Ayush Kumar

Harvard Medical School | HMS · Department of Ophthalmology, Schepens Eye Research Institute

Tracking head movement in outdoor activities is more challenging than in controlled indoor lab environments. Large-magnitude head scanning is common under natural conditions. Compensatory gaze (head and eye) scanning while walking may be critical for people with visual field loss. We compared the accuracy of two outdoor head tracking methods: diffe...

This paper proposes an open source visual analytics tool consisting of several views and perspectives on eye movement data collected during code reading tasks when writing computer programs. Hence the focus of this work is on code and program comprehension. The source code is shown as a visual stimulus. It can be inspected in combination with overl...

We explore techniques for eye gaze estimation using machine learning. Eye gaze estimation is a common problem for various behavior analysis and human-computer interfaces. The purpose of this work is to discuss various model types for eye gaze estimation and present the results from predicting gaze direction using eye landmarks in unconstrained sett...

Eye movements are closely related to the cognitive processes and often act as a window to the brain and mind. To facilitate a window to the brain using eye movements, we propose EyeFIX, an interactive visual analytics interface. Our interface currently focuses on processing gaze movements to generate the two most prominent events, fixations, and sa...

With great technological advancement, the scientific community is overwhelmed with the amount of data being produced. Thus, analyzing these data has become a crucial part of the decision-making process in almost all research fields, be it medicine, gaming, chemistry, physics, psychology, transportation, economics, and others. Challenges deepen when...

Many applications in eye tracking have been increasingly employing neural networks to solve machine learning tasks. In general, neural networks have achieved impressive results in many problems over the past few years, but they still suffer from the lack of * Corresponding interpretability due to their black-box behavior. While previous research on...

Eye movement data analysis plays an important role in examining human cognitive processes and perceptions. Such analysis at times needs data recording from additional sources too during experiments. In this paper, we study a pair programming based collaboration using two eye trackers, stimulus recording, and an external camera recording. To analyze...

We present an algorithmic and visual grouping of participants and eye-tracking metrics derived from recorded eye-tracking data. Our method utilizes two well-established visualization concepts. First, parallel coordinates are used to provide an overview of the used metrics, their interactions, and similarities, which helps select suitable metrics th...

Yarbus' claim to decode the observer's task from eye movements has received mixed reactions. In this paper, we have supported the hypothesis that it is possible to decode the task. We conducted an exploratory analysis on the dataset by projecting features and data points into a scatter plot to visualize the nuance properties for each task. Followin...

Analysis of road accidents is crucial to understand the factors involved and their impact. Accidents usually involve multiple variables like time, weather conditions, age of driver, etc. and hence it is challenging to analyze the data. To solve this problem, we use Multiple Correspondence Analysis (MCA) to first, filter out the most number of varia...

Eye movements recorded for many study participants are difficult to interpret, in particular when the task is to identify similar scanning strategies over space, time, and participants. In this paper we describe an approach in which we first compare scanpaths, not only based on Jaccard (JD) and bounding box (BB) similarities, but also on more compl...

Analyzing and visualizing eye movement data can provide useful insights into the connectivities and linkings of points and areas of interest (POIs and AOIs). Those typically time-varying relations can give hints about applied visual scanning strategies by either individual or many eye tracked people. However, the challenging issue with this kind of...

In this paper we describe an interactive and web-based visual analytics tool combining linked visualization techniques and algorithmic approaches for exploring the hierarchical visual scanning behavior of a group of people when solving tasks in a static stimulus. This has the benefit that the recorded eye movement data can be observed in a more str...

In this paper, we describe the design of an interactive visualization tool for the comparison of eye movement data with a special focus on the outliers. In order to make the tool usable and accessible to anyone with a data science background, we provide a web-based solution by using the Dash library based on the Python programming language and the...

Yarbus' claim to decode the observer's task from eye movements has received mixed reactions. In this paper, we have supported the hypothesis that it is possible to decode the task. We conducted an exploratory analysis on the dataset by projecting features and data points into a scatter plot to visualize the nuance properties for each task. Followin...

Analysis of road accidents is crucial to understand the factors involved and their impact. Accidents usually involve multiple variables like time, weather conditions, the age of driver etc. and hence it is challenging to analyze the data. To solve this problem, we use Multiple Correspondence Analysis (MCA) to first, filter out the most number of va...

This work studies the use of a conventional eye tracking system for analysis of an online game player's thinking processes. For this purpose, the eye gaze data of several users playing a simple online turn-based checkers game were recorded and made available in real-time to gaze-informed players. The motivation behind this work is to determine if m...

