Saiteja Malisetty
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saiteja Malisetty has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Elham Rastegari
Creighton University, Omaha, USA
3 shared publications - Hesham Ali
Computer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt
3 shared publications - Ka-Chun Siu
Department of Health & Rehabilitation Sciences, College of Allied Health Professions University of Nebraska Medical Center Omaha Nebraska USA
3 shared publications - Bharadwaj Thuraka
School of Computer Science and Information Systems, Northwest Missouri State University, Maryville, MO 64468, USA
2 shared publications - Chandra Shikhi Kodete
Eastern Illinois University,School of Technology,Charleston,IL,USA,61920
2 shared publications - Vikram Pasupuleti
School of Technology, Eastern Illinois University, Charleston, IL 61920, USA
2 shared publications
Latest Publications
- Open Access
Hormonal Influences on Skeletal Muscle Function in Women across Life Stages: A Systematic Review
Skeletal muscle function is vital for locomotion, posture, and metabolism, significantly impacting overall health and preventing falls, morbidity, and mortality, especially in elderly populations. This systematic review investigates the influence of hormonal fluctuations on skeletal muscle function across different life stages in women, including adolescence, the reproductive years, and menopause. A comprehensive literature search was conducted using databases such as PubMed, Scopus, and Web of Science to identify relevant studies. This review includes 45 studies that met the inclusion criteria, examining the roles of estrogen, progesterone, and other hormones in muscle metabolism, strength, and recovery. The findings highlight significant stage-specific hormonal impacts on muscle function, revealing how puberty, menstrual cycles, pregnancy, and menopause uniquely affect muscle health. Effective hormonal and non-hormonal interventions tailored to each life stage were identified, offering insights for optimizing muscle function and health management in women. This synthesis aims to bridge the gaps in understanding the hormonal regulation of muscle function, providing a foundation for future research and guiding clinical practices.
Open AccessHormonal Influences on Skeletal Muscle Function in Women across Life Stages: A Systematic Review
Skeletal muscle function is vital for locomotion, posture, and metabolism, significantly impacting overall health and preventing falls, morbidity, and mortality, especially in elderly populations. This systematic review investigates the influence of hormonal fluctuations on skeletal muscle function across different life stages in women, including adolescence, the reproductive years, and menopause. A comprehensive literature search was conducted using databases such as PubMed, Scopus, and Web of Science to identify relevant studies. This review includes 45 studies that met the inclusion criteria, examining the roles of estrogen, progesterone, and other hormones in muscle metabolism, strength, and recovery. The findings highlight significant stage-specific hormonal impacts on muscle function, revealing how puberty, menstrual cycles, pregnancy, and menopause uniquely affect muscle health. Effective hormonal and non-hormonal interventions tailored to each life stage were identified, offering insights for optimizing muscle function and health management in women. This synthesis aims to bridge the gaps in understanding the hormonal regulation of muscle function, providing a foundation for future research and guiding clinical practices.
- Top Cited PapersOpen Access
Enhancing Supply Chain Agility and Sustainability through Machine Learning: Optimization Techniques for Logistics and Inventory Management
Background: In the current global market, supply chains are increasingly complex, necessitating agile and sustainable management strategies. Traditional analytical methods often fall short in addressing these challenges, creating a need for more advanced approaches. Methods: This study leverages advanced machine learning (ML) techniques to enhance logistics and inventory man-agement. Using historical data from a multinational retail corporation, including sales, inventory levels, order fulfillment rates, and operational costs, we applied a variety of ML algorithms, in-cluding regression, classification, clustering, and time series analysis. Results: The application of these ML models resulted in significant improvements across key operational areas. We achieved a 15% increase in demand forecasting accuracy, a 10% reduction in overstock and stockouts, and a 95% accuracy in predicting order fulfillment timelines. Additionally, the approach identified at-risk shipments and enabled customer segmentation based on delivery preferences, leading to more personalized service offerings. Conclusions: Our evaluation demonstrates the transforma-tive potential of ML in making supply chain operations more responsive and data-driven. The study underscores the importance of adopting advanced technologies to enhance deci-sion-making, evidenced by a 12% improvement in lead time efficiency, a silhouette coefficient of 0.75 for clustering, and an 8% reduction in replenishment errors.
Top Cited PapersOpen AccessEnhancing Supply Chain Agility and Sustainability through Machine Learning: Optimization Techniques for Logistics and Inventory Management
Background: In the current global market, supply chains are increasingly complex, necessitating agile and sustainable management strategies. Traditional analytical methods often fall short in addressing these challenges, creating a need for more advanced approaches. Methods: This study leverages advanced machine learning (ML) techniques to enhance logistics and inventory man-agement. Using historical data from a multinational retail corporation, including sales, inventory levels, order fulfillment rates, and operational costs, we applied a variety of ML algorithms, in-cluding regression, classification, clustering, and time series analysis. Results: The application of these ML models resulted in significant improvements across key operational areas. We achieved a 15% increase in demand forecasting accuracy, a 10% reduction in overstock and stockouts, and a 95% accuracy in predicting order fulfillment timelines. Additionally, the approach identified at-risk shipments and enabled customer segmentation based on delivery preferences, leading to more personalized service offerings. Conclusions: Our evaluation demonstrates the transforma-tive potential of ML in making supply chain operations more responsive and data-driven. The study underscores the importance of adopting advanced technologies to enhance deci-sion-making, evidenced by a 12% improvement in lead time efficiency, a silhouette coefficient of 0.75 for clustering, and an 8% reduction in replenishment errors.
