Informa (Sweden)

Abstract 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 be even more sensitive to data poisoning than is the case for non-AutoML generated models. On the other hand, the usage of AutoML also has the potential of improving the robustness of a model by adapting the model to adversarial patterns. In this way, good accuracy can be maintained despite the attacker’s efforts to poison the data. However, no previous studies have investigated these effects. In this paper, we examine the risks associated with adversarial trajectory attacks in mobile systems, specifically looking into mobility prediction problems. By using mobility data from two different simulation frameworks: a simulator developed by Ericsson, which is based on a real-world deployment of Airtel’s open-network topology, and the ONE framework, we investigate three different AutoML frameworks and how the mobility accuracy for the frameworks is affected by a mobile trajectory attack. Our results show that re-running AutoML at every retraining is vulnerable to adversarial mobility poisoning and shows high accuracy variance. By contrast, using a single, well-chosen model from an initial AutoML search achieves more stable performance across adversarial conditions, even when the training set includes up to 10% adversarial mobility data.

Smart health systems represent a transformative advancement in healthcare, offering numerous benefits such as remote consultations, digital medical results, and online prescription management. However, these systems come with their own set of challenges, particularly concerning sustainability. Sustainability is a multifaceted concept that encompasses various dimensions, including social, technical, economic, and environmental. Understanding how these aspects influence software systems is crucial for integrating sustainability into smart health solutions. This chapter explores the intersection of sustainability and smart health systems, highlighting the importance of integrating sustainability considerations from the early stages of development.

In the digital era, the growing demand for computer literacy has underscored the importance of effective programming education. Programming educational games help students learn programming knowledge through a "learning by playing" approach. However, effectively applying the beyond-the-game experiences brought by metagame design to programming educational games remains a challenge. This study analyzed related studies using Latent Dirichlet Allocation (LDA) topic modeling, revealing that introducing metagame elements can stimulate students' deep thinking and self-directed learning motivation. Based on these findings, propose the following design principles: Embedding programming knowledge into game narratives, Integrating metagame elements into game mechanics, and Utilizing multiple endings for game-based assessment. This work contributes actionable strategies for designing inclusive and innovative programming educational games, aligning with the evolving needs of digital literacy education.

We offer a new model of the sensemaking process for data analysis and visualization. Whereas past sensemaking models have been grounded in positivist assumptions about the nature of knowledge, we reframe data sensemaking in critical, humanistic terms by approaching it through an interpretivist lens. Our three-phase process model uses the analogy of an iceberg, where data is the visible tip of underlying schemas. In the Add phase, the analyst acquires data, incorporates explicit schemas from the data, and absorbs the tacit schemas of both data and people. In the Check phase, the analyst interprets the data with respect to the current schemas and evaluates whether the schemas match the data. In the Refine phase, the analyst considers the role of power, articulates what was tacit into explicitly stated schemas, updates data, and formulates findings. Our model has four important distinguishing features: Tacit and Explicit Schemas, Schemas First and Always, Data as a Schematic Artifact, and Schematic Multiplicity. We compare the roles of schemas in past sensemaking models and draw conceptual distinctions based on a historical review of schemas in different academic traditions. We validate the descriptive and prescriptive power of our model through four analysis scenarios: noticing uncollected data, learning to wrangle data, downplaying inconvenient data, and measuring with sensors. We conclude by discussing the value of interpretivism, the virtue of epistemic humility, and the pluralism this sensemaking model can foster.

In cell-free (CF) networks, access points (APs) jointly serve the user equipments (UEs). In user-centric (UC) variant, only a handful of APs serve a particular UE, namely the ones with the best channels. In this paper, we propose a hybrid beamforming aided uplink receiver scheme for highly loaded UC massive MIMO (mMIMO) networks, operating in millimeter-wave (mmWave) frequencies, employing single carrier modulation under frequency selective channels. Every AP employs its own analog beamformer (AB) called the modified eigen-beamformer (MEB), which promotes a trend of fairness. In the digital domain, two detectors are proposed; Cell-Free Iterative Detector (CFI-D) and User-Centric Iterative Subset-Detector (UCIS-D). CFI-D introduces the iterative block decision feedback equalization (IB-DFE) method for CF networks. UCIS-D is an alternative to CFI-D. UCIS-D is UC, has low computational complexity (CCP) and is scalable. UCIS-D relies on parallel interference cancellation (PIC) aided IB-DFE. Interfering UEs are divided into three sets. Weak interferers are processed with PIC, strong interferers with IB-DFE which considers the residual interference from PIC. Weakest interferers are ignored. Both PIC and IB-DFE utilize the soft decisions from previous iterations. Simulation results show that these receivers can handle ultra high loads in terms of bit-error-rate (BER) and achievable information rate (AIR).

