Browsing by Author "Shenoy, Meetha V."

Now showing 1 - 20 of 22

A 8-bit SAR ADC using current mode approach for bio-medical applications
(IEEE, 2014) Shenoy, Meetha V.
This paper deals with the design of a SAR-ADC with 8-bit resolution suited for bio-medical application. The design of the key components of the SAR ADC namely, DAC, Comparator and Sample and Hold circuit (S/H) has been carried out using current mode approach with the DAC operating at sub-threshold regime. The input current range is 10nA to 2.57μA with 10nA as the LSB. The circuit has been designed in UMC 180nm technology Twin-Well Process.
BSwarm robot — A low cost mobile wireless sensor research platform using COTS products
(IEEE, 2015) Shenoy, Meetha V.
MWSN is an emerging area of research and most of the work in the field of MWSN is done at the simulation level as there is hardly any cost effective hardware platform(node/mote) available for MWSN applications. To handle mobility, the MWSN node should be much more efficient than the nodes in static WSN. Moreover, a MWSN node should be capable of handling real time mobility control, path planning and navigation. The application domains of MWSN can be further expanded by incorporating swarm like intelligence in MWSN. We have developed a low cost, small form factor hardware platform which will function as a node in MWSN using custom off the shelf(COTS) products. Our mobile hardware platform, henceforth called as BSwarm robot supports self-assembly, to achieve complex tasks. The platform also support image assisted navigation and provides extensive I/O support for further feature expansion. The testbed consisting of multiple BSwarm robot can be utilized for the development and validation of algorithms/protocols related to MWSNs, distributed control of Swarm robots, real time image processing etc. BSwarm robot is a multi processor based robot designed in such a way that it can be used for applications which may demand varied degree of processing, communication and input-output capabilities. This paper also highlights major factors that can be taken into consideration while choosing the hardware platform for MWSNs so that the protocol stack development for MWSNs becomes easier.
Cherry Plucking Strategies for Coffee Harvester
(IEEE, 2021) Shenoy, Meetha V.
Coffee is one of the major agricultural produce popular worldwide. Coffee harvesting is performed in two ways (a) Selective harvesting - in which only ripe coffee cherries are picked, leaving the unripe coffee cherries intact. (b) Strip harvesting - in which the cherries are stripped out without separation of ripe and unripe ones. Although this can be completed quickly, this results in higher percentages of unripe, which reduce the quality and sale value, resulting in less profit for producers. The selective coffee cherry harvester should identify and distinguish ripe and unripe cherries and hence a fully automated harvesting system should be vision-guided. The design of developing a vision-based harvesting system for coffee cherries is particularly difficult due to the size of the coffee cherries, the clustered arrangement of the coffee cherries, and the height of the coffee plant. Currently available harvesters are based on strip harvesting and hence there is a need to develop harvestors for selective harvesting of coffee cherries. In this work, we present cherry plucking strategies for a selective coffee harvester robot. This analysis is one of the key work required towards the implementation of the vision guided-selective harvester. The proposed work is tested in simulation as well as on hardware consisting of Interbotix ReactorX150 robot arm and Intel Realsense 435i camera.
Convolutional Neural Network Hardware Optimization Using Bayesian Method
(IEEE, 2024-04) Asati, Abhijit; Shenoy, Meetha V.
Convolutional Neural Network (CNN) models have demonstrated significant benefits in the realm of computer vision and applications related to image processing. Optimizing hyperparameters in CNN models is crucial to ensuring an effective implementation of the model, whether on software, hardware, or a ‘software-hardware co-design’ platform, thereby enhancing overall performance and results. This work proposes a CNN architecture and applies the Bayesian optimization algorithm to find the best set of hyperparameter values which reduces training and recognition time both. In addition, a new parameter i.e., ‘Network optimization parameter’ (NOP) is defined which considers optimization of hardware resources for a given accuracy of the trained model. This parameter needs to be minimized which helps evaluate the best set of hyperparameter values and is essential for further implementing the CNN model in the hardware platform. The optimization is performed on both the processors, a Central Processing Unit (CPU) and a Graphical Processing Unit (GPU), in optimizing the CNN model to clearly understand the impacts of utilizing different processing units. An accuracy of 99.48 % is achieved for the Modified National Institute of Standards and Technology (MNIST) database, and an accuracy of 88.78 % is achieved for the Canadian Institute For Advanced Research (CIFAR-10) database. The proposed models are highly optimized and have lesser resource requirements (due to the lesser layer complexities and smaller filter sizes) while delivering higher accuracies compared to the available literature. Further, the calculated NOP for the proposed network is highly reduced compared to the published literature.
