2023 IEEE/SICE International Symposium on System Integration (SII)
Experiments using large numbers of miniature swarm robots are desirable to teach, study, and test... more Experiments using large numbers of miniature swarm robots are desirable to teach, study, and test multirobot and swarm intelligence algorithms and their applications. To realize the full potential of a swarm robot, it should be capable of not only motion but also sensing, computing, communication, and power management modules with multiple options. Current swarm robot platforms developed for commercial and academic research purposes lack several of these critical attributes by focusing only on a few of these aspects. Therefore, in this paper, we propose the HeRoSwarm, a fullycapable swarm robot platform with open-source hardware and software support. The proposed robot hardware is a low-cost design with commercial off-the-shelf components that uniquely integrates multiple sensing, communication, and computing modalities with various power management capabilities into a tiny footprint. Moreover, our swarm robot with odometry capability with Robot Operating Systems (ROS) support is unique in its kind. This simple yet powerful swarm robot design has been extensively verified with different prototyping variants and multi-robot experimental demonstrations.
Respiratory infections disrupt the microbiota in the upper respiratory tract (URT), putting patie... more Respiratory infections disrupt the microbiota in the upper respiratory tract (URT), putting patients at a risk for subsequent infections. During the pandemic, cases of COVID-19 were aggravated by secondary infections because of impaired immunity and medical interventions, which was clearly evident in the second wave of COVID-19 in India. The potential dangers and clinical difficulties of bacterial and fungal secondary infections in COVID-19 patients necessitate microbial exploration of the URT. In this regard, mass spectrometry (MS)-based proteome data of nasopharyngeal swab samples from COVID-19 patients was used to investigate the metaproteome. The MS datasets were searched against a comprehensive protein sequence database of common URT pathogens using multiple search platforms (MaxQuant, MSFragger, and Search GUI/PeptideShaker). The detected microbial peptides were verified using PepQuery, which analyses peptide-spectrum pairs to give statistical output for determining confident ...
Proceedings of the 28th Asia and South Pacific Design Automation Conference
Emerging data intensive AI/ML workloads encounter memory and power wall when run on general-purpo... more Emerging data intensive AI/ML workloads encounter memory and power wall when run on general-purpose compute cores. This has led to the development of a myriad of techniques to deal with such workloads, among which DNN accelerator architectures have found a prominent place. In this work, we propose a hardwaresoftware co-design approach to achieve system-level benefits. We propose a quantized data-aware POSIT number representation that leads to a highly optimized DNN accelerator. We demonstrate this work on SOTA SIMBA architecture, extendable to any other accelerator. Our proposal reduces the buffer/storage requirements within the architecture and reduces the data transfer cost between the main memory and the DNN accelerator. We have investigated the impact of using integer, IEEE floating point, and posit multipliers for LeNet, ResNet and VGG NNs trained and tested on MNIST, CIFAR10 and ImageNet datasets, respectively. Our system-level analysis shows that the proposed approximate-fixed-posit multiplier when implemented on SIMBA architecture, achieves on average ∼2.2× speed up, consumes ∼3.1× less energy and requires ∼3.2× less area, respectively, against the baseline SOTA architecture, without loss of accuracy (∼ ±1%) CCS Concepts • Hardware → Emerging architectures; • Computer systems organization → Neural networks; Data flow architectures; • Computing methodologies → Neural networks.
Nocardia are gram-positive bacilli that cause opportunistic infections in susceptible populations... more Nocardia are gram-positive bacilli that cause opportunistic infections in susceptible populations. We describe a case of post-transplant infection of pulmonary Nocardiosis caused by the rare strain Nocardia cyriacigeorgica and the challenges faced in reaching a definitive diagnosis. This case report emphasizes on keeping Nocardiosis as a differential diagnosis in transplant recipients as this disease is largely underdiagnosed and underreported.
International Journal of Electrical and Computer Engineering (IJECE)
Internet of things (IoT) is been advancing over a long period of time in many aspects. For data t... more Internet of things (IoT) is been advancing over a long period of time in many aspects. For data transfer between IoT devices in a wireless sensor network, various IoT protocols are proposed. Among them, the most widely used are constrained application protocol (CoAP) and message queue telemetry transport (MQTT). Overcoming the limitations of CoAP, lightweight machine-to-machine (LwM2M) framework was designed above CoAP. Recent statistics show that LwM2M and MQTT are the widely used, but LwM2M is still less used than MQTT. Our paper is aimed at comparing both MQTT and LwM2M on the basis of performance efficiency, which will be achieved by sending same file through both protocols to the server. Performance efficiency will be calculated in two scenarios, i) when the client makes a connection with the server i.e., while initial connection and ii) while sending data file to server i.e., while data transfer. Both the protocols will be tested on the number of packets sent and the variabili...
