M. Naresh
Research Subjects
M. Naresh has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Samineni Peddakrishna
School of Electronics Engineering, VIT-AP University, Amaravati, India
4 shared publications Samineni Peddakrishna
VIT-AP University,School of Electronics Engineering,Amaravti,Andhra Pradesh,India,522241
2 shared publicationsAjitha G
Engineering Institute of Aeronautical Engineering,Department of Electronics and Communication,Hyderabad,India,500043
1 shared publicationAvtar Singh
Adama Science and Technology University,School of Electrical Engineering & Computing,Adama,Ethiopia
1 shared publicationDontabhaktuni Jayakumar
VIT-AP University,School of Electronics Engineering,Amaravti,Andhra Pradesh,India,522241
1 shared publicationJayendra Kumar
School of Electronics Engineering, VIT-AP University, Amaravti, Guntur, 522241, Andhra Pradesh, India
1 shared publication
Latest Publications
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Lane Detection with U-Net Optimization through Hyperparameter Tuning and Cross Validation
The implementation of secure technology in intelligent vehicles is essential, particularly with lane detection playing a crucial role in autonomous driving systems for enhanced navigation and traffic management efficiency. This paper presents a methodology for optimizing a UNet-based model for lane detection. The UNet architecture is utilized for image segmentation tasks, with an extensive evaluation of model performance conducted using various metrics. The training of the model involves fine-tuning hyperparameters within a specified search space that includes learning rates, batch sizes, and dropout rates. By iteratively adjusting these parameters based on validation loss, we aim to identify the most effective hyperparameters that will enhance the model’s performance. Additionally, a five-fold cross-validation is conducted to ensure the model’s robustness and ability to generalize to different datasets. The final model is constructed based on the best hyperparameters obtained from the tuning process. Throughout the training process, the model demonstrates a high level of accuracy, achieving a training accuracy of $\mathbf{9 9. 9 3 \%}$ and a corresponding loss of $\mathbf{0. 0 0 3 1}$. Furthermore, the validation accuracy stands at an impressive 99.81% with a validation loss of 0.01. The model achieves a high accuracy of $\mathbf{9 9. 7 8 \%}$ on the test set, with an IoU score of 0.8861 and an F1 score of 0.9396. These metrics suggest that the model effectively learns and generalizes proficiently to new, unseen data.- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Lane Detection with U-Net Optimization through Hyperparameter Tuning and Cross Validation
The implementation of secure technology in intelligent vehicles is essential, particularly with lane detection playing a crucial role in autonomous driving systems for enhanced navigation and traffic management efficiency. This paper presents a methodology for optimizing a UNet-based model for lane detection. The UNet architecture is utilized for image segmentation tasks, with an extensive evaluation of model performance conducted using various metrics. The training of the model involves fine-tuning hyperparameters within a specified search space that includes learning rates, batch sizes, and dropout rates. By iteratively adjusting these parameters based on validation loss, we aim to identify the most effective hyperparameters that will enhance the model’s performance. Additionally, a five-fold cross-validation is conducted to ensure the model’s robustness and ability to generalize to different datasets. The final model is constructed based on the best hyperparameters obtained from the tuning process. Throughout the training process, the model demonstrates a high level of accuracy, achieving a training accuracy of $\mathbf{9 9. 9 3 \%}$ and a corresponding loss of $\mathbf{0. 0 0 3 1}$. Furthermore, the validation accuracy stands at an impressive 99.81% with a validation loss of 0.01. The model achieves a high accuracy of $\mathbf{9 9. 7 8 \%}$ on the test set, with an IoU score of 0.8861 and an F1 score of 0.9396. These metrics suggest that the model effectively learns and generalizes proficiently to new, unseen data.- Open Access
Non-invasive glucose prediction and classification using NIR technology with machine learning
- 11 November 2023
- Published by Springer Nature
- p. 95-103
Non-invasive Glucose Measurement with 940 nm Sensor Using Short Wave NIR Technique
- 11 November 2023
- Published by Springer Nature
- p. 95-103
Non-invasive Glucose Measurement with 940 nm Sensor Using Short Wave NIR Technique
- 5 September 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (3) , 747-757
Non-invasive glucose measurement using 950 nm reflective short wave NIR technique
- 5 September 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (3) , 747-757
Non-invasive glucose measurement using 950 nm reflective short wave NIR technique
- Open Access
- 30 July 2023
- Published by International Academic Publishing House in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
- Vol. 31 (Spl Volume) , 119-130
Non-Invasive Near-Infrared-Based Optical Glucose Detection System for Accurate Prediction and Multi-Class Classification
