All posts under category "Research"
Generating medical reports from chest X-ray images is a critical and time-consuming task for radiologists, especially in emergencies. To alleviate the stress on radiologists and reduce the risk of misdiagnosis, numerous research efforts have been ded
In this paper, we consider anisotropic diffusion with decay, and the diffusivity coefficient to be a second-order symmetric and positive definite tensor. It is well-known that this particular equation is a second-order elliptic equation, and satisfie
ASD is a complicated neurodevelopmental disorder marked by variation in symptom presentation and neurological underpinnings, making early and objective diagnosis extremely problematic. This paper presents a Graph Convolutional Network (GCN) model, in
IT offers some benefits and collaborations in various sectors. This research focuses on exploring higher education subjects via social technology, YouTube. YouTube is the world largest video based contents application in the world. Current learning m
Low-Mass X-ray Binaries (LMXRBs), believed to be the progenitors of recycled millisecond pulsars (MSPs), occur abundantly in globular clusters (GCs). GCs are therefore expected to host large numbers of MSPs. This is also confirmed observationally. Th
With a view towards understanding why undesirable outcomes often arise in ICT projects, we draw attention to three aspects in this essay. First, we present several examples to show that incorporating an ethical framework in the design of an ICT syste
Volume containing the Late-Breaking Abstracts submitted to the Evo 2025 Conference, held in Trieste (Italy) from April 23rd to 25th. These extended abstracts showcase ongoing research and preliminary findings exploring the application of various Bio
We study evolution of isolated neutron stars on long time scale and calculate distribution of these sources in the main evolutionary stages: Ejector, Propeller, Accretor, and Georotator. We compare different initial magnetic field distributions takin
We give a simple polynomial-time algorithm to exactly count the number of Euler Tours (ETs) of any Eulerian generalized series-parallel graph, and show how to adapt this algorithm to exactly sample a random ET of the given generalized series-parallel
Artificial intelligence (AI) is increasingly permeating healthcare, from physician assistants to consumer applications. Since AI algorithm's opacity challenges human interaction, explainable AI (XAI) addresses this by providing AI decision-making ins
Wireless Sensor Networks (WSNs) often lack interfaces for remote debugging. Thus, fault diagnosis and troubleshooting are conducted at the deployment site. Currently, WSN operators lack dedicated tools that aid them in this process. Therefore, we int
Since the emergence of joint-stock companies, financial fraud by listed firms has repeatedly undermined capital markets. Fraud is difficult to detect because of covert tactics and the high labor and time costs of audits. Traditional statistical model
We present proofs of basic results, including those developed by Harold Bell, for the plane fixed point problem: does every map of a non-separating plane continuum have a fixed point? Some of these results had been announced much earlier by Bell but
In our former work [K. Tadaki, Local Proceedings of CiE 2008, pp.425-434, 2008], we developed a statistical mechanical interpretation of algorithmic information theory by introducing the notion of thermodynamic quantities at temperature T, such as fr
A metabolic model can be represented as bipartite graph comprising linked reaction and metabolite nodes. Here it is shown how a network of conserved fluxes can be assigned to the edges of such a graph by combining the reaction fluxes with a conserved
Local reasoning about programs exploits the natural local behaviour common in programs by focussing on the footprint - that part of the resource accessed by the program. We address the problem of formally characterising and analysing the footprint no
Because contemporary large software systems are pervasively inconsistent, it is not safe to reason about them using classical logic. The goal of Direct Logic is to be a minimal fix to classical mathematical logic that meets the requirements of large-
This study investigates how generative AI systems interpret the architectural intelligence embedded in vernacular form. Using the Iranian pigeon tower as a case study, the research tests three diffusion models, Midjourney v6, DALL-E 3, and DreamStudi
Image manipulation localization (IML) faces a fundamental trade-off between minimizing annotation cost and achieving fine-grained localization accuracy. Existing fully-supervised IML methods depend heavily on dense pixel-level mask annotations, which
Diabetic Retinopathy (DR) remains a leading cause of preventable blindness, with early detection critical for reducing vision loss worldwide. Over the past decade, deep learning has transformed DR screening, progressing from early convolutional neura
Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture the global
The 0/1 multidimensional knapsack problem is the 0/1 knapsack problem with m constraints which makes it difficult to solve using traditional methods like dynamic programming or branch and bound algorithms. We present a genetic algorithm for the multi
G'odel's second incompleteness theorem is proved for Herbrand consistency of some arithmetical theories with bounded induction, by using a technique of logarithmic shrinking the witnesses of bounded formulas, due to Z. Adamowicz [Herbrand consistency
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential, particularly for structured dat
We introduce hierarchical neighbor graphs, a new architecture for connecting ad hoc wireless nodes distributed in a plane. The structure has the flavor of hierarchical clustering and requires only local knowledge and minimal computation at each node
