Search

Abstract Ongoing research endeavors are exploring the potential of artificial intelligence to enhance the efficiency of wireless communication systems. Nevertheless, complex computational mechanisms, such as those inherent in neural networks, are not optimally suited for applications where the reduction of computational intricacy is of paramount importance. The rise in Bluetooth-enabled devices has led to the widespread adoption of Bluetooth Low Energy (BLE) in various IoT applications, primarily due to its low power consumption. For specific applications, such as lost and found tags which operate on small batteries, it’s especially important to further reduce power usage. With the objective of achieving low power consumption by optimally selecting channels and advertisement intervals, this paper introduces a parameter selection method derived from the Multi-Armed Bandit (MAB) algorithm, a technique known for addressing human decision-making challenges. In this study, we evaluate our proposed method using simulations in diverse environments. The outcomes indicate that, without compromising much on reliability, our approach can reduce power consumption by up to 40% based on the wireless surroundings. Additionally, when this method was implemented on an actual BLE device, it demonstrated effectiveness in reducing power consumption by about 35% in real environments.

In recent years, the demand for new applications using various Internet of Things (IoT) devices has led to an increase in the number of devices connected to wireless networks. However, owing to the limitation of available frequency resources for IoT devices, the degradation of the communication quality caused by channel congestion is a practical problem in developing IoT technology. Many IoT devices have hardware and software limitations that prevent centralized channel allocation, and congestion is even more severe in massive IoT networks without a central controller. Therefore, developing a distributed and sophisticated channel selection algorithm is necessary. In previous studies, the channel selection of each IoT device was modeled as a multi-armed bandit (MAB) problem, and a wireless channel selection method based on the MAB algorithm, which is a simple reinforcement learning, was proposed. In particular, it has been shown that the MAB algorithm of tug-of-war (TOW) dynamics can efficiently select channels with much lower computational complexity and power compared with other reinforcement learning-based channel-selection methods. This paper proposes a distributed channel selection method based on TOW dynamics in fully decentralized networks. We evaluate the effectiveness of the proposed method and other distributed channel-selection methods on the communication success rate in massive IoT networks by experiments and simulations. The results show that the proposed method improves the communication success rate more than other distributed channel selection methods even in a dense and dynamic network environment.

Data-driven and feedback cycle-based approaches are necessary to optimize the performance of modern complex wireless communication systems. Machine learning technologies can provide solutions for these requirements. This study shows a comprehensive framework of optimizing wireless communication systems and proposes two optimal decision schemes that have not been well-investigated in existing research. The first one is supervised learning modeling and optimal decision making by optimization, and the second is a simple and implementable reinforcement learning algorithm. The proposed schemes were verified through real-world experiments and computer simulations, which revealed the necessity and validity of this research.

Long-Range (LoRa) devices have been deployed in many Internet of Things (IoT) applications due to their ability to communicate over long distances with low power consumption. The scalability and communication performance of the LoRa systems are highly dependent on the spreading factor (SF) and channel allocations. In particular, it is important to set the SF appropriately according to the distance between the LoRa device and the gateway since the signal reception sensitivity and bit rate depend on the used SF, which are in a trade-off relationship. In addition, considering the surge in the number of LoRa devices recently, the scalability of LoRa systems is also greatly affected by the channels that the LoRa devices use for communications. It was demonstrated that the lightweight decentralized learning-based joint channel and SF-selection methods can make appropriate decisions with low computational complexity and power consumption in our previous study. However, the effect of the location situation of the LoRa devices on the communication performance in a practical larger-scale LoRa system has not been studied. Hence, to clarify the effect of the location situation of the LoRa devices on the communication performance in LoRa systems, in this paper, we implemented and evaluated the learning-based joint channel and SF-selection methods in a practical LoRa system. In the learning-based methods, the channel and SF are decided only based on the ACKnowledge information. The learning methods evaluated in this paper were the Tug of War dynamics, Upper Confidence Bound 1, and ϵ-greedy algorithms. Moreover, to consider the relevance of the channel and SF, we propose a combinational multi-armed bandit-based joint channel and SF-selection method. Compared with the independent methods, the combinations of the channel and SF are set as arms. Conversely, the SF and channel are set as independent arms in the independent methods that are evaluated in our previous work. From the experimental results, we can see the following points. First, the combinatorial methods can achieve a higher frame success rate and fairness than the independent methods. In addition, the FSR can be improved by joint channel and SF selection compared to SF selection only. Moreover, the channel and SF selection dependents on the location situation to a great extent.

