Search

The goal of field boundary delineation is to predict the polygonal boundaries and interiors of individual crop fields in overhead remotely sensed images (e.g., from satellites or drones). Automatic delineation of field boundaries is a necessary task for many real-world use cases in agriculture, such as estimating cultivated area in a region or predicting end-of-season yield in a field. Field boundary delineation can be framed as an instance segmentation problem, but presents unique research challenges compared to traditional computer vision datasets used for instance segmentation. The practical applicability of previous work is also limited by the assumption that a sufficiently-large labeled dataset is available where field boundary delineation models will be applied, which is not the reality for most regions (especially under-resourced regions such as Sub-Saharan Africa). We present an approach for segmentation of crop field boundaries in satellite images in regions lacking labeled data that uses multi-region transfer learning to adapt model weights for the target region. We show that our approach outperforms existing methods and that multi-region transfer learning substantially boosts performance for multiple model architectures. Our implementation and datasets are publicly available to enable use of the approach by end-users and serve as a benchmark for future work., Comment: Accepted for 2023 AAAI Workshop on AI to Accelerate Science and Engineering

Multi-Agent Path Finding (MAPF), which involves finding collision-free paths for multiple robots, is crucial in various applications. Lifelong MAPF, where targets are reassigned to agents as soon as they complete their initial targets, offers a more accurate approximation of real-world warehouse planning. In this paper, we present a novel mechanism named Caching-Augmented Lifelong MAPF (CAL-MAPF), designed to improve the performance of Lifelong MAPF. We have developed a new type of map grid called cache for temporary item storage and replacement, and created a locking mechanism to improve the planning solution's stability. A task assigner (TA) is designed for CAL-MAPF to allocate target locations to agents and control agent status in different situations. CAL-MAPF has been evaluated using various cache replacement policies and input task distributions. We have identified three main factors significantly impacting CAL-MAPF performance through experimentation: suitable input task distribution, high cache hit rate, and smooth traffic. In general, CAL-MAPF has demonstrated potential for performance improvements in certain task distributions, map and agent configurations.

COVID-19 pandemic has brought unprecedented challenges to the world, and vaccination has been a key strategy to combat the disease. Since Twitter is one of the most widely used public microblogging platforms, researchers have analysed COVID-19 vaccines and vaccination Twitter discourse to explore the conversational dynamics around the topic. While contributing to the crisis informatics literature, we curate a large-scale geotagged Twitter dataset, GeoCovaxTweets Extended, and explore the discourse through multiple spatiotemporal analyses. This dataset covers a longer time span of 38 months, from the announcement of the first vaccine to the availability of booster doses. Results show that 43.4% of the collected tweets, although containing phrases and keywords related to vaccines and vaccinations, were unrelated to the COVID-19 context. In total, 23.1% of the discussions on vaccines and vaccinations were classified as Pro, 16% as Hesitant, 11.4% as Anti, and 6.1% as Informative. The trend shifted towards Pro and Informative tweets globally as vaccination programs progressed, indicating a change in the public's perception of COVID-19 vaccines and vaccination. Furthermore, we explored the discourse based on account attributes, i.e., followers counts and tweet counts. Results show a significant pattern of discourse differences. Our findings highlight the potential of harnessing a large-scale geotagged Twitter dataset to understand global public health communication and to inform targeted interventions aimed at addressing vaccine hesitancy.

The existing notion of the shared entangled state-assisted remote preparation of unitary operator (equivalently the existing notion of quantum remote control) using local operation and classical communication is generalized to a scenario where under the control of a supervisor two users can jointly implement arbitrary unitaries (one unknown unitary operation by each or equivalently a single unitary decomposed into two unitaries of the same dimension and given to two users) on an unknown quantum state available with a geographically separated user. It is explicitly shown that the task can be performed using a four-qubit hyperentangled state, which is entangled simultaneously in both spatial and polarization degrees of freedom of photons. The proposed protocol which can be viewed as primitive for distributed photonic quantum computing is further generalized to the case that drops the restrictions on the number of controllers and the number of parties performing unitaries and allows both the numbers to be arbitrary. It is also shown that all the existing variants of quantum remote control schemes can be obtained as special cases of the present scheme., Comment: 12 pages, 4 figures