Current cyber-physical systems, including multi-robot systems, often fail to interoperate effectively, resulting in suboptimal performance, inefficient resource utilization, and poor resilience. Inspired by natural symbiotic relationships, such as tree-fungi networks, we propose an architecture that integrates ecological symbiosis principles into multi-robot system specifications. Specifically, we incorporate symbiotic principles into multiagent reinforcement learning (MARL) within a centralized training, decentralized execution framework. Comprehensive scenario-based evaluations in a simulated warehouse environment show that our symbiotic MARL framework improves system performance (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$10.7\%$</tex>) and resource utilization (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$13.81\%$</tex>) compared to non-symbiotic baselines. Agents dynamically adjust their behavior in response to environmental changes, ensuring continuous task execution, efficient navigation, and balanced energy use. These findings demonstrate that integrating ecological principles into MARL enhances the system's efficiency and performance. The framework's success in promoting sustainable resource usage while maintaining high task performance suggests broader applications across various cyber-physical domains where adaptive coordination is crucial.

Hundreds of loci have been robustly associated with obesity-related traits, but functional characterization of candidate genes remains a bottleneck. Aiming to systematically characterize candidate genes for a role in accumulation of lipids in adipocytes and other cardiometabolic traits, we developed a pipeline using CRISPR/Cas9, non-invasive, semi-automated fluorescence imaging and deep learning-based image analysis in live zebrafish larvae. Results from a dietary intervention show that 5 days of overfeeding is sufficient to increase the odds of lipid accumulation in adipocytes by 10 days post-fertilization (dpf, n = 275). However, subsequent experiments show that across 12 to 16 established obesity genes, 10 dpf is too early to detect an effect of CRISPR/Cas9-induced mutations on lipid accumulation in adipocytes (n = 1014), and effects on food intake at 8 dpf (n = 1127) are inconsistent with earlier results from mammals. Despite this, we observe effects of CRISPR/Cas9-induced mutations on ectopic accumulation of lipids in the vasculature (sh2b1 and sim1b) and liver (bdnf); as well as on body size (pcsk1, pomca, irs1); whole-body LDLc and/or total cholesterol content (irs2b and sh2b1); and pancreatic beta cell traits and/or glucose content (pcsk1, pomca, and sim1a). Taken together, our results illustrate that CRISPR/Cas9- and image-based experiments in zebrafish larvae can highlight direct effects of obesity genes on cardiometabolic traits, unconfounded by their – not yet apparent – effect on excess adiposity.

This paper proposes a nonlinear model predictive control (NMPC) approach for incrementally input-to-state stable gated recurrent units (GRU) neural networks affected by state and output disturbances. In particular, a Luenbergerlike observer is designed for state and disturbance estimation with guaranteed convergence properties. This paves the way for the design of an NMPC regulator capable of rejecting unknown piecewise-constant disturbances. The method is tested in simulation on a nonlinear benchmark system, i.e., a chemical reaction process, showing promising results.

The Impulsive Goodwin’s Oscillator (IGO) is a mathematical model that represents a hybrid closed-loop system. It arises by closing a specific of type continuous positive linear time-invariant system with impulsive feedback, incorporating both amplitude and frequency pulse modulation. The structure of the IGO precludes the existence of equilibria and thus ensures that all of its solutions, whether periodic or non-periodic, are oscillatory. Originating in mathematical biology, the IGO also constitutes a control paradigm applicable to a wide range of fields, particularly to closed-loop dosing of chemicals and medicines. The pulse modulated feedback introduces strong nonlinearity and non-smoothness into the closed-loop dynamics thus rendering conventional controller design methods not applicable. However, the hybrid dynamics of IGO reduce to a nonlinear discrete-time system, exhibiting a one-to-one correspondence between solutions of the original hybrid IGO and those of the discrete-time system. The paper proposes a design approach that leverages the linearization of the equivalent discrete-time dynamics in the vicinity of a fixed point. An efficient local stability condition of the 1 -cycle in terms of the characteristics of the amplitude and frequency modulation functions is obtained. Unlike the conventional Schur-Cohn and Jury stability conditions applied to the Jacobian matrix, the obtained criterion requires checking a single inequality that is linear in the slopes of the modulation characteristics.