Theodoros Theodoridis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Theodoros Theodoridis has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Guowu Wei
School of Science, Engineering and Environment, University of Salford, Salford M5 4WT, UK
6 shared publications - William Holderbaum
Department of Control Engineering, Manchester Metropolitan University, Manchester, UK
5 shared publications - Gasak Abdul Hussain
School of Science, Engineering and Environment, University of Salford, Salford M5 4WT, UK
2 shared publications - Abraham Goodman
University of Salford, Salford, United Kingdom; Nottingham Trent University, Nottingham, United Kingdom, UK
1 shared publication - Alaa Al-Ibadi
University of Basrah
1 shared publication - Anastasia Vatopoulou
Department of Obstetrics and Gynaecology, Medical School, University of Ioannina, 45500 Ioannina, Greece
1 shared publication
Latest Publications
- Open Access
- 1 July 2026
- Published by MDPI AG in Preprints.org
Surgical Instrument Recognition in Laparoscopic Cholecystectomy Using YOLOv8
The recognition of surgical instruments using Artificial Intelligence (AI) in Minimally Invasive Surgery (MIS) offers significant opportunities for data-driven improvements in surgical training and patient safety, with surgical instrument recognition being a critical component. MIS remains challenging due to complex intraoperative conditions that limit conventional real-time object detection AI algorithms. This paper optimises the state-of-the-art YOLOv8 object detection architecture for surgical instrument recognition and takes a novel approach to deal with imbalance of the dataset. A large-scale dataset of 25 surgical videos, consolidated from CholecTrack20, CholecT50, and Cholec80, underwent custom cleaning and strategic partitioning to address severe class imbalance. A systematic tournament identified YOLOv8l as the best-performing variant of the YOLOv8 versions, achieving Mean Average Precision (mAP)@0.5 of 64.4% on the test set. Despite hyperparameter tuning, the attempt led to overfitting, while the data-balancing strategy, despite a slight reduction in overall mAP@0.5 to 60.4%, the approach significantly improved per-class accuracy, notably doubling performance for the rarely used instruments such as Scissors and Clippers. This study establishes a new performance baseline for surgical instrument recognition using a carefully configured YOLOv8l model, underscoring that data imbalance, rather than architecture, is the primary limitation. Future progress for surgical instrument recognition will hinge on data-centric strategies for robust and clinically reliable models.
- 1 July 2026
- Published by MDPI AG in Preprints.org
Open AccessSurgical Instrument Recognition in Laparoscopic Cholecystectomy Using YOLOv8
The recognition of surgical instruments using Artificial Intelligence (AI) in Minimally Invasive Surgery (MIS) offers significant opportunities for data-driven improvements in surgical training and patient safety, with surgical instrument recognition being a critical component. MIS remains challenging due to complex intraoperative conditions that limit conventional real-time object detection AI algorithms. This paper optimises the state-of-the-art YOLOv8 object detection architecture for surgical instrument recognition and takes a novel approach to deal with imbalance of the dataset. A large-scale dataset of 25 surgical videos, consolidated from CholecTrack20, CholecT50, and Cholec80, underwent custom cleaning and strategic partitioning to address severe class imbalance. A systematic tournament identified YOLOv8l as the best-performing variant of the YOLOv8 versions, achieving Mean Average Precision (mAP)@0.5 of 64.4% on the test set. Despite hyperparameter tuning, the attempt led to overfitting, while the data-balancing strategy, despite a slight reduction in overall mAP@0.5 to 60.4%, the approach significantly improved per-class accuracy, notably doubling performance for the rarely used instruments such as Scissors and Clippers. This study establishes a new performance baseline for surgical instrument recognition using a carefully configured YOLOv8l model, underscoring that data imbalance, rather than architecture, is the primary limitation. Future progress for surgical instrument recognition will hinge on data-centric strategies for robust and clinically reliable models.
