Shyamanta M Hazarika

Indian Institute of Technology Guwahati | IIT Guwahati · Department of Mechanical Engineering

This work analyzes existing soft hand exoskeleton models in-depth, points out their drawbacks and difficulties, and offers design suggestions that prioritize adaptability, comfort, and compactness. The key areas of interest are the tendon-driven mechanism, tendon routing, and dynamics analysis because they provide essential knowledge for selecting...

Maintaining object grasp stability represents a pivotal challenge within the domain of robotic manipulation and upper-limb prosthetics. Perturbations originating from external sources frequently disrupt the stability of grasps, resulting in slippage occurrences. Also, if the grasping forces are not optimal while controlling the slip, it may result...

Deep learning-based affordance research is motivated by the need to achieve higher degrees of automation and accuracy. On the contrary, the concept of affordance originated to explain the intuitive intelligent responses of humans in their interaction with the environment. With a state-of-the-art supervised deep learning model, achieving high accura...

Grasp classification is pivotal for understanding human interactions with objects, with wide-ranging applications in robotics, prosthetics, and rehabilitation. This study introduces a novel methodology utilizing a multisensory data glove to capture intricate grasp dynamics, including finger posture bending angles and fingertip forces. Our dataset c...

Data gloves play a crucial role in study of human grasping, and could provide insights into grasp synergies. Grasp synergies lead to identification of underlying patterns to develop control strategies for hand exoskeletons. This paper presents the design and implementation of a data glove that has been enhanced with instrumentation and fabricated u...

The rehabilitation of hand functionality stands as a crucial challenge in the medical field, especially for individuals with neuromuscular impairments. Traditional robotic systems, while beneficial, often lack the flexibility and comfort required for patient-friendly rehabilitation. Addressing this, we introduce a novel tendon-driven soft hand exos...

This paper presents the development of a novel soft hand exoskeleton for the rehabilitation of stroke patients with disability in extreme upper limbs. The research aims to achieve, at low cost, a fully integrated system that assists in sufficient hand opening and closing in rehabilitation process while grasping objects used in daily living activiti...

Grasping, a fundamental aspect of human motor skills, involves the intricate coordination of sensory and motor systems to manipulate objects effectively. Accurate grasp classification, crucial for advancing human-machine interaction in robotics and prosthetics, involves categorizing various hand-grasping patterns. This study explores a grasp classi...

For visual information processing, the derivation of meaningful low-level spatio-temporal information is challenging. In line with human visualisation and perception in spatial problem- solving, we believe explicit representations hold promise for efficient low-level abstractions. An approach for mapping spa- tial objects and relations, exploring d...

Human grasps involved in activities of daily living rely on the correlation of multiple degrees of freedom in a hand. This correlation is called grasp synergies and holds promise for efficient control of robotic hands including prostheses and exoskeletons. A number of studies involving human grasping experiments have been reported. However, the app...

This paper presents a comprehensive study of real-time finger movement classification using surface electromyogram (EMG) signals. The objective is to accurately classify four different grasp types by analyzing the signals obtained from the forearm muscles. Various commonly used EMG signal classification methods are evaluated and compared: K-Nearest...

Tactile perception is crucial for detecting contact and identifying the attributes associated with it. In this research, we demonstrate the mechanical properties of objects may be inferred by employing data-driven algorithms from fingertip contact. We collected information from a fingertip pressure sensor as it established contact with several obje...

The ability to manipulate objects with stability is a crucial characteristic of human hands. However, it still remains a challenge to replicate this function in robotic hands in totality. While commanding the actuators to grasp an object, disturbances may occur which can result in slippage of the object, making it difficult to manipulate the object...

Haptics, or the sense of touch, is critical in hand prostheses since providing haptic feedback can significantly enhance control. Research on haptic feedback for upper limb prostheses today is focused on the neuromorphic encoding of the sensory cues leading to the feeling of an embodiment of the prosthetic device. The present paper provides a surve...

