D. Manjunath
YOU?
Author Swipe
View article: Studies on effect of auxin on rooting of stem cuttings of orange jasmine (Murraya paniculata)
Studies on effect of auxin on rooting of stem cuttings of orange jasmine (Murraya paniculata) Open
The present study investigates the effect of various auxin treatments on the rooting and shooting behavior of semi-hardwood stem cuttings of Murraya paniculata (orange jasmine), a valuable ornamental shrub in landscaping and floriculture. …
View article: SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems
SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems Open
Domain-adaptive thermal object detection plays a key role in facilitating visible (RGB)-to-thermal (IR) adaptation by reducing the need for co-registered image pairs and minimizing reliance on large annotated IR datasets. However, inherent…
View article: Exploring Machine Learning Approaches Speech Emotion Recognition System
Exploring Machine Learning Approaches Speech Emotion Recognition System Open
The basis for human-machine interaction depends on speech recognition technology that utilizes two platforms between virtual assistance systems and voice command interfaces. The performance of a machine learningbased speech recognition sys…
View article: When Online Algorithms Influence the Environment: A Dynamical Systems Analysis of the Unintended Consequences
When Online Algorithms Influence the Environment: A Dynamical Systems Analysis of the Unintended Consequences Open
We analyze the effect that online algorithms have on the environment that they are learning. As a motivation, consider recommendation systems that use online algorithms to learn optimal product recommendations based on user and product att…
View article: IndraEye: Infrared Electro-Optical UAV-based Perception Dataset for Robust Downstream Tasks
IndraEye: Infrared Electro-Optical UAV-based Perception Dataset for Robust Downstream Tasks Open
Deep neural networks (DNNs) have shown exceptional performance when trained on well-illuminated images captured by Electro-Optical (EO) cameras, which provide rich texture details. However, in critical applications like aerial perception, …
View article: Partial Server Pooling in Delay Systems
Partial Server Pooling in Delay Systems Open
We consider a strategic resource pooling interaction between two service providers, each of which is modelled as a multi-server queue. The traditional full resource pooling mechanism, while improving the overall system performance measure,…
View article: Influencing Bandits: Arm Selection for Preference Shaping
Influencing Bandits: Arm Selection for Preference Shaping Open
We consider a non stationary multi-armed bandit in which the population preferences are positively and negatively reinforced by the observed rewards. The objective of the algorithm is to shape the population preferences to maximize the fra…
View article: Pigouvian Tolls and Welfare Optimality with Parallel Servers and Heterogeneous Customers
Pigouvian Tolls and Welfare Optimality with Parallel Servers and Heterogeneous Customers Open
Congestion externalities are a well-known phenomenon in transportation and communication networks, healthcare etc. Optimization by self-interested agents in such settings typically results in equilibria which are sub-optimal for social wel…
View article: Index Coding at the WiFi Edge: An Implementation Study for Video Delivery
Index Coding at the WiFi Edge: An Implementation Study for Video Delivery Open
HTTP based video streaming has become the de facto standard for video content delivery across different video streaming services. However, video content delivery continues to be challenged at the wireless edge by inadequate and highly vari…
View article: Online Caching and Coding at the WiFi Edge: Gains and Tradeoffs
Online Caching and Coding at the WiFi Edge: Gains and Tradeoffs Open
Video content delivery at the wireless edge continues to be challenged by insufficient bandwidth and highly dynamic user behavior which affects both effective throughput and latency. Caching at the network edge and coded transmissions have…
View article: Maintaining Ferment: On Opinion Control Over Social Networks
Maintaining Ferment: On Opinion Control Over Social Networks Open
We consider the design of external inputs to achieve a control objective on the opinions, represented by scalars, in a social network. The opinion dynamics follow a variant of the discrete-time Friedkin-Johnsen model. We first consider two…
View article: Partial Server Pooling in Redundancy Systems
Partial Server Pooling in Redundancy Systems Open
Partial sharing allows providers to possibly pool a fraction of their resources when full pooling is not beneficial to them. Recent work in systems without sharing has shown that redundancy can improve performance considerably. In this pap…
View article: Sponsored Data with ISP Competition
Sponsored Data with ISP Competition Open
We analyze the effect of sponsored data platforms when Internet service providers (ISPs) compete for subscribers and content providers (CPs) compete for a share of the bandwidth usage by the customers. Our analytical model is of a full inf…
View article: Reproductive performance of Trichomalopsis uziae as influenced by density of its female and host (Exorista bombycis) with a note on host exposure duration for parasitism
Reproductive performance of Trichomalopsis uziae as influenced by density of its female and host (Exorista bombycis) with a note on host exposure duration for parasitism Open
Trichomalopsis uziae Sureshan and Narendra Kumar (Hymenoptera: Pteromalidae) is a new addition to the already reported parasitoid complex of the tachinid uzi fly, Exorista bombycis (Diptera: Tachinidae), which causes 10-20% reduction to th…
View article: Learning Recommendations While Influencing Interests
Learning Recommendations While Influencing Interests Open
Personalized recommendation systems (RS) are extensively used in many services. Many of these are based on learning algorithms where the RS uses the recommendation history and the user response to learn an optimal strategy. Further, these …
View article: On the Whittle Index for Restless Multiarmed Hidden Markov Bandits
On the Whittle Index for Restless Multiarmed Hidden Markov Bandits Open
We consider a restless multi-armed bandit in which each arm can be in one of two states. When an arm is sampled, the state of the arm is not available to the sampler. Instead, a binary signal with a known randomness that depends on the sta…
View article: Strategic Arrivals to Queues Offering Priority Service
Strategic Arrivals to Queues Offering Priority Service Open
We consider strategic arrivals to a FCFS service system that starts service at a fixed time and has to serve a fixed number of customers, e.g., an airplane boarding system. Arriving early induces a higher waiting cost (waiting before servi…
View article: A Hidden Markov Restless Multi-armed Bandit Model for Playout Recommendation Systems
A Hidden Markov Restless Multi-armed Bandit Model for Playout Recommendation Systems Open
We consider a restless multi-armed bandit (RMAB) in which there are two types of arms, say A and B. Each arm can be in one of two states, say $0$ or $1.$ Playing a type A arm brings it to state $0$ with probability one and not playing it i…
View article: On Threshold Routing in a Service System with Highest-Bidder-First and FIFO Services
On Threshold Routing in a Service System with Highest-Bidder-First and FIFO Services Open
In this paper, we consider a two server system serving heterogeneous customers. One of the server has a FIFO scheduling policy and charges a fixed admission price to each customer. The second queue follows the highest-bidder-first (HBF) po…
View article: Revenue Maximization in Service Systems with Heterogeneous Customers
Revenue Maximization in Service Systems with Heterogeneous Customers Open
In this paper, we consider revenue maximization problem for a two server system in the presence of heterogeneous customers. We assume that the customers differ in their cost for unit delay and this is modeled as a continuous random variabl…
View article: Optimal Recommendation to Users that React: Online Learning for a Class of POMDPs
Optimal Recommendation to Users that React: Online Learning for a Class of POMDPs Open
We describe and study a model for an Automated Online Recommendation System (AORS) in which a user's preferences can be time-dependent and can also depend on the history of past recommendations and play-outs. The three key features of the …