arXiv subjects

Sharmin Akter

Publications and source records attributed to Sharmin Akter.

13 recordsLinked to original sources

arXiv2026

Post-Lecture Interactive Environments for Conceptual Learning: A Randomized Comparison of Mixed Reality and Tangible Instruction in Undergraduate STEM Education

Developing conceptual understanding in engineering requires learners to connect spatial reasoning with abstract representations, yet lecture-based instruction often provides limited support for this process. Interactive learning environments, including mixed reality (MR) and tangible tools, may help students revisit difficult concepts through action, feedback, and visible system response. This pilot randomized study compared two post-lecture interventions, an immersive MR application and a tangible Engineering Toolkit, with lecture-only instruction in undergraduate solid mechanics. Twenty-four participants completed a baseline assessment, a common lecture, and a post-instruction knowledge test; participants in the interactive conditions also completed usability and learner-experience measures. Learning outcomes were analyzed using ANCOVA with baseline knowledge as a covariate and were supported by normalized learning gains. Instructional modality had a significant effect on post-test performance, $F(2, 20) = 3.60$, $p = .048$, partial $\eta^2 = .263$. Both interactive conditions outperformed lecture-only instruction in planned contrasts. MR showed the highest normalized learning gain ($g = .57$), whereas the tangible toolkit showed higher usability and learner confidence. In the MR condition, virtual reality sickness symptoms measured via the Virtual Reality Sickness Questionnaire remained low before and after the intervention, suggesting that the MR application was well-tolerated by participants. These results suggest that post-lecture interactive environments may support immediate conceptual learning while offering different modality-specific strengths that require larger, time-matched follow-up studies.

cs.HC↗

arXiv2026

Visualizing Engineering Fundamentals: Design of Mixed Reality and Physical Toolkits for Effective Learning

This study examined students' experiences with mixed-reality applications and physical toolkits in Engineering Mechanics to inform design guidelines for educational tools. In a user study with 24 participants, we compared classroom instruction alone, classroom instruction with a mixed-reality application, and classroom instruction with physical toolkits. Thematic analysis of participant feedback revealed that learners' workflows and engagement with fundamental mechanics problems varied across instructional modalities. Participants valued multimodal and interactive experiences that combined visualization with hands-on interaction, while reporting challenges with complex or unclear visualizations. These insights support the human-centered design of mixed-reality and physical tools for engineering education.

cs.HC↗

arXiv2024

Generative AI: A Pix2pix-GAN-Based Machine Learning Approach for Robust and Efficient Lung Segmentation

Chest radiography is climacteric in identifying different pulmonary diseases, yet radiologist workload and inefficiency can lead to misdiagnoses. Automatic, accurate, and efficient segmentation of lung from X-ray images of chest is paramount for early disease detection. This study develops a deep learning framework using a Pix2pix Generative Adversarial Network (GAN) to segment pulmonary abnormalities from CXR images. This framework's image preprocessing and augmentation techniques were properly incorporated with a U-Net-inspired generator-discriminator architecture. Initially, it loaded the CXR images and manual masks from the Montgomery and Shenzhen datasets, after which preprocessing and resizing were performed. A U-Net generator is applied to the processed CXR images that yield segmented masks; then, a Discriminator Network differentiates between the generated and real masks. Montgomery dataset served as the model's training set in the study, and the Shenzhen dataset was used to test its robustness, which was used here for the first time. An adversarial loss and an L1 distance were used to optimize the model in training. All metrics, which assess precision, recall, F1 score, and Dice coefficient, prove the effectiveness of this framework in pulmonary abnormality segmentation. It, therefore, sets the basis for future studies to be performed shortly using diverse datasets that could further confirm its clinical applicability in medical imaging.

eess.IV↗

arXiv2024

Unlocking Futures: A Natural Language Driven Career Prediction System for Computer Science and Software Engineering Students

