Ali Shokoufandeh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ali Shokoufandeh has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Schwartz
Drexel University
8 shared publications - Yusuf Osmanlıoğlu
Drexel University
7 shared publications - Dario D. Salvucci
Drexel University
5 shared publications - Genevieve Dion
Drexel University
5 shared publications - Richard Vallett
Drexel University 3141 Chestnut Street Philadelphia 19104 PA
4 shared publications Bahareh Shakibajahromi
Department of Computer Science, Drexel University, Philadelphia, PA 19105, USA
2 shared publications
Latest Publications
- Open Access
- 29 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (4) , 1-25
Resource-Efficient Gesture Recognition through Convexified Attention EICS006
Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00% accuracy on tap gestures and 100.00% on swipe gestures—consistent across 10-fold cross-validation and held-out test evaluation—while requiring only 120–360 parameters, a 97% reduction compared to conventional approaches. With sub-millisecond inference times (290–296 μ s) and minimal storage requirements (< 7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.
- 29 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (4) , 1-25
Open AccessResource-Efficient Gesture Recognition through Convexified Attention EICS006
Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00% accuracy on tap gestures and 100.00% on swipe gestures—consistent across 10-fold cross-validation and held-out test evaluation—while requiring only 120–360 parameters, a 97% reduction compared to conventional approaches. With sub-millisecond inference times (290–296 μ s) and minimal storage requirements (< 7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.
- Open Access
Resource-Efficient Gesture Recognition through Convexified Attention
Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00\% accuracy on tap gestures and 100.00\% on swipe gestures -- consistent across 10-fold cross-validation and held-out test evaluation -- while requiring only 120--360 parameters, a 97\% reduction compared to conventional approaches. With sub-millisecond inference times (290--296$μ$s) and minimal storage requirements ($<$7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.
Open AccessResource-Efficient Gesture Recognition through Convexified Attention
Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00\% accuracy on tap gestures and 100.00\% on swipe gestures -- consistent across 10-fold cross-validation and held-out test evaluation -- while requiring only 120--360 parameters, a 97\% reduction compared to conventional approaches. With sub-millisecond inference times (290--296$μ$s) and minimal storage requirements ($<$7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.
- Open Access
- 1 December 2025
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 1 (1) , 015009
Enhanced iCVD reactor optimization through convexified attention networks: improving liquid repellency in fluoropolymers
Initiated chemical vapor deposition (iCVD) reactors offer a versatile, solvent-free platform for the precise fabrication of ultrathin polymer coatings through surface-initiated polymerization. Our previous work demonstrated that Convexified Convolutional Neural Networks (CCNNs) effectively model and optimize iCVD reactor parameters to maximize liquid repellency in fluoropolymers. However, standard CCNNs lack adaptive feature prioritization, limiting their performance on sparse industrial datasets. This paper introduces CCNNs with Convexified Attention Mechanism (CCNNCA), which dynamically weights input features while preserving convexity guarantees. Using the same dataset of 49 experimental batches from our AIChE Journal publication, CCNNCA achieves significantly improved prediction accuracy (R2 = 0.95) compared to previous CNN (R2 = 0.83–0.89) and CCNN (R2 = 0.92) models. The framework identifies promising process conditions that are predicted to enhance liquid repellency, with a 75.4% reduction in prediction error compared to prior methods. Through visualized attention weights, the model provides interpretable feature importance, revealing the critical roles of initiator flow rate and reactor temperature. This methodological advancement offers a more accurate predictive framework to guide future experimental optimization in data-limited, experiment-intensive engineering applications.
