Antifreeze protein-based ultrastretchable and highly sensitive hydrogel for human-machine interaction

This paper proposes a risk analysis method for human-machine interaction system (HMIS). There are five correlated risk factors being analyzed in the HMIS: human conditions, human decision processes, human behaviors, machine and environment. With the considering of the system hazards in three types of risk scenario, we put forward an evaluation method on human-machine interaction risk for the HMIS, which provides a formalized table and contains the interaction interfaces risk evaluation procedure. In the method, we use a fuzzy method to quantify the human-machine interaction risk. Finally, a case study of the unmanned aerial vehicle (UAV) control system is conducted to illustrate the effectiveness of the method, and some advices for human-machine design are given.

Conventional Human–Machine Interaction (HMI) interfaces have predominantly relied on GUI and voice commands. However, natural human communication also consists of non-verbal communication, including hand gestures like pointing. Thus, recent works in HMI systems have tried to incorporate pointing gestures as an input, making significant progress in recognizing and integrating them with voice commands. However, existing approaches often treat these input modalities independently, limiting their capacity to handle complex multimodal instructions requiring intricate reasoning of language and gestures. On the other hand, multimodal tasks requiring complex reasoning are being challenged in the language and vision domain, but these typically do not include gestures like pointing. To bridge this gap, we explore one of the challenging multimodal tasks, called Referring Expression Comprehension (REC), within multimodal HMI systems incorporating pointing gestures. We present a virtual setup in which a robot shares an environment with a user and is tasked with identifying objects based on the user’s language and gestural instructions. Furthermore, to address this challenge, we propose a hybrid neuro-symbolic model combining deep learning’s versatility with symbolic reasoning’s interpretability. Our contributions include a challenging multimodal REC dataset for HMI systems, an interpretable neuro-symbolic model, and an assessment of its ability to generalize the reasoning to unseen environments, complemented by an in-depth qualitative analysis of the model’s inner workings.

The impact of immediate emotions on human decision-making has been extensively studied; however, their role within human–machine interactive systems remains underexplored. This study investigates how emotional states influence decision-making behaviors in such systems by introducing a novel two-tiered progressive inquiry model—environment–emotion and emotion–decision. Using Kuhn poker as an experimental context, we developed an intelligent decision support system based on Counterfactual Regret Minimization algorithms to provide real-time strategic advice to participants. Our findings reveal that positive emotional states lead individuals to be more risk-seeking and less inclined to collaborate with the AI-driven system, whereas negative emotional states result in risk-averse tendencies and higher compliance with system recommendations. By systematically uncovering the causal mechanisms through which environmental factors regulate emotions and subsequently affect decision-making, this research provides critical theoretical and empirical insights for optimizing human–machine interaction design.

A flexible pressure sensor based on melamine foam capped by copper nanowires and reduced graphene oxide

A class of proteins known as antifreeze proteins (AFPs) appear in some organisms, allowing them to survive in low-temperature environments. These AFPs irreversibly adsorb to the surfaces of ice crystals and reduce the freezing temperature without significantly affecting the equilibrium melting point. Ice crystal growth is inhibited in the temperature gap between the melting point and the non-equilibrium freezing point, referred to as thermal hysteresis (TH). The irreversible adsorption of AFPs on the surfaces of ice crystals has been questioned because it is not consistent with the concentration dependence of the TH activity obtained from experimental studies. In this study, based on adsorption–inhibition theory, a random sequential adsorption model of AFPs was used to investigate the irreversible adsorption of hyperactive AFPs that have been found in the yellow mealworm beetle Tenebrio molitor (TmAFPs). The occupied fractions covered by TmAFP on ice crystal surfaces were obtained. The time and concentration dependence of the TH activity of TmAFP was analyzed. The theoretical results obtained from this model were consistent with reported experimental data. This work provides ideas and a theoretical basis for understanding the TH activity during the irreversible adsorption of AFPs.

Human-machine interaction (HMI) systems are widely used in the healthcare field, and they play an essential role in assisting the rehabilitation of patients. Currently, a large number of HMI-related research studies focus on piezoresistive sensors, self-power sensors, visual and auditory receivers, and so forth. These sensing modalities do not possess high reliability with regard to breathing condition detection. The humidity signal conveyed by breathing provides excellent stability and a fast response; however, humidity-based HMI systems have rarely been studied. Herein, we integrate a humidity sensor and a graphene thermoacoustic device into a humidity-based HMI system (HHMIS), which is capable of monitoring respiratory signals and emitting acoustic signals. HHMIS has a practical value in healthcare to assist patients. For example, it works as a prewarning system for respiratory-related disease patients with abnormal respiratory rates, and as an artificial throat device for aphasia patients. Achieved based on a laser direct writing technology, this wearable device features low cost, high flexibility, and can be prepared on a large scale. This portable non-contact HMMIS has broad application prospects in many fields such as medical health and intelligent control.

