61378 research outputs found
Sort by
Constructing Autonomy: Experiences of Women Living Organ Donors in Turkey
No full texteditorial reviewed5. Gender equalit
Which company adjustment matter? Insights from Uplift Modeling on Financial Health
No full textpeer reviewedUplift modeling has achieved significant success in various fields, particularly in online marketing. It is a method that primarily utilizes machine learning and deep learning to estimate individual treatment effects. This paper we apply uplift modeling to analyze the effect of company adjustment on their financial status, and we treat these adjustment as treatments or interventions in this study. Although there have been extensive studies and application regarding binary treatments, multiple treatments, and continuous treatments, company adjustment are often more complex than these scenarios, as they constitute a series of multiple time-dependent actions. The effect estimation of company adjustment needs to take into account not only individual treatment traits but also the temporal order of this series of treatments. This study collects a real-world data set about company financial statements and reported behavior in Luxembourg for the experiments. First, we use meta-learners and other well-known uplift models to analyze different company adjustment by simplifying the adjustment as binary treatments. Furthermore, we propose a new uplift modeling framework (MTDnet) to address the time-dependent nature of these adjustment, and the experimental result shows the necessity of considering the timing of these adjustment.SCRIP
Das parasitäre Dasein der Dinge: Über Schuhe, Federschmuck und ein Schwert in der Theaterperformance Lost Puppy vom Korso-op.Kollektiv
No full textpeer reviewe
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Full text linkpeer reviewedMost log-based anomaly detectors assume logs are stable, though logs are
often unstable due to software or environmental changes. Anomaly detection on
unstable logs (ULAD) is therefore a more realistic, yet under-investigated
challenge. Current approaches predominantly employ machine learning (ML)
models, which often require extensive labeled data for training. To mitigate
data insufficiency, we propose FlexLog, a novel hybrid approach for ULAD that
combines ML models -- decision tree, k-nearest neighbors, and a feedforward
neural network -- with a Large Language Model (Mistral) through ensemble
learning. FlexLog also incorporates a cache and retrieval-augmented generation
(RAG) to further enhance efficiency and effectiveness. To evaluate FlexLog, we
configured four datasets for \task, namely ADFA-U, LOGEVOL-U, SynHDFS-U, and
SYNEVOL-U. FlexLog outperforms all baselines by at least 1.2 percentage points
(pp) in F1 score while using much less labeled data (62.87 pp reduction). When
trained on the same amount of data as the baselines, FlexLog achieves up to a
13 pp increase in F1 score on ADFA-U across varying training dataset sizes.
Additionally, FlexLog maintains inference time under one second per log
sequence, making it suitable for most applications, except latency-sensitive
systems. Further analysis reveals the positive impact of FlexLog's key
components: cache, RAG and ensemble learning
AI-Driven RSMA Beamforming for Integrated Sensing and Communication in Terrestrial-Satellite Networks
No full textpeer reviewedThe increasing demand for high-capacity and globally accessible wireless services has intensified the need for spectrum-efficient and wide-coverage solutions. Integrated terrestrial-satellite networks (ITSNs) offer a promising architecture to address these challenges, while with the deployment of integrated sensing and communication (ISAC) and rate-splitting multiple access (RSMA) further enhances system functionality by supporting joint communication and sensing while effectively managing interference.
This paper investigates RSMA for a multi-antenna LEO satellite that shares the licensed spectrum of terrestrial distributed MIMO systems to simultaneously perform target sensing and provide communication services.
A weighted sum-rate maximization problem is formulated, subject to power, sensing, and interference constraints. To solve the resulting non-convex problem, we develop a hybrid solution that combines a deep convolutional neural network (CNN) for power allocation with a semidefinite relaxation (SDR)-based method for precoding and rate optimization.
Simulation results demonstrate that the proposed scheme satisfies all constraints and achieves performance close to a successive convex approximation (SCA)-based benchmark, while significantly reducing computational time, which makes it suitable for real-time deployment in resource-constrained satellite systems. Additionally, the RSMA-based approach outperforms conventional baseline methods