This paper explores Physical-Layer Security (PLS) in Flexible Duplex (FlexD) networks, considering scenarios involving eavesdroppers. Our investigation revolves around the intricacies of the sum secrecy rate maximization problem, particularly when faced with coordinated and distributed eavesdroppers employing a Minimum Mean Square Error (MMSE) receiver. Our contributions include an iterative classical optimization solution and an unsupervised learning strategy based on Graph Neural Networks (GNNs). To the best of our knowledge, this work marks the initial exploration of GNNs for PLS applications. Additionally, we extend the GNN approach to address the absence of eavesdroppers' channel knowledge. Extensive numerical simulations highlight FlexD's superiority over Half-Duplex (HD) communications and the GNN approach's superiority over the classical method in both performance and time complexity.
Background: Eating disorders are increasingly prevalent, and social networks offer valuable information. Objective: Our goal was to identify efficient machine learning models for categorizing tweets related to eating disorders. Methods: Over three months, we collected tweets about eating disorders. A 2,000-tweet subset was labeled for: (1) being written by individuals with eating disorders, (2) promoting eating disorders, (3) informativeness, and (4) scientific content. Both traditional machine learning and deep learning models were employed for classification, assessing accuracy, F1 score, and computational time. Results: From 1,058,957 collected tweets, transformer-based bidirectional encoder representations achieved the highest F1 scores (71.1%-86.4%) across all four categories. Conclusions: Transformer-based models outperform traditional techniques in classifying eating disorder-related tweets, though they require more computational resources.
Data annotation is an essential step for constructing new datasets. However, the conventional approach of data annotation through crowdsourcing is both time-consuming and expensive. In addition, the complexity of this process increases when dealing with low-resource languages owing to the difference in the language pool of crowdworkers. To address these issues, this study proposes an autonomous annotation method by utilizing large language models, which have been recently demonstrated to exhibit remarkable performance. Through our experiments, we demonstrate that the proposed method is not just cost-efficient but also applicable for low-resource language annotation. Additionally, we constructed an image captioning dataset using our approach and are committed to open this dataset for future study. We have opened our source code for further study and reproducibility.
We present an active learning algorithm for the problem of body schema learning, i.e. estimating a kinematic model of a serial robot. The learning process is done online using Recursive Least Squares (RLS) estimation, which outperforms gradient methods usually applied in the literature. In addiction, the method provides the required information to apply an active learning algorithm to find the optimal set of robot configurations and observations to improve the learning process. By selecting the most informative observations, the proposed method minimizes the required amount of data. We have developed an efficient version of the active learning algorithm to select the points in real-time. The algorithms have been tested and compared using both simulated environments and a real humanoid robot.
In Software Product Lines (SPLs) it may be difficult or even impossible to test all the products of the family because of the large number of valid feature combinations that may exist. Thus, we want to find a minimal subset of the product family that allows us to test all these possible combinations (pairwise). Furthermore, when testing a single product is a great effort, it is desirable to first test products composed of a set of priority features. This problem is called Prioritized Pairwise Test Data Generation Problem. State-of-the-art algorithms based on Integer Linear Programming for this problema are faster enough for small and medium instances. However, there exists some real instances that are too large to be computed with these algorithms in a reasonable time because of the exponential growth of the number of candidate solutions. Also, these heuristics not always lead us to the best solutions. In this work we propose a new approach based on a hybrid metaheuristic algorithm called Construct, Merge, Solve & Adapt. We compare this matheuristic with four algorithms: a Hybrid algorithm based on Integer Linear Programming ((HILP), a Hybrid algorithm based on Integer Nonlinear Programming (HINLP), the Parallel Prioritized Genetic Solver (PPGS), and a greedy algorithm called prioritized-ICPL. The analysis reveals that CMSA results in statistically significantly better quality solutions in most instances and for most levels of weighted coverage, although it requires more execution time.
Over the recent years, the emergence of large language models (LLMs) has given rise to a proliferation of domain-specific models that are intended to reflect the particularities of linguistic context and content as a correlate of the originating domain. This paper details the conception, design, training and evaluation of DAEDRA, a LLM designed to detect regulatory-relevant outcomes (mortality, ER attendance and hospitalisation) in adverse event reports elicited through passive reporting (PR). While PR is a highly cost-efficient way of eliciting information from a wide and diverse audience -- typically including not only physicians and healthcare providers but also patients, family members and other lay stakeholders --, this diversity makes PR corpora difficult to analyse. Generic language models may not capture the complex clinical dimensions while specific clinical or biomedical models may not perform well on lay reports. To evaluate the utility of a subdomain-specific language model, an adaptive training approach was adapted, wherein base language model candidates were evaluated on a subset of the corpus, and the best performer was trained on the entire corpus. This yielded a small but significant improvement in $F_1$ (+1%), precision (+2.5%) and recall (+3.8%), at a relatively low training cost and a single-day training time. Subdomain-specific LLMs continue to be viable options for better results when analysing highly specialised corpora.
