Mohammad Noroozi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammad Noroozi has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Ankit Shah
Indiana University, Bloomington, IN, USA
3 shared publications - Guillermo Vazquez
Department of Materials Science and Engineering Texas A&M University College Station 77843 TX USA
2 shared publications - Ibrahim Karaman
Department of Materials Science and Engineering, Texas A&M University, College Station, TX 77843, USA
2 shared publications - Mahdiyeh Eslami
Department of Electrical Engineering, Ke.C., Islamic Azad University, Kerman, Iran
2 shared publications - Raymundo Arróyave
Department of Materials Science and Engineering, Texas A&M University, College Station, TX 77843, USA
2 shared publications - Sina Hossein Zadeh
Materials Science and Engineering Department, Texas A&M University, College Station, USA
2 shared publications
Latest Publications
- Open Access
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 127119-127131
Toward Optimal Defect Detection in Assembled Printed Circuit Boards Under Adverse Conditions
Defects in the printed circuit board assembly significantly impact product functionality and quality. Automated optical inspection (AOI) systems, employed by manufacturing quality control teams, are designed to accurately detect these defects in a timely manner, thereby reducing the underkill (false negatives) and overkill (false positives) rates. An AOI system requires optimal settings for resolution, brightness, camera angle, and data variety to ensure effective defect detection. However, consistently achieving these ideal conditions in a manufacturing environment presents challenges. Our proposed framework enhances defect detection through data preparation and detection modules, effectively addressing these manufacturing challenges. We developed one- and two-stage object detectors and assessed their performance using precision, recall, and intersection over union metrics. Our framework employs a diverse range of augmentation techniques to effectively train the defect detectors, enabling the expansion of a limited data set. The trained detectors are evaluated using real-world data. We assessed quality control plans across various confidence thresholds. At a 65% confidence threshold, one-stage detector models did not exhibit any false negatives and had minimal false positives. The You Only Learn One Representation (YOLOR) model outperformed both one-stage and two-stage detectors, achieving 100% precision and recall, a 96% mIoU, and an impressive inference time of 11 ms, making it an ideal choice for high-production printed circuit board assembly lines.
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 127119-127131
Open AccessToward Optimal Defect Detection in Assembled Printed Circuit Boards Under Adverse Conditions
Defects in the printed circuit board assembly significantly impact product functionality and quality. Automated optical inspection (AOI) systems, employed by manufacturing quality control teams, are designed to accurately detect these defects in a timely manner, thereby reducing the underkill (false negatives) and overkill (false positives) rates. An AOI system requires optimal settings for resolution, brightness, camera angle, and data variety to ensure effective defect detection. However, consistently achieving these ideal conditions in a manufacturing environment presents challenges. Our proposed framework enhances defect detection through data preparation and detection modules, effectively addressing these manufacturing challenges. We developed one- and two-stage object detectors and assessed their performance using precision, recall, and intersection over union metrics. Our framework employs a diverse range of augmentation techniques to effectively train the defect detectors, enabling the expansion of a limited data set. The trained detectors are evaluated using real-world data. We assessed quality control plans across various confidence thresholds. At a 65% confidence threshold, one-stage detector models did not exhibit any false negatives and had minimal false positives. The You Only Learn One Representation (YOLOR) model outperformed both one-stage and two-stage detectors, achieving 100% precision and recall, a 96% mIoU, and an impressive inference time of 11 ms, making it an ideal choice for high-production printed circuit board assembly lines.
