Satish Kumar

Shreyas Gawde, Shruti Patil, Satish Kumar et al.

Industry 4.0 is an era of smart manufacturing. Manufacturing is impossible without the use of machinery. Majority of these machines comprise rotating components and are called rotating machines. The engineers' top priority is to maintain these critical machines to reduce the unplanned shutdown and increase the useful life of machinery. Predictive maintenance (PDM) is the current trend of smart maintenance. The challenging task in PDM is to diagnose the type of fault. With Artificial Intelligence (AI) advancement, data-driven approach for predictive maintenance is taking a new flight towards smart manufacturing. Several researchers have published work related to fault diagnosis in rotating machines, mainly exploring a single type of fault. However, a consolidated review of literature that focuses more on multi-fault diagnosis of rotating machines is lacking. There is a need to systematically cover all the aspects right from sensor selection, data acquisition, feature extraction, multi-sensor data fusion to the systematic review of AI techniques employed in multi-fault diagnosis. In this regard, this paper attempts to achieve the same by implementing a systematic literature review on a Data-driven approach for multi-fault diagnosis of Industrial Rotating Machines using Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) method. The PRISMA method is a collection of guidelines for the composition and structure of systematic reviews and other meta-analyses. This paper identifies the foundational work done in the field and gives a comparative study of different aspects related to multi-fault diagnosis of industrial rotating machines. The paper also identifies the major challenges, research gap. It gives solutions using recent advancements in AI in implementing multi-fault diagnosis, giving a strong base for future research in this field.

A S M Iftekhar, Raphael Ruschel, Satish Kumar et al.

Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting triplets outside of a predefined set, primarily due to their reliance on dependent feature learning. To address this issue, we propose DDS -- a decoupled dynamic scene-graph generation network -- that consists of two independent branches that can disentangle extracted features. The key innovation of the current paper is the decoupling of the features representing the relationships from those of the objects, which enables the detection of novel object-relationship combinations. The DDS model is evaluated on three datasets and outperforms previous methods by a significant margin, especially in detecting previously unseen triplets.

Satish Kumar, Ivan Arevalo, ASM Iftekhar et al.

Methane (CH$_4$) is the chief contributor to global climate change. Recent Airborne Visible-Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) has been very useful in quantitative mapping of methane emissions. Existing methods for analyzing this data are sensitive to local terrain conditions, often require manual inspection from domain experts, prone to significant error and hence are not scalable. To address these challenges, we propose a novel end-to-end spectral absorption wavelength aware transformer network, MethaneMapper, to detect and quantify the emissions. MethaneMapper introduces two novel modules that help to locate the most relevant methane plume regions in the spectral domain and uses them to localize these accurately. Thorough evaluation shows that MethaneMapper achieves 0.63 mAP in detection and reduces the model size (by 5x) compared to the current state of the art. In addition, we also introduce a large-scale dataset of methane plume segmentation mask for over 1200 AVIRIS-NG flight lines from 2015-2022. It contains over 4000 methane plume sites. Our dataset will provide researchers the opportunity to develop and advance new methods for tackling this challenging green-house gas detection problem with significant broader social impact. Dataset and source code are public

Bowen Zhang, Jesse T. Boulerice, Charvi Mendiratta et al.