International Journal of Next-Generation Computing, 2021
Unable to communicate verbally is a disability. In order to exchange thoughts and interact, there... more Unable to communicate verbally is a disability. In order to exchange thoughts and interact, there exist severalways. The most predominant method involves use of hand-gestures. The prime motive of the proposed researchwork is to bridge the research gap in Sign Language Recognition with maximum efficiency. The goal is to replacethe human mediator with a machine to minimize human interference. This paper focuses on the recognition of ASLin real-time. In automatic sign language translator design the challenging part lies in selecting a good classifierto classify the static input gestures with high accuracy. CNN architecture is used to design a classifier for signlanguage recognition in the proposed system. The model and the pipeline architecture is developed by keras basedconvolutional neural network to classify 27 alphabets that is 26 English language alphabets and a unique character,space. With different parameter configurations, the system has trained the classifier with different pa...
Objectives: To propose a model which could classify in real-time if an individual is wearing a fa... more Objectives: To propose a model which could classify in real-time if an individual is wearing a face mask or not wearing a face mask. A lightweight system that could be easily deployed and assist in surveillance. Methods/Statistical analysis: Analysis of the proposed model shows a limited number of research studies with regards to facial localizations. Several state-of-the-art methods were taken into considerations out of which the CNN architectural approach is analyzed in this study. Taking into consideration the use-case of deployments and structuring, a new Keras-based model is proposed that surpasses the achievement results of MobileNet-V2 and VGG-16 standard architectures. Effective facial localization is tackled with the MTCNN approach. Findings: The system has achieved a confidence score of 0.9914, an average weighted F1-score of 0.98, a precision value of 0.99. The proposed model has been compared with standard architectures of VGG16 and MobileNetV2 with regard to the accuracy, support values, precision, recall, and F1-score metrics. The proposed model performs better w.r.t traditional architectures. The average latency involved in prediction is 0.034 seconds making the average FPS 30 Frames per second. The compact architecture makes the model best for deployment in real-time scenarios. The system incorporates the concept of image localization with Multi-Task Cascaded Convolutional Neural Network (MTCNN) architecture. The analysis shows MTCNN is performing much better than Haar-Cascade in real-time facial prediction scenarios. Novelty/Applications: This compact architecture with minimal layers is easily deployable in edge devices. It can be used for mass screening at public places like railway stops, bus stops, streets, malls, entrances, schools, and many service-oriented business verticals requiring users to access the services as long as the mask has been worn correctly.
Silica plays an important role in aluminium-based materials. However, role of silica in aluminium... more Silica plays an important role in aluminium-based materials. However, role of silica in aluminium matrix composite is not clear so far. In the present study, pure silica was successfully extracted from rice husk by thermal and chemical treatments. The extracted silica had undergone FESEM, FTIR, and XRD for characterizing the purity of silica particles. The results showed that the obtained silica particles were highly pure. The rice husk-extracted pure silica was used as reinforcement in graphite/aluminium matrix hybrid composites. Composites were made using powder metallurgy process followed by sintering. Reinforcements of silica and graphite in aluminium matrix composites were done at different compositions to control the hardness in order to improve machinability. The aluminium matrix hybrid composites had shown excellent physical, mechanical, and thermal properties in terms of surface strength along with light mass as well as controlled thermal conductivity. The hardness of the hybrid composites had increased significantly compared to the single phase aluminium and also was controlled by the combined effect of added silica nanoparticle and graphite flake as reinforcements. Beside mechanical properties, these hybrid composites showed significantly desired thermal properties, particularly lower thermal expansion than that of pristine aluminium. Hence, the newly developed rice husk-extracted pure silica reinforced graphite/aluminium matrix hybrid composites can be used as potential materials for various advanced applications including microelectronic devices, engine piston, and automobile components.
2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), 2020
One of the most important senses for a living is vision. Millions of people living in this world ... more One of the most important senses for a living is vision. Millions of people living in this world deal with visual impairment. These people encounter difficulties in navigating independently and safely, facing issues in accessing information and communication. The objective of the proposed work is to change the visual world into an audio world by notifying the blind people about the objects in their path. This will help visually impaired people to navigate independently without any external assistance just by using the real-time object detection system. The application uses image processing and machine learning techniques to determine real-time objects through the camera and inform blind people about the object and its location through the audio output. Inability to differentiate between objects has led to many limitations to the existing approach which includes less accuracy and lowperformance results. The main objective of the proposed work is to provide good accuracy, best performance results and a viable option for the visually impaired people to make the world a better place for them.
Nuclear genome sequences incompletely characterize the genomic content and thus the genetic diver... more Nuclear genome sequences incompletely characterize the genomic content and thus the genetic diversity of fungal species. Here, we present the complete mitochondrial genome sequences of nine Aspergillus flavus strains, providing useful information for inter- and intraspecific analyses.
