Browsing by Author "Mohan, M."

Now showing 1 - 20 of 47

A Clustering-based model for the Generation of Diversified Recommendations
(Institute of Electrical and Electronics Engineers Inc., 2022) Chaitanya, V.S.; Mohan, M.; Santhi Thilagam, P.S.
The primary goal of a recommender system is to generate accurate recommendations according to the user's interests. But the user's satisfaction increases when they get a chance to view the diverse categories of items. There exist several works on the generation of diverse recommendations but the performance of these methods often gets limited due to the issues such as cold start, filter bubble long tail, and grey sheep. Moreover, these methods do not consider the user's preference regarding exploration and exploitation while generating the recommendations. To this extent, this work proposes a model known as the iterative clustering-based diversity model, which can generate diverse recommendations and also solve the above-said issues. It groups the items based on the item description using the TF-IDF algorithm. The model generates two recommendations in such a way that one recommendation is similar and the other is different in comparison with the last interaction made by the user. The model has been evaluated on the benchmark dataset and has achieved promising results. Â© 2022 IEEE.
A study of performance scalability by parallelizing loop iterations on multi-core SMPs
(2010) Raghavendra, P.S.; Behki, A.K.; Hariprasad, K.; Mohan, M.; Jain, P.; Bhat, S.S.; Thejus, V.M.; Prabhu, V.
Today, the challenge is to exploit the parallelism available in the way of multi-core architectures by the software. This could be done by re-writing the application, by exploiting the hardware capabilities or expect the compiler/software runtime tools to do the job for us. With the advent of multi-core architectures ([1] [2]), this problem is becoming more and more relevant. Even today, there are not many run-time tools to analyze the behavioral pattern of such performance critical applications, and to re-compile them. So, techniques like OpenMP for shared memory programs are still useful in exploiting parallelism in the machine. This work tries to study if the loop parallelization (both with and without applying transformations) can be a good case for running scientific programs efficiently on such multi-core architectures. We have found the results to be encouraging and we strongly feel that this could lead to some good results if implemented fully in a production compiler for multi-core architectures. Â© Springer-Verlag Berlin Heidelberg 2010.
Analysis of Critical Gap and Capacity at Skewed Uncontrolled Intersections
(Institute for Transport Studies in the European Economic Integration, 2023) Arathi, A.R.; Harikrishna, M.; Mohan, M.
Critical gaps and capacity of movements at uncontrolled intersections are influenced by intersection geometry, especially in mixed traffic conditions. However, existing models to compute the capacity of uncontrolled base intersections are only suitable for intersections with 00 to 100 skew angles. This study aims to bridge the gap by evaluating the effect of skew angle on the critical gap and capacity of uncontrolled intersections. The critical gap models are developed for different vehicle types. The capacity of uncontrolled intersections is determined for different skew angles (00 to 270) using simulation and Indo-HCM models. The comparison reveals that the Indo-HCM model over-predicts the capacities. Thus, new capacity models are proposed, and it is observed that the capacity varies as a quadratic function of the skew angle, where the constant indicates base capacity. This study also provides the adjustment factors for Indo-HCM capacity models to deduce the capacity of any skew-angled intersections. © 2023 Institute for Transport Studies in the European Economic Integration. All rights reserved.
Analysis of traffic growth on a rural highway: A case study from India
(Institute for Transport Studies in the European Economic Integration istiee@univ.trieste.it, 2019) Nandakumar, R.; Mohan, M.
Over the years, the rate of traffic growth had always been a significant concern in the development of road infrastructures as it could either lead to premature failure of the pavement or could result in the wastage of valuable resources. The lack of proper study regarding the prediction of traffic growth has led to development of concerns in this field. The present study attempts to develop traffic forecasting models using the data collected from 2013 to 2017at the Paliyekkara toll plaza situated in southern part of India. The study identified Gross Domestic Product, population and vehicle ownership as the main factors that influence traffic growth and an exponential model was developed relating these factors with traffic volume. The proposed model was then validated by comparing the forecasted traffic with the actual traffic data of 2018. Further, on comparing with the output from existing models, it was concluded that the proposed model outperforms the available models as it had the least error in prediction. The study also modeled the variation in traffic volume that occurs in a year and this could be used to forecast the traffic for any particular month of any year. © 2019 Institute for Transport Studies in the European Economic Integration. All rights reserved.