Automated wildlife monitoring from aerial imagery is vital for conservation but remains limited by two persistent challenges: the difficulty of detecting small, rare species and the high cost of large-scale expert annotation. Prairie dogs exemplify this problem -- they are ecologically important yet appear tiny, sparsely distributed, and visually indistinct from their surroundings, posing a severe challenge for conventional detection models. To overcome these limitations, we present RareSpot+, a detection framework that integrates multi-scale consistency learning, context-aware augmentation, and geospatially guided active learning to address these issues. A novel multi-scale consistency loss aligns intermediate feature maps across detection heads, enhancing localization of small (approx. 30 pixels wide) objects without architectural changes, while context-aware augmentation improves robustness by synthesizing hard, ecologically plausible examples. A geospatial active learning module exploits domain-specific spatial priors linking prairie dogs and burrows, together with test-time augmentation and a meta-uncertainty model, to reduce redundant labeling. On a 2 km^2 aerial dataset, RareSpot+ improves detection over the baseline mAP@50 by +35.2% (absolute +0.13). Cross-dataset tests on HerdNet, AED, and several other wildlife benchmarks demonstrate robust detector-level transferability. The active learning module further boosts prairie dog AP by 14.5% using an annotation budget of just 1.7% of the unlabeled tiles. Beyond detection, RareSpot+ enables spatial ecological analyses such as clustering and co-occurrence, linking vision-based detection with quantitative ecology.

Satish Kumar, Rui Kou, Henry Hill et al.

From agriculture to mining, to energy, surface water quality monitoring is an essential task. As oil and gas operators work to reduce the consumption of freshwater, it is increasingly important to actively manage fresh and non-fresh water resources over the long term. For large-scale monitoring, manual sampling at many sites has become too time-consuming and unsustainable, given the sheer number of dispersed ponds, small lakes, playas, and wetlands over a large area. Therefore, satellite-based environmental monitoring presents great potential. Many existing satellite-based monitoring studies utilize index-based methods to monitor large water bodies such as rivers and oceans. However, these existing methods fail when monitoring small ponds-the reflectance signal received from small water bodies is too weak to detect. To address this challenge, we propose a new Water Quality Enhanced Index (WQEI) Model, which is designed to enable users to determine contamination levels in water bodies with weak reflectance patterns. Our results show that 1) WQEI is a good indicator of water turbidity validated with 1200 water samples measured in the laboratory, and 2) by applying our method to commonly available satellite data (e.g. LandSat8), one can achieve high accuracy water quality monitoring efficiently in large regions. This provides a tool for operators to optimize the quality of water stored within surface storage ponds and increasing the readiness and availability of non-fresh water.

Satish Kumar, ASM Iftekhar, Ekta Prashnani et al.

This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings. The problem of unseen Object Attribute (OA) associations has been well studied in the field, however, the performance of existing methods is limited in challenging scenes. In this context, our key contribution is a modular approach to localizing objects and attributes of interest in a weakly supervised context that generalizes robustly to unseen configurations. Localization coupled with a composition classifier significantly outperforms state of the art (SOTA) methods, with an improvement of about 12% on currently available challenging datasets. Further, the modularity enables the use of localized feature extractor to be used with existing OA compositional learning methods to improve their overall performance.

Satish Kumar, A S M Iftekhar, Michael Goebel et al.

Precise measurement of physiological signals is critical for the effective monitoring of human vital signs. Recent developments in computer vision have demonstrated that signals such as pulse rate and respiration rate can be extracted from digital video of humans, increasing the possibility of contact-less monitoring. This paper presents a novel approach to obtaining physiological signals and classifying stress states from thermal video. The proposed network--"StressNet"--features a hybrid emission representation model that models the direct emission and absorption of heat by the skin and underlying blood vessels. This results in an information-rich feature representation of the face, which is used by spatio-temporal network for reconstructing the ISTI ( Initial Systolic Time Interval: a measure of change in cardiac sympathetic activity that is considered to be a quantitative index of stress in humans ). The reconstructed ISTI signal is fed into a stress-detection model to detect and classify the individual's stress state ( i.e. stress or no stress ). A detailed evaluation demonstrates that StressNet achieves estimated the ISTI signal with 95% accuracy and detect stress with average precision of 0.842. The source code is available on Github.

Bowen Zhang, Jesse T. Boulerice, Nikhil Kuniyil et al.