Design of a tunable delay line with on-chip calibration to generate process-invariant PWM signal for in-memory computing
(Springer, 2023-06) Shenoy, Meetha V.; Chaturvedi, Nitin
The recent compute-in-memory (CiM) architectures are proposed as a promising solution to support Deep Neural Network and Convolutional Neural Network to solve large and complex tasks in various machine learning applications. The CiM architecture overcomes the limitation of the current Von-Neumann architecture by performing logic computations within the memory also called as in-memory computing. In most CiM, the in-memory logic operations are performed on the weights stored in memory using the inputs that are processed through bitlines or wordlines using pulse width modulated (PWM) signals. For precise operation, the applied input signals must be stable. However, one of the main challenges faced during the input signal generation is the deviation in the width values due to process, voltage, and temperature variations. Addressing this challenge, in this work, we aim to mitigate the impact of one of these variations on the generated PWM signals. Therefore, in this work, we propose to design a tunable delay line that provides a linear PWM signal corresponding to an input vector which is further utilized to perform local computation in memory. Further, to minimize the impact of process variations, we propose an autonomous on-chip calibration circuit that dynamically tunes the delay lines to obtain stable and process-invariant pulse width modulated signals. Our simulation results for the proposed DL demonstrate a total delay of 559 psec with a delay error of less than 2% under various process corners.
DTTA - Distributed, Time-division Multiple Access based Task Allocation Framework for Swarm Robots
(CORE, 2017-05) Shenoy, Meetha V.
Swarm robotic systems, unlike traditional multi-robotic systems, deploy number of cost effective robots which can co-operate, aggregate to form patterns/formations and accomplish missions beyond the capabilities of individual robot. In the event of fire, mine collapse or disasters like earthquake, swarm of robots can enter the area, conduct rescue operations, collect images and convey locations of interest to the rescue team and enable them to plan their approach in advance. Task allocation among members of the swarm is a critical and challenging problem to be addressed. DTTA- a distributed, Time-division multiple access (TDMA) based task allocation framework is proposed for swarm of robots which can be utilised to solve any of the 8 different types of task allocation problem identified by Gerkey and Mataric ́. DTTA is reactive and supports task migration via extended task assignments to complete the mission in case of failure of the assigned robot to complete the task. DTTA can be utilised for any kind of robot in land or for co-operative systems comprising of land robots and air-borne drones. Dependencies with other layers of the protocol stack were identified and a quantitative analysis of communication and computational complexity is provided. To our knowledge this is the first work to be reported on task allocation for clustered scalable networks suitable for handling all 8 types of multi-robot task allocation problem. Effectiveness and feasibility of deploying DTTA in real world scenarios is demonstrated by testing the framework for two diverse application scenario
Efficient edge AI implementation for IoT device identification for hierarchical federated learning
(Inder Science, 2025-03) Shenoy, Meetha V.
As IoT devices proliferate, efficient IoT device identification is crucial for resource management, planning, and detecting anomalous traffic. Traditional ML-based identification relies on centralised training, but federated learning (FL) offers a privacy-preserving alternative, enabling collaborative model training without sharing raw data. FL enhances edge devices' ability to identify previously unconnected devices. However, resource constraints like limited computation, power, and communication capabilities may prevent some edge devices from actively participating in FL. We propose a solution where resource-limited IoT devices benefit from FL by subscribing to server-based services. This work presents an efficient AI model implementation for IoT device identification on embedded edge devices, detailing the toolflow from model generation to hardware implementation. We apply and evaluate various model optimisation techniques to balance performance and resource trade-offs, offering insights to advance edge-AI and scalable FL-based ML applications for IoT networks.