A career is a crucial aspect for any person to fulfill their desires through hard work. During their studies, students cannot find the best career suggestions unless they receive meaningful guidance tailored to their skills. Therefore, we developed an AI-assisted model for early prediction to provide better career suggestions. Although the task is difficult, proper guidance can make it easier. Effective career guidance requires understanding a student's academic skills, interests, and skill-related activities. In this research, we collected essential information from Computer Science (CS) and Software Engineering (SWE) students to train a machine learning (ML) model that predicts career paths based on students' career-related information. To adequately train the models, we applied Natural Language Processing (NLP) techniques and completed dataset pre-processing. For comparative analysis, we utilized multiple classification ML algorithms and deep learning (DL) algorithms. This study contributes valuable insights to educational advising by providing specific career suggestions based on the unique features of CS and SWE students. Additionally, the research helps individual CS and SWE students find suitable jobs that match their skills, interests, and skill-related activities.

cs.AI↗

arXiv2024

SugarcaneNet: An Optimized Ensemble of LASSO-Regularized Pre-trained Models for Accurate Disease Classification

Sugarcane, a key crop for the world's sugar industry, is prone to several diseases that have a substantial negative influence on both its yield and quality. To effectively manage and implement preventative initiatives, diseases must be detected promptly and accurately. In this study, we present a unique model called sugarcaneNet2024 that outperforms previous methods for automatically and quickly detecting sugarcane disease through leaf image processing. Our proposed model consolidates an optimized weighted average ensemble of seven customized and LASSO-regularized pre-trained models, particularly InceptionV3, InceptionResNetV2, DenseNet201, DenseNet169, Xception, and ResNet152V2. Initially, we added three more dense layers with 0.0001 LASSO regularization, three 30% dropout layers, and three batch normalizations with renorm enabled at the bottom of these pre-trained models to improve the performance. The accuracy of sugarcane leaf disease classification was greatly increased by this addition. Following this, several comparative studies between the average ensemble and individual models were carried out, indicating that the ensemble technique performed better. The average ensemble of all modified pre-trained models produced outstanding outcomes: 100%, 99%, 99%, and 99.45% for f1 score, precision, recall, and accuracy, respectively. Performance was further enhanced by the implementation of an optimized weighted average ensemble technique incorporated with grid search. This optimized sugarcaneNet2024 model performed the best for detecting sugarcane diseases, having achieved accuracy, precision, recall, and F1 score of 99.67%, 100%, 100%, and 100% , respectively.

cs.CV↗

arXiv2023

An Improved Model for Diabetic Retinopathy Detection by using Transfer Learning and Ensemble Learning

Diabetic Retinopathy (DR) is an ocular condition caused by a sustained high level of sugar in the blood, which causes the retinal capillaries to block and bleed, causing retinal tissue damage. It usually results in blindness. Early detection can help in lowering the risk of DR and its severity. The robust and accurate prediction and detection of diabetic retinopathy is a challenging task. This paper develops a machine learning model for detecting Diabetic Retinopathy that is entirely accurate. Pre-trained models such as ResNet50, InceptionV3, Xception, DenseNet121, VGG19, NASNetMobile, MobileNetV2, DensNet169, and DenseNet201 with pooling layer, dense layer, and appropriate dropout layer at the bottom of them were carried out in transfer learning (TL) approach. Data augmentation and regularization was performed to reduce overfitting. Transfer Learning model of DenseNet121, Average and weighted ensemble of DenseNet169 and DenseNet201 TL architectures contribute individually the highest accuracy of 100%, the highest precision, recall, F-1 score of 100%, 100%, and 100%, respectively.

eess.IV↗

arXiv2023

An Improved Model Ensembled of Different Hyper-parameter Tuned Machine Learning Algorithms for Fetal Health Prediction

Fetal health is a critical concern during pregnancy as it can impact the well-being of both the mother and the baby. Regular monitoring and timely interventions are necessary to ensure the best possible outcomes. While there are various methods to monitor fetal health in the mother's womb, the use of artificial intelligence (AI) can improve the accuracy, efficiency, and speed of diagnosis. In this study, we propose a robust ensemble model called ensemble of tuned Support Vector Machine and ExtraTrees (ETSE) for predicting fetal health. Initially, we employed various data preprocessing techniques such as outlier rejection, missing value imputation, data standardization, and data sampling. Then, seven machine learning (ML) classifiers including Support Vector Machine (SVM), XGBoost (XGB), Light Gradient Boosting Machine (LGBM), Decision Tree (DT), Random Forest (RF), ExtraTrees (ET), and K-Neighbors were implemented. These models were evaluated and then optimized by hyperparameter tuning using the grid search technique. Finally, we analyzed the performance of our proposed ETSE model. The performance analysis of each model revealed that our proposed ETSE model outperformed the other models with 100% precision, 100% recall, 100% F1-score, and 99.66% accuracy. This indicates that the ETSE model can effectively predict fetal health, which can aid in timely interventions and improve outcomes for both the mother and the baby.