One of the most common diseases around the world is diabetes. Intrusive methods involving blood samples via a finger prick are required to test for diabetes. These treatments are uncomfortable and prone to infection. Non-invasive testing is proposed as a solution to this concerning problem. To test the glucose levels of subjects, a shortwave near-infrared-based optical detection system with a 950 nm wavelength sensor in reflective mode is presented. The system collects the measured signal through voltage, transmittance, absorbance and reflections to estimate glucose. The relation between voltage and predicted glucose is evaluated from the absorbance, reflectance, and voltage for 575 samples. A Multiple linear regression (MLR) expression is used in the proposed method to enhance the accuracy. The proposed method achieves a coefficient of determination (R2) of 99% and a mean absolute derivative of 3.6 mg/dl in real-time data analysis with the sensor. The root mean square error (RMSE) is also calculated as 3.46 mg/dl. Three additional machine learning classifiers are employed to achieve high accuracy in multi-class classification. Adaboosting and Gaussian Naïve Bayes classifiers achieve an accuracy of 97% each. Furthermore, the system computes performance metrics such as precision, recall, and F1-score, and predicts the class on the test sample.
- 30 July 2023
- Published by International Academic Publishing House in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
- Vol. 31 (Spl Volume) , 119-130
Open AccessNon-Invasive Near-Infrared-Based Optical Glucose Detection System for Accurate Prediction and Multi-Class Classification
One of the most common diseases around the world is diabetes. Intrusive methods involving blood samples via a finger prick are required to test for diabetes. These treatments are uncomfortable and prone to infection. Non-invasive testing is proposed as a solution to this concerning problem. To test the glucose levels of subjects, a shortwave near-infrared-based optical detection system with a 950 nm wavelength sensor in reflective mode is presented. The system collects the measured signal through voltage, transmittance, absorbance and reflections to estimate glucose. The relation between voltage and predicted glucose is evaluated from the absorbance, reflectance, and voltage for 575 samples. A Multiple linear regression (MLR) expression is used in the proposed method to enhance the accuracy. The proposed method achieves a coefficient of determination (R2) of 99% and a mean absolute derivative of 3.6 mg/dl in real-time data analysis with the sensor. The root mean square error (RMSE) is also calculated as 3.46 mg/dl. Three additional machine learning classifiers are employed to achieve high accuracy in multi-class classification. Adaboosting and Gaussian Naïve Bayes classifiers achieve an accuracy of 97% each. Furthermore, the system computes performance metrics such as precision, recall, and F1-score, and predicts the class on the test sample.
- 1 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 303-305
Design and Implementation of Low-Cost Smart Contactless Thermometer with Polynomial Regression Model
Body temperature is an important measure of a person's health. It is used to diagnose a variety of disorders. Core temperature measurement takes some time and puts patients under strain. To measure temperature in real-time and without contact. We proposed a contactless thermometer that can be calibrated by deriving the ambient and body temperatures from thermometer readings. We analyze this accuracy using second-order polynomial linear regression. After getting the actual body temperature of 124 subjects, we achieved 99% prediction temperature accuracy and linearity with gold standard reference temperature sensors. Additionally, the application has been developed to save the readings. This application can be connected through either OTG or Bluetooth depending on the user's preference. They will have the option to save multiple people's temperature data in separate excel sheets. Following that, the user can access the data and share the link to the data using any of the shareable platforms.
- 1 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 303-305
Design and Implementation of Low-Cost Smart Contactless Thermometer with Polynomial Regression Model
Body temperature is an important measure of a person's health. It is used to diagnose a variety of disorders. Core temperature measurement takes some time and puts patients under strain. To measure temperature in real-time and without contact. We proposed a contactless thermometer that can be calibrated by deriving the ambient and body temperatures from thermometer readings. We analyze this accuracy using second-order polynomial linear regression. After getting the actual body temperature of 124 subjects, we achieved 99% prediction temperature accuracy and linearity with gold standard reference temperature sensors. Additionally, the application has been developed to save the readings. This application can be connected through either OTG or Bluetooth depending on the user's preference. They will have the option to save multiple people's temperature data in separate excel sheets. Following that, the user can access the data and share the link to the data using any of the shareable platforms.