This paper outlines a method to design an underactuated, linkage-based hand exoskeleton. A planar 8-link mechanism with phalanges and articulations as part of the kinematic chain is used for each finger. The links are attached to the proximal and distal phalanges. For the thumb, a planar 6-link mechanism directly connected at the distal phalanx is...

Human hand performs multiple grasp types during daily living activities. Adaptation of grasping force to avoid object slippage as employed by human brain has been postulated as an intelligent approach. Recently, research for prosthetic hands with human-like capabilities has been followed by many researchers, but with limited success. Advanced prost...

Object affordance, a characterization of the different functionalities of an object, refers to an object's numerous possibilities of interaction. It has a significant part to play in priming motoric actions which depends on the actor's spontaneous neurological behaviour. Action Observation (AO) and Motor Imagery (MI) also lead to the stimulation of...

The present work focuses on the investigation of unsteady aerodynamics of plunging cambered foil with conditions corresponding to that of a Micro Air Vehicle. The effect of non-dimensional plunge amplitude, plunging frequency and the dimensionless plunge velocity on the propulsive performance of a harmonically plunging cambered foil are studied by...

For an underactuated anthropomorphic hand, apart from replicating the geometry, biomimicry of human counterpart requires design based on functional biomimesis. Optimization based on grasping capabilities to generate a stable grasp for underactuated anthropomorphic hands has been a recent focus. In this article, we optimize the actuation parameters...

We present a novel and efficient semantic segmentation architecture termed Light U-Net in this paper. Light U-Net is less complex with regard to the parameter and model size than the original U-Net. We also propose a network and training strategy based on geometric data augmentation for efficient use of the annotated images from small and limited d...

Scene parsing is the problem of densely labeling every pixel in an image with a meaningful class label. Driven by powerful methods, remarkable progress has been achieved in scene parsing over a short period of time. With growing data, non-parametric scene parsing or label transfer approach has emerged as an exciting and rapidly growing research are...

A biomimetic wing is designed by considering the wing of a natural flyer (Passer Domesticus) as a reference. Since the birds have thin wings, Bergey BW-3, a thin and highly cambered airfoil, is used to design wing’s cross-section. To investigate the aerodynamic characteristics of biomimetic wing, numerical and experimental studies are carried out a...

This paper aims to investigate the effect of pitching amplitude, mean angle of attack and frequency of oscillation on the propulsive characteristics of a harmonically oscillating cambered airfoil at Reynolds number of 5x10^4. The flow field around the foil is analysed to study the influence of the above parameters and to understand the reasons behi...

We are interested in the encoding of local descriptors of an image (e.g. SIFT) to design a compact representation vector and thereby address scalable image retrieval. We revisit the implicit design choices in the popular vector of locally aggregated descriptors (VLAD), which aggregates the residuals of descriptors to the codewords. VLAD’s use of a...

Emotion Recognition is an important problem within Affective Computing and Human Computer Interaction. In recent years, various machine learning models have provided significant progress in the field of emotion recognition. This paper proposes a framework for EEG-based emotion recognition using Multi Layer Perceptron (MLP). Power Spectral Density f...

Given very poor accessibility to prostheses, particularly in low income countries, this paper discusses design and development of a non-assembly hand prostheses. The non-assembly five fingered hand is arrived from an anthropomorphic CAD model following non-assembly mechanism design principles. An in-house low cost light dependent resistor band, tog...

Lately there has been an increasing interest in learning object affordances. This is particularly to address human activity understanding and intention recognition for household robots. However, most existing approaches do not concentrate on imbibing new perceptual models of inferring affordances from visual input. Such models are key for object us...

Explicit reasoning over a spatial substrate, i.e., space–time information structures underlying a spatial problem, simplifies reasoning. Diagrammatic reasoning makes use of diagrams for exploiting such underlying structures. This paper proposes a novel approach combining diagrammatic reasoning with qualitative spatial and temporal reasoning techniq...

For effective Human-Robot Interaction (HRI), an intelligent wheelchair (IW) need to be cognitively enhanced. Robot Operating System (ROS) has been steadily gaining popularity among robotics researchers as an open source framework for robot control. This paper presents ccaROS - a new ROS node for a Cognitive Collaborative Architecture to achieve bet...