Automated detection of small and rare wildlife in aerial imagery is crucial for effective conservation, yet remains a significant technical challenge. Prairie dogs exemplify this issue: their ecological importance as keystone species contrasts sharply with their elusive presence--marked by small size, sparse distribution, and subtle visual features--which undermines existing detection approaches. To address these challenges, we propose RareSpot, a robust detection framework integrating multi-scale consistency learning and context-aware augmentation. Our multi-scale consistency approach leverages structured alignment across feature pyramids, enhancing fine-grained object representation and mitigating scale-related feature loss. Complementarily, context-aware augmentation strategically synthesizes challenging training instances by embedding difficult-to-detect samples into realistic environmental contexts, significantly boosting model precision and recall. Evaluated on an expert-annotated prairie dog drone imagery benchmark, our method achieves state-of-the-art performance, improving detection accuracy by over 35% compared to baseline methods. Importantly, it generalizes effectively across additional wildlife datasets, demonstrating broad applicability. The RareSpot benchmark and approach not only support critical ecological monitoring but also establish a new foundation for detecting small, rare species in complex aerial scenes.

Satish Kumar, Anirban Pathak

United Nation (UN) security council has fifteen members, out of which five permanent members of the council can use their veto power against any unfavorable decision taken by the council. In certain situation, a member using right to veto may prefer to remain anonymous. This need leads to the requirement of the protocols for anonymous veto which can be viewed as a special type of voting. Recently, a few protocols for quantum anonymous veto have been designed which clearly show quantum advantages in ensuring anonymity of the veto. However, none of the efficient protocols for quantum anonymous veto have yet been experimentally realized. Here, we implement 2 of those protocols for quantum anonymous veto using an IBM quantum computer named IBMQ Casablanca and different quantum resources like Bell, GHZ and cluster states. In this set of proof-of-principle experiments, it's observed that using the present technology, a protocol for quantum anonymous veto can be realized experimentally if the number of people who can veto remains small as in the case of UN council. Further, it's observed that Bell state based protocol implemented here performs better than the GHZ/cluster state based implementation of the other protocol in an ideal scenario as well as in presence of different types of noise (amplitude damping, phase damping, depolarizing and bit-flip noise). In addition, it's observed that based on diminishing impact on fidelity, different noise models studied here can be ordered in ascending order as phase damping, amplitude damping, depolarizing, bit-flip.

A S M Iftekhar, Satish Kumar, R. Austin McEver et al.

The human-object interaction (HOI) detection task refers to localizing humans, localizing objects, and predicting the interactions between each human-object pair. HOI is considered one of the fundamental steps in truly understanding complex visual scenes. For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs. This issue is addressed by the novel self-attention based guided transformer network, GTNet. GTNet encodes this spatial contextual information in human and object visual features via self-attention while achieving state of the art results on both the V-COCO and HICO-DET datasets. Code will be made available online.

Satish Kumar, Tao Chen, Rami Bahsoon et al.

The rapidly changing workload of service-based systems can easily cause under-/over-utilization on the component services, which can consequently affect the overall Quality of Service (QoS), such as latency. Self-adaptive services composition rectifies this problem, but poses several challenges: (i) the effectiveness of adaptation can deteriorate due to over-optimistic assumptions on the latency and utilization constraints, at both local and global levels; and (ii) the benefits brought by each composition plan is often short term and is not often designed for long-term benefits -- a natural prerequisite for sustaining the system. To tackle these issues, we propose a two levels constraint reasoning framework for sustainable self-adaptive services composition, called DATESSO. In particular, DATESSO consists of a re ned formulation that differentiates the "strictness" for latency/utilization constraints in two levels. To strive for long-term benefits, DATESSO leverages the concept of technical debt and time-series prediction to model the utility contribution of the component services in the composition. The approach embeds a debt-aware two level constraint reasoning algorithm in DATESSO to improve the efficiency, effectiveness and sustainability of self-adaptive service composition. We evaluate DATESSO on a service-based system with real-world WS-DREAM dataset and comparing it with other state-of-the-art approaches. The results demonstrate the superiority of DATESSO over the others on the utilization, latency and running time whilst likely to be more sustainable.