FlexEye — A flexible camera mote for sensor networks
(IEEE, 2015) Shenoy, Meetha V.
In this paper the description of FlexEye - a visual sensor mote suitable of functioning as super node in the static wireless sensor networks is provided. With mobility features added on to FlexEye, the platform can be used as high performance mobile node in mobile wireless sensor networks or as a node in swarm robotics. A comparison of FlexEye with existing camera platforms developed for sensor networks is made on parameters like processing capabilities, power consumption, cost, time to prototype, support for future expansion, etc. The paper elaborates on the custom off the shelf hardware components used in design and the resource pipelined image acquisition technique implemented on the FlexEye mote for acquiring the high resolution images in real time using minimalistic resources. The paper also provides quantitative details on the achieved frame rates and power consumption details of the FlexEye platform.
HAFedL: a hessian-aware adaptive privacy preserving horizontal federated learning scheme for IOT applications
(IEEE, 2024-09) Shenoy, Meetha V.
Federated Learning (FL) is a paradigm in distributed machine learning, which has gained significant attention in the recent years especially in the domain of Internet of Things. Federated Learning saves communication bandwidth when compared to centralized machine learning process and is also considered to be privacy preserving as the raw data at the clients need not be transmitted to the server for the FL learning. Recent studies on FL have exposed privacy vulnerabilities particularly in the form of Gradient Leakage Attacks (GLA) in which the adversaries can generate training data of the client from shared gradients or model updates from clients. The available solutions in the literature for GLA based on perturbing the gradients from clients leads to a drop in the performance of the FL system while attempting to preserve privacy. We propose HAFedL, an improved novel hessian aware adaptive privacy preserving FL scheme in which the performance of the model is not significantly affected due to the aspects introduced in the FL architecture to improve the privacy of the model against the GLA. The HAFedL is also robust to the data heterogeneity and device heterogeneity (particularly straggler effect) which may be present in the clients participating in the FL. The performance of HAFedL is tested for two applications- IoT device identification and digit classification. The proposed HAFedL scheme can be utilized in privacy sensitive domains such as smart city applications, Industrial Internet of Things, Internet of Robotic Things, Internet of Medical Things, etc.
HFedDI: A novel privacy preserving horizontal federated learning based scheme for IoT device identification
(IEEE, 2023-05) Shenoy, Meetha V.
As the number of IoT devices that are getting connected to the Internet is increasing, there is a need to automatically detect the IoT devices connected to the network for efficient network resource management and planning, identification of security attacks and anomalies in the network. Centralized machine learning techniques for device identification lead to the use of excessive communication bandwidth and can at times lead to privacy issues as data has to be transported to the central location. In this paper, we propose HFedDI- a novel horizontal learning based federated learning scheme for IoT device identification. The proposed federated learning technique is scalable as an edge device that does device identification can identify the devices which were never connected to it previously due to the achieved generalization accuracy as a result of model updates from other edge devices. Our work has indicated significant performance improvement in device identification across IID scenarios, and non-IID (specifically tested for data and label distribution skew) scenarios when tested on three publically available datasets. The proposed device identification technique is privacy preserving and is promising as the existing work in literature which utilized federated learning for other applications has indicated very poor results under non-IID label skew scenarios.
A Holistic Framework for Crime Prevention, Response, and Analysis With Emphasis on Women Safety Using Technology and Societal Participation
(IEEE, 2021-04) Gupta, Rajiv; Gupta, Anu; Shenoy, Meetha V.