Denoising Diffusion Probabilistic Models (DDPMs) are a very popular class of deep generative model that have been successfully applied to a diverse range of problems including image and video generation, protein and material synthesis, weather forecasting, and neural surrogates of partial differential equations. Despite their ubiquity it is hard to find an introduction to DDPMs which is simple, comprehensive, clean and clear. The compact explanations necessary in research papers are not able to elucidate all of the different design steps taken to formulate the DDPM and the rationale of the steps that are presented is often omitted to save space. Moreover, the expositions are typically presented from the variational lower bound perspective which is unnecessary and arguably harmful as it obfuscates why the method is working and suggests generalisations that do not perform well in practice. On the other hand, perspectives that take the continuous time-limit are beautiful and general, but they have a high barrier-to-entry as they require background knowledge of stochastic differential equations and probability flow. In this note, we distill down the formulation of the DDPM into six simple steps each of which comes with a clear rationale. We assume that the reader is familiar with fundamental topics in machine learning including basic probabilistic modelling, Gaussian distributions, maximum likelihood estimation, and deep learning.
Continuum soft robots are nonlinear mechanical systems with theoretically infinite degrees of freedom (DoFs) that exhibit complex behaviors. Achieving motor intelligence under dynamic conditions necessitates the development of control-oriented reduced-order models (ROMs), which employ as few DoFs as possible while still accurately capturing the core characteristics of the theoretically infinite-dimensional dynamics. However, there is no quantitative way to measure if the ROM of a soft robot has succeeded in this task. In other fields, like structural dynamics or flexible link robotics, linear normal modes are routinely used to this end. Yet, this theory is not applicable to soft robots due to their nonlinearities. In this work, we propose to use the recent nonlinear extension in modal theory -- called eigenmanifolds -- as a means to evaluate control-oriented models for soft robots and compare them. To achieve this, we propose three similarity metrics relying on the projection of the nonlinear modes of the system into a task space of interest. We use this approach to compare quantitatively, for the first time, ROMs of increasing order generated under the piecewise constant curvature (PCC) hypothesis with a high-dimensional finite element (FE)-like model of a soft arm. Results show that by increasing the order of the discretization, the eigenmanifolds of the PCC model converge to those of the FE model.
Self-supervised learning (SSL) for automated speech recognition in terms of its emotional content, can be heavily degraded by the presence noise, affecting the efficiency of modeling the intricate temporal and spectral informative structures of speech. Recently, SSL on large speech datasets, as well as new audio-specific SSL proxy tasks, such as, temporal and frequency masking, have emerged, yielding superior performance compared to classic approaches drawn from the image augmentation domain. Our proposed contribution builds upon this successful paradigm by introducing CochCeps-Augment, a novel bio-inspired masking augmentation task for self-supervised contrastive learning of speech representations. Specifically, we utilize the newly introduced bio-inspired cochlear cepstrogram (CCGRAM) to derive noise robust representations of input speech, that are then further refined through a self-supervised learning scheme. The latter employs SimCLR to generate contrastive views of a CCGRAM through masking of its angle and quefrency dimensions. Our experimental approach and validations on the emotion recognition K-EmoCon benchmark dataset, for the first time via a speaker-independent approach, features unsupervised pre-training, linear probing and fine-tuning. Our results potentiate CochCeps-Augment to serve as a standard tool in speech emotion recognition analysis, showing the added value of incorporating bio-inspired masking as an informative augmentation task for self-supervision. Our code for implementing CochCeps-Augment will be made available at: https://github.com/GiannisZgs/CochCepsAugment.
The paper develops a novel motion model, called Generalized Multi-Speed Dubins Motion Model (GMDM), which extends the Dubins model by considering multiple speeds. While the Dubins model produces time-optimal paths under a constant-speed constraint, these paths could be suboptimal if this constraint is relaxed to include multiple speeds. This is because a constant speed results in a large minimum turning radius, thus producing paths with longer maneuvers and larger travel times. In contrast, multi-speed relaxation allows for slower speed sharp turns, thus producing more direct paths with shorter maneuvers and smaller travel times. Furthermore, the inability of the Dubins model to reduce speed could result in fast maneuvers near obstacles, thus producing paths with high collision risks. In this regard, GMDM provides the motion planners the ability to jointly optimize time and risk by allowing the change of speed along the path. GMDM is built upon the six Dubins path types considering the change of speed on path segments. It is theoretically established that GMDM provides full reachability of the configuration space for any speed selections. Furthermore, it is shown that the Dubins model is a specific case of GMDM for constant speeds. The solutions of GMDM are analytical and suitable for real-time applications. The performance of GMDM in terms of solution quality (i.e., time/time-risk cost) and computation time is comparatively evaluated against the existing motion models in obstacle-free as well as obstacle-rich environments via extensive Monte Carlo simulations. The results show that in obstacle-free environments, GMDM produces near time-optimal paths with significantly lower travel times than the Dubins model while having similar computation times. In obstacle-rich environments, GMDM produces time-risk optimized paths with substantially lower collision risks.