- Open Access
- 18 February 2024
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 13 (4) , 1150
Exploring the Impact of Hand Dominance on Laparoscopic Surgical Skills Development Using Network Models
Background: Laparoscopic surgery demands high precision and skill, necessitating effective training protocols that account for factors such as hand dominance. This study investigates the impact of hand dominance on the acquisition and proficiency of laparoscopic surgical skills, utilizing a novel assessment method that combines Network Models and electromyography (EMG) data. Methods: Eighteen participants, comprising both medical and non-medical students, engaged in laparoscopic simulation tasks, including peg transfer and wire loop tasks. Performance was assessed using Network Models to analyze EMG data, capturing muscle activity and learning progression. The NASA Task Load Index (TLX) was employed to evaluate subjective task demands and workload perceptions. Results: Our analysis revealed significant differences in learning progression and skill proficiency between dominant and non-dominant hands, suggesting the need for tailored training approaches. Network Models effectively identified patterns of skill acquisition, while NASA-TLX scores correlated with participants’ performance and learning progression, highlighting the importance of considering both objective and subjective measures in surgical training. Conclusions: The study underscores the importance of hand dominance in laparoscopic surgical training and suggests that personalized training protocols could enhance surgical precision, efficiency, and patient outcomes. By leveraging advanced analytical techniques, including Network Models and EMG data analysis, this research contributes to optimizing clinical training methodologies, potentially revolutionizing surgical education and improving patient care.
- 18 February 2024
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 13 (4) , 1150
Open AccessExploring the Impact of Hand Dominance on Laparoscopic Surgical Skills Development Using Network Models
Background: Laparoscopic surgery demands high precision and skill, necessitating effective training protocols that account for factors such as hand dominance. This study investigates the impact of hand dominance on the acquisition and proficiency of laparoscopic surgical skills, utilizing a novel assessment method that combines Network Models and electromyography (EMG) data. Methods: Eighteen participants, comprising both medical and non-medical students, engaged in laparoscopic simulation tasks, including peg transfer and wire loop tasks. Performance was assessed using Network Models to analyze EMG data, capturing muscle activity and learning progression. The NASA Task Load Index (TLX) was employed to evaluate subjective task demands and workload perceptions. Results: Our analysis revealed significant differences in learning progression and skill proficiency between dominant and non-dominant hands, suggesting the need for tailored training approaches. Network Models effectively identified patterns of skill acquisition, while NASA-TLX scores correlated with participants’ performance and learning progression, highlighting the importance of considering both objective and subjective measures in surgical training. Conclusions: The study underscores the importance of hand dominance in laparoscopic surgical training and suggests that personalized training protocols could enhance surgical precision, efficiency, and patient outcomes. By leveraging advanced analytical techniques, including Network Models and EMG data analysis, this research contributes to optimizing clinical training methodologies, potentially revolutionizing surgical education and improving patient care.
- Open Access
An Innovative Comparative Analysis Approach for the Assessment of Laparoscopic Surgical Skills
Over the past few decades, surgeon training has changed dramatically. Surgical skills are now taught in a surgical skills laboratory instead of the operating room. Simulation-based training helps medical students improve their skills, but it has not revolutionized clinical education. One critical barrier to reaching such a desired goal is the lack of reliable, robust, and objective methods for assessing the effectiveness of training sessions and the development of students. In this paper, we will develop a new comparative analysis approach that employs network models as the central concept in establishing a new assessment tool for the evaluation of the surgical skills of trainees as well as the training processes. The model is populated using participants electromyography data while performing a simulation task. Furthermore, using NASA Task Load Index score, participants’ subjective overload levels are analyzed to examine the impact of participants’ perception of their mental demand, physical demand, temporal demand, performance, effort, and frustration on how participants perform each simulation task. Obtained results indicate that the proposed approach enables us to extract useful information from the raw data and provides an objective method for assessment the of surgical simulation tasks and how the participants’ perception of task impacts their performance.
Open AccessAn Innovative Comparative Analysis Approach for the Assessment of Laparoscopic Surgical Skills
Over the past few decades, surgeon training has changed dramatically. Surgical skills are now taught in a surgical skills laboratory instead of the operating room. Simulation-based training helps medical students improve their skills, but it has not revolutionized clinical education. One critical barrier to reaching such a desired goal is the lack of reliable, robust, and objective methods for assessing the effectiveness of training sessions and the development of students. In this paper, we will develop a new comparative analysis approach that employs network models as the central concept in establishing a new assessment tool for the evaluation of the surgical skills of trainees as well as the training processes. The model is populated using participants electromyography data while performing a simulation task. Furthermore, using NASA Task Load Index score, participants’ subjective overload levels are analyzed to examine the impact of participants’ perception of their mental demand, physical demand, temporal demand, performance, effort, and frustration on how participants perform each simulation task. Obtained results indicate that the proposed approach enables us to extract useful information from the raw data and provides an objective method for assessment the of surgical simulation tasks and how the participants’ perception of task impacts their performance.