Ensuring women's safety in smart cities is a need of the hour. Even though several legal and technological steps are adopted worldwide, women's safety continues to be an international concern. Criminal records are maintained by law enforcement agencies and are most often not available to the public in an easily comprehensible form. While some wearable devices and mobile applications are available which are touted to aid in ensuring women's safety, they utilize limited societal intervention and are not very efficient in ensuring the safety of the women as and when required. Most often the crime response, crime analysis, and crime prevention schemes are not integrated, leading to gaps in ensuring women's safety. Our major contribution is in developing a holistic system encompassing the three crucial aspects, i.e crime analysis and mapping, crime prevention, and emergency response by leveraging societal participation for women safety management. This work applies the Geographic Information System (GIS) for the identification of hotspots and patterns of crime. The proposed system uses data generated from the mobile application and/or wearable gadget prototyped as a part of this work along with the criminal history records for crime response, analysis, and prevention. The system for the hotspot identification is demonstrated for the Pilani town in the Jhunjhunu district in the state of Rajasthan, India, and can be easily scaled up geographically and utilized as a safety strategy for smart cities. While the common man is provided a cost-effective solution via the developed mobile application or wearable gadget, the various components are integrated into a website for supervisory management and can be utilized by law enforcement agencies.
Hybrid Consensus and Recovery Block-Based Detection of Ripe Coffee Cherry Bunches Using RGB-D Sensor
(IEEE, 2022-01) Chaturvedi, Nitin; Shenoy, Meetha V.
Detection of fruits for automatic harvesting using vision sensors has gained attention in recent times. In this work, we consider the problem of the detection of ripe cherry bunches for the selective harvesting of coffee cherries. The coffee cherries are small in size and appear in a clustered arrangement which makes it difficult to detect them. Also, the previous studies indicate that the accuracy of the available techniques for fruit detection is not sufficient for use in real-time harvesting operations. Hence, we propose a novel Hybrid Consensus and Recovery Block (HCRB) based technique for the reliable detection of the ripe coffee cherry bunches for the coffee harvester robot using RGB-D sensor. Our studies via simulation as well as on hardware set-up indicate a significant increase in true positive and decrease in false positive detections which makes it suitable for use in real-time harvesters. The proposed system provides accuracy, precision, recall, and F1- score of 93%, 97%, 92%, and 93% respectively when tested on the NVIDIA Jetson Nano Development board.
Indoor localization in NLOS conditions using asynchronous WSN and neural network
(IEEE, 2017) Shenoy, Meetha V.
Development of technologies for accurate localization of objects in indoor environments can transform wide application domains like healthcare, warehouses and fitness industries. In this paper, we present a novel neural network and asynchronous wireless sensor network (WSN) based indoor localization scheme. A custom designed ultrasonic trans-receiver serves as the back bone of the localization scheme. In addition to the experiments on hardware, we utilize Locusim, an acoustic simulator to augument extensive analysis on Non line of Sight (NLOS) conditions. We demonstrate that the neural network based localization scheme can provide an accuracy suitable for most of the real world applications even under NLOS conditions.
A lightweight ANN based robust localization technique for rapid deployment of autonomous systems
(Springer, 2019-05) Shenoy, Meetha V.
The capability to localize or identify position in the field of deployment is a primary requirement of future autonomous system in domains such as warehouse transportation, ambient-assisted living/ health care systems, search and rescue, motion monitoring, etc. Although reliable indoor localization in the order of few centimeters can be achieved with the existing localization systems in Line-of-Sight (LOS) conditions, the localization under Non-line-of-Sight (NLOS) conditions is an open area of research. In range-based localization systems, distance estimation is a pre-requisite for location estimation. Time of Arrival (ToA) is considered to be the most accurate technique for distance estimation when compared to Time Difference of Arrival (TDoA) or Received Signal Strength Indication (RSSI). Most of the work available as literature on indoor localization under NLOS conditions is based on the profiling of the indoor deployment area under various NLOS conditions and mitigating NLOS affected timestamps from the ToA measurements. However, it is not practically possible to obtain a comprehensive data set containing all possible conditions of NLOS in indoor environments. In this paper, an Artificial Neural Network based Location Estimation Unit (ANN-LEU) based scheme is proposed to estimate the two-dimensional (2-D) location of an object under LOS and NLOS conditions. One of the unique features of the novel location estimation scheme is that the training of the system is required to be performed only under LOS conditions, thus facilitating the quick deployment in new environments. The proposed ANN-LEU is robust as it identifies the presence of NLOS if any, in the ToA measurements and thus removing false position estimations if any. The Mean Average Error (MAE) error in position estimated during the performance analysis of the proposed system was restricted to lesser than 20 cm, if the object is in range of three beacons in LOS, and also for the scenarios in which one of the three beacon nodes are in NLOS. The proposed scheme eliminates false position identification. The proposed scheme requires lesser number of beacons for localization when compared to the available indoor localization systems, thus also improving the cost and energy efficiency.