- 27 April 2023
- Published by Elsevier in Computational Materials Science
- Vol. 226, 112225
An interpretable boosting-based predictive model for transformation temperatures of shape memory alloys
- 27 April 2023
- Published by Elsevier in Computational Materials Science
- Vol. 226, 112225
An interpretable boosting-based predictive model for transformation temperatures of shape memory alloys
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 8 (6) , 3572-3592
An AI-Assisted Systematic Literature Review of the Impact of Vehicle Automation on Energy Consumption
Impacts of vehicle automation and connectivity have been studied widely from the perspectives of fuel economy, ecology, and safety. Synthesis of various segments of this literature through review papers has also been presented. However, a systematic review is needed for the growing body of recent literature examining how energy consumption of automated vehicles is influenced by the advancements in powertrain operation and planning/control of driving patterns in different traffic conditions. To address this need, we have first developed an AI-based methodology to effectively find the most relevant papers from a very high volume of related literature. The methodology, comprising natural language processing and machine learning models with humans in the loop, has two phases: search query refinement and relevancy determination. The former ensures that almost all the potentially relevant papers are identified. The latter seeks to automatically eliminate (most) irrelevant papers. Application of our method reduced several thousands of papers from an initial step to 430 potentially relevant papers. Manual review of these papers further characterized many as irrelevant resulting in the final pool of 172 papers. We organized these papers based on various means of influencing power consumption, which are powertrain control, platooning, car-following, intersection management, speed planning, traffic control, lane changing, and on-ramp merging. Synthesis of the papers reveals that the existing studies vary greatly in their design, implementation, and comparison baselines, and thus offer widely differing predictions. Hence, more application specific and comprehensive studies are required to appropriately benchmark energy consumption impact of vehicle automation.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 8 (6) , 3572-3592
An AI-Assisted Systematic Literature Review of the Impact of Vehicle Automation on Energy Consumption
Impacts of vehicle automation and connectivity have been studied widely from the perspectives of fuel economy, ecology, and safety. Synthesis of various segments of this literature through review papers has also been presented. However, a systematic review is needed for the growing body of recent literature examining how energy consumption of automated vehicles is influenced by the advancements in powertrain operation and planning/control of driving patterns in different traffic conditions. To address this need, we have first developed an AI-based methodology to effectively find the most relevant papers from a very high volume of related literature. The methodology, comprising natural language processing and machine learning models with humans in the loop, has two phases: search query refinement and relevancy determination. The former ensures that almost all the potentially relevant papers are identified. The latter seeks to automatically eliminate (most) irrelevant papers. Application of our method reduced several thousands of papers from an initial step to 430 potentially relevant papers. Manual review of these papers further characterized many as irrelevant resulting in the final pool of 172 papers. We organized these papers based on various means of influencing power consumption, which are powertrain control, platooning, car-following, intersection management, speed planning, traffic control, lane changing, and on-ramp merging. Synthesis of the papers reveals that the existing studies vary greatly in their design, implementation, and comparison baselines, and thus offer widely differing predictions. Hence, more application specific and comprehensive studies are required to appropriately benchmark energy consumption impact of vehicle automation.
- Open Access
- 6 February 2023
- Published by MDPI AG in Preprints.org
An Interpretable Boosting-based Predictive Model for Transformation Temperatures of Shape Memory Alloys
In this study, we demonstrate how the incorporation of appropriate feature engineering together with the selection of a Machine Learning (ML) algorithm that best suits the available dataset, leads to the development of a predictive model for transformation temperatures that can be applied to a wide range of shape memory alloys. We develop a gradient boosting ML surrogate model capable of predicting Martensite Start, Martensite Finish, Austenite Start, and Austenite Finish transformation temperatures with an average accuracy of more than 95% by explicitly taking care of potential distribution changes when modeling different alloy systems. We included heat treatment, rolling, extrusion processing parameters, and alloy system categorical features in the model input features to achieve more accurate and realistic results. In addition, using Shapley values, which are calculated based on the average marginal contribution of features to all possible coalitions, this study was able to gain insights into the governing features and their effect on predicted transformation temperatures, providing a unique opportunity to examine the critical parameters and features in martensite transformation temperatures.
- 6 February 2023
- Published by MDPI AG in Preprints.org
Open AccessAn Interpretable Boosting-based Predictive Model for Transformation Temperatures of Shape Memory Alloys
In this study, we demonstrate how the incorporation of appropriate feature engineering together with the selection of a Machine Learning (ML) algorithm that best suits the available dataset, leads to the development of a predictive model for transformation temperatures that can be applied to a wide range of shape memory alloys. We develop a gradient boosting ML surrogate model capable of predicting Martensite Start, Martensite Finish, Austenite Start, and Austenite Finish transformation temperatures with an average accuracy of more than 95% by explicitly taking care of potential distribution changes when modeling different alloy systems. We included heat treatment, rolling, extrusion processing parameters, and alloy system categorical features in the model input features to achieve more accurate and realistic results. In addition, using Shapley values, which are calculated based on the average marginal contribution of features to all possible coalitions, this study was able to gain insights into the governing features and their effect on predicted transformation temperatures, providing a unique opportunity to examine the critical parameters and features in martensite transformation temperatures.
