Search results

In this paper we present a method for line segment detection in images, based on a semi-supervised framework. Leveraging the use of a consistency loss based on differently augmented and perturbed unlabeled images with a small amount of labeled data, we show comparable results to fully supervised methods. This opens up application scenarios where annotation is difficult or expensive, and for domain

This paper presents NMCu-CNN, a near-memory computing (NMC) co-processor for the hardware acceleration of convolutional neural networks (CNNs) on a low-power, flexible MCU platform. The scalable architecture and the selected platform enable adaptability to the rapidly evolving Edge AIoT landscape, where energy and performance requirements are constrained. Application-tailored NMC units, equipped w

With the growing need to process large volumes of data, edge computing near data collection sources has become increasingly important. However, the resource constraints of edge devices require more efficient data processing techniques. Near-memory computing (NMC) presents an efficient solution, especially for data-intensive applications, by enabling processing that is both energy-efficient and har

A multi-variable adaptive controller is derived as the explicit solution to a minimax dynamic game. The minimizing player selects the control action as a function of past state measurements and inputs. The maximizing player selects disturbances and model parameters for the underlying linear time-invariant dynamics. This leads to a Bellman equation that can be solved explicitly for the case with un

We introduce Thalassa, a framework designed to convert nonlinear systems of partial differential equations (PDEs) with a time-like component into tensor programs that solve these equations. These programs can run on GPUs as well as machine learning (ML) acceleration hardware, enabling scientific computing fields such as computational fluid dynamics, astrophysics, mechanics and biology to utilize a

The modified diet history methodology of the Malmö Diet and Cancer cohort 2016-09-05 1 The modified diet history methodology of the Malmö Diet Cancer cohort Edited by Elisabet Wirfält, Emily Sonestedt Resource persons: - Dietary data collection at baseline: Ulrika Ericson (ulrika.ericson@med.lu.se) Peter Wallström (especially supplements) (peter.wallstrom@med.lu.se) - Consultation on dietary data

https://www.malmo-kohorter.lu.se/sites/malmo-kohorter.lu.se/files/mdc_diet_history.pdf - 2026-05-30

Objective: To assessmyoepithelium with p63 in fresh breast cancer (BC)tissue samples collected in RNA later for further analysis with NextGeneration Sequencing (NGS) technique. For a better understanding ofthe NGS bulk-analysis, a central part of the sample in RNA-later isformalin-fixed paraffin-embedded to score relative cellularity in % onhematoxylin-eosin (HE) staining (% of invasive cancer, ca

Photoinduced bimolecular charge transfer processes involving the iron(III) N-heterocyclic carbene (FeNHC) photosensitizer [Fe(phtmeimb)2]+ (phtmeimb = phenyltris(3-methyl-imidazolin-2-ylidene)borate) and triethylamine as well as N,N-dimethylaniline donors have been studied using optical spectroscopy. The full photocycle of charge separation and recombination down to ultrashort time scales was stud

Purpose - The purpose of this paper is to examine if gendered differences in risk perception automatically mean that women and men rank the hazards of their community differently, focusing any risk reduction measures on the priority risks of only part of the population. Design/methodology/approach - The study applies survey research through structured personal interviews in three municipalities in

This article argues for the importance of explicit discussions of what is valuable as a foundation for any disaster risk reduction initiative to be effective. It does so by stating that it is impossible to talk about risk at all if not having some notion of uncertain potential impacts on something that humans value. What is assumed as valuable and important to protect is then determining what haza

We examined the transduction efficiency of different adeno-associated virus (AAV) capsid serotypes encoding for green fluorescent protein (GFP) flanked by AAV2 inverted terminal repeats in the nonhuman primate basal ganglia as a prelude to translational studies, as well as clinical trials in patients with Parkinson's disease (PD). Six intact young adult cynomolgus monkeys received a single 10 mu l

In order to avoid extensive machine learning models selection and optimizations, Automated Machine Learning (AutoML) has arisen as a practical and efficient way to apply machine learning to many different application areas. Data poisoning is a real threat to the accuracy of machine learning models in different settings, and it has in recent research studies been shown that the usage of AutoML can

Characteristic Mode analysis is a widely used technique in antenna design, providing insight into the fundamental electromagnetic behavior of radiating structures. In this paper, we establish fundamental bounds on the slope of characteristic mode eigenvalues and angles, demonstrating that their rate of change is subject to fundamental constraints for all possible realizations within a given design

We study dynamical optimal transport of discrete time systems (dDOT) with Lagrangian cost. The problem is approached by combining optimal control and Kantorovich duality theory. Based on the derived solution, a first order splitting algorithm is proposed for numerical implementation. While solving partial differential equations is often required in the continuous time case, a salient feature of ou

The growing use of 5G networks for critical services makes them vulnerable to Distributed Denial of Service (DDoS) attacks. While numerous Machine Learning (ML)-based approaches have been proposed, the real-world deployability of these models remains understudied. This work presents what is, based on existing literature, the first simulation-driven methodology to evaluate both the transferability

Code Language Model (code-LM)-based vulnerability detection for C/C++ faces a substantial challenge. Previous research has shown that even though it is better than any prior machine learning approach, it still struggles to generalize well, as shown by the low F1 score. Prior works treated the problem as a binary classification: either vulnerable or non-vulnerable. Looking deeper at the various vul

Before performing 177Lu-DOTATATE therapy for neuroendocrine tumors, somatostatin receptor (SSTR) PET imaging is currently used to confirm sufficient tumor SSTR expression, but it also has potential to be used to personalize treatment by predicting absorbed doses to critical organs. This study aims to validate the predictive capability of SSTR PET in anticipating renal absorbed dose in the first cy

Extended Reality (XR) serves as a broad term that encompasses several immersive technologies, including Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR). Currently, most XR devices are connected by cables, which restrict user mobility and negatively impact the overall Quality of Experience (QoE) for users. XR devices face limitations not only in terms of connectivity but also i

Localizing users and mapping the environment using radio signals is a key task in emerging applications such as reliable communications, location-aware security, and safety critical navigation. Recently introduced multipath-based simultaneous localization and mapping (MP-SLAM) can jointly localize a mobile agent and the reflective surfaces in radio frequency (RF) environments. Most existing MP-SLA