Assessment of Safety Orientation in Driving Skills Aligned With Performance: A Data-Triangulation Approach
(Lund University Faculty of Engineering, 2024) Arichandran, R.; Mohan, M.; Sreekumar, M.
Accurate assessment of Subjective Driving Skills (SDS) is crucial for improving road safety, as direct methods are often biased and do not align well with actual driving performance. This study aimed to develop an unbiased SDS assessment method aligned with driving performance. The specific objectives are (1) reducing bias in SDS assessments, (2) verifying alignment between assessed safety orientation and ground driving performance, and (3) exploring the influence of socio-demographic factors on safety orientation. A combined questionnaire and photographic speed survey were conducted among 389 experienced car drivers in Mangalore, India. Factor analysis, a Double Lane Change (DLC) test conducted on the ground with a test vehicle equipped with Inertial Measurement Unit (IMU) sensors, correlation analysis and multiple linear regression were performed. Factor analysis confirmed the two-factor structure: Perceptual-Motor (PM) and safety skills. Further, PM and safety skills scores were calculated using factor loadings, and safety orientation was determined from their difference. DLC results showed that the assessed safety orientation aligned with the ground performance. Correlation and regression analyses showed that male drivers perceived slightly higher PM skills than female drivers. PM skills decreased with age, while safety orientation increased. Academic education had no significant effect on safety skills or safety orientation. While on-road exposure improved PM skills, weekly driving distance reduced safety orientation. Formally trained drivers had slightly higher safety skills and safety orientation than lay-instructed drivers. These findings provide several valuable insights for enhancing road safety. They suggest that safety programs address overconfidence in male drivers, incorporate road safety awareness into educational curriculums, and offer enhanced training for all experienced drivers. Younger drivers may benefit from targeted safety campaigns, while professional drivers could require specialised safety programs. Regular safety assessments and refresher courses are crucial for maintaining safety awareness, particularly for drivers with higher weekly driving distances. © 2024, Lund University Faculty of Engineering. All rights reserved.
Bithiophene based red light emitting material - Photophysical and DFT studies
(2019) Mohan, M.; Satyanarayan, M.N.; Trivedi, D.R.
Bithiophene based red fluorescent light emitting material BTCN has been synthesized by Schiff base condensation reaction and characterized by standard spectroscopic techniques. The effect of -CN substituted amino pyrazole unit covalently linked to bithiophene moiety enhances the emission intensity in the system. In solid state BTCN exhibits an emission wavelength of 651nm with 170nm FWHM. Cyclic voltammogram shows the HOMO energy level of the BTCN to be -5.59 eV with LUMO around -3.24 eV. DFT optimized geometry of BTCN possesses a high amount of planarity in their structure and TD-DFT estimates the nature of electronic transitions occurring in the system. Overall, BTCN can act as good red light emitting material for organic light emitting applications. � 2019 Author(s).
Bithiophene based red light emitting material - Photophysical and DFT studies
(American Institute of Physics Inc. subs@aip.org, 2019) Mohan, M.; Satyanarayan, M.N.; Trivedi, D.
Bithiophene based red fluorescent light emitting material BTCN has been synthesized by Schiff base condensation reaction and characterized by standard spectroscopic techniques. The effect of -CN substituted amino pyrazole unit covalently linked to bithiophene moiety enhances the emission intensity in the system. In solid state BTCN exhibits an emission wavelength of 651nm with 170nm FWHM. Cyclic voltammogram shows the HOMO energy level of the BTCN to be -5.59 eV with LUMO around -3.24 eV. DFT optimized geometry of BTCN possesses a high amount of planarity in their structure and TD-DFT estimates the nature of electronic transitions occurring in the system. Overall, BTCN can act as good red light emitting material for organic light emitting applications. Â© 2019 Author(s).
Chemosensor Based on Hydrazinyl Pyridine for Selective Detection of F? Ion in Organic Media and CO3 2? Ions in Aqueous Media: Design, Synthesis, Characterization and Practical Application
(Wiley-Blackwell info@wiley.com, 2019) Singh, A.; Mohan, M.; Trivedi, D.
