Composite materials are extensively used in aircraft structures, wherein they are subjected to cy... more Composite materials are extensively used in aircraft structures, wherein they are subjected to cyclic loads and subsequently impact-induced damages. Progressive fatigue degradation can lead to catastrophic failure. This highlights the need for an efficient prognostic framework to predict crack propagation in the field of structural health monitoring (SHM) of composite structures to improve functional safety and reliability. However, achieving good accuracy in crack growth prediction is challenging due to uncertainties in the material properties, loading conditions, and environmental factors. This paper presents a particle-filter-based online prognostic framework for damage prognosis of composite laminates due to crack-induced delamination and fiber breakage. An optimized Paris law model is used to describe the damage propagation in glass-fiber-reinforced polymer (GFRP) laminates subject to low-velocity impacts. Our proposed methodology deduces the jump energy/inflection point online...
Composite materials have become extremely important for several engineering applications due to t... more Composite materials have become extremely important for several engineering applications due to their superior mechanical properties. However, a major challenge in the use of composites is to detect, locate and quantify fatigue induced damage, particularly delamination, by using limited experimental data. The use of guided Lamb wave based health monitoring with embedded sensors has emerged as a potential solution to effectively predict delamination size. To do this, machine learning prediction models have been used in the past, however, a transfer learning approach which can address the problem of inadequate labeled data by allowing the use of a pretrained model for predicting damage in a new composite specimen, has not been explored in this field. This paper proposes a temporal convolutional network (TCN) based transfer learning (TCN-trans) scheme for predicting delamination damage using sensor measurements. The application of proposed framework is demonstrated on Lamb wave sensor ...
It is important to be able to accurately predict the evolution of damage in structural components... more It is important to be able to accurately predict the evolution of damage in structural components to evaluate the mechanical reliability of engineering structures. This requires modeling complex mechanisms in damage including crack nucleation and propagation. These pose significant computational challenges to simulation, specifically the singular crack tip field as well as the moving boundary problem inherent in crack propagation. In order to address these problems, many different approaches in computational mechanics have been developed including the cohesive zone method, the extended finite element method and the phase-field method, although all these methods are still relatively expensive in computational effort. In order to reduce the computational burden, reduced order models based on the proper orthogonal decomposition (POD) approach can be used to exploit the spatial correlation to get a set of modes characterizing the spatial structure of the model. For the multidimensional ...
Computational analysis of multi-parametric high-content imaging dataset can be particularly tedio... more Computational analysis of multi-parametric high-content imaging dataset can be particularly tedious and daunting to implement for a laboratory biologist with no bioinformatics expertise and hence, there is an unmet need of software tools to facilitate this type of analysis. We present a web-based application "HCS-PhenoCluster" for the analysis of high-content image-based data which can be used for discovering novel cellular phenotypes beyond visual inspection. This application is interfaced with a single-cell extraction pipeline which performs cell segmentation and multi-feature extraction of high-content imaging data. HCS-PhenoCluster has been implemented in Swift language using Vapor framework and consists of a MySQL database. The image analysis workflow of HCS-PhenoCluster is based on machine learning models implemented in Python and comprises five modules of data processing which include multi-level quality control modules and an unsupervised clustering module to revea...
Analysis of high-content screening (HCS) data mostly relies on supervised machine learning based ... more Analysis of high-content screening (HCS) data mostly relies on supervised machine learning based approaches employing user-defined image features. This strategy has limited applications due to the requirement of a priori knowledge of expected cellular phenotypes / perturbations and the time-consuming process of manually annotating these phenotypes. To address these issues, we propose a machine learning based unsupervised framework for high-content analysis. The framework performs anomaly detection using features transferred from natural images to the cellular images by deep learning models. We applied this framework to detect anomalous effects of FDA approved drugs on human monocytic cells. Drug anomaly detection based on image features derived using three deep learning architectures, DenseNet-121, ResNet-50 and VGG-16, is compared with the anomaly scores computed from user-defined features extracted from individually segmented cells. The drug anomaly scores of automatically extract...