- Open Access
- 2 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10673
The Design and Development of a Wearable Cable-Driven Shoulder Exosuit (CDSE) for Multi-DOF Upper Limb Assistance
This study presents the design, development, and experimental validation of a novel cable-driven shoulder exosuit (CDSE) for upper limb rehabilitation and assistance. Unlike existing exoskeletons, which are often bulky, limited in degrees of freedom (DOFs), or impractical for home use, the proposed DSE offers a lightweight (≈2 kg), portable, and wearable solution capable of supporting three shoulder movements: abduction, flexion, and horizontal adduction. The system employs a bioinspired tendon-driven mechanism using Bowden cables, transferring actuation forces from a backpack to the arm, thereby reducing user load and improving comfort. Mathematical models and inverse kinematics were derived to determine cable length variations for targeted motions, while control strategies were implemented using a PID-based approach in MATLAB Simscape-Multibody simulations. The prototype was fabricated in three iterations using PLA, aluminum, and carbon fiber—culminating in a durable and ergonomic final version. Experimental evaluations on a healthy subject demonstrated high accuracy in position tracking (<5% error) and torque profiles consistent with simulation outcomes, validating system robustness. The CDSE successfully supported loads up to 4 kg during rehabilitation tasks, highlighting its potential for clinical and at-home applications. This research contributes to advancing wearable robotics by addressing portability, biomechanical alignment, and multi-DOF functionality in upper limb exosuits.
- 2 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10673
Open AccessThe Design and Development of a Wearable Cable-Driven Shoulder Exosuit (CDSE) for Multi-DOF Upper Limb Assistance
This study presents the design, development, and experimental validation of a novel cable-driven shoulder exosuit (CDSE) for upper limb rehabilitation and assistance. Unlike existing exoskeletons, which are often bulky, limited in degrees of freedom (DOFs), or impractical for home use, the proposed DSE offers a lightweight (≈2 kg), portable, and wearable solution capable of supporting three shoulder movements: abduction, flexion, and horizontal adduction. The system employs a bioinspired tendon-driven mechanism using Bowden cables, transferring actuation forces from a backpack to the arm, thereby reducing user load and improving comfort. Mathematical models and inverse kinematics were derived to determine cable length variations for targeted motions, while control strategies were implemented using a PID-based approach in MATLAB Simscape-Multibody simulations. The prototype was fabricated in three iterations using PLA, aluminum, and carbon fiber—culminating in a durable and ergonomic final version. Experimental evaluations on a healthy subject demonstrated high accuracy in position tracking (<5% error) and torque profiles consistent with simulation outcomes, validating system robustness. The CDSE successfully supported loads up to 4 kg during rehabilitation tasks, highlighting its potential for clinical and at-home applications. This research contributes to advancing wearable robotics by addressing portability, biomechanical alignment, and multi-DOF functionality in upper limb exosuits.
- Open Access
- 12 December 2024
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 13 (24) , 7574
Abstracts of the 16th European Congress of Paediatric and Adolescent Gynaecology †
Objectives of Paediatric and Adolescent Gynaecology (PAG): PAG aims to foster a collaborative environment that bridges knowledge from various disciplines to ensure the highest quality of care for children and adolescents with gynaecological issues. The European Association of PAG and HellenicPAG, like all National PAG Societies, support research and education to advance new insights, improve health outcomes, enhance quality of life, and protect future fertility. Additionally, PAG promotes international cooperation by proposing guidelines for good clinical practice in terms of prevention, diagnosis, procedures, and treatment. Scientific Program and Highlights: The scientific committee curated a comprehensive program featuring renowned experts and researchers from across Europe. Over four days, participants explored a wide range of topics through lectures, panel discussions, case studies, debates, video presentations, and workshops. The conference attracted professionals from various disciplines, including gynaecology, paediatrics, paediatric endocrinology, psychology, plastic surgery, and paediatric surgery. The collaboration between the European Association of Paediatric and Adolescent Gynaecology and the Hellenic Society of Paediatric and Adolescent Gynaecology resulted in a cutting-edge scientific program. World-renowned experts (Appendix A) presented on all aspects of paediatric and adolescent gynaecology, with a particular focus on emerging topics such as abortion, global rights, transgender care, teenage pregnancy, and more. Theme—Individualized Care in an Evolving World: The congress theme aligned perfectly with the evolving landscape of PAG. By presenting high-quality, evidence-based topics, the program aimed to equip the next generation of specialists with the knowledge and skills needed to provide individualized care in a rapidly changing world.