A Novel Method for Suitable Hyperparameter Selection in an Accurate Convolutional Neural Network Architecture
(Springer, 2021-11) Asati, Abhijit; Shenoy, Meetha V.
The deep convolutional neural network (CNN) models are of great use in many areas and applications such as image processing and computer vision. The hyperparameter optimization in the CNN architectures is essential for an efficient implementation of model on software or hardware or “software-hardware co-design” platform to achieve better characteristics. In this paper, we have proposed CNN architecture models trained using MNIST dataset that explores the selection of various hyperparameters and their impact on the accuracy to achieve the hyperparameter optimization. The work presents thorough evaluation of various hyperparameters which offers a higher accuracy and keeps the architecture simple as compared with other published results.
OEAD: An Online Ensemble-based Anomaly Detection technique for RPL network
(ACM Digital Library, 2024-01) Shenoy, Meetha V.
Routing Protocol for Low-Power and Lossy Networks (RPL) is a widely used routing protocol in low-power and lossy networks especially when convergecast traffic is predominant. RPL routing protocol can be widely used in applications (such as smart grids, smart homes, or smart city applications) that use convergecast traffic in which nodes transmit data to a central node in a multi-hop fashion for monitoring and control purposes. However, the RPL routing protocol is prone to several attacks, and such anomalous conditions are to be identified at the earliest to prevent a network failure. Most of the recent works for anomaly detection rely on supervised machine learning techniques. A supervised network can thus only identify the categories on which it has been trained prior. Due to the wide variety of attacks to which the networks are prone, the supervised techniques are of limited use in practical applications. In this work, we propose an Online unsupervised Ensemble-based Anomaly Detection (OEAD) technique for anomaly detection. This online model can be adapted and retrained using the latest and representative traffic that reflects the current network conditions. A drift detector unit to identify significant changes in the network traffic is utilized in OEAD architecture which can update the ML model on the detection of drift in the network. The proposed OEAD technique is tested on a publicly available RADAR dataset and the results indicate that the proposed technique is promising for anomaly detection in real-time applications.
Platform for biomimetic swarms
(ACM Digital Library, 2015-07) Shenoy, Meetha V.
In the past decade, a large number of robots were designed to mimic mobility behavior of organisms in nature. The biologically inspired robots improve the mobility of traditional robotic vehicles and make them robust for different terrains unlike the traditional robots. Navigation in most of the biomimetic robots developed so far are either controlled by dedicated pattern generator modules within robotic structure or by loading the control patterns generated in a computer onto the robots. These biomimetic robots are not fully autonomous in their abilities to navigate in the area of interest. We propose to build a biomimetic snake like robotic module from a set of independent robotic modules. These modules are autonomous and can function as swarm of robots or can link together to form a biomimetic snake like unit using their intelligence. Such a behaviour can be utilized in search and rescue operations, accessing hazardous or inaccessible terrains, monitoring pipelines etc. In this paper we evaluate the hardware requirements for building such a biomimetic robot and also illustrate the research platform which we have developed based on the assessment. This platform has enough computational and peripheral capabilities to provide autonomous behavior to the robot and also to support the swarm and biomimetic behaviour. This low cost prototype is modular and hence enable the user to make modifications to the structure to suit a specific application.