The concept of a protein diffusing in its free energy folding landscape has been fruitful for both theory and experiment. Yet the choice of the reaction coordinate (RC) introduces an undesirable degree of arbitrariness into the problem. We analyze ex
How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and inheritance is embedded within the network. By uniting hypernetworks,
Real world image super-resolution (Real-ISR) often leverages the powerful generative priors of text-to-image diffusion models by regularizing the output to lie on their learned manifold. However, existing methods often overlook the importance of the
In the outer solar system beyond Jupiter, water ice is a dominant component of planetary bodies, and most solid objects in this region are classified as icy bodies. Icy bodies display a remarkable diversity of geological, geophysical, and atmospheric
We analyze the recently published Fermi-LAT diffuse gamma-ray measurements in the context of leptonically annihilating or decaying dark matter (DM) with the aim to explain simultaneously the isotropic diffuse gamma-ray and the PAMELA, Fermi and HESS
Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unknown model behavior under the specific perturbations used. This paper in
Sparse Inertial Measurement Units (IMUs) based human motion capture has gained significant momentum, driven by the adaptation of fundamental AI tools such as recurrent neural networks (RNNs) and transformers that are tailored for temporal and spatial
In this paper we study Inozemtsev's su(m) quantum spin model with hyperbolic interactions and the associated spin chain of Haldane-Shastry type introduced by Frahm and Inozemtsev. We compute the spectrum of Inozemtsev's model, and use this result and
We describe a family of instanton-based optimization methods developed recently for the analysis of the error floors of low-density parity-check (LDPC) codes. Instantons are the most probable configurations of the channel noise which result in decodi
In this work we introduce hierarchy in wireless networks that can be modeled by a decentralized multiple access channel and for which energy-efficiency is the main performance index. In these networks users are free to choose their power control stra
As the volume of published scholarly literature continues to grow, finding relevant literature becomes increasingly difficult. With the rise of generative Artificial Intelligence (AI), and particularly Large Language Models (LLMs), new possibilities
In ``Rips complexes and covers in the uniform category'' the authors define, following James, covering maps of uniform spaces and introduce the concept of generalized uniform covering maps. Conditions for the existence of universal uniform covering m
In this paper we study the relation of radio emission to X-ray spectral and variability properties for a large sample of black hole X-ray binary systems. This is done to test, refine and extend -- notably into the timing properties -- the previously
Real-time sea state estimation is vital for applications like shipbuilding and maritime safety. Traditional methods rely on accurate wave-vessel transfer functions to estimate wave spectra from onboard sensors. In contrast, our approach jointly estim
Modern codebases evolve continuously: files are renamed or deleted; public APIs drift; behavior shifts within otherwise familiar modules. A model trained yesterday to map a developer's natural-language question to the exact set of repository file pat
This paper develops a novel framework for sharing secret keys using the Automatic Repeat reQuest (ARQ) protocol. We first characterize the underlying information theoretic limits, under different assumptions on the channel spatial and temporal correl
GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that produces and iteratively refines
Low latency event-selection (trigger) algorithms are essential components of Large Hadron Collider (LHC) operation. Modern machine learning (ML) models have shown great offline performance as classifiers and could improve trigger performance, thereby
We take two key steps in automating the open-ended discovery of new mathematical theories, a grand challenge in artificial intelligence. First, we introduce emph{FERMAT} , a reinforcement learning (RL) environment that models concept discovery and t
Artificial intelligence systems in critical fields like autonomous driving and medical imaging analysis often continually learn new tasks using a shared stream of input data. For instance, after learning to detect traffic signs, a model may later nee
The Whisper model, an open-source automatic speech recognition system, is widely adopted for its strong performance across multilingual and zero-shot settings. However, it frequently suffers from hallucination errors, especially under noisy acoustic
Taming the Terahertz waves (100 GHz-10 THz) is considered the next frontier in wireless communications. While components for the ultra-high bandwidth Terahertz wireless communications were in rapid development over the past several years, however, th
Linearized catalytic reaction equations modeling e.g. the dynamics of genetic regulatory networks under the constraint that expression levels, i.e. molecular concentrations of nucleic material are positive, exhibit nontrivial dynamical properties, wh
This research examines the potential of datasets generated by Large Language Models (LLMs) to support Natural Language Processing (NLP) tasks, aiming to overcome challenges related to data acquisition and privacy concerns associated with real-world d
Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing caching mechanisms,such as tok
Enter keywords to search articles