There has been a lack of progress in developing spiking neuron models for pattern classification,... more There has been a lack of progress in developing spiking neuron models for pattern classification, which can achieve similar performance as state-of-the-art. To pursue this goal of creating powerful spike-based classifiers, the role of dendrites in neuronal information processing is considered. The neurobiological evidence for dendritic processing has been established in the last few years by neuroscientists across the globe. However, computational models of spiking neurons in machine learning systems have not utilized this mechanism yet. Our work attempts to bridge this gap and explore the possible computational benefits of passive delay and active ionic dendritic mechanisms. A spike-based model for pattern classification is presented which employs neurons with functionally distinct multicompartment dendritic branches. In this model, synaptic integration involves location-dependent processing of inputs on each dendritic compartment, followed by nonlinear processing of the total synaptic input on a dendrite and finally linear integration of the total dendritic output at the soma. This gives the neuron a capacity to perform a large number of input-output mappings. Firstly, a spiking neuron model is developed based on modifying delays associated with the spikes arriving at an afferent. The application of this model is demonstrated on memorizing spatio-temporal patterns by updating only a few delays corresponding to the most synchronous part of a spike pattern. This model explores the time-based computing approach to design a novel learning algorithm which provides an alternative to the traditional weight-based learning and offers the advantage of simpler hardware implementation without multipliers or digitalanalog converters (DACs). The classification accuracy of the system with a load (number of patterns relative to the number of synapses) of up to 2 was shown to be about 80−100%. In our pursuit of achieving improved performance and a hardware-friendly learning algorithm, a model is further proposed which consists of nonlinear dendrites and is inspired by the mechanism of
The synthesis of glycans and sorting of proteins are critical functions of the Golgi apparatus an... more The synthesis of glycans and sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNAi screening offers opportunities to explore this organelle organisation and the gene network underlying it. To date, image-based Golgi screens were based on a single parameter or supervised analysis with pre-defined Golgi structural classes. Here, we report the use of multi-parametric data extracted from a single marker and a computational unsupervised analysis framework to explore Golgi phenotypic diversity more extensively. In contrast with the 3 visually definable phenotypes, our framework reproducibly identified 10 Golgi phenotypes. They were used to quantify and stratify phenotypic similarities among genetic perturbations. The derived phenotypic network overlaps partially with previously reported protein-protein interactions as well as suggests novel functional interactions. ...
ABSTRACT We present an architecture of a spike based multi-class classifier using neurons with no... more ABSTRACT We present an architecture of a spike based multi-class classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 − 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources.
The development of power-efficient neuromorphic devices presents the challenge of designing spike... more The development of power-efficient neuromorphic devices presents the challenge of designing spike pattern classification algorithms which can be implemented on low-precision hardware and can also achieve state-of-the-art performance. In our pursuit of meeting this challenge, we present a pattern classification model which uses a sparse connection matrix and exploits the mechanism of nonlinear dendritic processing to achieve high classification accuracy. A rate-based structural learning rule for multiclass classification is proposed which modifies a connectivity matrix of binary synaptic connections by choosing the best "k" out of "d" inputs to make connections on every dendritic branch (k < < d). Because learning only modifies connectivity, the model is well suited for implementation in neuromorphic systems using address-event representation (AER). We develop an ensemble method which combines several dendritic classifiers to achieve enhanced generalization ...
Composite materials are extensively used in aircraft structures, wherein they are subjected to cy... more Composite materials are extensively used in aircraft structures, wherein they are subjected to cyclic loads and subsequently impact-induced damages. Progressive fatigue degradation can lead to catastrophic failure. This highlights the need for an efficient prognostic framework to predict crack propagation in the field of structural health monitoring (SHM) of composite structures to improve functional safety and reliability. However, achieving good accuracy in crack growth prediction is challenging due to uncertainties in the material properties, loading conditions, and environmental factors. This paper presents a particle-filter-based online prognostic framework for damage prognosis of composite laminates due to crack-induced delamination and fiber breakage. An optimized Paris law model is used to describe the damage propagation in glass-fiber-reinforced polymer (GFRP) laminates subject to low-velocity impacts. Our proposed methodology deduces the jump energy/inflection point online...
Composite materials have become extremely important for several engineering applications due to t... more Composite materials have become extremely important for several engineering applications due to their superior mechanical properties. However, a major challenge in the use of composites is to detect, locate and quantify fatigue induced damage, particularly delamination, by using limited experimental data. The use of guided Lamb wave based health monitoring with embedded sensors has emerged as a potential solution to effectively predict delamination size. To do this, machine learning prediction models have been used in the past, however, a transfer learning approach which can address the problem of inadequate labeled data by allowing the use of a pretrained model for predicting damage in a new composite specimen, has not been explored in this field. This paper proposes a temporal convolutional network (TCN) based transfer learning (TCN-trans) scheme for predicting delamination damage using sensor measurements. The application of proposed framework is demonstrated on Lamb wave sensor ...
It is important to be able to accurately predict the evolution of damage in structural components... more It is important to be able to accurately predict the evolution of damage in structural components to evaluate the mechanical reliability of engineering structures. This requires modeling complex mechanisms in damage including crack nucleation and propagation. These pose significant computational challenges to simulation, specifically the singular crack tip field as well as the moving boundary problem inherent in crack propagation. In order to address these problems, many different approaches in computational mechanics have been developed including the cohesive zone method, the extended finite element method and the phase-field method, although all these methods are still relatively expensive in computational effort. In order to reduce the computational burden, reduced order models based on the proper orthogonal decomposition (POD) approach can be used to exploit the spatial correlation to get a set of modes characterizing the spatial structure of the model. For the multidimensional ...
