A Review on Cognitive Machine Learning for Cybersecurity Systems in Operational Technology Networks

Learning ability is the basic characteristic of human intelligence. The July 1, 2005 issue of Science published a list of 125 important questions in science. Among them, the question 94 “What are the limits of learning by machines?”. The annotation “Computers can already beat the world’s best chess players, and they have a wealth of information on the Web to draw on. But abstract reasoning is still beyond any machine”. In recent artificial intelligence has made great progresses. In 1997, the rise of the man-machine war, IBM Supercomputer Deep Blue defeated the chess master Garry Kasparov. On February 14, 2011, IBM’s Watson supercomputer won a practice round against Jeopardy champions Ken Jennings and Brad Rutter. In March 2016, Google DeepMind’s AlphaGo sealed a 4-1 victory over a South Korean Go grandmaster Lee Se-dol. This paper focuses on the machine learning methods of AlphaGo, including reinforcement learning, deep learning, deep reinforcement learning, analysis of the existing problems and the latest research progress. Deep reinforcement learning is the combination of deep learning and reinforcement learning, which can realize the learning algorithm from the perception to action. Simply said, this is the same as human behavior, input sensing information such as vision, and then, direct output action through the deep neural network. Deep reinforcement learning has the potential to learn a variety of skills for the robot to achieve full autonomy. Even though reinforcement learning is practiced successfully, but feature states need to manually set, for complex scene is a difficult thing, especially easy to cause the dimension disaster, and expression is not good. In 2010, Sascha Lange and Martin Riedmiller proposed deep auto-encoder neural networks in reinforcement learning to extract feature, which is used to control the visual correlation. In 2013, DeepMind proposed deep Q-network (DQN) in NIPS 2013, using convolution neural network to extract features, and then applied in reinforcement learning. They continue to improve and published an improved version of DQN on Nature in 2015, which has aroused widespread concern. In order to break through the limits of learning by machines, cognitive machine learning is proposed, which is the combination of machine learning and brain cognition, so that the machine intelligence is constantly evolving, and gradually reaches the human level of artificial intelligence. A cognitive model entitled Consciousness And Memory (CAM) is proposed by author, which consists of memory, consciousness, high-level cognitive functions, perception and motor. High-level cognitive functions of the brain include learning, language, thinking, decision making, emotion, and so on. Learning is a course to accept the stimulus through the nervous system and obtain new behavior, habits and accumulation experience. According to the current research progress of brain science and cognitive science, cognitive machine learning may be interested in learning emergence, procedural memory knowledge learning, learning evolution and so on. For intelligence, so-called evolution is refers to the learning of learning and the structure also follows the change. It is important to record the learning result by structure changing and improve the learning method.

Cognitive Computing (CC) is a contemporary field of studies on intelligent computing methodologies and brain-inspired mechanisms of cognitive systems, cognitive machine learning and cognitive robotics. The IEEE conference ICCI*CC'17 on Cognitive Informatics and Cognitive Computing was focused on the theme of neurocomputation, cognitive machine learning and brain-inspired systems. This article reports the plenary panel (Part II) in IEEE ICCI*CC'17 at Oxford University. The summary is contributed by distinguished panelists who are part of the world's renowned scholars in the transdisciplinary field of cognitive computing.

At present, countries all over the world are actively carrying out research on digital transformation in various fields. From this, we can see that digital transformation in the field of standards will also be the general trend. Aiming at the requirements, key technologies and application scenarios of digital transformation of electric power standards, this paper proposes a research on digital transformation of electric power standards oriented to "human-human interaction, human-machine interaction and machine-machine interaction". Firstly, according to the demand of standard digital transformation in the power field, the demand analysis diagram of standard digital transformation is proposed. Secondly, according to the concept and connotation of standard digitization, the digital analysis chart of standard itself and the digital analysis chart of standard process are proposed. At the same time, for the key technologies of standard digitization, the standardization theory covering "smallest information unit, standardization architecture model, standard information model and standard management shell" is proposed, the artificial intelligence technology covering "natural language understanding and knowledge atlas" is proposed, and the information security technology covering "cryptography" is proposed. Moreover, for the application scenario of digital transformation of power standards, three application scenarios including "full-text search, dynamic prompt of standard update, and display of standard related content" are proposed. The research motivation of this paper is that the current standard digitization field is in the exploration stage, and no one has proposed the key technical framework and application scenarios of standard digitization. The significance of the research is to promote the top-level design and Implementation Path Research in the field of standard digitization. The research contribution lies in innovatively putting forward a key technical framework of standard digitization and a digital application scenario of power standards, revealing the profound connotation of standard digitization transformation, and pointing out that standard digitization involves not only technical problems, but also a series of engineering problems such as management mechanism.

Two open, online educational platforms, OpenStax Exercises and OpenStax Tutor, are working to revolutionize the way in which students learn concepts in diverse subject areas. Born and tested in the area of signal processing education, these tools bring to bear cutting-edge ideas in cognitive science and machine learning to automatically build personalized learning pathways for today's students and to advance the field of learning science. These platforms are introduced and initial results discussed.

We present an open multiagent architecture for intelligent collaborative information systems based on the concepts of cognitive agents and machine learning. We assume a double hypothesis: (i) agents collaborate to reach their goals; (ii) agents can find and interact with other agents in a network. This assumption implies specialized services that have as functions: (a) relate the needs of user agents with the services of supplier agents; (b) integrate several answers in order to produce better results; (c) send regular notification to user agents about changes in the world. The location of such services depends on the architecture one adopts. We focus on the definition of architecture able to dynamically integrate new agents into the system. Thus, agents shall have machine learning capabilities inherited from a generic agent. An open architecture brings some benefits to the system performance such as adaptability, availability of services, incremental development and improvement of lifetime. System proactive capabilities may extend the knowledge human users have about the process.