- 12 December 2024
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 13 (24) , 7574
Open AccessAbstracts of the 16th European Congress of Paediatric and Adolescent Gynaecology †
Objectives of Paediatric and Adolescent Gynaecology (PAG): PAG aims to foster a collaborative environment that bridges knowledge from various disciplines to ensure the highest quality of care for children and adolescents with gynaecological issues. The European Association of PAG and HellenicPAG, like all National PAG Societies, support research and education to advance new insights, improve health outcomes, enhance quality of life, and protect future fertility. Additionally, PAG promotes international cooperation by proposing guidelines for good clinical practice in terms of prevention, diagnosis, procedures, and treatment. Scientific Program and Highlights: The scientific committee curated a comprehensive program featuring renowned experts and researchers from across Europe. Over four days, participants explored a wide range of topics through lectures, panel discussions, case studies, debates, video presentations, and workshops. The conference attracted professionals from various disciplines, including gynaecology, paediatrics, paediatric endocrinology, psychology, plastic surgery, and paediatric surgery. The collaboration between the European Association of Paediatric and Adolescent Gynaecology and the Hellenic Society of Paediatric and Adolescent Gynaecology resulted in a cutting-edge scientific program. World-renowned experts (Appendix A) presented on all aspects of paediatric and adolescent gynaecology, with a particular focus on emerging topics such as abortion, global rights, transgender care, teenage pregnancy, and more. Theme—Individualized Care in an Evolving World: The congress theme aligned perfectly with the evolving landscape of PAG. By presenting high-quality, evidence-based topics, the program aimed to equip the next generation of specialists with the knowledge and skills needed to provide individualized care in a rapidly changing world.
- Open Access
- 30 September 2024
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 8 (5) , 216
A Statistical Analysis of Commercial Articulated Industrial Robots and Cobots
This paper aims to elucidate the state-of-the-art, prevailing priorities, and the focus of the industry, and identify both limitations and potential gaps regarding industrial robots and collaborative robots (cobots). Additionally, it outlines the advantages and disadvantages of cobots compared to traditional industrial robots. Furthermore, three novel factors are introduced in this survey as metrics to evaluate the efficiency and performance of industrial robots and cobots. To achieve these purposes, a statistical analysis and review of commercial articulated industrial robots and cobots are conducted based on their documented specifications, such as maximum payload, weight, reach, repeatability, average maximum angular speed, and degrees of freedom (DOF). Additionally, the statistical distributions of the efficiency factors are investigated to develop a systematic method for robot selection. Finally, specifications exhibiting strong correlations are compared in pairs using regressions to find out trends and relations between them, within each company and across them all. The investigation of the distribution of specifications demonstrates that the focus of the industry and robot makers is mostly on articulated industrial robots and cobots with higher reach, lower payload capacity, lower weight, better repeatability, lower angular speed, and six degrees of freedom. The regressions reveal that the weight of robots increases exponentially as the reach increases, primarily due to the added weight and torque resulting from the extended reach. They also indicate that the angular speed of robots linearly decreases with increasing reach, as robot manufacturers intentionally reduce the angular speed through reductive gearboxes to compensate for the additional torque required as the reach extends. The trends obtained from the regressions explain the reasons behind these interrelationships, the design purpose of robot makers, and the limitations of industrial robots and cobots. Additionally, they help industries predict the dependent specifications of articulated robots based on the specifications they require. Moreover, an accompanying program has been developed and uploaded on to GitHub, taking the required specifications and returning a list of proper and efficient robots sourced from different companies according to the aforementioned selection method.