We present HiRA-Pro, a novel procedure to align, at high spatio-temporal resolutions, multimodal signals from real-world processes and systems that exhibit diverse transient, nonlinear stochastic dynamics, such as manufacturing machines. It is based on discerning and synchronizing the process signatures of salient kinematic and dynamic events in these disparate signals. HiRA-Pro addresses the challenge of aligning data with sub-millisecond phenomena, where traditional timestamp, external trigger, or clock-based alignment methods fall short. The effectiveness of HiRA-Pro is demonstrated in a smart manufacturing context, where it aligns data from 13+ channels acquired during 3D-printing and milling operations on an Optomec-LENS MTS 500 hybrid machine. The aligned data is then voxelized to generate 0.25 second aligned data chunks that correspond to physical voxels on the produced part. The superiority of HiRA-Pro is further showcased through case studies in additive manufacturing, demonstrating improved machine learning-based predictive performance due to precise multimodal data alignment. Specifically, testing classification accuracies improved by almost 35% with the application of HiRA-Pro, even with limited data, allowing for precise localization of artifacts. The paper also provides a comprehensive discussion on the proposed method, its applications, and comparative qualitative analysis with a few other alignment methods. HiRA-Pro achieves temporal-spatial resolutions of 10-1000 us and 100 um in order to generate datasets that register with physical voxels on the 3D-printed and milled part. These resolutions are at least an order of magnitude finer than the existing alignment methods that employ individual timestamps, statistical correlations, or common clocks, which achieve precision of hundreds of milliseconds.

Streaming applications are becoming widespread across an extensive range of business domains as an increasing number of sources continuously produce data that need to be processed and analysed in real time. Modern businesses are aggressively using streaming data to generate valuable knowledge that can be used to automate processes, help decision-making, optimize resource usage, and ultimately generate revenue for the organization. Despite their increased adoption and tangible benefits, support for the automated deployment and management of streaming applications is yet to emerge. Although a plethora of stream management systems have flooded the open source community in recent years, all of the existing frameworks demand a considerably challenging and lengthy effort from human operators to manually and continuously tune their configuration and deployment environment in order to reach and maintain the desired performance goals. To address these challenges, this article proposes a vision for creating Deep Reinforcement Learning (DRL)-based methods for transforming stream processing engines into self-managed serverless solutions. This will lead to an increase in productivity as engineers can focus on the actual development process, an increase in application performance potentially leading to reduced response times and more accurate and meaningful results, and a considerable decrease in operational costs for organizations., Comment: 21 pages, 10 figures

The amount of data being produced at every epoch of second is increasing every moment. Various sensors, cameras and smart gadgets produce continuous data throughout its installation. Processing and analyzing raw data at a cloud server faces several challenges such as bandwidth, congestion, latency, privacy and security. Fog computing brings computational resources closer to IoT that addresses some of these issues. These IoT devices have low computational capability, which is insufficient to train machine learning. Mining hidden patterns and inferential rules from continuously growing data is crucial for various applications. Due to growing privacy concerns, privacy preserving machine learning is another aspect that needs to be inculcated. In this paper, we have proposed a fog enabled distributed training architecture for machine learning tasks using resources constrained devices. The proposed architecture trains machine learning model on rapidly changing data using online learning. The network is inlined with privacy preserving federated learning training. Further, the learning capability of architecture is tested on a real world IIoT use case. We trained a neural network model for human position detection in IIoT setup on rapidly changing data., Comment: Conference paper accepted at BDA 2021

This follow-on work investigates the effect of temperature on the frequency limit of 2-dimensional electron gas (2DEG) Hall-effect sensors., Comment: 4 pages

This paper presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error ($L_1$ difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth.

We present H2O-Danube, a series of small 1.8B language models consisting of H2O-Danube-1.8B, trained on 1T tokens, and the incremental improved H2O-Danube2-1.8B trained on an additional 2T tokens. Our models exhibit highly competitive metrics across a multitude of benchmarks and, as of the time of this writing, H2O-Danube2-1.8B achieves the top ranking on Open LLM Leaderboard for all models below the 2B parameter range. The models follow core principles of LLama 2 and Mistral, and we leverage and refine various techniques for pre-training large language models. We additionally release chat models trained with supervised fine-tuning followed by direct preference optimization. We make all models openly available under Apache 2.0 license further democratizing LLMs to a wider audience economically.

Facial super-resolution/hallucination is an important area of research that seeks to enhance low-resolution facial images for a variety of applications. While Generative Adversarial Networks (GANs) have shown promise in this area, their ability to adapt to new, unseen data remains a challenge. This paper addresses this problem by proposing an incremental super-resolution using GANs with knowledge distillation (ISR-KD) for face to cartoon. Previous research in this area has not investigated incremental learning, which is critical for real-world applications where new data is continually being generated. The proposed ISR-KD aims to develop a novel unified framework for facial super-resolution that can handle different settings, including different types of faces such as cartoon face and various levels of detail. To achieve this, a GAN-based super-resolution network was pre-trained on the CelebA dataset and then incrementally trained on the iCartoonFace dataset, using knowledge distillation to retain performance on the CelebA test set while improving the performance on iCartoonFace test set. Our experiments demonstrate the effectiveness of knowledge distillation in incrementally adding capability to the model for cartoon face super-resolution while retaining the learned knowledge for facial hallucination tasks in GANs.

Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image. The Convolutional Neural Network (CNN)-based approaches have been extensively exploited with self-supervised contrastive learning for image hashing. However, the existing approaches suffer due to lack of effective utilization of global features by CNNs and biased-ness created by false negative pairs in the contrastive learning. In this paper, we propose a TransClippedCLR model by encoding the global context of an image using Transformer having local context through patch based processing, by generating the hash codes through product quantization and by avoiding the potential false negative pairs through clipped contrastive learning. The proposed model is tested with superior performance for unsupervised image retrieval on benchmark datasets, including CIFAR10, NUS-Wide and Flickr25K, as compared to the recent state-of-the-art deep models. The results using the proposed clipped contrastive learning are greatly improved on all datasets as compared to same backbone network with vanilla contrastive learning.

Frequent and intensive disasters make the repeated and uncertain post-disaster recovery process. Despite the importance of the successful recovery process, previous simulation studies on the post-disaster recovery process did not explore the sufficient number of household return decision model types, population sizes, and the corresponding critical transition conditions of the system. This paper simulates the recovery process in the agent-based model with multilayer networks to reveal the impact of household return decision model types and population sizes in a toy network. After that, this paper applies the agent-based model to the five selected counties affected by Hurricane Harvey in 2017 to check the urban-rural recovery differences by types of household return decision models. The agent-based model yields three conclusions. First, the threshold model can successfully substitute the binary logit model. Second, high thresholds and less than 1,000 populations perturb the recovery process, yielding critical transitions during the recovery process. Third, this study checks the urban-rural recovery value differences by different decision model types. This study highlights the importance of the threshold models and population sizes to check the critical transitions and urban-rural differences in the recovery process., Comment: 21 pages, 5 figures

In 1996, Karger [Kar96] gave a startling randomized algorithm that finds a minimum-cut in a (weighted) graph in time $O(m\log^3n)$ which he termed near-linear time meaning linear (in the size of the input) times a polylogarthmic factor. In this paper, we give the first deterministic algorithm which runs in near-linear time for weighted graphs. Previously, the breakthrough results of Kawarabayashi and Thorup [KT19] gave a near-linear time algorithm for simple graphs. The main technique here is a clustering procedure that perfectly preserves minimum cuts. Recently, Li [Li21] gave an $m^{1+o(1)}$ deterministic minimum-cut algorithm for weighted graphs; this form of running time has been termed "almost-linear''. Li uses almost-linear time deterministic expander decompositions which do not perfectly preserve minimum cuts, but he can use these clusterings to, in a sense, "derandomize'' the methods of Karger. In terms of techniques, we provide a structural theorem that says there exists a sparse clustering that preserves minimum cuts in a weighted graph with $o(1)$ error. In addition, we construct it deterministically in near linear time. This was done exactly for simple graphs in [KT19, HRW20] and with polylogarithmic error for weighted graphs in [Li21]. Extending the techniques in [KT19, HRW20] to weighted graphs presents significant challenges, and moreover, the algorithm can only polylogarithmically approximately preserve minimum cuts. A remaining challenge is to reduce the polylogarithmic-approximate clusterings to $1+o(1/\log n)$-approximate so that they can be applied recursively as in [Li21] over $O(\log n)$ many levels. This is an additional challenge that requires building on properties of tree-packings in the presence of a wide range of edge weights to, for example, find sources for local flow computations which identify minimum cuts that cross clusters., Comment: SODA 2024, 60 pages

Point canonical transformation (PCT) has been used to find out new exactly solvable potentials in the position-dependent mass (PDM) framework. We solve $1$-D Schr\"{o}dinger equation in the PDM framework by considering two different fairly generic position-dependent masses $ (i) M(x)=\lambda g'(x)$ and $(ii) M(x) = c \left( {g'(x)} \right)^\nu $, $\nu =\frac{2\eta}{2\eta+1},$ with $\eta= 0,1,2\cdots $. In the first case, we find new exactly solvable potentials that depend on an integer parameter $m$, and the corresponding solutions are written in terms of $X_m$-Laguerre polynomials. In the latter case, we obtain a new one parameter $(\nu)$ family of isochronous solvable potentials whose bound states are written in terms of $X_m$-Laguerre polynomials. Further, we show that the new potentials are shape invariant by using the supersymmetric approach in the framework of PDM., Comment: 17 pages, 5 Figs, Latex