2023 IEEE/SICE International Symposium on System Integration (SII)
Experiments using large numbers of miniature swarm robots are desirable to teach, study, and test... more Experiments using large numbers of miniature swarm robots are desirable to teach, study, and test multirobot and swarm intelligence algorithms and their applications. To realize the full potential of a swarm robot, it should be capable of not only motion but also sensing, computing, communication, and power management modules with multiple options. Current swarm robot platforms developed for commercial and academic research purposes lack several of these critical attributes by focusing only on a few of these aspects. Therefore, in this paper, we propose the HeRoSwarm, a fullycapable swarm robot platform with open-source hardware and software support. The proposed robot hardware is a low-cost design with commercial off-the-shelf components that uniquely integrates multiple sensing, communication, and computing modalities with various power management capabilities into a tiny footprint. Moreover, our swarm robot with odometry capability with Robot Operating Systems (ROS) support is unique in its kind. This simple yet powerful swarm robot design has been extensively verified with different prototyping variants and multi-robot experimental demonstrations.
Respiratory infections disrupt the microbiota in the upper respiratory tract (URT), putting patie... more Respiratory infections disrupt the microbiota in the upper respiratory tract (URT), putting patients at a risk for subsequent infections. During the pandemic, cases of COVID-19 were aggravated by secondary infections because of impaired immunity and medical interventions, which was clearly evident in the second wave of COVID-19 in India. The potential dangers and clinical difficulties of bacterial and fungal secondary infections in COVID-19 patients necessitate microbial exploration of the URT. In this regard, mass spectrometry (MS)-based proteome data of nasopharyngeal swab samples from COVID-19 patients was used to investigate the metaproteome. The MS datasets were searched against a comprehensive protein sequence database of common URT pathogens using multiple search platforms (MaxQuant, MSFragger, and Search GUI/PeptideShaker). The detected microbial peptides were verified using PepQuery, which analyses peptide-spectrum pairs to give statistical output for determining confident ...
Proceedings of the 28th Asia and South Pacific Design Automation Conference
Emerging data intensive AI/ML workloads encounter memory and power wall when run on general-purpo... more Emerging data intensive AI/ML workloads encounter memory and power wall when run on general-purpose compute cores. This has led to the development of a myriad of techniques to deal with such workloads, among which DNN accelerator architectures have found a prominent place. In this work, we propose a hardwaresoftware co-design approach to achieve system-level benefits. We propose a quantized data-aware POSIT number representation that leads to a highly optimized DNN accelerator. We demonstrate this work on SOTA SIMBA architecture, extendable to any other accelerator. Our proposal reduces the buffer/storage requirements within the architecture and reduces the data transfer cost between the main memory and the DNN accelerator. We have investigated the impact of using integer, IEEE floating point, and posit multipliers for LeNet, ResNet and VGG NNs trained and tested on MNIST, CIFAR10 and ImageNet datasets, respectively. Our system-level analysis shows that the proposed approximate-fixed-posit multiplier when implemented on SIMBA architecture, achieves on average ∼2.2× speed up, consumes ∼3.1× less energy and requires ∼3.2× less area, respectively, against the baseline SOTA architecture, without loss of accuracy (∼ ±1%) CCS Concepts • Hardware → Emerging architectures; • Computer systems organization → Neural networks; Data flow architectures; • Computing methodologies → Neural networks.
Nocardia are gram-positive bacilli that cause opportunistic infections in susceptible populations... more Nocardia are gram-positive bacilli that cause opportunistic infections in susceptible populations. We describe a case of post-transplant infection of pulmonary Nocardiosis caused by the rare strain Nocardia cyriacigeorgica and the challenges faced in reaching a definitive diagnosis. This case report emphasizes on keeping Nocardiosis as a differential diagnosis in transplant recipients as this disease is largely underdiagnosed and underreported.
International Journal of Electrical and Computer Engineering (IJECE)
Internet of things (IoT) is been advancing over a long period of time in many aspects. For data t... more Internet of things (IoT) is been advancing over a long period of time in many aspects. For data transfer between IoT devices in a wireless sensor network, various IoT protocols are proposed. Among them, the most widely used are constrained application protocol (CoAP) and message queue telemetry transport (MQTT). Overcoming the limitations of CoAP, lightweight machine-to-machine (LwM2M) framework was designed above CoAP. Recent statistics show that LwM2M and MQTT are the widely used, but LwM2M is still less used than MQTT. Our paper is aimed at comparing both MQTT and LwM2M on the basis of performance efficiency, which will be achieved by sending same file through both protocols to the server. Performance efficiency will be calculated in two scenarios, i) when the client makes a connection with the server i.e., while initial connection and ii) while sending data file to server i.e., while data transfer. Both the protocols will be tested on the number of packets sent and the variabili...