Abstract The problem of ‘uneven distribution of wealth’ accelerated during the COVID-19 pandemic. In the chaotic modern society, there is an increasing demand for the realisation of true ‘fairness’. In this study, we propose a fair distribution method ‘using physics’, which imitates the Greek mythology, Themis, having a ‘balance of judgement’ in her left hand, for the profit in games of characteristic function form. Specifically, we show that the linear programming problem for calculating ‘nucleolus (a solution for the fair distribution)’ can be efficiently solved by considering it as a physical system in which gravity works. In addition to significantly reducing the computational complexity, the proposed scheme provides a new perspective to open up a physics-based policymaker that is adaptable to real-time changes. We will be able to implement it not only in liquid systems but also in many other physical systems, including semiconductor chips. The fair distribution problem can be solved immediately using physical systems, which should reduce disputes and conflicts based on inaccurate information and misunderstandings, eliminating fraud and injustice.

In this study, we investigated the human capacity to generate randomness in decision-making processes using the rock-paper-scissors (RPS) game. The randomness of the time series was evaluated using the time-series data of RPS moves made by 500 subjects who played 50 consecutive RPS games. The indices used for evaluation were the Lempel–Ziv complexity and a determinism index obtained from a recurrence plot, and these indicators represent the complexity and determinism of the time series, respectively. The acquired human RPS time-series data were compared to a pseudorandom RPS sequence generated by the Mersenne Twister and the RPS time series generated by the RPS game’s strategy learned using the human RPS time series acquired via genetic programming. The results exhibited clear differences in randomness among the pseudorandom number series, the human-generated series, and the AI-generated series.

In recent times, the number of Internet of Things devices has increased considerably. Numerous Internet of Things devices generate enormous traffic, thereby causing network congestion and packet loss. To address network congestion in massive Internet of Things systems, an efficient channel allocation method is necessary. Although some channel allocation methods have already been studied, as far as we know, there is no research focusing on the implementation phase of Internet of Things devices while considering massive heterogeneous Internet of Things systems where different kinds of Internet of Things devices coexist in the same Internet of Things system. This paper focuses on the multi-armed-bandit-based channel allocation method that can be implemented on resource-constrained Internet of Things devices with low computational processing ability while avoiding congestion in massive Internet of Things systems. This paper first evaluates some well-known multi-armed-bandit-based channel allocation methods in massive Internet of Things systems. The simulation results show that an improved multi-armed-bandit-based channel selection method called Modified Tug of War can achieve the highest frame success rate in most cases. Specifically, the frame success rate can reach 95% when the numbers of channels and IoT devices are 60 and 10,000, respectively, while 12% channels are suffering traffic load by other kinds of IoT devices. In addition, the performance in terms of frame success rate can be improved by 20% compared to the equality channel allocation. Moreover, the multi-armed-bandit-based channel allocation methods is implemented on 50 Wi-SUN Internet of Things devices that support IEEE 802.15.4g/4e communication and evaluate the performance in frame success rate in an actual wood house coexisting with LoRa devices. The experimental results show that the modified multi-armed-bandit method can achieve the highest frame success rate compared to other well-known frame success rate-based channel selection methods.

Abstract Reinforcement learning involves decision making in dynamic and uncertain environments and constitutes an important element of artificial intelligence (AI). In this work, we experimentally demonstrate that the ultrafast chaotic oscillatory dynamics of lasers efficiently solve the multi-armed bandit problem (MAB), which requires decision making concerning a class of difficult trade-offs called the exploration–exploitation dilemma. To solve the MAB, a certain degree of randomness is required for exploration purposes. However, pseudorandom numbers generated using conventional electronic circuitry encounter severe limitations in terms of their data rate and the quality of randomness due to their algorithmic foundations. We generate laser chaos signals using a semiconductor laser sampled at a maximum rate of 100 GSample/s, and combine it with a simple decision-making principle called tug of war with a variable threshold, to ensure ultrafast, adaptive, and accurate decision making at a maximum adaptation speed of 1 GHz. We found that decision-making performance was maximized with an optimal sampling interval, and we highlight the exact coincidence between the negative autocorrelation inherent in laser chaos and decision-making performance. This study paves the way for a new realm of ultrafast photonics in the age of AI, where the ultrahigh bandwidth of light wave can provide new value.