Common Spatial Pattern (CSP) is the most popular method in motor imagery (MI) based Brain–Computer Interfaces (BCI) for extracting features from electroencephalogram (EEG) signals. Due to the non-stationary nature of EEG signals, the CSP computed on the training data may not be optimal for the evaluation data. One of the major causes of such non-st...

In the era of intelligent computing, computational progress in text processing is an essential consideration. Many systems have been developed to process text over different languages. Though, there is considerable development, they still lack in understanding of the text, i.e., instead of keeping text as knowledge, many treat text as a data. In th...

Prosthetic hands have made a significant influence on the quality of life of people with upper arm amputation. Research on prosthetic hands today is focused on replicating the functionalities of the biological hands. The present article provides a bibliometric survey on bionic hands, done through a compilation of a scientific publications database...

There is a rising trend in exploring the capability of inverse reinforcement learning (IRL) in high dimensional demonstrations. Our aim is to recognise human intents from video data within an IRL framework. For this, we present a two-layered maximum likelihood IRL model. The usefulness of knowledge representation (KR) schemes and availability of ad...

Motion patterns are spatiotemporal.Talukdar, Upasana Human everyday spatiotemporal reasoning is predominantly qualitative; hence, Hazarika, Shyamanta M. qualitative abstraction of motion patterns holds promise. Reasoning over qualitative models of spatiotemporal change is referred to as qualitative spatiotemporal reasoning (QSTR). Recognition of pa...

Autonomous vehicles rely on their sensors specializing in specific tasks to understand their surroundings. Camera is perhaps one of the most versatile of them. Frames from a camera, when processed, form the basis for object detection in the surroundings, which is an embodiment of perception. The major tasks in perception are object tracking and loc...

Objective: Electroencephelogram (EEG) signals are non-stationary. This could be due to the internal fluctuation of brain states such as fatigue, frustration, etc. This necessitates the development of adaptive Brain-Computer Interfaces (BCI) whose performance does not deteriorate significantly with the adversary change in the cognitive state. In th...

We revisit the implicit design choices in the popular vector of locally aggregated descriptors (VLAD), which aggregates the residuals of local image descriptors. Since original VLAD ignores high-order statistics the resultant vector is not discriminative enough. We address this issue by exploiting high-order statistics for gaining complementary inf...

Scene parsing refers to the task of labeling every pixel in an image with the class label it belongs to. In this paper, we propose a novel scalable non-parametric scene parsing system based on superpixels correspondence. The non-parametric approach requires almost no training and can scale up to datasets with thousands of labels. This involves retr...

Robotic devices can accelerate the rehabilitation process of an impaired patient by increasing the frequency of treatment and eliminating the need for a physiotherapist. This paper presents the development of a novel human finger exoskeleton for the motor rehabilitation of post-stroke patients by providing assistance-as-required support to patients...

Even though it has long been felt that psychological state influences the performance of brain-computer interfaces (BCI), formal analysis to support this hypothesis has been scant. This study investigates the inter-relationship between motor imagery (MI) and mental fatigue using EEG: a. whether prolonged sequences of MI produce mental fatigue and b...

Estimating a proper grasping force for a prosthetic hand is a difficult problem. This is partly due to a lack of detailed sensory feedback. Application of too small a grasping force may allow an object to slip; on the contrary a large applied force may deform the grasped object. For a prosthetic hand, bionic reflex refers to reconstruction of the h...

Within human Intent Recognition (IR), a popular approach to learning from demonstration is Inverse Reinforcement Learning (IRL). IRL extracts an unknown reward function from samples of observed behaviour. Traditional IRL systems require large datasets to recover the underlying reward function. Object affordances have been used for IR. Existing lite...

This paper presents a bionic reflex control strategy for a kinematically constrained robotic finger. Here, the bionic reflex is achieved through a force tracking impedance control strategy. The dynamic model of the finger is reduced subject to kinematic constraints. Thereafter, an impedance control strategy that allows exact tracking of forces is d...

