotoxicity of these bromine-substituted Ru(ii) complexes highlights their potential as promising biomaterial candidates for targeted anticancer therapy. This journal is The Royal Society of Chemistry and the Centre National de la Recherche Scientifique, 2026 -
Engineering the functionality of porous organic polymers (POPs) for metal/cocatalyst-free CO2 fixation at atmospheric conditions
Carbon dioxide (CO2) utilization as C1 feedstock under metal/co-catalyst-free conditions facilitates the development of eco-friendly routes for mitigating atmospheric CO2 concentration and producing value-added compounds. In this regard, herein, we designed a bifunctional porous organic polymer (POP-1) by incorporating acidic (-CONH) and CO2-philic (-NH/N) sites by judicious choice of organic precursors. Indeed, POP-1 exhibits high heat of interaction for CO2 (40.2 kJ/mol) and excellent catalytic performance for transforming carbon dioxide to cyclic carbonates, a high-value commodity chemical with high selectivity and yield under metal/cocatalyst/solvent-free atmospheric pressure conditions. Interestingly, an analogous polymer (POP-2) that lacks basic (-NH/N) sites showed lower CO2 interaction energy (31.6 kJ/mol) and catalytic activity than that of POP-1. The theoretical studies further supported the superior catalytic activity of POP-1 in the absence of Lewis acidic metal and cocatalyst. Notably, POP-1 showed excellent reusability with retention of catalytic performance for multiple cycles of usage. Overall, this work presents a novel approach to metal/cocatalyst/solvent-free utilization of CO2 under eco-friendly atmospheric pressure conditions. 2024 Elsevier Ltd -
English language traning for core course instruction in commerce courses :
Tracing the scope and growth of English in the globalised world, this research focusses on helping the learners to improve their English language proficiency through core course instruction. The research has identified the scope of study in the Commerce discipline of higher education setting. The study aims to locate the possibility of learning and improving general vocabulary for the purpose of communication. It traces the existing studies in integrating English language in core course content at various levels and establishes the gap in the study. The mileage that English Language Teaching has covered in the past few decades is far newlinefrom listing. However, areas of study that might seem familiar and established still newlineseem to provide more scope for research. English language, no doubt has become newlinethe medium of instruction in most of the higher education settings. Students get newlineexposed to different course content through English, and training teachers for various skills has become an important quarter in the education setting. With each passing generation, there is a need to create a training approach that suits the lifestyle, advancements in various forums and needs of the learners. This research attempts to create a training module for the purpose of equipping teachers with the ability to teach English, which is the medium of instruction, through core course instruction in the higher education scenario. The research provides a module that could serve as a model for teachers to use language effectively and equip their learners not just with the knowledge of the subject, but also the knowledge of the language through which the content is delivered. The purpose of this study is to highlight the need for a holistic understanding of the language used for content delivery and also to enable students to be able to use the language inputs received here, in daily life communication too. -
English to Hindi Translation System Using Hybrid Techniques
Good communication is critical for overcoming cultural and linguistic divides in today's internationalized society. An essential communication component is the Translation of written materials, primarily academic papers, from one language into another. This abstract focuses on the research involved in translating academic publications from Hindi to English. Translating Hindi academic papers into English is naturally hard due to the significant linguistic and cultural differences between the two languages. The proposed work provided an analytical analysis of various models used in language translation, including the seq-to-seq model, MT5, and LSTM, with the help of BLEU score, Learning rate, and average loss. MT5 model outshines others in terms of an average loss of 4.75; meanwhile, LSTM has an average loss of 5.56, and the seq-to-seq model has an average loss of 6.09, implying weaker Translation. 2024 IEEE. -
Enhanced AIS Based Intrusion Detection System Using Natural Killer Cells