We propose a simple model for an atomic switch-based decision maker (ASDM), and show that, as long as its total number of metal atoms is conserved when coupled with suitable operations, an atomic switch system provides a sophisticated ``decision-making'' capability that is known to be one of the most important intellectual abilities in human beings. We considered a popular decision-making problem studied in the context of reinforcement learning, the multi-armed bandit problem (MAB); the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. These decisions are made as dictated by each volume of precipitated metal atoms, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war game. The ``tug-of-war (TOW) dynamics'' of the ASDM exhibits higher efficiency than conventional reinforcement-learning algorithms. We show analytical calculations that validate the statistical reasons for the ASDM to produce such high performance, despite its simplicity. Efficient MAB solvers are useful for many practical applications, because MAB abstracts a variety of decision-making problems in real-world situations where an efficient trial-and-error is required. The proposed scheme will open up a new direction in physics-based analog-computing paradigms, which will include such things as ``intelligent nanodevices'' based on self-judgment.

Ellsberg paradox in decision theory posits that people will inevitably choose a known probability of winning over an unknown probability of winning even if the known probability is low [1]. One of the prevailing theories that addresses the Ellsberg paradox is known as “ambiguity-aversion.” In this study, we investigated the properties of ambiguity-aversion in four distinct types of reinforcement learning algorithms: ucb1-tuned [2], modified ucb1-tuned, softmax [3], and tug-of-war [4, 5]. We took the following scenario as our sample, in which there were two slot machines and each machine dispenses a coin according to a probability that is generated by its own probability density function (PDF). We then investigated the choices of a learning algorithm in such multi-armed bandit tasks. There were different reactions in multi-armed bandit tasks, depending on the ambiguity-preference in the learning algorithms. Notably, we discovered a clear performance enhancement related to ambiguity-preference in a learning algorithm. Although this study does not directly address the issue of ambiguity-aversion theory highlighted in Ellsberg paradox, the differences among different learning algorithms suggest that there is room for further study regarding the Ellsberg paradox and the decision theory.

Choosing a better move correctly and quickly is a fundamental skill of living organisms that corresponds to solving a computationally demanding problem. A unicellular plasmodium of Physarum polycephalum searches for a solution to the travelling salesman problem (TSP) by changing its shape to minimize the risk of being exposed to aversive light stimuli. In our previous studies, we reported the results on the eight-city TSP solution. In this study, we show that the time taken by plasmodium to find a reasonably high-quality TSP solution grows linearly as the problem size increases from four to eight. Interestingly, the quality of the solution does not degrade despite the explosive expansion of the search space. Formulating a computational model, we show that the linear-time solution can be achieved if the intrinsic dynamics could allocate intracellular resources to grow the plasmodium terminals with a constant rate, even while responding to the stimuli. These results may lead to the development of novel analogue computers enabling approximate solutions of complex optimization problems in linear time.

We investigate the effect of a memory parameter on the performance of adaptive decision making using a tug-of-war method with the chaotic oscillatory dynamics of a semiconductor laser. We experimentally generate chaotic temporal waveforms of the semiconductor laser with optical feedback and apply them for adaptive decision making in solving a multiarmed bandit problem that aims at maximizing the total reward from slot machines whose hit probabilities are dynamically switched. We examine the dependence of making correct decisions on different values of the memory parameter. The degree of adaptivity is found to be enhanced with a smaller memory parameter, whereas the degree of convergence to the correct decision is higher for a larger memory parameter. The relations among the adaptivity, environmental changes, and the difficulties of the problem are also discussed considering the requirement of past decisions. This examination of ultrafast adaptive decision making highlights the importance of memorizing past events and paves the way for future photonic intelligence.