Maximum relevance and minimum redundancy (mRMR) has been well recognised as one of the best feature selection methods. This paper proposes a Kernel Partial Least Square (KPLS) based mRMR method, aiming for easy computation and improving classification accuracy for high-dimensional data. Experiments with this approach have been conducted on seven re...

In this chapter, the history of robotics is traced. The emphasis is on highlighting significant moments in robotics history that had far-reaching consequences on the field. A brief presentation of the technical intricacies is followed by highlight of the recent trends. The chapter finally dwells on the direction robotics is surging and poised to ch...

For people with mobility impairment, powered wheelchairs are able to extend independent transportation. However, most users find it difficult to operate the powered wheelchairs effectively. This can be due to variety of physical or cognitive impairments. Herein lies the motivation of developing intelligent wheelchairs that provide the user, assista...

Human activity recognition (HAR) deals with recognition of activities or interactions that include humans within a video. Entities occurring in a video frame can be abstracted in variety of ways, ranging from the detailed silhouette of the entity to the very basic axis-aligned minimum bounding rectangles (MBR). On one end of the spectrum, using a d...

We present an inclusive review of recent and successful content-based e-mail spam filtering techniques. Our focus is mainly on machine learning-based spam filters and variants inspired from them. We report on relevant ideas, techniques, taxonomy, major efforts, and the state-of-the-art in the field. The initial interpretation of the prior work exam...

In Formal Concept Analysis, stability is an important utility measure to rank concepts. However, computation of stability is considered to be a hard problem. Efficient algorithms having good bounds to estimate stability holds promise. In this paper, an effective graph based technique is proposed to estimate stability. Our estimation algorithm has a...

Appropriate qualitative abstraction of a given domain is essential for qualitative reasoning. This chapter presents a method of extracting episodes from a video, where an episode is a maximal temporal interval within which qualitative spatial relations between objects do not change. Movement patterns of objects during an episode are also estimated....

Ontology is a formal description of a conceptualization for a domain of discourse. Revision of an ontology is primarily required because of changes in the domain, its conceptualization, or in the defined specification. This paper proposes an approach for revision of SHOIN-D ontology, wherein changes are incorporated into the ontology without human...

This paper presents a comprehensive representation for video analysis combining qualitative reasoning with diagrammatic reasoning. The hybrid approach is motivated by the power of diagrams that allows explicit relational representation of entities involved. Perception of qualitative information over the underlying representation, employment of inte...

Of late, human activity recognition (HAR) in video has generated much interest. A fundamental step is to develop a computational representation of interactions. Human body is often abstracted using minimum bounding rectangles (MBRs) and approximated as a set of MBRs corresponding to different body parts. Such approximations assume each MBR as an in...

Within rehabilitation robotics, machines are being designed to help human in activities of everyday life. Mobility is an essential component for independent living. Autonomous machines with their high degree of mobility are becoming an integral part of assistive devices leading to a number of developments in mobility assistance. This is primarily i...

The paper presents a method that automatically segment EEG data and design an optimal spatio-temporal filter to improve the performance of EEG based BCIs. An adaptive sliding window method is proposed for automatic trial segmentation. Common Spatial Pattern is used for extracting features while Davies Bouldin Index is used as a cost function to sel...

Effective human–machine collaboration is a long standing problem within rehabilitation robotics. Machines that affect peer-to-peer interaction hold promise. Agents can serve as the basis for such machines. Belief–desire–intention (BDI) paradigm is used to achieve human-like intelligence. However, the BDI model does not emulate human-like qualities...

Retention of residual skills for persons who partially lose their cognitive or physical ability is of utmost importance. Research is focused on developing systems that provide need-based assistance for retention of such residual skills. This paper describes a novel cognitive collaborative control architecture C3A, designed to address the challenges...

Mental Fatigue is a cognitive state which is an outcome of labour or protracted exercise finally leading to downgrading of mental performance. This leads to reduction in efficiency and disinclination of motor skills. Analysis of mental fatigue thus becomes momentous for assessing one’s capability. The aim here is to analyse whether motor imagery is...