- 30 September 2024
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 8 (5) , 216
Open AccessA Statistical Analysis of Commercial Articulated Industrial Robots and Cobots
This paper aims to elucidate the state-of-the-art, prevailing priorities, and the focus of the industry, and identify both limitations and potential gaps regarding industrial robots and collaborative robots (cobots). Additionally, it outlines the advantages and disadvantages of cobots compared to traditional industrial robots. Furthermore, three novel factors are introduced in this survey as metrics to evaluate the efficiency and performance of industrial robots and cobots. To achieve these purposes, a statistical analysis and review of commercial articulated industrial robots and cobots are conducted based on their documented specifications, such as maximum payload, weight, reach, repeatability, average maximum angular speed, and degrees of freedom (DOF). Additionally, the statistical distributions of the efficiency factors are investigated to develop a systematic method for robot selection. Finally, specifications exhibiting strong correlations are compared in pairs using regressions to find out trends and relations between them, within each company and across them all. The investigation of the distribution of specifications demonstrates that the focus of the industry and robot makers is mostly on articulated industrial robots and cobots with higher reach, lower payload capacity, lower weight, better repeatability, lower angular speed, and six degrees of freedom. The regressions reveal that the weight of robots increases exponentially as the reach increases, primarily due to the added weight and torque resulting from the extended reach. They also indicate that the angular speed of robots linearly decreases with increasing reach, as robot manufacturers intentionally reduce the angular speed through reductive gearboxes to compensate for the additional torque required as the reach extends. The trends obtained from the regressions explain the reasons behind these interrelationships, the design purpose of robot makers, and the limitations of industrial robots and cobots. Additionally, they help industries predict the dependent specifications of articulated robots based on the specifications they require. Moreover, an accompanying program has been developed and uploaded on to GitHub, taking the required specifications and returning a list of proper and efficient robots sourced from different companies according to the aforementioned selection method.
- Open Access
Enhancing Gearbox Fault Diagnosis through Advanced Feature Engineering and Data Segmentation Techniques
Efficient gearbox fault diagnosis is crucial for the cost-effective maintenance and reliable operation of rotating machinery. Despite extensive research, effective fault diagnosis remains challenging due to the multitude of features available for classification. Traditional feature selection methods often fail to achieve optimal performance in fault classification tasks. This study introduces diverse ranking methods for selecting the relevant features and utilizes data segmentation techniques such as sliding, windowing, and bootstrapping to strengthen predictive model performance and scalability. A comparative analysis of these methods was conducted to identify the potential causes and future solutions. An evaluation of the impact of enhanced feature engineering and data segmentation on predictive maintenance in gearboxes revealed promising outcomes, with decision trees, SVM, and KNN models outperforming others. Additionally, within a fully connected network, windowing emerged as a more robust and efficient segmentation method compared to bootstrapping. Further research is necessary to assess the performance of these techniques across diverse datasets and applications, offering comprehensive insights for future studies in fault diagnosis and predictive maintenance.
Open AccessEnhancing Gearbox Fault Diagnosis through Advanced Feature Engineering and Data Segmentation Techniques
Efficient gearbox fault diagnosis is crucial for the cost-effective maintenance and reliable operation of rotating machinery. Despite extensive research, effective fault diagnosis remains challenging due to the multitude of features available for classification. Traditional feature selection methods often fail to achieve optimal performance in fault classification tasks. This study introduces diverse ranking methods for selecting the relevant features and utilizes data segmentation techniques such as sliding, windowing, and bootstrapping to strengthen predictive model performance and scalability. A comparative analysis of these methods was conducted to identify the potential causes and future solutions. An evaluation of the impact of enhanced feature engineering and data segmentation on predictive maintenance in gearboxes revealed promising outcomes, with decision trees, SVM, and KNN models outperforming others. Additionally, within a fully connected network, windowing emerged as a more robust and efficient segmentation method compared to bootstrapping. Further research is necessary to assess the performance of these techniques across diverse datasets and applications, offering comprehensive insights for future studies in fault diagnosis and predictive maintenance.
- Open Access
Modified Nonlinear Hysteresis Approach for a Tactile Sensor
Soft tactile sensors based on piezoresistive materials have large-area sensing applications. However, their accuracy is often affected by hysteresis which poses a significant challenge during operation. This paper introduces a novel approach that employs a backpropagation (BP) neural network to address the hysteresis nonlinearity in conductive fiber-based tactile sensors. To assess the effectiveness of the proposed method, four sensor units were designed. These sensor units underwent force sequences to collect corresponding output resistance. A backpropagation network was trained using these sequences, thereby correcting the resistance values. The training process exhibited excellent convergence, effectively adjusting the network’s parameters to minimize the error between predicted and actual resistance values. As a result, the trained BP network accurately predicted the output resistances. Several validation experiments were conducted to highlight the primary contribution of this research. The proposed method reduced the maximum hysteresis error from 24.2% of the sensor’s full-scale output to 13.5%. This improvement established the approach as a promising solution for enhancing the accuracy of soft tactile sensors based on piezoresistive materials. By effectively mitigating hysteresis nonlinearity, the capabilities of soft tactile sensors in various applications can be enhanced. These sensors become more reliable and more efficient tools for the measurement and control of force, particularly in the fields of soft robotics and wearable technology. Consequently, their widespread applications extend to robotics, medical devices, consumer electronics, and gaming. Though the complete elimination of hysteresis in tactile sensors may not be feasible, the proposed method effectively modifies the hysteresis nonlinearity, leading to improved sensor output accuracy.