Massive IoT including the large number of resource-constrained IoT devices has gained great attention. IoT devices generate enormous traffic, which causes network congestion. To manage network congestion, multi-channel-based algorithms are proposed. However, most of the existing multi-channel algorithms require strict synchronization, an extra overhead for negotiating channel assignment, which poses significant challenges to resource-constrained IoT devices. In this paper, a distributed channel selection algorithm utilizing the tug-of-war (TOW) dynamics is proposed for improving successful frame delivery of the whole network by letting IoT devices always select suitable channels for communication adaptively. The proposed TOW dynamics-based channel selection algorithm has a simple reinforcement learning procedure that only needs to receive the acknowledgment (ACK) frame for the learning procedure, while simply requiring minimal memory and computation capability. Thus, the proposed TOW dynamics-based algorithm can run on resource-constrained IoT devices. We prototype the proposed algorithm on an extremely resource-constrained single-board computer, which hereafter is called the cognitive-IoT prototype. Moreover, the cognitive-IoT prototype is densely deployed in a frequently-changing radio environment for evaluation experiments. The evaluation results show that the cognitive-IoT prototype accurately and adaptively makes decisions to select the suitable channel when the real environment regularly varies. Accordingly, the successful frame ratio of the network is improved.

A high-density random number generator (RNG) based on spin signals in a multidomain ferromagnetic layer in a magnetic tunnel junction (MTJ) is proposed and fabricated. Unlike conventional spin-based RNGs, the proposed method does not require one to control an applied current, leading to a time delay in the system. RNG demonstrations are performed at room temperature. The randomness of the bit sequences generated by the proposed RNG is verified using the FIPS 140-2 statistical test suite provided by the NIST. The test results validate the effectiveness of the proposed RNGs. Our results suggest that we can obtain high-density, ultrafast RNGs if we can achieve high integration on the chip.

Solution searching that accompanies combinatorial explosion is one of the most important issues in the age of artificial intelligence. Natural intelligence, which exploits natural processes for intelligent functions, is expected to help resolve or alleviate the difficulties of conventional computing paradigms and technologies. In fact, we have shown that a single-celled organism such as an amoeba can solve constraint satisfaction problems and related optimization problems as well as demonstrate experimental systems based on non-organic systems such as optical energy transfer involving near-field interactions. However, the fundamental mechanisms and limitations behind solution searching based on natural processes have not yet been understood. Herein, we present a theoretical background of solution searching based on optical excitation transfer from a category-theoretic standpoint. One important indication inspired by the category theory is that the satisfaction of short exact sequences is critical for an adequate computational operation that determines the flow of time for the system and is termed as “short-exact-sequence-based time.” In addition, the octahedral and braid structures known in triangulated categories provide a clear understanding of the underlying mechanisms, including a quantitative indication of the difficulties of obtaining solutions based on homology dimension. This study contributes to providing a fundamental background of natural intelligence.

Decision-making is one of the most important intellectual abilities of not only humans but also other biological organisms, helping their survival. This ability, however, may not be limited to biological systems and may be exhibited by physical systems. Here we demonstrate that any physical object, as long as its volume is conserved when coupled with suitable operations, provides a sophisticated decision-making capability. We consider the multi-armed bandit problem (MBP), the problem of finding, as accurately and quickly as possible, the most profitable option from a set of options that gives stochastic rewards. Efficient MBP solvers are useful for many practical applications, because MBP abstracts a variety of decision-making problems in real-world situations in which an efficient trial-and-error is required. These decisions are made as dictated by a physical object, which is moved in a manner similar to the fluctuations of a rigid body in a tug-of-war (TOW) game. This method, called ‘TOW dynamics’, exhibits higher efficiency than conventional reinforcement learning algorithms. We show analytical calculations that validate statistical reasons for TOW dynamics to produce the high performance despite its simplicity. These results imply that various physical systems in which some conservation law holds can be used to implement an efficient ‘decision-making object’. The proposed scheme will provide a new perspective to open up a physics-based analog computing paradigm and to understanding the biological information-processing principles that exploit their underlying physics.