- 1 December 2025
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 1 (1) , 015009
Open AccessEnhanced iCVD reactor optimization through convexified attention networks: improving liquid repellency in fluoropolymers
Initiated chemical vapor deposition (iCVD) reactors offer a versatile, solvent-free platform for the precise fabrication of ultrathin polymer coatings through surface-initiated polymerization. Our previous work demonstrated that Convexified Convolutional Neural Networks (CCNNs) effectively model and optimize iCVD reactor parameters to maximize liquid repellency in fluoropolymers. However, standard CCNNs lack adaptive feature prioritization, limiting their performance on sparse industrial datasets. This paper introduces CCNNs with Convexified Attention Mechanism (CCNNCA), which dynamically weights input features while preserving convexity guarantees. Using the same dataset of 49 experimental batches from our AIChE Journal publication, CCNNCA achieves significantly improved prediction accuracy (R2 = 0.95) compared to previous CNN (R2 = 0.83–0.89) and CCNN (R2 = 0.92) models. The framework identifies promising process conditions that are predicted to enhance liquid repellency, with a 75.4% reduction in prediction error compared to prior methods. Through visualized attention weights, the model provides interpretable feature importance, revealing the critical roles of initiator flow rate and reactor temperature. This methodological advancement offers a more accurate predictive framework to guide future experimental optimization in data-limited, experiment-intensive engineering applications.
- Open Access
- 9 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Minimalist Neural Networks for Gesture Recognition on Wearable Capacitive Touch Textiles With Comparative User Study
- 9 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessMinimalist Neural Networks for Gesture Recognition on Wearable Capacitive Touch Textiles With Comparative User Study
- 1 September 2025
- Published by Springer Nature
- p. 46-59
A Minimal Neural Network for Reproducible Gesture Recognition on Knitted Capacitive Touch Sensors
- 1 September 2025
- Published by Springer Nature
- p. 46-59
A Minimal Neural Network for Reproducible Gesture Recognition on Knitted Capacitive Touch Sensors
- 10 May 2025
- Published by Springer Nature
- p. 32-46
Efficient Combinatorial Alignment for Improved Graph Generation Using GraphVAEs
- 10 May 2025
- Published by Springer Nature
- p. 32-46
Efficient Combinatorial Alignment for Improved Graph Generation Using GraphVAEs
- 3 February 2025
- Published by Drexel University Libraries
Scalable and interpretable deep learning via convex architectures and bio-inspired strategies
Deep learning has achieved remarkable success across numerous domains, yet persistent challenges in robustness, interpretability, and computational efficiency limit its application in high-stakes environments. This dissertation addresses these challenges by introducing a comprehensive framework that integrates bio-inspired neural architectures, convex optimization principles, and sparse representations to enhance both the theoretical foundations and practical applications of deep learning systems. The work begins by investigating bio-inspired neural models that leverage sparsity as a core principle to enhance computational efficiency and interpretability. Building on this foundation, a convexified neural network is introduced as a surrogate model for process optimization tasks, demonstrating its ability to solve complex problems through a simplified closed-form solution while incorporating domain-specific constraints, such as operational feasibility and physical parameter limits, to ensure robust and optimized outcomes. This foundation enables the development of a novel convex attention mechanism, which dynamically weights input features to improve learning focus and resource allocation, and a convex capsule network, which advances spatial hierarchical learning by capturing complex feature relationships while maintaining robustness and interpretability. Through comparative evaluations in wearable gesture recognition and industrial optimization tasks, these convexified frameworks consistently demonstrate superior performance over traditional neural networks. Key results include faster convergence, enhanced robustness to input variability, and improved interpretability, with measurable benefits such as reduced computation time and increased predictive accuracy. By addressing critical challenges in deep learning, this dissertation highlights the transformative potential of convex optimization-based approaches, offering a robust foundation for scalable, interpretable, and reliable machine learning solutions.
- 3 February 2025
- Published by Drexel University Libraries
Scalable and interpretable deep learning via convex architectures and bio-inspired strategies
Deep learning has achieved remarkable success across numerous domains, yet persistent challenges in robustness, interpretability, and computational efficiency limit its application in high-stakes environments. This dissertation addresses these challenges by introducing a comprehensive framework that integrates bio-inspired neural architectures, convex optimization principles, and sparse representations to enhance both the theoretical foundations and practical applications of deep learning systems. The work begins by investigating bio-inspired neural models that leverage sparsity as a core principle to enhance computational efficiency and interpretability. Building on this foundation, a convexified neural network is introduced as a surrogate model for process optimization tasks, demonstrating its ability to solve complex problems through a simplified closed-form solution while incorporating domain-specific constraints, such as operational feasibility and physical parameter limits, to ensure robust and optimized outcomes. This foundation enables the development of a novel convex attention mechanism, which dynamically weights input features to improve learning focus and resource allocation, and a convex capsule network, which advances spatial hierarchical learning by capturing complex feature relationships while maintaining robustness and interpretability. Through comparative evaluations in wearable gesture recognition and industrial optimization tasks, these convexified frameworks consistently demonstrate superior performance over traditional neural networks. Key results include faster convergence, enhanced robustness to input variability, and improved interpretability, with measurable benefits such as reduced computation time and increased predictive accuracy. By addressing critical challenges in deep learning, this dissertation highlights the transformative potential of convex optimization-based approaches, offering a robust foundation for scalable, interpretable, and reliable machine learning solutions.