Open AccessModified Nonlinear Hysteresis Approach for a Tactile Sensor
Soft tactile sensors based on piezoresistive materials have large-area sensing applications. However, their accuracy is often affected by hysteresis which poses a significant challenge during operation. This paper introduces a novel approach that employs a backpropagation (BP) neural network to address the hysteresis nonlinearity in conductive fiber-based tactile sensors. To assess the effectiveness of the proposed method, four sensor units were designed. These sensor units underwent force sequences to collect corresponding output resistance. A backpropagation network was trained using these sequences, thereby correcting the resistance values. The training process exhibited excellent convergence, effectively adjusting the network’s parameters to minimize the error between predicted and actual resistance values. As a result, the trained BP network accurately predicted the output resistances. Several validation experiments were conducted to highlight the primary contribution of this research. The proposed method reduced the maximum hysteresis error from 24.2% of the sensor’s full-scale output to 13.5%. This improvement established the approach as a promising solution for enhancing the accuracy of soft tactile sensors based on piezoresistive materials. By effectively mitigating hysteresis nonlinearity, the capabilities of soft tactile sensors in various applications can be enhanced. These sensors become more reliable and more efficient tools for the measurement and control of force, particularly in the fields of soft robotics and wearable technology. Consequently, their widespread applications extend to robotics, medical devices, consumer electronics, and gaming. Though the complete elimination of hysteresis in tactile sensors may not be feasible, the proposed method effectively modifies the hysteresis nonlinearity, leading to improved sensor output accuracy.
- Open Access
- 21 July 2023
- Published by MDPI AG in Informatics
- Vol. 10 (3) , 63
Finding Good Attribute Subsets for Improved Decision Trees Using a Genetic Algorithm Wrapper; a Supervised Learning Application in the Food Business Sector for Wine Type Classification
This study aims to provide a method that will assist decision makers in managing large datasets, eliminating the decision risk and highlighting significant subsets of data with certain weight. Thus, binary decision tree (BDT) and genetic algorithm (GA) methods are combined using a wrapping technique. The BDT algorithm is used to classify data in a tree structure, while the GA is used to identify the best attribute combinations from a set of possible combinations, referred to as generations. The study seeks to address the problem of overfitting that may occur when classifying large datasets by reducing the number of attributes used in classification. Using the GA, the number of selected attributes is minimized, reducing the risk of overfitting. The algorithm produces many attribute sets that are classified using the BDT algorithm and are assigned a fitness number based on their accuracy. The fittest set of attributes, or chromosomes, as well as the BDTs, are then selected for further analysis. The training process uses the data of a chemical analysis of wines grown in the same region but derived from three different cultivars. The results demonstrate the effectiveness of this innovative approach in defining certain ingredients and weights of wine’s origin.
- 21 July 2023
- Published by MDPI AG in Informatics
- Vol. 10 (3) , 63
Open AccessFinding Good Attribute Subsets for Improved Decision Trees Using a Genetic Algorithm Wrapper; a Supervised Learning Application in the Food Business Sector for Wine Type Classification
This study aims to provide a method that will assist decision makers in managing large datasets, eliminating the decision risk and highlighting significant subsets of data with certain weight. Thus, binary decision tree (BDT) and genetic algorithm (GA) methods are combined using a wrapping technique. The BDT algorithm is used to classify data in a tree structure, while the GA is used to identify the best attribute combinations from a set of possible combinations, referred to as generations. The study seeks to address the problem of overfitting that may occur when classifying large datasets by reducing the number of attributes used in classification. Using the GA, the number of selected attributes is minimized, reducing the risk of overfitting. The algorithm produces many attribute sets that are classified using the BDT algorithm and are assigned a fitness number based on their accuracy. The fittest set of attributes, or chromosomes, as well as the BDTs, are then selected for further analysis. The training process uses the data of a chemical analysis of wines grown in the same region but derived from three different cultivars. The results demonstrate the effectiveness of this innovative approach in defining certain ingredients and weights of wine’s origin.