Two new organic receptors, receptors R1 and R2 based on hydrazinyl pyridine have been synthesized for colorimetric detection of fluoride, acetate, and carbonate anions. Receptor R1 selectively recognizes fluoride ions over the other interference anions in the dimethyl sulfoxide based on hydrogen bonding interaction, followed by deprotonation and reflects 1:2 complex formation between the receptor and the fluoride ion. Noticeable, R2 is able to discriminate between fluoride and acetate ions via optical changes despite similar basicity with bathochromic shift of 215 nm and 194 nm. In addition, R1 and R2 exhibit splendid selectivity toward carbonate ions in the aqueous media via visible colour change from pale yellow to aqua with detection limit of 0.51 ppm and 0.47 ppm. The binding mode of fluoride and carbonate to receptor R1 and R2 is supported by Density functional theory calculation. Moreover, receptor R1 and R2 show practical visible colorimetric test strip for the detection of fluoride, acetate, and carbonate ions. © 2019 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim
Classification of Lateral Driving Events Using Vehicle Response Signals for Profiling Driving Behaviors
(Springer Science and Business Media Deutschland GmbH, 2025) Arichandran, R.; Kumar, A.; Krishnakar, H.S.; Mohan, M.
Classification of driving events is crucial in profiling driving behaviors, which could significantly increase road safety. In several studies classifying driving events, drivers were asked to perform hard turns and lane changes. However, these represented simulated situations much different from real-life scenarios. The main aim of this study was to classify lateral driving events (turn) and non-events from naturalistic driving data in actual driving conditions. A stretch of 8Â km state highway was identified as the study road, and the data were collected using 8 drivers. The acceleration and gyroscope data were collected using Inertial Measurement Unit (IMU) sensors with a frequency of approximately 200Â Hz with the timestamps. A dashboard camera was fixed to capture the driverâ€™s view with timestamps. The start and end times of the turns (left turn and right turn) and non-events were manually marked using the timestamps in the recorded videos. The total count of marked events and non-events was 1246, and their start and end times were used to label the driving events in the IMU sensor data. These labeled driving events were split into the train (934 driving events) and test (312 driving events) datasets. The Hidden Markov Model (HMM) algorithm was adopted to create classification models for the driving events. HMM models were developed using the training dataset for various features, such as lateral and longitudinal acceleration. The accuracy of these models was then compared to a test dataset. The models achieved 96.09% and 95.1% accuracy in classifying turns and non-events using data from the gyroscopeâ€™s y-axis. Â© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
Classification of Longitudinal Driving Events Using Vehicle Response Signals for Profiling Driving Behaviors
(Springer Science and Business Media Deutschland GmbH, 2025) Arichandran, R.; Krishnakar, H.S.; Kumar, A.; Mohan, M.
Driving behavior profiling (DBP) involves evaluating driving patterns to determine a safety score for drivers. Proper classification of driving events increases the accuracy of profiling driving behaviors. Most driving event classification models consider lateral driving events, such as turning and lane changes. In heavy traffic conditions, it is impossible to perform lateral events independent of the position of other vehicles. This research aims to develop a model for classifying longitudinal driving events (acceleration and braking) and nonevents using vehicle response signals. To develop the model, naturalistic driving data were collected using a passenger car on a 19Â km road stretch. Vehicle response signals were collected using Inertial Measurement Unit (IMU) sensors fixed on the test vehicle with a frequency of approximately 200Â Hz with timestamps. The driverâ€™s pedal operation was also captured with timestamps using a camera to map the ground truth labels with vehicle response signals. The data were collected from 5 drivers, totaling a dataset for approximately 190Â km. The start and end times of all 634 events (444 driving events and 190 nonevents) were used to label the driving events in the IMU sensor data. These labeled driving events were split into the train (476 events) and test (158 events) datasets. Hidden Markov Model (HMM) algorithm was used to develop classification models for the driving events. The models were developed for various combinations of accelerations using the training dataset. The accuracy of these models was then compared to a test dataset. The models achieved 90.99% and 77.08% accuracy, respectively, in classifying events and nonevents using data from the accelerometer. Â© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
Colorimetric and fluorometric turn-on sensor for selective detection of fluoride ions: Sol-gel transition studies and theoretical insights
(Royal Society of Chemistry, 2018) Pangannaya, S.; Mohan, M.; Trivedi, D.R.