- 27 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Analyzing Walking and Driving Behavior Across Different Age Groups Using Population Analysis and Correlation Networks
Altered mobility patterns are one of the early symptoms of aging. Several motor-related disorders such as Parkinson's disease are also associated with decreased or altered mobility. However, there is no standard clinical test to identify decreased mobility or diagnose movement variations. In recent years, wearable devices have become popular in measuring mobility parameters and quantifying physical activities such as walking and driving. Furthermore, wearable devices have been widely used in the collection and analysis of mobility data because they are small, affordable, and easy to use. The main objective of this research is to develop a data-driven computational model that can analyze mobility data collected from a group of individuals from different age groups and capture potential aging-related movement variabilities. Such a model would also allow computational tools to extract meaningful correlations between age groups and physical activity. In this study, we have analyzed the mobility data collected from 32 healthy adults from different age groups while they are walking outdoors, climbing stairs, and driving. We developed correlation network models and employed a population analysis-based approach to unravel the associations between aging and physical activities; mainly walking and driving. Although our analysis produced interesting results and identified key parameters that impacted the walking and driving patterns, it didn't significantly different between subjects belonging to different age groups, which we believe is mainly due to the limited use dataset in terms of size and variability. However, the proposed model and recommended approach pave the way for future studies that will further explore the relationships between mobility and aging using richer datasets.
- 27 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Analyzing Walking and Driving Behavior Across Different Age Groups Using Population Analysis and Correlation Networks
Altered mobility patterns are one of the early symptoms of aging. Several motor-related disorders such as Parkinson's disease are also associated with decreased or altered mobility. However, there is no standard clinical test to identify decreased mobility or diagnose movement variations. In recent years, wearable devices have become popular in measuring mobility parameters and quantifying physical activities such as walking and driving. Furthermore, wearable devices have been widely used in the collection and analysis of mobility data because they are small, affordable, and easy to use. The main objective of this research is to develop a data-driven computational model that can analyze mobility data collected from a group of individuals from different age groups and capture potential aging-related movement variabilities. Such a model would also allow computational tools to extract meaningful correlations between age groups and physical activity. In this study, we have analyzed the mobility data collected from 32 healthy adults from different age groups while they are walking outdoors, climbing stairs, and driving. We developed correlation network models and employed a population analysis-based approach to unravel the associations between aging and physical activities; mainly walking and driving. Although our analysis produced interesting results and identified key parameters that impacted the walking and driving patterns, it didn't significantly different between subjects belonging to different age groups, which we believe is mainly due to the limited use dataset in terms of size and variability. However, the proposed model and recommended approach pave the way for future studies that will further explore the relationships between mobility and aging using richer datasets.
- 27 June 2022
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 74, 1011-1035
Impact of Imputation Strategies on Fairness in Machine Learning
Research on Fairness and Bias Mitigation in Machine Learning often uses a set of reference datasets for the design and evaluation of novel approaches or definitions. While these datasets are well structured and useful for the comparison of various approaches, they do not reflect that datasets commonly used in real-world applications can have missing values. When such missing values are encountered, the use of imputation strategies is commonplace. However, as imputation strategies potentially alter the distribution of data they can also affect the performance, and potentially the fairness, of the resulting predictions, a topic not yet well understood in the fairness literature. In this article, we investigate the impact of different imputation strategies on classical performance and fairness in classification settings. We find that the selected imputation strategy, along with other factors including the type of classification algorithm, can significantly affect performance and fairness outcomes. The results of our experiments indicate that the choice of imputation strategy is an important factor when considering fairness in Machine Learning. We also provide some insights and guidance for researchers to help navigate imputation approaches for fairness.
- 27 June 2022
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 74, 1011-1035
Impact of Imputation Strategies on Fairness in Machine Learning
Research on Fairness and Bias Mitigation in Machine Learning often uses a set of reference datasets for the design and evaluation of novel approaches or definitions. While these datasets are well structured and useful for the comparison of various approaches, they do not reflect that datasets commonly used in real-world applications can have missing values. When such missing values are encountered, the use of imputation strategies is commonplace. However, as imputation strategies potentially alter the distribution of data they can also affect the performance, and potentially the fairness, of the resulting predictions, a topic not yet well understood in the fairness literature. In this article, we investigate the impact of different imputation strategies on classical performance and fairness in classification settings. We find that the selected imputation strategy, along with other factors including the type of classification algorithm, can significantly affect performance and fairness outcomes. The results of our experiments indicate that the choice of imputation strategy is an important factor when considering fairness in Machine Learning. We also provide some insights and guidance for researchers to help navigate imputation approaches for fairness.