- Open Access
- 29 June 2023
- Published by MDPI AG in Preprints.org
Modified Nonlinear Hysteresis Approach of a Tactile Sensor
Soft tactile sensors based on piezoresistive materials have various large-area sensing applications. However, their accuracy is often affected by hysteresis, a phenomenon that poses a significant challenge during operation. This paper introduces a novel approach that employs a backpropagation (BP) neural network to address the hysteresis nonlinearity in conductive fibre-based tactile sensors. To assess the effectiveness of the proposed method, four sensor units with different layer configurations (1, 3, 6, and 12) were designed. These sensor units underwent force sequences to collect corresponding output resistances. A backpropagation network was trained using these force sequences, thereby correcting the resistance values. The training process exhibited excellent convergence, effectively adjusting the network's parameters to minimize the error between predicted and actual resistance values. As a result, the trained BP network accurately predicted the output resistances. Several validation experiments were conducted to highlight the primary contribution of this research. The proposed method reduced the maximum hysteresis error from 24.2% of the sensor's full-scale output to 13.5%. This improvement establishes the approach as a promising solution for enhancing the accuracy of soft tactile sensors based on piezoresistive materials. By effectively mitigating hysteresis nonlinearity, the capabilities of soft tactile sensors in various applications can be enhanced. These sensors become more reliable and more efficient tools for force measurement and control, particularly in the fields of soft robotics and wearable technology. Consequently, their widespread applications extend to robotics, medical devices, consumer electronics, and gaming. Notably, the complete elimination of hysteresis in tactile sensors may not be feasible. Nevertheless, the proposed method effectively modifies the hysteresis nonlinearity, leading to improved sensor output accuracy.
- 29 June 2023
- Published by MDPI AG in Preprints.org
Open AccessModified Nonlinear Hysteresis Approach of a Tactile Sensor
Soft tactile sensors based on piezoresistive materials have various large-area sensing applications. However, their accuracy is often affected by hysteresis, a phenomenon that poses a significant challenge during operation. This paper introduces a novel approach that employs a backpropagation (BP) neural network to address the hysteresis nonlinearity in conductive fibre-based tactile sensors. To assess the effectiveness of the proposed method, four sensor units with different layer configurations (1, 3, 6, and 12) were designed. These sensor units underwent force sequences to collect corresponding output resistances. A backpropagation network was trained using these force sequences, thereby correcting the resistance values. The training process exhibited excellent convergence, effectively adjusting the network's parameters to minimize the error between predicted and actual resistance values. As a result, the trained BP network accurately predicted the output resistances. Several validation experiments were conducted to highlight the primary contribution of this research. The proposed method reduced the maximum hysteresis error from 24.2% of the sensor's full-scale output to 13.5%. This improvement establishes the approach as a promising solution for enhancing the accuracy of soft tactile sensors based on piezoresistive materials. By effectively mitigating hysteresis nonlinearity, the capabilities of soft tactile sensors in various applications can be enhanced. These sensors become more reliable and more efficient tools for force measurement and control, particularly in the fields of soft robotics and wearable technology. Consequently, their widespread applications extend to robotics, medical devices, consumer electronics, and gaming. Notably, the complete elimination of hysteresis in tactile sensors may not be feasible. Nevertheless, the proposed method effectively modifies the hysteresis nonlinearity, leading to improved sensor output accuracy.