A new organic receptor R1 based on a naphthyl unit covalently linked to a long alkyl chain has been designed, synthesized and characterized by standard spectroscopic techniques. The colorimetric response of receptor R1 from colorless to a pale yellow color and blue fluorescence emission in the presence of F- ions revealed its selective sensing ability in the solution phase. UV-Vis titration, fluorescence titration and 1H NMR titration studies confirmed the formation of the R1-F- complex. Receptor R1 formed a stable gel in DMSO and was confirmed through the standard heating-and-cooling method. Addition of F- ions resulted in disruption of the gel forming a solution that exhibited blue fluorescence emission. The binding constant of the R1-F- complex was found to be of the order of 5.9 × 105 M-1. DFT studies revealed the formation of the receptor-anion complex agreeing well with the experimental results. The detection limit was calculated and found to be 0.8 ppm, implying the potential for application of receptor R1 in environmental applications. © 2018 The Royal Society of Chemistry and the Centre National de la Recherche Scientifique.
COMPARATIVE ANALYSIS OF CRITICAL HEADWAY ESTIMATION AT URBAN SINGLE-LANE ROUNDABOUTS; UPOREDNA ANALIZA PROCJENE KRITIČNOG INTERVALA SLJEĐENJA NA URBANIM JEDNOTRAČNIM KRUŽNIM RASKRSNICAMA
(Faculty of Transport and Traffic Engineering, 2022) Radović Stojčić, D.; Mohan, M.; Bogdanović, V.
According to models commonly used in practice, the capacity of roundabouts largely depends on the value of critical headway. The value of critical headway depends on the characteristics of vehicles, driving conditions, and geometric characteristics of intersections, but also on driver behaviour. Driver behaviour is the result of many factors that depend on the influence of the local environment, driver habits, mentality, etc. Accordingly, to calculate the capacity of roundabouts within the operational and planning analyses of roundabouts more accurately, it is necessary to use data that correspond to local conditions. In this paper, the critical headway was estimated at five urban single-lane roundabouts using five methods: Harders’, Logit, Raff ’s, Wu’s, and the maximum likelihood method. In order to determine which of the stated methods provides the most realistic estimate of critical headway, a comparison of field capacity values with theoretical capacity values was performed. Based on the comparative analysis performed in MATLAB, as well as the calculation of percentage prediction error, it was found that the Harders' method provides the most accurate estimate of critical headway at observed roundabouts in two cities in Bosnia and Herzegovina. Due to the similarity in the design of roundabouts and driver be-haviour, the results obtained in this paper can be applied in the surrounding countries, i.e., Southeast Europe. © 2022, Faculty of Transport and Traffic Engineering. All rights reserved.
Correction to: Simulation-based Performance Evaluation of Skewed Uncontrolled Intersections (International Journal of Intelligent Transportation Systems Research, (2023), 21, 2, (349-360), 10.1007/s13177-023-00360-6)
(Springer, 2023) Arathi, A.R.; Harikrishna, M.; Mohan, M.
Upon further review, the authors wish to make the following correction to the article: After reviewing the online print, it was observed that the first and second authorâ€™s have initials in their last name. Therefore, their names appear in citation as A. R., A., M., H. & Mohan, M. In this case, it will be fully of initials in place of 1st and 2nd author names. So we would like to change the appearance of first and second name of authors so that it will appear in citation as Arathi, A. R., Harikrishna, M., Mohan, M. We humbly request you to correct the author names appearance in online print as A. R. Arathi, M. Harikrishna & Mithun Mohan so that the citation (bibtex) will become Arathi, A. R., Harikrishna, M. & Mohan, M. First Author: First Name: A. R. Last Name: Arathi Co Author 1: First Name: M. Last Name: Harikrishna Co Author 2: First Name: Mithun Last Name: Mohan The authors wish to apologize for any inconvenience. Â© 2023, The Author(s), under exclusive licence to Intelligent Transportation Systems Japan.
CURRENT SCENARIO OF SARS-CORONAVIRUS 2: EPIDEMIOLOGY; POST-COVID-19 AND GLOBAL IMPACTS
(Slovak University of Agriculture, 2021) Sampath, V.P.; Govindaraj, P.; Ramasamy, R.; Mohan, M.
Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a highly contagious strain of coronavirus that causes Coronavirus Disease 2019 (COVID-19) infection, which has distressed the world's health and wealth. This Global Pandemic outbreak has affected public health enormously at various customs. The investigation of SARS-CoV-2 is still at infancy; however, based on the available reports, this review gives an overview of the epidemiology, genomic landscape, diversity of SARS-CoV-2, viral genome pathogenic interactions, associating factors for COVID-19 infections, post-COVID-19, disease manifestations with their comorbidities, the major obstacles and the preventive measures along with current vaccine strategies of SARS-CoV-2. This review also summarizes all the relevant evidence of COVID-19 illness, which can provide valuable information on the SARS-CoV-2 genome and its mode of action strategies, thus delivering additional knowledge about COVID-19. © 2021. All Rights Reserved.