International Journal of Next-Generation Computing, 2021
Unable to communicate verbally is a disability. In order to exchange thoughts and interact, there... more Unable to communicate verbally is a disability. In order to exchange thoughts and interact, there exist severalways. The most predominant method involves use of hand-gestures. The prime motive of the proposed researchwork is to bridge the research gap in Sign Language Recognition with maximum efficiency. The goal is to replacethe human mediator with a machine to minimize human interference. This paper focuses on the recognition of ASLin real-time. In automatic sign language translator design the challenging part lies in selecting a good classifierto classify the static input gestures with high accuracy. CNN architecture is used to design a classifier for signlanguage recognition in the proposed system. The model and the pipeline architecture is developed by keras basedconvolutional neural network to classify 27 alphabets that is 26 English language alphabets and a unique character,space. With different parameter configurations, the system has trained the classifier with different pa...
Objectives: To propose a model which could classify in real-time if an individual is wearing a fa... more Objectives: To propose a model which could classify in real-time if an individual is wearing a face mask or not wearing a face mask. A lightweight system that could be easily deployed and assist in surveillance. Methods/Statistical analysis: Analysis of the proposed model shows a limited number of research studies with regards to facial localizations. Several state-of-the-art methods were taken into considerations out of which the CNN architectural approach is analyzed in this study. Taking into consideration the use-case of deployments and structuring, a new Keras-based model is proposed that surpasses the achievement results of MobileNet-V2 and VGG-16 standard architectures. Effective facial localization is tackled with the MTCNN approach. Findings: The system has achieved a confidence score of 0.9914, an average weighted F1-score of 0.98, a precision value of 0.99. The proposed model has been compared with standard architectures of VGG16 and MobileNetV2 with regard to the accuracy, support values, precision, recall, and F1-score metrics. The proposed model performs better w.r.t traditional architectures. The average latency involved in prediction is 0.034 seconds making the average FPS 30 Frames per second. The compact architecture makes the model best for deployment in real-time scenarios. The system incorporates the concept of image localization with Multi-Task Cascaded Convolutional Neural Network (MTCNN) architecture. The analysis shows MTCNN is performing much better than Haar-Cascade in real-time facial prediction scenarios. Novelty/Applications: This compact architecture with minimal layers is easily deployable in edge devices. It can be used for mass screening at public places like railway stops, bus stops, streets, malls, entrances, schools, and many service-oriented business verticals requiring users to access the services as long as the mask has been worn correctly.
Silica plays an important role in aluminium-based materials. However, role of silica in aluminium... more Silica plays an important role in aluminium-based materials. However, role of silica in aluminium matrix composite is not clear so far. In the present study, pure silica was successfully extracted from rice husk by thermal and chemical treatments. The extracted silica had undergone FESEM, FTIR, and XRD for characterizing the purity of silica particles. The results showed that the obtained silica particles were highly pure. The rice husk-extracted pure silica was used as reinforcement in graphite/aluminium matrix hybrid composites. Composites were made using powder metallurgy process followed by sintering. Reinforcements of silica and graphite in aluminium matrix composites were done at different compositions to control the hardness in order to improve machinability. The aluminium matrix hybrid composites had shown excellent physical, mechanical, and thermal properties in terms of surface strength along with light mass as well as controlled thermal conductivity. The hardness of the hybrid composites had increased significantly compared to the single phase aluminium and also was controlled by the combined effect of added silica nanoparticle and graphite flake as reinforcements. Beside mechanical properties, these hybrid composites showed significantly desired thermal properties, particularly lower thermal expansion than that of pristine aluminium. Hence, the newly developed rice husk-extracted pure silica reinforced graphite/aluminium matrix hybrid composites can be used as potential materials for various advanced applications including microelectronic devices, engine piston, and automobile components.
2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), 2020
One of the most important senses for a living is vision. Millions of people living in this world ... more One of the most important senses for a living is vision. Millions of people living in this world deal with visual impairment. These people encounter difficulties in navigating independently and safely, facing issues in accessing information and communication. The objective of the proposed work is to change the visual world into an audio world by notifying the blind people about the objects in their path. This will help visually impaired people to navigate independently without any external assistance just by using the real-time object detection system. The application uses image processing and machine learning techniques to determine real-time objects through the camera and inform blind people about the object and its location through the audio output. Inability to differentiate between objects has led to many limitations to the existing approach which includes less accuracy and lowperformance results. The main objective of the proposed work is to provide good accuracy, best performance results and a viable option for the visually impaired people to make the world a better place for them.
Nuclear genome sequences incompletely characterize the genomic content and thus the genetic diver... more Nuclear genome sequences incompletely characterize the genomic content and thus the genetic diversity of fungal species. Here, we present the complete mitochondrial genome sequences of nine Aspergillus flavus strains, providing useful information for inter- and intraspecific analyses.
Uploads
Papers by Aryan Gupta