This work studies the use of a conventional eye tracking system for analysis of an online game player's thinking processes. For this purpose, the eye gaze data of several users playing a simple online turn-based checkers game were recorded and made available in real-time to gaze-informed players. The motivation behind this work is to determine if m...

We present an algorithmic and visual grouping of participants and eye-tracking metrics derived from recorded eye-tracking data. Our method utilizes two well-established visuali-zation concepts. First, parallel coordinates are used to provide an overview of the used metrics, their interactions, and similarities, which helps select suitable metrics t...

We describe a matrix-based visualization technique for algorithmically and visually comparing metrics in eye movement data. To reach this goal, a set of scanpath trajectories is first preprocessed andtransformedintoasetofmetricsdescribingcommonalitiesand differences of eye movement trajectories. To keep the generated diagrams simple, understandable,...

We introduce a visualization technique called color bands for showing the time-varying eye movement behavior of eye-tracked people. Our contribution is the clutter-free representation of time-varying x- and y-positions of gaze data. We map these coordinates to vertical positions from left to right as in traditional line plots. On top, we display th...

We introduce the concept of Data Memes as artistic visuals of data in which users can merge data visualizations with an image such that the structure of the image supports the user's intended meaning (or interpretation) of the data. Since Data Memes can represent very personal views, it is natural to employ them in the visualization of personal dat...

In this paper, we propose a new image interpolation method using adaptive weights based on inverse gradients and distances from the pixels used in prediction. Since the weights are based on different spatial locations of the pixels, this allows preservation of important edge information and hence to prevent extensive blurring across edges in the up...

Interpolation is a technique for obtaining new unknown data points within the range of discrete known data points and is often used to recover an image from its downsampled version, or to simply perform image expansion. Recently a lot of interpolation algorithms are proposed, but these interpolation algorithms are highly computationally expensive....

Quality degradation and computational complexity are the major challenges for image interpolation algorithms. Advanced interpolation techniques achieve to preserve fine image details but typically suffer from lower computational efficiency, while simpler interpolation techniques lead to lower quality images. In this paper, we propose an edge preser...

Incredible evolution of Internet, Digital devices and communication channels lead to an enormous increase in data leading to demand of Data security systems. Image stenography is the technique to hide data inside an image. This paper proposes a message dependent image stenography technique for concealing information into a cover image. Arnold trans...

In view of high data embedding capacity and many real time applications, we have proposed a reversible invisible watermarking algorithm. The technique is used to embed a set of watermark data in an image using a one pass embedding process and later recovering the original image without any loss, after the extraction of watermark. Main motivation be...

This paper proposes an efficient procedure for removal of salt and pepper noises from the noisy images on the basis of their local edge preserving filters. This algorithm consists of two major stages. In the first stage, the maximum and minimum pixel value in the the corrupted image is used to select noisy pixels or noise free pixels and then in se...

This paper presents a new generic algorithm for image interpolation as well as lossless image coding. Main motivation behind the work is to reduce computational complexity involved in using Least Square Error Minimization (LS). The proposed method down samples the given image to its quarter size and then to its (1/16)th size. For each downsampled i...

In this paper a wavelet transform based optimum subband thresholding algorithm is proposed. This algorithm is used for denoising of heart sound signals that are highly corrupted by noise. The proposed algorithm applies signal dependent optimum thresholding to all the subbands of the signal. The algorithm is tested against different noise densities...

Segmentation and exact timing information of PCG(Phonocardiographic) Signals and its components S1, Systolic period, S2 and Diastolic period in order with time of great importance for accurate diagnosis. In this work, we propose a novel algorithm for the segmentation of Phonocardiographic Signals into its constituent components having both normal a...

This paper proposes a new interpolation approach for obtaining high resolution (HR) images from its low resolution (LR) images. We are using the Least Squared based block by block prediction scheme to estimate the predictors using Jacobian iteration method. In spite of Jacobian's Iterative property of convergence for diagonally dominant matrices on...

In this paper, we propose a new adaptive image interpolation algorithm for enhancement of natural images. The proposed method uses different algorithms namely SAI, SPIA and Context-Based Image Interpolation Algorithm (CBIA) techniques, for both edgy and smooth type of images. The detailed part of smooth type image is interpolated by SAI, while we p...

Recently a lot of interpolation algorithms are proposed, but these interpolation algorithms are highly computationally expensive. Hence these algorithms cannot be implemented and used in real time applications. In view of real time applications we have proposed a computationally simple interpolation algorithm. In our proposed algorithm the unknown...