Design and synthesis new colorimetric receptors for naked-eye detection of biologically important fluoride and acetate anions in organic and arsenite in aqueous medium based on ICT mechanism: DFT study and test strip application
(Elsevier B.V., 2020) Singh, A.; Mohan, M.; Trivedi, D.R.
Novel three colorimetric anion receptors R1, R2 and R3 have been designed and synthesized via condensation reaction and characterized using IR, MS, and NMR spectroscopic techniques. Anion sensing properties were studied using colorimetric, UV–vis titration, 1H NMR titration, and Cyclic Voltammetric Studies. Comparing the UV–visible titration data of the receptors R1 and R2, R2 showed high redshift (??max) in the mixed competitive solution (DMSO: H2O, 9: 1; v/v) of about 155 nm, 157 nm, 169 nm for Na+F?, Na+AcO?, and Na+AsO2 ? ions with LOD of 0.23 ppm, 0.18 ppm, and 0.30 ppm, respectively. The observed spectral change of receptor R2 is due to the anion-induced deprotonation of the OH proton, which is confirmed by UV–vis titration, 1HNMR titration, and cyclic voltammetric studies. Theoretical studies via DFT calculation were carried for R1 and R2 to optimize the structure and to explain the anion-binding mechanism. The application of designed receptor R2 was successfully demonstrated for the detection of F? and AsO2 ? ions using a test strip. The receptors R1 and R2 proved itself to be potentially useful for real-life application by sensing F? and AcO? ions in real samples like toothpaste, mouthwash, vinegar and seawater in a complete aqueous medium. © 2019 Elsevier B.V.
Design and synthesis of malonohydrazide based colorimetric receptors for discrimination of maleate over fumarate and detection of F?, AcO? and AsO2 ? ions
(Elsevier B.V., 2020) Singh, A.; Mohan, M.; Trivedi, D.R.
In this study, we have designed and synthesized two new organic receptors R1 and R2 based on malonohydrazide for the recognition of biologically important anions. The receptor R1 capable of colorimetric discrimination of maleate over fumarate ion, exhibit significant color change from pale yellow to wine red due to intermolecular hydrogen bond between the R1 and maleate ion, supported by 1HNMR titration, where the peak at ?12.0 ppm attributed to the NH proton experiences a downfield shift upon binding with maleate ion. Receptor R1, equipped with two electron-withdrawing [sbnd]NO2 moieties as the chromogenic signaling unit enhance the hydrogen bonding tendency and acidity, and thus when comparing with receptor R2, R1 displayed substantial higher redshift (??max) of 148 nm, 143 nm, and 140 nm towards F?, AcO?, and maleate anion in the DMSO. In addition, the synthesized receptors R1 and R2 are able to detect F?, AcO?, and AsO2 ? ions as their sodium salts in an aqueous solution with visual color change. Receptor R1 exhibit electrochemical response towards F? and AcO? ions. The receptors R1 and R2 are successfully applied for quantitative detection of F? ion in the toothpaste solution in an aqueous medium. Additionally, R1 and R2 exhibit fluorescence enhancement towards F? and AcO? ions in the DMSO. As well, R1 and R2 demonstrate to be potentially useful colorimetric chemosensor for sensing maleate ion using the test strip. The theoretical calculation based on TD-DFT corroborates well with the experimental results of the receptors R1 and R2 with fluoride, acetate and maleate. © 2019 Elsevier B.V.
Design and Synthesis of New Bithiophene Based Planar AIE Red Light Emitters: A Detailed Theoretical and Experimental Analysis**
(John Wiley and Sons Inc, 2022) Mohan, M.; Satyanarayan, M.N.; Trivedi, D.R.
Bithiophene core with −CN substituted pyrazole and imidazole side chains yielding B1, B2, and B3 have been designed and synthesized viz Schiff's base condensation reaction. Molecules, at their solid-state exhibited red-light emission supporting AIE mechanism. The series exhibited the highest relative quantum yield of value 18.66 % by B1 with the lowest recorded for B3 exhibiting 2.4 %. DFT results reveal the synthesized molecules at their optimized ground state adopt a planar structure. Theoretical calculation further validates the molecules to adopt a slip-stacking type of molecular packing arrangement at its condensed state, conducive for AIE. A large π-π stacking distance between the lattice plane of 3.4 Å, 3.6 Å and 3.5 Å possessed by B1, B2, and B3 respectively, favors AIE. Computational calculation on electron and hole reorganization energy reveals the effective role of two −CN groups in altering the hole mobility in comparison with the other molecules in the series. © 2022 Wiley-VCH GmbH.