- 24 October 2024
- Published by Drexel University Libraries
Exploiting graphical structures of data and neural network architectures
The goal of this dissertation is to demonstrate the computational advantages gained by exploiting the graphical structures implicit in data, as well as the graph-theoretical underpinnings of computational architectures such as neural networks. A new computational architecture, Ortus, that uses a graph-based model to process structured data is introduced, which can be thought of as an approximation to a biologically-grounded Boltzmann machine. Next, sparse super-regular networks are developed to show the applicability of using sparse architectural network design toward solving real-world problems. Then, probabilistic hybrid graph convolutional networks show the practical applications of leveraging the inherent structural interdependencies within data by using hybrid neural network architectures. Within these networks, subnetworks are geared to extract particular types of relationships, similar to how Ortus routes specific types of information through predetermined channels. Finally, the benefits of merging structural sparsity with structured information processing are demonstrated by substituting super-regular network layers in place of fully-connected layers within the probabilistic hybrid architectures.
- 24 October 2024
- Published by Drexel University Libraries
Exploiting graphical structures of data and neural network architectures
The goal of this dissertation is to demonstrate the computational advantages gained by exploiting the graphical structures implicit in data, as well as the graph-theoretical underpinnings of computational architectures such as neural networks. A new computational architecture, Ortus, that uses a graph-based model to process structured data is introduced, which can be thought of as an approximation to a biologically-grounded Boltzmann machine. Next, sparse super-regular networks are developed to show the applicability of using sparse architectural network design toward solving real-world problems. Then, probabilistic hybrid graph convolutional networks show the practical applications of leveraging the inherent structural interdependencies within data by using hybrid neural network architectures. Within these networks, subnetworks are geared to extract particular types of relationships, similar to how Ortus routes specific types of information through predetermined channels. Finally, the benefits of merging structural sparsity with structured information processing are demonstrated by substituting super-regular network layers in place of fully-connected layers within the probabilistic hybrid architectures.
- 19 August 2022
- Published by Drexel University Libraries
Problems in extremal and combinatorial geometry
This thesis deals with three families of optimization problems: (1) Euclidean optimization problems on random point sets; (2) independent sets in hypergraphs; and (3) packings in point lattices. First, we consider bounds on several monochromatic and bichromatic optimization problems including minimum matching, minimum spanning trees, and the travelling salesman problem. Many of these problems lend themselves to representations in terms of hierarchically separated trees - trees with uniform branching factor and depth, and having edge weights exponential in the depth of the edge in the tree. In the second part, we consider the independent set problem on uniform hypergraphs, in anticipation of applying it to the third part, packing problems on point lattices. In these problems we wish to select a subset of points from an n n ::: n grid avoiding particular patterns. We also study several generalizations of these problems that have not been handled previously.
- 19 August 2022
- Published by Drexel University Libraries
Problems in extremal and combinatorial geometry
This thesis deals with three families of optimization problems: (1) Euclidean optimization problems on random point sets; (2) independent sets in hypergraphs; and (3) packings in point lattices. First, we consider bounds on several monochromatic and bichromatic optimization problems including minimum matching, minimum spanning trees, and the travelling salesman problem. Many of these problems lend themselves to representations in terms of hierarchically separated trees - trees with uniform branching factor and depth, and having edge weights exponential in the depth of the edge in the tree. In the second part, we consider the independent set problem on uniform hypergraphs, in anticipation of applying it to the third part, packing problems on point lattices. In these problems we wish to select a subset of points from an n n ::: n grid avoiding particular patterns. We also study several generalizations of these problems that have not been handled previously.