Computational analysis of multi-parametric high-content imaging dataset can be particularly tedio... more Computational analysis of multi-parametric high-content imaging dataset can be particularly tedious and daunting to implement for a laboratory biologist with no bioinformatics expertise and hence, there is an unmet need of software tools to facilitate this type of analysis. We present a web-based application "HCS-PhenoCluster" for the analysis of high-content image-based data which can be used for discovering novel cellular phenotypes beyond visual inspection. This application is interfaced with a single-cell extraction pipeline which performs cell segmentation and multi-feature extraction of high-content imaging data. HCS-PhenoCluster has been implemented in Swift language using Vapor framework and consists of a MySQL database. The image analysis workflow of HCS-PhenoCluster is based on machine learning models implemented in Python and comprises five modules of data processing which include multi-level quality control modules and an unsupervised clustering module to revea...
Analysis of high-content screening (HCS) data mostly relies on supervised machine learning based ... more Analysis of high-content screening (HCS) data mostly relies on supervised machine learning based approaches employing user-defined image features. This strategy has limited applications due to the requirement of a priori knowledge of expected cellular phenotypes / perturbations and the time-consuming process of manually annotating these phenotypes. To address these issues, we propose a machine learning based unsupervised framework for high-content analysis. The framework performs anomaly detection using features transferred from natural images to the cellular images by deep learning models. We applied this framework to detect anomalous effects of FDA approved drugs on human monocytic cells. Drug anomaly detection based on image features derived using three deep learning architectures, DenseNet-121, ResNet-50 and VGG-16, is compared with the anomaly scores computed from user-defined features extracted from individually segmented cells. The drug anomaly scores of automatically extract...
There has been a lack of progress in developing spiking neuron models for pattern classification,... more There has been a lack of progress in developing spiking neuron models for pattern classification, which can achieve similar performance as state-of-the-art. To pursue this goal of creating powerful spike-based classifiers, the role of dendrites in neuronal information processing is considered. The neurobiological evidence for dendritic processing has been established in the last few years by neuroscientists across the globe. However, computational models of spiking neurons in machine learning systems have not utilized this mechanism yet. Our work attempts to bridge this gap and explore the possible computational benefits of passive delay and active ionic dendritic mechanisms. A spike-based model for pattern classification is presented which employs neurons with functionally distinct multicompartment dendritic branches. In this model, synaptic integration involves location-dependent processing of inputs on each dendritic compartment, followed by nonlinear processing of the total synaptic input on a dendrite and finally linear integration of the total dendritic output at the soma. This gives the neuron a capacity to perform a large number of input-output mappings. Firstly, a spiking neuron model is developed based on modifying delays associated with the spikes arriving at an afferent. The application of this model is demonstrated on memorizing spatio-temporal patterns by updating only a few delays corresponding to the most synchronous part of a spike pattern. This model explores the time-based computing approach to design a novel learning algorithm which provides an alternative to the traditional weight-based learning and offers the advantage of simpler hardware implementation without multipliers or digitalanalog converters (DACs). The classification accuracy of the system with a load (number of patterns relative to the number of synapses) of up to 2 was shown to be about 80−100%. In our pursuit of achieving improved performance and a hardware-friendly learning algorithm, a model is further proposed which consists of nonlinear dendrites and is inspired by the mechanism of
The synthesis of glycans and sorting of proteins are critical functions of the Golgi apparatus an... more The synthesis of glycans and sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNAi screening offers opportunities to explore this organelle organisation and the gene network underlying it. To date, image-based Golgi screens were based on a single parameter or supervised analysis with pre-defined Golgi structural classes. Here, we report the use of multi-parametric data extracted from a single marker and a computational unsupervised analysis framework to explore Golgi phenotypic diversity more extensively. In contrast with the 3 visually definable phenotypes, our framework reproducibly identified 10 Golgi phenotypes. They were used to quantify and stratify phenotypic similarities among genetic perturbations. The derived phenotypic network overlaps partially with previously reported protein-protein interactions as well as suggests novel functional interactions. ...
ABSTRACT We present an architecture of a spike based multi-class classifier using neurons with no... more ABSTRACT We present an architecture of a spike based multi-class classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 − 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources.
The development of power-efficient neuromorphic devices presents the challenge of designing spike... more The development of power-efficient neuromorphic devices presents the challenge of designing spike pattern classification algorithms which can be implemented on low-precision hardware and can also achieve state-of-the-art performance. In our pursuit of meeting this challenge, we present a pattern classification model which uses a sparse connection matrix and exploits the mechanism of nonlinear dendritic processing to achieve high classification accuracy. A rate-based structural learning rule for multiclass classification is proposed which modifies a connectivity matrix of binary synaptic connections by choosing the best "k" out of "d" inputs to make connections on every dendritic branch (k < < d). Because learning only modifies connectivity, the model is well suited for implementation in neuromorphic systems using address-event representation (AER). We develop an ensemble method which combines several dendritic classifiers to achieve enhanced generalization ...
Uploads
Papers by Shaista Hussain