Object affordances provide useful information related to understanding of human activities. The aim of this paper is to create an ontology for object affordance reasoning that can be shared across different assistive robots operating within the household domain. A novel ontology called O-PrO (Object Property Ontology) consisting of 61 household obj...

Assistive technology for the visually impaired and blind people is a research field that is gaining increasing prominence owing to an explosion of new interest in it from disparate disciplines. The field has a very relevant social impact on our ever-increasing aging and blind populations. While many excellent state-of-the-art accounts have been wri...

Electroencephalograph (EEG) signals associated with motor imagery (MI) are highly non-Gaussian, non-stationary and have non- linear characteristics. Bispectral analysis is an advanced signal processing technique that quantifies quadratic non-linearities (phase-coupling) among the components of a signal and holds promise for characterizing MI-relate...

Emotion recognition from electroencephalogram (EEG) signals is one of the most challenging tasks. Bispectral analysis offers a way of gaining phase information by detecting phase relationships between frequency components and characterizing the non- Gaussian information contained in the EEG signals. In this paper, we explore derived features of bis...

In this paper we present a collaborative control architecture for a robotic wheelchair with the aim of providing “assistance as required”. The architecture is based on cBDI - an extension to the Belief-Desire-Intention model to support human-machine collaboration. We present results of an evaluation of the architecture in a simulated environment an...

For a collaborative assistive device, human intent recognition (IR) is one of the first and foremost requirements. Formalizing the complex process of human IR in a compact yet expressive mathematical model holds promise. We put forward a Hierarchical Finite State Machine (H-FSM) for human IR within a generalized framework for collaborative assistiv...

In quest for an efficient representation schema for activity recognition in video, we employ techniques combining diagrammatic reasoning (DR) with qualitative spatial and temporal reasoning (QSTR). QSTR allows qualitative abstraction of spatio-temporal relations among objects of interest; and is often thwart by ambiguous conclusions. 'Diagrams' inf...

Deriving a low-dimensional yet informative and distinguishing feature set to significantly improve the performance of electromyogram (EMG)-based grasp recognition is one of the long standing problems in rehabilitation robotics. This paper proposes the use of the R2 value derived from one-way analysis of variance to evaluate the linear relationship...

We present a comprehensive review of the most effective content-based e-mail spam filtering techniques. We focus primarily on Machine Learning-based spam filters and their variants, and report on a broad review ranging from surveying the relevant ideas, efforts, effectiveness, and the current progress. The initial exposition of the background exami...

Special Session on Perception: Cognition & HCI, IHCI 2015, IIIT-Allahabad, India. Paper Code: S01

This article address the issue of natural gait cycle emulation by lower limb prosthesis. We present a model predictive controller (MPC) for gait control of the Jaipur Foot; developed by Bhagwan Mahaveer Viklang Sahayata Samiti, India. The controller anticipates future gait cycle for the prosthetic leg based on initial time horizon of human gait cyc...

Learning patterns from spatio-temporal data streams is an important problem within Artificial Intelligence. Knowledge is important for recognition of patterns. Representation of large and diverse knowledge requires formal basis. Description Logics (DLs) constitute a family of knowledge representation formalism which provide object-oriented represen...

This paper presents a wearable navigation assistive system for the blind and the visually impaired built with off-the-shelf technology. Microsoft Kinect's on board depth sensor is used to extract Red, Green, Blue and Depth (RGB-D) data of the indoor environment. Speeded-Up Robust Features (SURF) and Bag-of-Visual-Words (BOVW) model is used to extra...

This paper describes the Tezpur University dataset of online handwritten Assamese characters. The online data acquisition process involves the capturing of data as the text is written on a digitizer with an electronic pen. A sensor picks up the pen-tip movements, as well as pen-up/pen-down switching. The dataset contains 8,235 isolated online handw...

A long standing goal in rehabilitation robotics is to emulate the human-like stable grasping operations by upper limb prosthesis. For stable grasping and manipulation by a prosthetic hand, the finger joints should follow the trajectories of the natural counterparts. Although a number of commercial prosthetic hands and research prototypes have been...