Search results

Many forms of bioimage analysis involve the detection of objects and their outlines. In the context of microscopy-based high-throughput drug and genomic screening and even in smaller scale microscopy experiments, the objects that most often need to be detected are cells. In order to develop and benchmark algorithms and neural networks that can perform this task, high-quality datasets with annotate

With the rapid advancement of autonomous vehicle technology, integrating mixed autonomous and non-autonomous vehicles that are not cooperative in vehicular network has become a significant challenge. This paper presents an innovative Autonomous Intersection Management (AIM) system designed to optimize traffic flow and enhance intersection safety in such mixed traffic scenarios. By utilizing vehicl

Cloud Control Systems (CCSs) harness the power of cloud resources to carry out intense computational tasks, however, they face challenges in delivering time-critical control signals due to network and cloud-induced delays. In this paper, we introduce a novel framework, "Punctual Cloud", designed to enhance the timely delivery of control signals in CCS. This framework ensures that control signals a

Recently, the industry has been driven to move industrial control systems to the cloud due to the significant advantages it offers in terms of storage and computing resources. However, this shift also brings forth significant security challenges. By moving control systems to the cloud, the potential for attackers to infiltrate the system and launch damaging attacks increases. These attacks can res

In this paper, we focus on the design of the transmit waveforms of a frequency diverse array (FDA) in order to improve the output signal-to-interference-plus-noise ratio (SINR) in the presence of signal-dependent mainlobe interference. Since the classical multi-carrier matched filtering-based FDA receiver cannot effectively utilize the waveform diversity of FDA, a novel FDA receiver framework base

Connected autonomous vehicles can significantly improve the safety and mobility of urban transportation systems. However, these systems are vulnerable to model uncertainties, wireless communication impairments, and external disturbances. In this article, we propose a new autonomous intersection management (AIM) system, called hierarchical model predictive control (HMPC). In HMPC, the intersection

Songbirds have evolved diverse strategies to cope with seasonality, including long-, medium-, and short-distance migration. There is some evidence that birds with a longer migration distance deposit fuel faster. However, most studies focus on long-distance migrants. Comparisons between species with different migration distances are necessary to broaden our understanding of fueling capacity in migr

Migratory birds must make complex decisions to use wind to their advantage during flight and increasing flight performance is particularly important while crossing ecological barriers. Age-related differences in how birds deal with wind have suggested experience improves necessary skills in gaining positive wind support. However, differences in wind support between age groups over ecological barri

Psychosis in Parkinson's disease is a common phenomenon associated with poor outcomes. To clarify the pathophysiology of this condition and the mechanisms of antipsychotic treatments, we have here characterized the neurophysiological brain states induced by clozapine, pimavanserin, and the novel prospective antipsychotic mesdopetam in a rodent model of Parkinson's disease psychosis, based on chron

In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of matches comes with a significantly increased runtime during robust estimation in RANSAC. To avoid this, we propose an efficient match summarization scheme which pro

Each spring, billions of Bogong moths escape hot conditions across southeast Australia by migrating up to 1,000 km to a place that they have never previously visited—a limited number of cool caves in the Australian Alps, historically used for aestivating over summer1,2. At the beginning of autumn, the same individuals make a return migration to their breeding grounds to reproduce and die. Here we

The emergence of sixth-generation (6G) networks has spurred the development of novel testbeds, including sub-THz networks, cell-free systems, and 6G simulators. To maximize the benefits of these systems, it is crucial to make the generated data publicly available and easily reusable by others. Although data sharing has become a common practice, a lack of standardization hinders data accessibility

Understanding the trade-off between energy expenditure of carrying large fuel loads and the risk of fuel depletion is imperative to understand the evolution of flight strategies during long-distance animal migration. Global flyways regularly involve sea crossings that may impose flight prolongations on migrating land-birds and thereby reduce their energy reserves and survival prospects. We studied

Electronic health records (EHRs) are a rich source of information for medical research and public health monitoring. Information systems based on EHR data could also assist in patient care and hospital management. However, much of the data in EHRs is in the form of unstructured text, which is difficult to process for analysis. Natural language processing (NLP), a form of artificial intelligence, h

Context: In the contemporary body of software engineering literature, some recurrent shortcomings characterize how threats to validity (TTV) are considered in studies. Objective: With this position paper, we aim to open a discourse on the current use of TTV sections. The goal of our position is to jointly reflect and systematically improve how we, as a research community, consider TTV in our studi

For a generalized (or non-central) camera model, the minimal problem for two views of six points has efficient solvers. However, minimal problems of three views with four points and three views of six lines have not yet been explored and solved, despite the efforts from the computer vision community. This paper develops the formulations of these two minimal problems and shows how state-of-the-art

The state-of-the-art machine learning techniques come with limited, if at all any, formal correctness guarantees. This has been demonstrated by adversarial examples in the deep learning domain. To address this challenge, here, we propose a scalable robustness verification framework for Deep Neural Networks (DNNs). The framework relies on Linear Programming (LP) engines and builds on decades of adv

In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains a global model by aggregating local models from hospitals. Existing FL techniques adopt a central server-based network topology, where the serv