Abstract

Developing a reinforcement learning (RL) framework that works satisfactorily in deterministic and stochastic environments is challenging. To address this problem, a twin agent RL framework is proposed in this work, wherein we amalgamate both stochastic and deterministic agents’ actions in a multiagent framework that works with a feedback mechanism that actively monitors the output. The proposed algorithm uses twin actor networks of different agents, corresponding to deterministic and stochastic agents, and an action selection critic network is used to choose the best action from both agents. Here, the algorithm blends the outcomes of two reinforcement learning (RL) agents, a stochastic agent and a deterministic agent, namely, Proximal Policy Optimization (PPO) and Twin Delayed Deep Deterministic Policy Gradient (TD3), respectively. We assess the effectiveness of the proposed algorithm by applying it to two case studies: (i) monoclonal antibody (mAb) production and (ii) production of propylene glycol (PG). The studies are conducted in the presence of parametric uncertainties, measurement noise, and nominal conditions. It is observed that for case study 1, the root-mean-square error (RMSE) value for the proposed algorithm is reduced by 40.9% when compared with TD3 and 27.57% when compared with PPO for the simulations. Similarly, for case study 2, the RMSE for the proposed algorithm is reduced by 8.87% when compared with TD3 and 5.8% with PPO. Based on extensive simulations, it is found that the proposed twin agent algorithm has faster convergence and better set-point tracking when compared to the agents operated individually.

Abstract

Graph neural networks (GNNs) are increasingly being used on sensitive graph-structured data, necessitating techniques for handling unlearning requests on the trained models, particularly node unlearning. However, unlearning nodes on GNNs is challenging due to the interdependence between the nodes in a graph. We compare MEGU, a state-of-the-art graph unlearning method, and SCRUB, a general unlearning method for classification, to investigate the efficacy of graph unlearning methods over traditional unlearning methods. Surprisingly, we find that SCRUB performs comparably or better than MEGU on random node removal and on removing an adversarial node injection attack. Our results suggest that 1) graph unlearning studies should incorporate general unlearning methods like SCRUB as baselines, and 2) there is a need for more rigorous behavioral evaluations that reveal the differential advantages of proposed graph unlearning methods. Our work, therefore, motivates future research into more comprehensive evaluations for assessing the true utility of graph unlearning algorithms.

Abstract

Charts are tools for data communication used in a wide range of documents. Recently, the pattern recognition community has shown interest in developing methods for automatically processing charts found in the wild. Following previous efforts on ICPR’s CHART-Infographics competitions, here we propose a newer, larger dataset and benchmark for analyzing and recognizing charts. Inspired by the steps required to make sense of a chart image, the benchmark is divided into 7 different tasks: chart image classification, chart text detection and recognition, text role classification, axis analysis, legend analysis, data extraction, and end-toend data extraction. We also show the performance of different baselines for the first five tasks. We expect that the increased scale of the proposed dataset will enable the development of better chart recognition systems.

Abstract

We present CheXtriev, a graph-based, anatomy-aware framework for chest radiograph retrieval. Unlike prior methods focussed on global features, our method leverages graph transformers to extract informative features from specific anatomical regions. Furthermore, it captures spatial context and the interplay between anatomical location and findings. This contextualization, grounded in evidence-based anatomy, results in a richer anatomy-aware representation and leads to more accurate, effective and efficient retrieval, particularly for less prevalent findings. CheXtriv outperforms state-of-the-art global and local approaches by to in retrieval accuracy and to in ranking quality.

Abstract

Biological processes like growth, aging, and disease progression are generally studied with follow-up scans taken at different time points, i.e., image time series (TS) based analysis. Image TS represents the evolution of anatomy over time, but different anatomies may have different structural characteristics and temporal paths. Therefore, separating the time-dependent path difference and time-independent basic anatomy/shape changes is important when comparing two image TS to understand the causes of the observed differences better. A method to untangle and quantify the path and shape difference between the TS is presented in this paper. The proposed method is evaluated with simulated and adult and fetal neuro templates. Results show that the metric can separate and quantify the path and shape differences between TS.

