Worker-Centered Design (WCD) has gained prominence over the past decade, offering researchers and practitioners ways to engage worker agency and support collective actions for workers. Yet few studies have systematically revisited WCD itself, examining its implementations, challenges, and practical impact. Through a four-lens analytical framework that examines multiple facets of WCD within food delivery industry, we identify critical tensions and blind spots from a Multi-Laborer System perspective. Our analysis reveals conflicts across labor chains, distorted implementations of WCD, designers’ sometimes limited political-economic understanding, and workers as active agents of change. These insights further inform a Diagnostic-Generative pathway that helps to address recurring risks, including labor conflicts and institutional reframing, while cultivating designers’ policy and economic imagination. Following the design criticism tradition, and through a four-lens reflexive analysis, this study expands the action space for WCD and strengthens its relevance to real-world practice.

Migration and technology studies increasingly recognize the importance of incorporating migrant perspectives in design processes. Speculative design methods have emerged as powerful tools for imagining alternative futures, particularly when working with marginalized communities. However, there remains a gap in understanding how to effectively engage long-term settled migrants in participatory design processes that honor their experiences and imaginative capacities. Here we show how integrating feminist care principles with speculative design methods can create more inclusive and empathetic approaches to technology design with migrant communities. Through workshops applying the ''magic machines'' methodology, we demonstrate how participatory speculation enables migrants to articulate their experiences, anxieties, and hopes for technological futures. Our findings reveal the importance of considering diasporic minds and cross-border connectivity in future technologies. This work provides immediate opportunities for researchers and designers to develop more inclusive approaches to speculative design while challenging dominant narratives about technological futures in migrant communities.

In rehabilitation applications, encouraging patients to actively participate in training is essential for effective recovery. However, personalized control design in robot-assisted therapy remains challenging due to variations in patients' motor capabilities. To address this issue, this paper proposes an assist-as-needed (AAN) control framework that integrates a hybrid fuzzy-transformer neural network (HFTN) with a fuzzy echo state network (FESN)-based variable impedance controller to ensure personalized support and active engagement. The HFTN integrates fuzzy logic with transformer architectures in parallel paths, establishing a novel neuro-fuzzy musculoskeletal (MSK) model that maps surface electromyography (sEMG) signals to joint torque through combined uncertainty and temporal modeling for enhanced real-time estimation. The variable impedance controller constructs the stiffness and damping matrices of the robotic system through the FESN and develops an adaptive update law for the FESN output weights, effectively addressing instability issues in variable stiffness control. Furthermore, driven by physiologically estimated joint torques from the HFTN, the adaption of the FESN reservoir states enables real-time modulation of stiffness and damping, facilitating transitions between human-dominated and robot-dominated modes. This realizes the AAN concept, ensuring personalized and responsive assistance. Various experiments on an upper limb rehabilitation robot were conducted to validate the effectiveness of both the neuro-fuzzy MSK model and the AAN controller in delivering optimal assistance while promoting active user participation.

HCI and design studies have increasingly identified challenges for gig workers and advocated for designs centered around worker justice. However, there’s an existing research gap in understanding how platform designers approach gig worker issues in their practice. Our study engaged ten platform designers from food delivery and ride-hailing platforms to investigate this gap. Through semi-structured interviews, we uncovered their strategies, the extent of authority and responsibilities, and the range of obstacles they encounter in influencing decision-making that could affect gig workers’ experiences with the platforms. While platform designers were aware of gig worker issues, they confronted challenges from business goals, decision-making power, policies, and job security in promoting worker well-being. We discuss the jurisdiction of platform designers and propose that HCI research should further support them, who are deeply engaged in the gig economy and have the potential to participate in addressing social justice issues.

Muscle force and joint kinematics estimation from surface electromyography (sEMG) are essential for real-time biomechanical analysis of the dynamic interplay among neural muscle stimulation, muscle dynamics, and kinetics. Recent advances in deep neural networks (DNNs) have shown the potential to improve biomechanical analysis in a fully automated and reproducible manner. However, the small sample nature and physical interpretability of biomechanical analysis limit the applications of DNNs. This paper presents a novel physics-informed low-shot adversarial learning method for sEMG-based estimation of muscle force and joint kinematics. This method seamlessly integrates Lagrange's equation of motion and inverse dynamic muscle model into the generative adversarial network (GAN) framework for structured feature decoding and extrapolated estimation from the small sample data. Specifically, Lagrange's equation of motion is introduced into the generative model to restrain the structured decoding of the high-level features following the laws of physics. A physics-informed policy gradient is designed to improve the adversarial learning efficiency by rewarding the consistent physical representation of the extrapolated estimations and the physical references. Experimental validations are conducted on two scenarios (i.e. the walking trials and wrist motion trials). Results indicate that the estimations of the muscle forces and joint kinematics are unbiased compared to the physics-based inverse dynamics, which outperforms the selected benchmark methods, including physics-informed convolution neural network (PI-CNN), vallina generative adversarial network (GAN), and multi-layer extreme learning machine (ML-ELM).

The gig economy and digital labor platforms, such as food delivery, have become essential while also troubling the current socioeconomic landscape. Delivery platforms promise entry-level work, flexibility, and other benefits. However, researchers remain divided on if these platforms benefit workers and society at large. This study aims to shed light on the comprehensive challenges in food delivery work, uncovering gig worker-centered design opportunities to improve the lives of food couriers. Adopting an exploratory research process, we analyzed 19 ride-along food delivery videos and performed nine semi-structured interviews with food couriers in Portugal. Our findings illustrated the complexity and challenging nature of delivery work due to the entangled physical, digital, social, natural, and human factors. We captured and discussed gig worker-centered opportunities that surfaced from work challenges, echoing the needs of food couriers about supporting work, justice, inclusion, and work vision.

Abstract Transitioning to and through University is a delicate period for students’ well-being. Moreover, the recent COVID-19 pandemic added a further toll through the various challenges related to studying, socializing, community-building, and safety. These challenges inspired the design of a mobile application, called Tecnico GO!, to support university students’ well-being and academic performance. This paper presents the design rationale and evaluation of the app conducted during the academic year 2021-2022. Findings cluster around three themes: i) students studying needs; ii) building a sense of community; iii) gamification strategies. The discussion elaborates on the student’s perceptions of well-being during pandemics. Students’ perception of the app is positive, appreciative of the crowdsensing features, supporting learning goals, community building, and safety. On the other hand, the gamification features, as currently deployed, do not achieve the expected goals.

Network traffic prediction is a great challenge due to complex statistical properties, generally covering the long-range correlations and self-similarity. To address this issue, this article applies an integrated neural computing model to predict network traffic, namely, enhanced echo-state restricted Boltzmann machine (eERBM). In structure, this model possesses the following functional components of feature learning, information compensation, input superposition, and supervised nonlinear approximation. It is motivated by the introduction of information theory in modeling the hybrid architecture of the echo state network and the restricted Boltzmann machine. This is the first attempt that eERBM is applied in network traffic prediction tasks of different origin and characteristics, considering TCP/IP packet and variable-bit-rate video. By performing a theoretical analysis, we show that eERBM achieves superior nonlinear approximation and robustness in comparison to the baseline methods, and effectively preserves the self-similarity of network traffic traces.