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.

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

Human-Machine Interaction in Future Nuclear Power Plant Control Rooms – A Review

The most powerful educational tool is interactive visualization platform. The purpose of educational visualization is to facilitate learners to learn quality based knowledge by considering different factors i.e. intelligence, prediction, perception, class participation and cognitive learning etc. Our study has explored the benefits of cognitive learning in different aspects. These aspects are the psychological implications of visualization applied to educational purposes, guiding the learners how to engage ourselves in cognitive learning, guiding teachers to use intelligent ways of teaching and to provide online learning platforms. During our research we have developed a visualized prototype application for course “data structure and algorithm” to facilitate students for better learning of this course and then we implemented this prototype application in a real time environment i.e. classroom. Finally after implementation we have conducted a survey to get the feedback from students, to know how the visualizations affect the learning. Our study has showed the benefits of using animation during lessons to engage learner’s attention in cognitive learning. From the survey results, we came to know that most of the students were unaware of education visualization applications.

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.

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.

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.

The move toward the Fourth Industrial Revolution (4IR) is rapidly progressing and organisations are changing faster than ever before (Bughin et al., 2018;SAICA, 2023). It has been predicted that the workforce of machines will complete more jobs than humans in 2025 (Smith & Anderson, 2014). Others highlight that through the 4IR and especially through AI and robotics, many more jobs will be created (CNBC, 2018). The 4IR will be driven by AI, System Dynamics, Human-Machine and Machine-Machine interaction (Mayer & Oosthuizen, 2020a).New AI applications, such as chatGBT, LaMDA or BARD are leading to far-reaching changes in all learning and work contexts and require far-reaching realignments in terms of competences and skills (Kroon et al., 2021). Adoption and adjustment are critical aspects in dealing with the technological changes and the new world of work (Davis, 2022) and leaders need to focus on developing comprehensibility, manageability, and meaningfulness to cope with the radical changes and promote mental health and well-being in organisations of the 4IR (Mayer & Oosthuizen, 2020b).Many professions and organisations have to change the way the work and how work is allocated (Schwab, 2016;Manyika et al., 2017;Rotatori et al., 2021). One the one hand, the new technologies present possible opportunities and on the other hand they pose challenges and difficulties for employees and organizations in terms of skill development and adaptability (Malomane et al., 2022;Prisecaru, 2016;Schwab, 2017;Xu et al., 2018).Organisations and workspaces need to collaborate with the educational sector -and in particular higher education -to define skills and competences which individuals across cultures and in specific cultural contexts need to develop to thrive in the 4IR (Rychen, 2016). Mayer (2020) has highlighted that a globalised 4IR workforce needs to develop key concepts, such as creativity, positive emotions, solution-focus and meaning-making in the 4IR to be sustainable and successful. The author further points out that these key concepts need to be developed in educational institutions and required by leaders of the 4IR, as precious skills.According to the Organisation for Economic Cooperation and Development (OECD) (2023), there is a need to develop the following three transformational skills to shape a desired future:Creating new values, balancing tensions, and dilemmas, and taking responsibility. To create new values, individuals need to ask questions, collaborate with others and try to think outside the box to find innovative solutions (Bentley, 2017;Grayling, 2017). This links a sense of purpose with critical thinking and creativity. In an interdependent world, individuals need to be able to balance conflicting or seemingly incompatible thinking and demands and become comfortable with complexity and ambiguity, taking responsibility for their actions and have a strong moral compass for critical reflection, cooperation with others, and respect for the environment and humanity (Melville & Robert, 2020).The discourse surrounding the 4IR indeed often presents it as a global phenomenon, characteried by the convergence of digital, physical, and biological technologies and their impact on various aspects of society, economy, and culture. Berger and Frey (2015), as well as Schwab (2016), have contributed significantly to this narrative, emphasizing the widespread nature of technological advancements and their transformative effects on industries and societies worldwide. However, it's essential to acknowledge the perspective that views the 4IR through a cultural lens. Oosthuizen and Mayer (2019) highlight that while the technological advancements associated with the 4IR may have global reach, their adoption, adaptation, and impact can vary significantly across different cultural contexts. Cultural factors such as values, norms, traditions, and governance structures can shape how societies engage with and are affected by these technological changes. This perspective underscores the importance of considering local contexts and cultural nuances when discussing the 4IR and its implications.It suggests that while there may be overarching trends and developments at the global level, the way these manifest and are experienced can differ significantly from one culture to another. This recognition prompts a more nuanced understanding of the 4IR and the need for tailored approaches to address its opportunities and challenges in different cultural settings. The editors wish all of the readers of this special issue an interesting read and hope to stimulate contemporary and future discourses on the 4IR!

Network interconnection, information interoperability, and crowds interaction on the Internet could inspire better computation models than Turing machine, since that human plays an important factor in Internet computing, so that the human-machine and machine-machine interactions have evolved to be the kernel of Internet computing. Internet has not been simply equivalent to a virtual huge computer, or a set of computers. On the Internet, human's behaviors are uncertain, the interactions and influence among people are also uncertain. These uncertainties cannot be described by Turing machine and traditional interaction machine. As a new computation platform, Internet computing requires new theories and methods. By combining topology in mathematics with the field theory in physics, we propose the topological potential approach, which set up a virtual field by the topological space to reflect individual activities, local effects and preferential attachments. This approach can be used to research the emergence of collective intelligence. Here, we introduce three case studies to illustrate the analysis on the collective intelligence on the Internet and discuss some potential applications of the topological potential approach.