- Open Access
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 110181-110194
Modified Salp Swarm Optimization for Parameter Estimation of Solar PV Models
The identification of parameters in solar cell models is still a major challenge in photovoltaic (PV) system simulation and design. Because of its more basic ideas, efficiency, adaptability, swarm and evolutionary optimization algorithms, as well as simple procedural frameworks, have been generally used in industry with real-world problems. However, due to the nonlinearity and complication of the PV parameter identification, the obtained solutions from swarm and evolutionary optimizers were immature. An efficient metaheuristic approach for identifying PV model parameters based on the salp swarm algorithm (SSA) is presented in this paper. In the suggested modified salp swarm optimization (MSSA), the leaders and followers will be updated based on the new formulas. The algorithm’s exploration potential is increased by this modification while also preventing it from converge prematurely. The behavior of the suggested technique is verified using benchmark functions, and the outcomes are contrasted with those of SSA and other successful optimization approaches. The suggested MSSA detects numerous characteristics in the PV model include single diode, double diode, and PV modules, in the most efficient way possible. According to the simulation results, MSSA outperforms the competition and may produce better optimal solutions. The findings demonstrate that the best value of RMSE obtained by MSSA is up to 69 percent lower than other methods and is nearly 5.6 percent lower than that assessed by SSA.
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 110181-110194
Open AccessModified Salp Swarm Optimization for Parameter Estimation of Solar PV Models
The identification of parameters in solar cell models is still a major challenge in photovoltaic (PV) system simulation and design. Because of its more basic ideas, efficiency, adaptability, swarm and evolutionary optimization algorithms, as well as simple procedural frameworks, have been generally used in industry with real-world problems. However, due to the nonlinearity and complication of the PV parameter identification, the obtained solutions from swarm and evolutionary optimizers were immature. An efficient metaheuristic approach for identifying PV model parameters based on the salp swarm algorithm (SSA) is presented in this paper. In the suggested modified salp swarm optimization (MSSA), the leaders and followers will be updated based on the new formulas. The algorithm’s exploration potential is increased by this modification while also preventing it from converge prematurely. The behavior of the suggested technique is verified using benchmark functions, and the outcomes are contrasted with those of SSA and other successful optimization approaches. The suggested MSSA detects numerous characteristics in the PV model include single diode, double diode, and PV modules, in the most efficient way possible. According to the simulation results, MSSA outperforms the competition and may produce better optimal solutions. The findings demonstrate that the best value of RMSE obtained by MSSA is up to 69 percent lower than other methods and is nearly 5.6 percent lower than that assessed by SSA.
- 20 September 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Towards optimal foreign object debris detection in an airport environment
- 20 September 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Towards optimal foreign object debris detection in an airport environment
- Top Cited PapersOpen Access
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 37515-37532
Golden Search Optimization Algorithm
This study introduces an effective population-based optimization algorithm, namely the Golden Search Optimization Algorithm (GSO), for numerical function optimization. The new algorithm has a simple but effective strategy for solving complex problems. GSO starts with random possible solutions called objects, which interact with each other based on a simple mathematical model to reach the global optimum. To provide a fine balance between the explorative and exploitative behavior of a search, the proposed method utilizes a transfer operator in the adaptive step size adjustment scheme. The proposed algorithm is benchmarked with 23 unimodal, multimodal, and fixed dimensional functions and the results are verified by a comparative study with the well-known Gravitational Search Algorithm (GSA), Sine-Cosine Algorithm (SCA), Grey Wolf Optimization (GWO), and Tunicate Swarm Algorithm (TSA). In addition, the nonparametric Wilcoxon’s rank sum test is performed to measure the pair-wise statistical performance of the GSO and provide a valid judgment about the performance of the algorithm. The simulation results demonstrate that GSO is superior and could generate better optimal solutions when compared with other competitive algorithms.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 37515-37532
Top Cited PapersOpen AccessGolden Search Optimization Algorithm
This study introduces an effective population-based optimization algorithm, namely the Golden Search Optimization Algorithm (GSO), for numerical function optimization. The new algorithm has a simple but effective strategy for solving complex problems. GSO starts with random possible solutions called objects, which interact with each other based on a simple mathematical model to reach the global optimum. To provide a fine balance between the explorative and exploitative behavior of a search, the proposed method utilizes a transfer operator in the adaptive step size adjustment scheme. The proposed algorithm is benchmarked with 23 unimodal, multimodal, and fixed dimensional functions and the results are verified by a comparative study with the well-known Gravitational Search Algorithm (GSA), Sine-Cosine Algorithm (SCA), Grey Wolf Optimization (GWO), and Tunicate Swarm Algorithm (TSA). In addition, the nonparametric Wilcoxon’s rank sum test is performed to measure the pair-wise statistical performance of the GSO and provide a valid judgment about the performance of the algorithm. The simulation results demonstrate that GSO is superior and could generate better optimal solutions when compared with other competitive algorithms.