QoI-Aware Camera Network-as-a-Service for Social Behavior Analysis
(IEEE, 2021) Shenoy, Meetha V.
The frames captured by the camera should be of sufficient quality, generally measured in pixel density on a target (pixels per foot or pixels per meter (ppm)) to derive information suitable for social behavior analysis. Achieving 24x7 high pixel density coverage incurs a large number of cameras and exorbitant network bandwidth for large scale deployments. In this paper, we introduce additional features to the Camera Network-as-a-Service (CNaaS) concept proposed by Misra et al. to address two aspects pertinent to services related to social behavioral analysis. We present a Quality of Information-Aware (QoI-Aware) CNaaS to address the two aspects. (1) To allow the reuse of cameras which are already available in a locality to minimize the number of additional cameras required to provide the CNaaS service. (2) Inclusion and exclusion of camera node(s) into the CNaaS platform while ensuring fair opportunities to the Camera Network Owners (CNOs) which provide the same Quality of Information (QoI). The simulation results indicate that the proposed scheme is fair to nodes providing the same QoI, reduces the energy consumption, and excludes the cameras which offer lesser QoI. This will lead to an improvement in the usage of network bandwidth, and the profit of the Camera Network Service Provider (CNSP).
RPL*: An Explainable AI-based routing protocol for Internet of Mobile Things
(Elsevier, 2024-10) Shenoy, Meetha V.
The Internet of Mobile Things (IoMT) is an emerging paradigm of Internet of Things (IoT) with special focus on enabling mobility to the ‘things’. Several IoMT applications such as group of robots or drones performing collaborative search and rescue operation, identification of mines, warehouse management, goods delivery, etc can be considered as examples of IoMT systems. In the applications mentioned above, the nodes may send the information in a multi-hop manner to the root or coordinator node which may be static or mobile. While the Routing Protocol for Low Power and Lossy Networks (RPL) is extensively utilized in static IoT networks, it encounters significant limitations in handling mobility and providing resilience against routing attacks in mobile IoT networks. In this work, we propose a modified RPL, RPL* which is robust to handling mobility in nodes and is resilient towards routing attacks. In RPL*, any deviation from the normal behaviors of the network are identified as anomalies using an unsupervised Explainable Artificial Intelligence (XAI) strategy. In RPL*, we propose a novel mobility detection mechanism that will identify the mobility in the network in an energy efficient manner without incurring additional communication overhead. To maintain the connectivity with parent node, we propose a novel proactive connectivity management mechanism in RPL* which will ensure a smooth transition from one parent to another if required, thus avoiding the network partitioning due to mobility. The performance analysis of the system has demonstrated an improvement in packet delivery ratio of the mobile nodes by 40% due to the proposed RPL* when compared to RPL. Also, the proposed XAI strategy provided an F1-score of over 95% for the detection of sink hole and black hole attacks in the tested IoMT network scenarios. It was observed that RPL* improves the performance of the IoMT network when compared to RPL. However it may be noted that the mechanisms introduced to support mobility does not lead to a drop in PDR or increase in control packet overhead for static networks. Hence, RPL* can be considered as an alternative to RPL for IoT as well as IoMT networks.
Sensor Information Processing for Wearable IoT Devices
(Springer, 2019-11) Shenoy, Meetha V.
Sensing technology is one of the core enablers of IoT and the improvement in sensing technology has lead to the proliferation of small form-factor, cost-effective and accurate sensors for wide variety of wearable applications. With wearable devices receiving widespread acceptance, their requirements are becoming more demanding, with the focus shifting from simple monitoring to context aware intelligent devices. This chapter presents a comprehensive description of the technical opportunities and challenges in the design of sensor information processing systems for wearables. A systematic survey of the state of the art architectures for sensor fusion for different application classes of wearable’s is presented. A discussion on design considerations for architecting sensor processing systems, including hardware, networking protocols, and algorithms at the edge, cloud level is provided. The chapter is concluded with a discussion on innovation directions in smart sensing and information processing in wearable devices.