Intrusion detection system is used to monitor the system and network activities to identify anomalies and attacks so that integrity, availability, and confidentiality can be preserved. Here an intrusion detection system based on Artificial Immune System is proposed based on Natural Killer (NK) cells with immunological memory. NK cells are created and each NK cells detection radius is determined using the negative selection algorithm and is trained to detect various attacks. Effective cells with high fairness values are proliferated and distributed to the network using clonal selection algorithm. In this paper, two types of NK cell are used-a Heavyweight NK cell (HWNK) and a number of Lightweight NK cells (LWNK). The incoming data is vectorized and Major Histocompatibility Complex Class I (MHC1) is created. Then based on this MHC1, any of the receptors i.e. Activating Receptor or Inhibiting Receptor is activated. If it is the signature of an attack, Activating Receptor is activated. Activating receptor activation results in either cytokine release or apoptosis. Here cytokine release means an alarm is generated informing the administrator and apoptosis stands for dropping of the packet. If Inhibiting Receptor is activated, it's a normal packet there is no action taken. The technique proposed yields high accuracy, better detection rate and quick response time. 2020 River Publishers. All Rights Reserved. -
Enhanced Approach for Precision Agriculture Using AI/ML Techniques
Precision-based agriculture has been made possible by recent technical breakthroughs and developments in information technology. These new developments have made it possible to better utilise contemporary methods and instruments, like IOT, soft computing, and wireless sensor technology, to increase the agricultural productions environmental and economic sustainability. Precision farming is a new trend in agriculture that sets itself apart from traditional farming methods by applying resources in a way that is efficient, planned, systematic, and justified in order to produce higher and better yields. Precision farming uses geographic information systems like weather patterns, remote sensing technologies like Wireless Sensor Networks (WSN), and soft computing tools like Support Vector Machines (SVM), Random Forest (RF), Artificial Neural Networks (ANN), and Decision Trees (DT) to monitor and predict farm produce requirements in real time and for the future. This study examines the application of several methods and tools used in precision farming. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Enhanced Artificial Neural Network for Emoji Sentiment Analysis
Emojis enhance textual communication by conveying emotions and providing contextual richness. This study compares the performance of supervised machine learning models such as Naive Bayes, Logistic Regression, Random Forest, K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANNs) for emoji sentiment classification. A major addition in this study is the enhancement of the ANN model using an informed weight initialization technique, which speeds up convergence and reduces training time while maintaining improved performance. The experimental results showed that the Enhanced ANN (EANN) model obtained 94% accuracy, a 2% improvement over the baseline ANN model, while lowering training time from 45 to 18 units (60% decrease), highlighting the importance of initialization strategies in deep learning. The initialization method helped the EANN network avoid overfitting, resulting in increased generalization and accuracy. Proper initialization balanced the gradients during backpropagation, avoiding gradient issues that limit deep networks. Also, the informed weight initialization guaranteed that the EANN began training closer to an optimal solution, lowering the possibility of becoming confined in suboptimal local minima. The findings from this study contribute to advances in sentiment analysis and text mining, particularly in terms of improving the efficiency and accuracy of deep learning approaches. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Enhanced Autism Prediction using Hybrid Machine Learning Model
Autism Spectrum Disorder (ASD) is a condition where individuals face challenges in neurological development and have verbal, non-verbal, learning and behavioral disorders. Even though this condition is identifiable in the first few years in the children's life, many remain undiagnosed until later. This leads to long term developmental issues and delayed interventions. This is what makes the early detection critical for improving development in children. Despite that, traditional diagnosis approaches like behavioral checklists and pre structured interviews rely on the clinician's expertise and are time consuming and have a risk of inconsistency. This study entails and addresses the above problem by proposing a machine learning based multi model to automate early detection in toddlers aged 12 to 36 months. In the initial stage, the traditional classification algorithms like Logistic Regression, SVM are evaluated with high accuracy, F1 score. Then, hybrid models are developed by combining Gradient Boosting as the anchor model with other high performing algorithms, to overcome the limitation of single classification models. These hybrid models help to overcome the limitations of the individual classifiers. Finally, the best-performing hybrid model is enhanced further by Hyperparameter tuning, Feature selection and Cross validation. The outcome of this research will be a hybrid model, combining machine learning algorithms with the best scores, ensuring high accuracy and low false positives. This aims to help in the detection of ASD in early stages in toddlers. 2025 IEEE.