cs.LG↗

arXiv2023

An Improved Heart Disease Prediction Using Stacked Ensemble Method

Heart disorder has just overtaken cancer as the world's biggest cause of mortality. Several cardiac failures, heart disease mortality, and diagnostic costs can all be reduced with early identification and treatment. Medical data is collected in large quantities by the healthcare industry, but it is not well mined. The discovery of previously unknown patterns and connections in this information can help with an improved decision when it comes to forecasting heart disorder risk. In the proposed study, we constructed an ML-based diagnostic system for heart illness forecasting, using a heart disorder dataset. We used data preprocessing techniques like outlier detection and removal, checking and removing missing entries, feature normalization, cross-validation, nine classification algorithms like RF, MLP, KNN, ETC, XGB, SVC, ADB, DT, and GBM, and eight classifier measuring performance metrics like ramification accuracy, precision, F1 score, specificity, ROC, sensitivity, log-loss, and Matthews' correlation coefficient, as well as eight classification performance evaluations. Our method can easily differentiate between people who have cardiac disease and those are normal. Receiver optimistic curves and also the region under the curves were determined by every classifier. Most of the classifiers, pretreatment strategies, validation methods, and performance assessment metrics for classification models have been discussed in this study. The performance of the proposed scheme has been confirmed, utilizing all of its capabilities. In this work, the impact of clinical decision support systems was evaluated using a stacked ensemble approach that included these nine algorithms

cs.LG↗

arXiv2021

Transformer Based Bengali Chatbot Using General Knowledge Dataset

An AI chatbot provides an impressive response after learning from the trained dataset. In this decade, most of the research work demonstrates that deep neural models superior to any other model. RNN model regularly used for determining the sequence-related problem like a question and it answers. This approach acquainted with everyone as seq2seq learning. In a seq2seq model mechanism, it has encoder and decoder. The encoder embedded any input sequence, and the decoder embedded output sequence. For reinforcing the seq2seq model performance, attention mechanism added into the encoder and decoder. After that, the transformer model has introduced itself as a high-performance model with multiple attention mechanism for solving the sequence-related dilemma. This model reduces training time compared with RNN based model and also achieved state-of-the-art performance for sequence transduction. In this research, we applied the transformer model for Bengali general knowledge chatbot based on the Bengali general knowledge Question Answer (QA) dataset. It scores 85.0 BLEU on the applied QA data. To check the comparison of the transformer model performance, we trained the seq2seq model with attention on our dataset that scores 23.5 BLEU.

cs.CL↗

arXiv2021

Static dipole polarizabilities of polyacenes using self-interaction-corrected density functional approximations

Density functional approximations are known to significantly overestimate the polarizabilities of long chain-like molecules. We study the static electric dipole polarizabilities and the vertical ionization potentials of polyacenes from benzene to pentacene using the Fermi-Löwdin orbital based self-interaction corrected (FLOSIC) density functional method. The orbital-by-orbital self-interaction correction corrects for the overestimation tendency of density functional approximations. The polarizabilities calculated with FLOSIC-DFA are however overly corrected. We also tested the recently developed locally-scaled self-interaction correction (LSIC) method on the polyacenes. The local-scaling method applies full SIC in the one-electron regions and restores the proper behavior of the SIC exchange-correlation functionals in the uniform density limit. The results show that LSIC removes the overcorrection tendency of the FLOSIC-DFA and produces results that are in excellent agreement with reference CCSD values. The vertical ionization potentials with LSIC also show good agreement with available experimental values.

physics.chem-ph↗

arXiv2020

Study of self-interaction errors in density functional predictions of dipole polarizabilities and ionization energies of water clusters using Perdew-Zunger and locally scaled self-interaction corrected methods