Antifreeze protein gene expression in winter flounder pre-hatch embryos: Implications for cryopreservation

Although in-vehicle interaction technologies offer assistances for drivers from multi-aspects, the distractions that may cause by these technologies would significantly challenge driving safety. This study examined the influences of three in-vehicle interactions on drivers' driving performance and eye movement behavior. The three in-vehicle interactions include phone pick-up (PPU), Bluetooth and audio $(\mathbf{BT}+\mathbf{AUD})$ and Bluetooth and head-up display $(\mathbf{BT}+\mathbf{HUD})$ . A control group (i.e., None, in which no human-machine interaction was included while driving) was designed to highlight the influences of the examined interactions. Fourteen licensed drivers participated in the simulation experiments. Their age ranged from 20 to 30 years old $(\mathbf{Mean}\pm \mathbf{SD}=25.1\pm 3.8)$ . They were required to complete the Location Based Service (LBS) tasks using the three interactions while driving. Both driving performance and eye movement data were collected for analysis. Results showed that, when using PPU or $\mathbf{BT}+\mathbf{HUD}$ , the minimum throttle opening, the steering wheel angle (SWA) and the Shannon entropy (SE) of SWA were all greater than those values when using $\mathbf{BT}+\mathbf{AUD}$ or None. As for the SE of throttle opening and all the examined eye movement features (frequency and duration of fixation/saccade), the values when using $\mathbf{BT}+\mathbf{AUD}$ or $\mathbf{BT}+\mathbf{HUD}$ were higher than the values when using PPU or None. The presented results in this study provide evidences for car manufactures to design better $\mathbf{BT} +\mathbf{AUD}$ human-machine interaction systems as a priority strategy.

Skin-like thermoelectric (TE) films with temperature- and strain-sensing functions are highly desirable for human-machine interaction systems and wearable devices. However, current TE films still face challenges in achieving high flexibility and excellent sensing performance simultaneously. Herein, for the first time, a facile roll-to-roll strategy is proposed to fabricate an ultraflexible chalcogenide glass-polytetrafluoroethylene composite film with superior temperature- and strain-sensing performance. The unique reticular network of the composite film endows it with efficient Seebeck effect and flexibility, leading to a high Seebeck coefficient (731 µV/K), rapid temperature response (≈0.7 s), and excellent strain sensitivity (gauge factor = 836). Based on this high-performance composite film, an intelligent robotic hand for action feedback and temperature alarm is fabricated, demonstrating its great potential in human-machine interaction. Such TE film fabrication strategy not only brings new inspiration for wearable inorganic TE devices, but also sets the stage for a wide implementation of multifunctional human-machine interaction systems.

Recently there is an increasing interest in video based interface techniques, allowing more natural interaction between users and systems than common interface devices do. We present a neural architecture for user localisation, embedded within a complex system for visually-based human machine interaction (HMI). User localisation is an absolute prerequisite to video based HMI. Due to the main objective, the greatest possible robustness of the localisation as well as the whole visual interface under highly varying environmental conditions, we propose a multiple cue approach. This approach combines the features of facial structure, head shoulder contour, skin color and motion, with a multiscale representation. The selection of the image region most likely containing a possible user is then realised via a WTA-process within the multiscale representation. Preliminary results show the reliability of the multiple cue approach.

Against the backdrop of rapid development in artificial intelligence and sensor technology, autonomous vehicles are steadily moving toward practical application. An efficient, natural, and safe human-machine interaction (HMI) system has become the core for gaining user trust and achieving wide-scale adoption. Focusing on the specific scenario of L4-level autonomous driving, this study proposes an HMI framework integrating multimodal perception, adaptive decision-making, and cognitive load optimization. It particularly examines deep learning-based intent recognition algorithms, dynamic optimization strategies for takeover requests in emergency situations, and multi-channel fusion mechanisms for presenting interactive information. Through high-fidelity driving simulators and real-vehicle road tests, combined with eye-tracking, physiological signal monitoring, and other relevant methods, the system’s effectiveness in reducing cognitive load, enhancing situational awareness, and shortening takeover reaction time was validated. Data show that the optimized HMI reduces average driver takeover reaction time by 42.7%, increases situational understanding accuracy to 91.3%, and significantly lowers subjective workload index. This research provides key technical support for building a highly usable and safe human-machine co-driving paradigm for autonomous vehicles and holds great significance for promoting the commercialization of autonomous driving.

