Arrow Research search

Author name cluster

Vijay Kumar

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers
2 author rows

Possible papers

17

JBHI Journal 2025 Journal Article

Deep Drug Synergy Prediction Network Using Modified Triangular Mutation-Based Differential Evolution

  • Dilbag Singh
  • Ahmad Ali AlZubi
  • Manjit Kaur
  • Vijay Kumar
  • Heung-No Lee

Drug combination therapy is crucial in cancer treatment, but accurately predicting drug synergy remains a challenge due to the complexity of drug combinations. Machine learning and deep learning models have shown promise in drug combination prediction, but they suffer from issues such as gradient vanishing, overfitting, and parameter tuning. To address these problems, the deep drug synergy prediction network, named as EDNet is proposed that leverages a modified triangular mutation-based differential evolution algorithm. This algorithm evolves the initial connection weights and architecture-related attributes of the deep bidirectional mixture density network, improving its performance and addressing the aforementioned issues. EDNet automatically extracts relevant features and provides conditional probability distributions of output attributes. The performance of EDNet is evaluated over two well-known drug synergy datasets, NCI-ALMANAC and deep-synergy. The results demonstrate that EDNet outperforms the competing models. EDNet facilitates efficient drug interactions, enhancing the overall effectiveness of drug combinations for improved cancer treatment outcomes.

Details DOI

JBHI Journal 2024 Journal Article

Guest Editorial Artificial Intelligence-Driven Biomedical Imaging Systems for Precision Diagnostic Applications

  • Vijay Kumar
  • Amit Kumar Singh
  • Robertas Damasevicius

Recent advances in Artificial Intelligence (AI) have revolutionized the area of biomedical imaging, providing unprecedented prospects for precision diagnoses. This special issue offers an overview of the integration of AI into biomedical imaging systems and its tremendous impact on improving diagnostic accuracy and efficiency. The combination of AI and biomedical imaging has resulted in intelligent systems capable of deciphering complex medical pictures with amazing precision. Deep learning algorithms, particularly convolutional neural networks (CNNs), have shown exceptional capabilities in recognising patterns and extracting meaningful information from a variety of imaging modalities, including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) [1].

Details DOI

JBHI Journal 2023 Journal Article

MLNet: Metaheuristics-Based Lightweight Deep Learning Network for Cervical Cancer Diagnosis

  • Manjit Kaur
  • Dilbag Singh
  • Vijay Kumar
  • Heung-No Lee

One of the leading causes of cancer-related deaths among women is cervical cancer. Early diagnosis and treatment can minimize the complications of this cancer. Recently, researchers have designed and implemented many deep learning-based automated cervical cancer diagnosis models. However, the majority of these models suffer from over-fitting, parameter tuning, and gradient vanishing problems. To overcome these problems, in this paper a metaheuristics-based lightweight deep learning network (MLNet) is proposed. Initially, the hyper-parameters tuning problem of convolutional neural network (CNN) is defined as a multi-objective problem. Particle swarm optimization (PSO) is used to optimally define the CNN architecture. Thereafter, Dynamically hybrid niching differential evolution (DHDE) is utilized to optimize the hyper-parameters of CNN layers. Each particle of PSO and solution of DHDE together represent the possible CNN configuration. F-score is used as a fitness function. The proposed MLNet is trained and validated on three benchmark cervical cancer datasets. On the Herlev dataset, MLNet outperforms the existing models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 1. 6254%, 1. 5178%, 1. 5780%, 1. 7145%, and 1. 4890%, respectively. Also, on the SIPaKMeD dataset, MLNet achieves better performance than the existing models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 2. 1250%, 2. 2455%, 1. 9074%, 1. 9258%, and 1. 8975%, respectively. Finally, on the Mendeley LBC dataset, MLNet achieves better performance than the competitive models in terms of accuracy, f-measure, sensitivity, specificity, and precision by 1. 4680%, 1. 5845%, 1. 3582%, 1. 3926%, and 1. 4125%, respectively.

Details DOI

NeurIPS Conference 2020 Conference Paper

Neurosymbolic Transformers for Multi-Agent Communication

  • Jeevana Priya Inala
  • Yichen Yang
  • James Paulos
  • Yewen Pu
  • Osbert Bastani
  • Vijay Kumar
  • Martin Rinard
  • Armando Solar-Lezama

We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.

PDF Details

RLDM Conference 2017 Conference Abstract

Neural Network Memory Architectures for Autonomous Robot Navigation

  • Steven Chen
  • Nikolay Atanasov
  • Arbaaz Khan
  • Konstantinos Karydis
  • Daniel Lee
  • Vijay Kumar

This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the environment to overcome cul-de-sacs and plan feasible motions. Yet, maintaining an accurate global map may be challenging in real-world settings. A possible way to mitigate this limitation is to use learning techniques that forgo hand-engineered map representations and infer appropriate control responses directly from sensed information. An important but unexplored aspect of such approaches is the effect of memory on their performance. This work is a study of memory structures for deep-neural-network-based robot navigation, and offers novel tools to train such networks from supervision and quantify their ability to generalize to unseen scenarios. We analyze the separation and generalization abilities of feedforward, long short-term memory, and differentiable neural computer networks by evaluating the generalization ability of neural networks by estimating the Vapnik-Chervonenkis (VC) dimension of maximum-margin hyperplanes trained in the feature space learned by the networks’ upstream layers. We validate that these VC-dimension measures are good predictors of actual test performance. The reported method can be applied to deep learning problems beyond robotics.