We studied the effect of self-interaction error (SIE) on the static dipole polarizabilities of water clusters modelled with three increasingly sophisticated, non-empirical density functional approximations (DFAs), viz. the local spin density approximation (LDA), the Perdew-Burke-Ernzherof (PBE) generalized-gradient approximation (GGA), and the strongly constrained and appropriately normed (SCAN) meta-GGA, using the Perdew-Zunger self-interaction-correction (PZ-SIC) energy functional in the Fermi-Löwdin orbital SIC (FLO-SIC) framework. Our results show that while all three DFAs overestimate the cluster polarizabilities, the description systematically improves from LDA to PBE to SCAN. The self-correlation free SCAN predicts polarizabilities quite accurately with a mean absolute error (MAE) of 0.58 Bohr$^3$ with respect to coupled cluster singles and doubles (CCSD) values. Removing SIE using PZ-SIC correctly reduces the DFA polarizabilities, but over-corrects, resulting in underestimated polarizabilities in SIC-LDA, -PBE, and -SCAN. Finally, we applied a recently proposed local-scaling SIC (LSIC) method using a quasi self-consistent scheme and using the kinetic energy density ratio as an iso-orbital indicator. The results show that the LSIC polarizabilities are in excellent agreement with mean absolute error of 0.08 Bohr$^3$ for LSIC-LDA and 0.06 Bohr$^3$ for LSIC-PBE with most recent CCSD polarizabilities. Likewise, the ionization energy estimates as an absolute of highest occupied energy eigenvalue predicted by LSIC are also in excellent agreement with CCSD(T) ionization energies with MAE of 0.4 eV for LSIC-LDA and 0.04 eV for LSIC-PBE. The LSIC-LDA predictions of ionization energies are comparable to the reported GW ionization energies while the LSIC-PBE ionization energies are more accurate than reported GW results.

physics.chem-ph↗

arXiv2020

An Efficient Routing Protocol for Secured Communication in Cognitive Radio Sensor Networks

This paper introduces an efficient reactive routing protocol considering the mobility and the reliability of a node in Cognitive Radio Sensor Networks (CRSNs). The proposed protocol accommodates the dynamic behavior of the spectrum availability and selects a stable transmission path from a source node to the destination. Outlined as a weighted graph problem, the proposed protocol measures the weight for an edge the measuring the mobility patterns of the nodes and channel availability. Furthermore, the mobility pattern of a node is defined in the proposed routing protocol from the viewpoint of distance, speed, direction, and node's reliability. Besides, the spectrum awareness in the proposed protocol is measured over the number of shared common channels and the channel quality. It is anticipated that the proposed protocol shows efficient routing performance by selecting stable and secured paths from source to destination. Simulation is carried out to assess the performance of the protocol where it is witnessed that the proposed routing protocol outperforms existing ones.

cs.NI↗

arXiv2020

A Spectrum Aware Mobility Pattern Based Routing Protocol for CR-VANETs

Cognitive radio technology offers an important function in the efficient utilization of the radio spectrum. Besides, it is expected that CR-enabled vehicular ad-hoc networks (CR-VANETs) enrich the communication performance of the existing vehicular networks (VANETs). However, to ensure efficient performance in a multi-hop communication, the routing protocol in CR-VANETs needs to consider the autonomous mobility of the vehicles as well as the stochastic availability of the channels. Hence, this paper introduces a spectrum-aware mobility pattern based reactive routing protocol for CR-VANET. The proposed protocol accommodates the dynamic behavior and selects a stable transmission path from a source node to the destination. Therefore, the proposed protocol is outlined as a weighted graph problem where the weight for an edge is measured based on a parameter termed as NHDF (Next-hop Determination Factor). The NHDF implicitly considers mobility patterns of the nodes and channel availability to select the optimum path for communication. Therefore, in the proposed routing protocol, the mobility pattern of a node is defined from the viewpoint of distance, speed, direction, and node's reliability. Furthermore, the spectrum awareness in the proposed protocol is measured over the number of shared common channels and the channel quality. It is anticipated that the proposed protocol shows efficient routing performance by selecting stable and secured paths from source to destination. Simulation is carried out to assess the performance of the protocol where it is witnessed that the proposed routing protocol outperforms existing ones.

cs.NI↗