Abstract

This paper presents the architecture of a two-wheeler mobile sensing platform aimed at collecting compre-hensive two-wheeler riding data. Two-wheelers, prevalent in many countries for their agility and efficiency lack extensive study in autonomous vehicle research. Recognizing this gap, our work introduces a scalable and modular platform equipped with multiple sensors and high-performance embedded systems. The platform captures essential data points such as GPS, acceleration, gyroscope, speed, and 360-degree image and depth data, crucial for developing deep learning models for autonomous navigation and accident prevention. We detail the hardware architecture, consisting of an Nvidia Jetson TX2 NX platform, Raspberry Pi 4 Model B, and various sensors, all tailored to operate efficiently on a two-wheeler. The software methodology is designed to synchronize and process the data effectively, hence allowing us to generate accurate and thorough datasets. Our results demonstrate the platform's potential in improving two-wheeler safety and contributing to the advancement of autonomous vehicle technologies.

Abstract

This work proposes a resource efficient robust control scheme for missile-target engagement scenarios subjected to external disturbances. The robustness is achieved by using an annular event-triggered artificial time-delayed control (ET-TDC) methodology with input saturation. The ET-TDC philosophy uses the TDC strategy through a dynamic predefined triggering mechanism which overcomes the requirement to update the control periodically for every sampling instant, unlike conventional TDC and other robust control schemes. Thus the proposed methodology can tackle uncertainties with minimal a-priori knowledge while significantly reducing the over-utilisation of system resources. In addition, the adopted event-triggered mechanism facilitates further conservation of energy which might be crucial for mid-to-long range engagement scenarios. The closed-loop stability is derived analytically and the simulation results illustrate the efficacy of the proposed guidance framework in comparison with other state-of-art robust control methodologies.

Abstract

Transportation of a suspended payload using quadrotor demands a controller to simultaneously track the desired path and stabilize the planar payload swing angles. Such a control objective is made challenging by the need to orchestrate the coupling between fully actuated dynamics (quadrotor attitude) and underactuated dynamics (quadrotor position and planar payload swings). State-of-the-art controllers cannot orchestrate such coupled dynamics in the presence of unmodeled and state-dependent terms, such as aerodynamic drags and rotor downwash. This article solves this control challenge by adaptively estimating the state-dependent uncertainty. Closed-loop stability for the coupled underactuated and fully actuated dynamics is established analytically. Extensive real-time experiments confirm significant improvements over the state-of-the-art under various scenarios, such as path tracking with suspended payload and anti-swing control against externally induced payload swings.

Abstract

Despite participants engaging in single modality stimuli, such as watching images or silent videos, recent work has demonstrated that multi-modal Transformer models can predict visual brain activity impressively well, even with incongruent modality representations. This raises the question of how accurately these multi-modal models can predict brain activity when participants are engaged in multi-modal stimuli. As these models grow increasingly popular, their use in studying neural activity provides insights into how our brains respond to such multi-modal naturalistic stimuli, i.e., where it separates and integrates information from different sensory modalities. We investigate this question by using multiple unimodal and two types of multi-modal models—cross-modal and jointly pretrained—to determine which type of models is more relevant to fMRI brain activity when participants were engaged in watching movies (videos with audio). We observe that both types of multi-modal models show improved alignment in several language and visual regions. This study also helps in identifying which brain regions process unimodal versus multi-modal information. We further investigate the impact of removal of unimodal features from multi-modal representations and find that there is additional information beyond the unimodal embeddings that is processed in the visual and language regions. Based on this investigation, we find that while for cross-modal models, their brain alignment is partially attributed to the video modality; for jointly pretrained models, it is partially attributed to both the video and audio modalities.

Abstract

LOCALITY and INTERFERENCE are two mechanisms which are attested to drive sentence comprehension. However, the relationship between them remains unclear—are they alternative explanations or do they operate independently? To answer this question, we test the hypothesis that in Hindi, interference effects (measured by semantic similarity and case markers) significantly predict locality effects (modelled using dependency length quantifying distance between syntactic heads and their dependents) within a sentence, while controlling for expectation-based measures and discourse givenness. Using data from the HindiUrdu Treebank corpus (HUTB), we validate the stated hypothesis. We demonstrate that sentences with longer dependency length consistently have semantically similar preverbal dependents, more case markers, greater syntactic surprisal, and violate intra-sentential givenness considerations. Overall, our findings point towards the conclusion that locality effects are reducible to broader memory interference effects rather than being distinct manifestations of locality in syntax. Finally, we discuss the implications of our findings for the theories of interference in comprehension.