In Manufacturing Technologies (OT), with the advent of Industry 4.0, Human-Machine Interaction (HMI) has evolved into Machine-Machine Interaction (MMI). This development has made the digitalization of manufacturing processes critical. The combined use and digitalization of machine, HMI, and MMI systems has also raised significant cybersecurity challenges. Because manufacturing technology networks lack a standardized structure, traditional security mechanisms are often inadequate to address the heterogeneity and time-sensitive nature of these environments. Therefore, systematic, adaptive, and learning-based solutions are required to provide resilient protection mechanisms in OT networks. In this context, unlike traditional approaches, cognitive machine learning offers systems that can dynamically adapt learning processes by understanding environmental data. Combining adaptive reasoning and contextual awareness, cognitive learning enables OT networks to identify new attack patterns and respond in real time, increasing their resilience and providing more effective security solutions. This article systematically reviews scientific publications on the use of cognitive machine learning in manufacturing technology networks. Focusing on recent contributions (2016–2025), the review highlights both the novelty and practical importance of applying cognitive machine learning to OT security challenges. The reviewed literature highlights that the use of cognitive machine learning for security purposes in OT networks has so far been largely limited to subsystem-level applications (e.g., PLCs, SCADA nodes, and IoT-enabled manufacturing devices). Furthermore, an end-to-end solution architecture has been lacking. This finding reveals a clear research gap and highlights the potential of cognitive machine learning methods as a promising and relevant topic for future academic and industrial research.

Human Machine Interface (HMI) and interactive systems applications are complex and diversified but human machine interaction in networks is even more complex. To design an interactive system, the designers must consider factors including design, technologies, people, activities and contexts. As the intermediary for human and machines, the interactive system takes charge of not only data transmission, display, storage and convertion, but also reactions to human behaviors. Based on human interaction, this paper focuses on the popular video streaming. As one of the most commonly used compression video formats, H.264 provides better quality at lower bit-rates than its previous standards in transmitting video/audio data. However, the quality of networked multimedia streaming easily fluctuates with the bit-rate variation. In order to maintain good video quality, this paper proposes to use the Kalman filter to implement the Auto bit-rate technique, which can regulate the bit-rate of the video/audio data automatically when the bit-rate is insufficient, and simultaneously guarantee the video quality. The experimental result proves that our proposed Auto bit-rate scheme can regulate the bit-rate to achieve the optimal visual quality and offer the best quality of service at the same time.

Hydrogel‐based electrophysiological sensors have garnered copious research interest for wearable human‐machine interaction (HMI), whereas existing HMI interfaces suffer from lack of self‐adhesion, mismatch of mechanical properties with skin, insufficient accuracy, mobility, and real‐time performance. Here, smart hydrogel epidermal electrodes based on honey and sodium chloride co‐modified polyacrylamide composite are proposed with superior self‐adhesion, skin compliance, stability, conductivity, antibacterial property, and biocompatibility. The hydrogel electrodes are integrated into a flexible adaptive sensing wristband, forming a conformal, stable, and low‐impedance interface with biological tissue. The wristband enables the stable acquisition of both dual‐channel high‐frequency surface electromyography (sEMG) signals and low‐frequency acceleration signals with a high signal‐to‐noise ratio (31 dB for sEMG). By combining a multimodal signal fusion algorithm with a lightweight and efficient Artificial Intelligence model, the wristband achieves a sign language recognition translation accuracy up to 97.2%. Furthermore, the study develops a dedicated mobile application (APP) in which the fusion algorithm and AI model are locally deployed and executed in real time on mobile devices. The integrated standalone HMI system demonstrates excellent accuracy, real‐time response, mobility, and extendability in performing various wireless intelligent interaction tasks under complex environments, including sign language recognition, robotic control, active rehabilitation, and motion monitoring, without using the internet.

Advanced technologies such as robotics, 5G mobile communications, IoT, cloud computing and wireless sensor networks have had a huge impact and influence on manufacturing, with an increased collaboration between humans and smart systems. As the manufacturing process becomes more automated using real-time data, communication systems, Artificial Intelligence (AI) techniques and robotics feed data back into the manufacturing process. This enables the design of products that are more customized and personal, and leads to a more competitive, efficient and value-added production process by reacting more quickly to technical or human errors to avoid product and system damage while increasing workplace safety, and reducing waste, pollution, and associated costs. This edited book covers challenges, concepts, systems, architectures, technologies, and design characteristics of human-machine cooperation and interaction systems in smart manufacturing environments using state of the art technologies including AI, 5G, IoTs, Blockchains, CPS, sensing, automation and robotics. The book is aimed at researchers and engineers working on the applications of robotics and automation, HMI, HCI, CPS, sensing, information and communications technology, data science, ML/DL/AI, AR/VR, cybersecurity and electronics. It is also a useful reference for advanced students and lecturers in these fields, and will appeal to manufacturers and automation system developers.