- Open Access
Optimizing Deep Learning Models For Raspberry Pi
Deep learning models have become increasingly popular for a wide range of applications, including computer vision, natural language processing, and speech recognition. However, these models typically require large amounts of computational resources, making them challenging to run on low-power devices such as the Raspberry Pi. One approach to addressing this challenge is to use pruning techniques to reduce the size of the deep learning models. Pruning involves removing unimportant weights and connections from the model, resulting in a smaller and more efficient model. Pruning can be done during training or after the model has been trained. Another approach is to optimize the deep learning models specifically for the Raspberry Pi architecture. This can include optimizing the model's architecture and parameters to take advantage of the Raspberry Pi's hardware capabilities, such as its CPU and GPU. Additionally, the model can be optimized for energy efficiency by minimizing the amount of computation required. Pruning and optimizing deep learning models for the Raspberry Pi can help overcome the computational and energy constraints of low-power devices, making it possible to run deep learning models on a wider range of devices. In the following sections, we will explore these approaches in more detail and discuss their effectiveness for optimizing deep learning models for the Raspberry Pi.
Open AccessOptimizing Deep Learning Models For Raspberry Pi
Deep learning models have become increasingly popular for a wide range of applications, including computer vision, natural language processing, and speech recognition. However, these models typically require large amounts of computational resources, making them challenging to run on low-power devices such as the Raspberry Pi. One approach to addressing this challenge is to use pruning techniques to reduce the size of the deep learning models. Pruning involves removing unimportant weights and connections from the model, resulting in a smaller and more efficient model. Pruning can be done during training or after the model has been trained. Another approach is to optimize the deep learning models specifically for the Raspberry Pi architecture. This can include optimizing the model's architecture and parameters to take advantage of the Raspberry Pi's hardware capabilities, such as its CPU and GPU. Additionally, the model can be optimized for energy efficiency by minimizing the amount of computation required. Pruning and optimizing deep learning models for the Raspberry Pi can help overcome the computational and energy constraints of low-power devices, making it possible to run deep learning models on a wider range of devices. In the following sections, we will explore these approaches in more detail and discuss their effectiveness for optimizing deep learning models for the Raspberry Pi.
- Open Access
Novel Design and Position Control Strategy of a Soft Robot Arm
This article presents a novel design of a continuum arm, which has the ability to extend and bend efficiently. Numerous designs and experiments have been done to different dimensions on both types of McKibben pneumatic muscle actuators (PMA) in order to study their performances. The contraction and extension behaviour have been illustrated with single contractor actuators and single extensor actuators, respectively. The tensile force for the contractor actuator and the compressive force for the extensor PMA are thoroughly explained and compared. Furthermore, the bending behaviour has been explained for a single extensor PMA, multi extensor actuators and multi contractor actuators. A two-section continuum arm has been implemented from both types of actuators to achieve multiple operations. Then, a novel construction is proposed to achieve efficient bending behaviour of a single contraction PMA. This novel design of a bending-actuator has been used to modify the presented continuum arm. Two different position control strategies are presented, arising from the results of the modified soft robot arm experiment. A cascaded position control is applied to control the position of the end effector of the soft arm at no load by efficiently controlling the pressure of all the actuators in the continuum arm. A new algorithm is then proposed by distributing the x, y and z-axis to the actuators and applying an effective closed-loop position control to the proposed arm at different load conditions.
Open AccessNovel Design and Position Control Strategy of a Soft Robot Arm
This article presents a novel design of a continuum arm, which has the ability to extend and bend efficiently. Numerous designs and experiments have been done to different dimensions on both types of McKibben pneumatic muscle actuators (PMA) in order to study their performances. The contraction and extension behaviour have been illustrated with single contractor actuators and single extensor actuators, respectively. The tensile force for the contractor actuator and the compressive force for the extensor PMA are thoroughly explained and compared. Furthermore, the bending behaviour has been explained for a single extensor PMA, multi extensor actuators and multi contractor actuators. A two-section continuum arm has been implemented from both types of actuators to achieve multiple operations. Then, a novel construction is proposed to achieve efficient bending behaviour of a single contraction PMA. This novel design of a bending-actuator has been used to modify the presented continuum arm. Two different position control strategies are presented, arising from the results of the modified soft robot arm experiment. A cascaded position control is applied to control the position of the end effector of the soft arm at no load by efficiently controlling the pressure of all the actuators in the continuum arm. A new algorithm is then proposed by distributing the x, y and z-axis to the actuators and applying an effective closed-loop position control to the proposed arm at different load conditions.