Design, Synthesis and Characterization of N-Substituted Heteroaromatics: DFT-Studies and Organic Light Emitting Device Application
(Wiley-Blackwell info@wiley.com, 2020) Mohan, M.; John, R.; Satyanarayan, M.N.; Trivedi, D.R.
Schiff's base condensation of 4,5-Dimethyl-1,2-phenylenediamine with various aldehydes namely fluorene-2-carboxaldehyde (MBF), N-ethyl-3-carboxaldehyde (MBE), 8-hydroxyjulolidine-9-carboxaldehyde (MBJ) and N-(4-formylphenyl) carbazole (MBB) functioning as light emitters have been synthesized. Solid-state emission reveals the exhibition of variant fluorescent color achieved by mere variation in the peripheral group attached to the core. Amongst the designed system, MBB showed a solid-state blue light emission with its emission peak centered at 453 nm. The fluorescence quantum yield of MBB displayed value of 44.82% in the solution state. Electrochemical studies on MBB estimated a HOMO energy level at ?5.7 eV and LUMO at ?3.2 eV. OLED realized with MBB as an active emitter material was successful in the generation of bluish-green emission with a maximum brightness of 280 cd/m2. Current efficiency of 2 cd/A and a power efficiency of 0.18 lm/W was observed for the fabricated device. © 2020 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim
Designing safe and accessible bus stops: an exploration of the interplay between perceived safety at crosswalk and transit ridership
(Routledge, 2025) Sethulakshmi, G.; Mohan, M.
Measuring personal safety perception is inherently complex, involving a multifaceted array of factors. This research advances the field of knowledge by developing a novel factor structure to assess pedestrian safety perceptions and modelling overall safety as a latent construct through a second-order Confirmatory Factor Analysis. Data were collected from 568 pedestrian interviews on safety perceptions near bus stops. The study concluded that perceived safety can be measured using four latent constructs: crosswalk infrastructure, crossing environment, management measures, and driver behavior, which collectively contribute to overall crosswalk safety. Using Structural Equation Modelling, the study confirms that as perceived safety while accessing bus stops via crosswalks decreases, bus ridership also declines. Findings also reveal demographic differences, with women, older individuals, and prior accident victims perceiving bus stop environments as less safe. Results suggest that policymakers should prioritize dedicated crosswalks and control speed and aggressive driving to maximize perceived safety at bus stops. © 2025 Informa UK Limited, trading as Taylor & Francis Group.
Development of lag size-based safety thresholds for skewed uncontrolled intersections
(Aracne Editrice, 2024) Arathi, A.R.; Harikrishna, M.; Mohan, M.
Gap/Lag acceptance is the primary basis for analysing uncontrolled intersections. Misjudgement in gap/lag acceptance imparts high risk to the drivers. The gap refers to the temporal difference between consecutive vehicles on a major road, whereas lag is a part of the available gap, occasionally coinciding with the first gap. Even though both are different in real scenarios, studies do not consider them separate. The lag acceptance behaviour of drivers must be studied thoroughly because the acceptance of shorter lags is more in developing countries due to the aggressive behaviour of drivers, which might lead to road crashes. However, such studies are very scarce compared to gap acceptance studies. A study of the lag acceptance process is essential for improved traffic safety and operational efficiency at skewed uncontrolled intersections. This study adopted machine-learning techniques to predict the lag acceptance decision of drivers to examine how it performs compared to commonly used methods. Data were collected at six intersections from various cities in Kerala, India, during peak hours. Artificial Neural Network (ANN), Logistic Regression (LR) and Support Vector Machine (SVM) models were developed, and their performance was compared. The occupancy time approach was used to determine the critical lag. The goodness of fit measures shows that the ANN model outperforms the LR and SVM models, with an accuracy of 93.6%. Furthermore, goodness-of-fit measures such as F1 score and R2 values are 0.964 and 0.892, indicating that the prediction of the ANN model is excellent. Lag sizes of less than 2.7, 3.5, and 3.0 seconds were shown to be less safe, corresponding to right-turn from major, right-turn from minor and through from major roads. © 2024, Aracne Editrice. All rights reserved.