PDF Details

IS Journal 2007 Journal Article

Integrating Human Inputs with Autonomous Behaviors on an Intelligent Wheelchair Platform

  • Sarangi P. Parikh
  • Valdir Grassi
  • Vijay Kumar
  • Jun Okamoto

Nearly five million individuals in the US have limited arm and hand movement, making it difficult or impossible for them to use computers and products with embedded computers, such as wheelchairs, household appliances, office electronic equipment, and robotic aids. Although some current wheelchair systems have embedded computers, they have very little computer control and require precise, low-level control inputs from the user; interfaces are similar to those found in passenger cars. The rider must continuously specify the chair's direction and, in some cases, velocity using a joystick-like device. Unfortunately, many users who could benefit from powered wheelchairs lack these fine motor skills. For instance, those with cerebral palsy might not be able to guide a chair through a narrow opening, such as a doorway, without repeatedly colliding into the sides. These types of physically challenging environments can be frustrating and require a lot of user effort. At the University of Pennsylvania's general robotics, automation, sensing, and perception lab, we developed the smart chair, a smart wheelchair with intelligent controllers that lets people with physical disabilities overcome these difficulties. By outfitting the wheelchair with cameras, a laser range finder, and onboard processing, we give the user an adaptable, intelligent control system. A computer-controlled wheelchair's shared control framework allows users complete control of the chair while ensuring their safety

Details DOI

ICRA Conference 2003 Conference Paper

A strategy and a fast testing algorithm for object caging by multiple cooperative robots

  • Zhi Dong Wang
  • Vijay Kumar
  • Yasuhisa Hirata
  • Kazuhiro Kosuge

This paper addresses the problem of multi-robots object transportation by using the concept of object closure. Once object closure is achieved, the robots can cooperatively drag or flow the trapped object to the desired goal. In this paper, we address the concept CC-closure object used for efficient testing of object closure. Properties of the CC-closure object and testing algorithm are described. Finally, an example of object closure constructed from both bodies and hands of mobile-manipulators is discussed and an experiment is presented for illustrating the proposed concept.

Details

ICRA Conference 2002 Conference Paper

Object Closure and Manipulation by Multiple Cooperating Mobile Robots

  • Zhi Dong Wang
  • Vijay Kumar

We address the manipulation of planar objects by multiple cooperating mobile robots using the concept of object closure. In contrast to form or force closure, object closure is a condition under which the object is trapped so that there is no feasible path for the object from the given position to any position that is beyond a specified threshold distance. Once object closure is achieved, the robots can cooperatively drag or flow the trapped object to the desired goal. We define object closure and develop a set of decentralized algorithms that allow the robots to achieve and maintain object closure. We show how simple, first-order, potential field based controllers can be used to implement multirobot manipulation tasks.

Details

ICRA Conference 1998 Conference Paper

Analysis of Frictional Contact Models for Dynamic Simulation

  • Peter R. Kraus
  • Vijay Kumar
  • Pierre Dupont

Simulation of dynamic systems possessing unilateral frictional contacts is important to many industrial applications. While rigid body models are often employed, it is well established that friction can cause problems with the existence and uniqueness of the forward dynamics problem. In these situations, we argue that compliant contact models, while increasing the length of the state vector, successfully resolve these ambiguities. The simplicity and efficiency of rigid body models, however, provide strong motivation for their use during those portions of a simulation when the compliant contact model indicates a unique and stable solution. We use singular perturbation theory in combination with linear complementarity theory to establish conditions for the validity of the rigid body model with rolling and sliding unilateral contacts for planar systems. The results are illustrated with a simple example.

Details

ICRA Conference 1997 Conference Paper

Compliant contact models for rigid body collisions

  • Peter R. Kraus
  • Vijay Kumar

Previous work in rigid body dynamic simulation has relied on rigid body impact models to model collisions. The well-known models due to Newton, Poisson, and Brach, are each based on a definition of a coefficient of restitution for rigid body impact. The objective of this paper is to develop a new model that overcomes the deficiencies of these models in frictional impacts and to present a formulation to solve problems with multiple concurrent impacts. The model is based on simple mechanical elements that model energy storage and dissipation at each contact. We present an algorithm for simulating concurrent impacts between rigid bodies and illustrate its application with a variation of the peg-in-hole insertion problem.

Details

ICRA Conference 1991 Conference Paper

Passive mechanical gravity compensation for robot manipulators

  • Nathan Ulrich
  • Vijay Kumar

A simple mechanical method for passively compensating for gravitationally induced joint torques is presented. This energy-conservative gravity-compensation method is suitable for a variety of manipulator designs. With cables and appropriate pulley profiles, changes in potential energy associated with link motion through a gravity field can be mapped to changes in strain energy storage in spring elements. The resulting system requires significant energy input only for acceleration and deceleration or to resist external forces. A testbed with both single- and double-link configurations has demonstrated the efficiency and accuracy of this gravity compensation method, as well as its robustness under dynamic loading conditions. >

Details