Abstract

The number of individuals having identical names on the internet is increasing. Thus making the task of searching for a specific individual tedious. The user must vet through many profiles with identical names to get to the actual individual of interest. The online presence of an individual forms the profile of the individual. We need a solution that helps users by consolidating the profiles of such individuals by retrieving factual information available on the web and providing the same as a single result. We present a novel solution that retrieves web profiles belonging to those bearing identical Full Names through an end-to-end pipeline. Our solution involves information retrieval from the web (extraction), LLM-driven Named Entity Extraction (retrieval), and standardization of facts using Wikipedia, which returns profiles with fourteen multi-valued attributes. After that, profiles that correspond to the same real-world individuals are determined. We accomplish this by identifying similarities among profiles based on the extracted facts using a Prefix Tree inspired data structure (validation) and utilizing ChatGPT's contextual comprehension (revalidation). The system offers varied levels of strictness while consolidating these profiles, namely strict, relaxed, and loose matching. The novelty of our solution lies in the innovative use of GPT -- a highly powerful yet an unpredictable tool, for such a nuanced task. A study involving twenty participants, along with other results, found that one could effectively retrieve information for a specific individual.

Abstract

A system and method for visualizing large graph data using spirals are provided. The method includes (i) generating communities from an input graph data, (ii) configuring nodes in the communities in an ascending order based on a centrality measure, (iii) determining a spiral for the communities by configuring (a) a node with a highest centrality measure at a spiral center and (b) the nodes in a spiral shape based on the ascending order of the centrality measure along the spiral shape, (iv) determining a first super edge for the spiral of the communities, (v) generating a coarse graph using super nodes, the first super edge, and a second super edge, (vi) configuring, using a standard force-directed layout algorithm, corresponding spirals of the communities on the generated coarse graph based on a weight of the second super edge and attractive forces to generate the visualization of the large graph data.

Abstract

The construction of a decision tree on a given data set involves certain features. In case these features have NULL values during the production environment, the decision tree performance suffers. In this work, we develop a methodology to generate subspace deci- sion tree classifiers, where each decision tree uses non-overlapping subsets of feature sets. We build an ensemble classifier over these subspace classifiers to get better performance. We consider different levels of missing data in our ensemble classifier, to show that it is resilient to missing data and can also give better performance even in cases of incomplete data (that is, data with missing values). We show the viability of our methodology using real-life and synthetic data sets. Our approach delivers a simple yet effective missing data resilient decision tree classifier

Abstract

In order to advance academic research, it is important to assess and evaluate the academic influence of researchers and the findings they produce. Citation metrics are universally used methods to evaluate researchers. Amongst the several variations of citation metrics, the h-index proposed by Hirsch has become the leading measure. Recent work shows that h-index is not an effective measure to determine scientific impact - due to changing authorship patterns. This can be mitigated by using h-index of a paper to compute hindex of an author. We show that using fractional allocation of h-index gives better results. In this work, we reapply two indices based on the h-index of a single paper. The indices are referred to as: hp-index and hp-frac-index. We run large-scale experiments in three different fields with about a million publications and 3,000 authors. Our experiments show that hp-frac-index provides a unique ranking when compared to h-index. It also performs better than h-index in providing higher ranks to the awarded researcher.

Abstract

A system and method for generating a table-driven mutable blockchain are provided. The system includes one or more users 102A-102N associated with one or more nodes 104A-104N, a distributed file unit 106, a distributed ledger 108. The distributed file unit 106 stores a Lineage Table 200 and a global variable P 112, to keep count on the total number of blockchains in the system. The distributed ledger 108 stores one or more blockchains. The node 104A receives transaction details of transaction provided by user 102A through network 110, and defines transaction. The node 104 initializes linked list structure and creates a transaction of which a plurality of modifications is performed on it. The node 104 creates modified transaction in subsequent blockchains and then links these versions by adding sequence of elements in Linked List. The node 104 authenticates new transactions in main blockchain and the modified transactions in subsequent blockchains.

Abstract

In order to advance academic research, it is important to assess and evaluate the academic influence of researchers and the findings they produce. Citation metrics are universally used methods to evaluate researchers. Amongst the several variations of citation metrics, the h-index proposed by Hirsch has become the leading measure. Recent work shows that h-index is not an effective measure to determine scientific impact - due to changing authorship patterns. This can be mitigated by using h-index of a paper to compute h- index of an author. We show that using fractional allocation of h-index gives better results. In this work, we reapply two indices based on the h-index of a single paper. The indices are referred to as: hp-index and hp-frac-index. We run large-scale experiments in three different fields with about a million publications and 3,000 authors. We also compare h-index of a paper with nine h-index like metrics. Our experiments show that hp-frac-index provides a unique ranking when compared to h-index. It also performs better than h-index in providing higher ranks to the awarded researcher.

Abstract

Consider a 2D coordinate space with a set of red and a set of blue points. We define a scenic point as a point that is equidistant to a red point and a blue point. The set of contiguous scenic points form a scenic path. The perpendicular bisectors to the line joining a red point and a blue point forms a scenic path between the red point and the blue point. A scenic route is a traversal made from scenic paths. In this paper, we address this novel problem by (i) designing algorithms for scenic route generation, (ii) studying the algorithms different properties and (iii) analyzing the routes generated by these algorithms. Scenic routes have applications in geo-spatial visualizations and visual analytics

Abstract

In a given 2D space, we can have points with different levels of importance. One would prefer viewing those points from a closer/farther position per their level of importance. A point in 2D from where the user can view two given points per his/her preference of distance is termed a scenic point. We develop the concept of scenic paths in a 2D space for two points that have weights associated with them. Subsequently, we propose algorithms to generate scenic routes a traveler can take, which cater to certain principles which define the scenic routes. Following are the contributions of this paper: (1) mathematical formulation of a scenic point, (2) introduction of scenic routes formed by such scenic points in two-class point configurations in 2D spaces, and (3) design of scenic route generation algorithms that fulfill certain defined requirements.

Abstract

The classic hide-and-seek game is an abstraction for many real- world scenarios like capturing intruders in a closed space, locating objects, patrolling an area, etc. Since most of the present work is based on static obstacles, we address solutions for the hide-and- seek game in an environment where the obstacles are not static. We design strategies that would facilitate seekers to capture hiders in an environment with moving obstacles. We have three strategies: Baseline strategy, Set-cover strategy, and Sweep strategy, which use different surveillance techniques to be followed by the seekers. We simulate the methods and compare their performance in different scenarios. While the baseline strategy demands many seekers in large environments, the other two strategies, set-cover and sweep, are ideal for applying in large environments as they require fewer seekers in the same environment.

Abstract

In this work, we introduce the problem of scenic routes among points in R d . The key development is the nature of the problem in terms of both defining the concept of scenic points and scenic routes and then coming up with algorithms that meet different criteria for the generated scenic routes. The scenic routes problem provides a visual trajectory for a user to comprehend the layout of high-dimensional points. The nature of this trajectory and the visual layout of the points have applications in comprehending the results of machine learning supervised and unsupervised learning techniques. We study the problem in 2D and 3D (with two color points) before exploring the issues in R d . The red/blue points in our examples could be to be in a class or not to be in a class. The applications could include landscape design to adhere to the scenic beauty of the artifacts on the ground. The generation of equally separated layouts for designing composite hardware where interference could be an issue. Keywords: sce