Homeostatic mechanisms play a crucial role in maintaining optimal functionality within the neural circuits of the brain. By regulating physiological and biochemical processes, these mechanisms ensure the stability of an organism’s internal environment, enabling it to better adapt to external changes. Among these mechanisms, the Bienenstock, Cooper, and Munro (BCM) theory has been extensively studied as a key principle for maintaining the balance of synaptic strengths in biological systems. Despite the extensive development of spiking neural networks (SNNs) as a model for bionic neural networks, no prior work in the machine learning community has integrated biologically plausible BCM formulations into SNNs to provide homeostasis. In this study, we propose a Dynamic Weight Adaptation Mechanism (DWAM) for SNNs, inspired by the BCM theory. DWAM can be integrated into the host SNN, dynamically adjusting network weights in real time to regulate neuronal activity, providing homeostasis to the host SNN without any fine-tuning. We validated our method through dynamic obstacle avoidance and continuous control tasks under both normal and specifically designed degraded conditions. Experimental results demonstrate that DWAM not only enhances the performance of SNNs without existing homeostatic mechanisms under various degraded conditions but also further improves the performance of SNNs that already incorporate homeostatic mechanisms.

Reliable and energy-efficient wireless transmission is very important for the future success of Internet of Thing (IoT). Due to the sporadic nature of IoT transmissions, the energy consumption for individual transmission session varies dramatically with channel condition as well as the quality of service (QoS) requirements. In this article, we analyze and optimize the statistical energy consumption for wireless relaying communications in IoT. Particularly, we consider a dual-hop communication system with a wirelessly-powered decode-and-forward (DF) relay. In terms of time switching (TS) and power splitting (PS) modes, we analyze and minimize the statistical energy consumption for transmitting a certain amount of data. Through selected numerical results, we illustrate various design tradeoffs between statistical energy consumption, data rate, and latency. These results will provide some important guidelines for green IoT communications.

The brain-inspired Spiking Neural Networks (SNNs) work in an event-driven manner and have an implicit recurrence in neuronal membrane potential to memorize information over time, which are inherently suitable to handle temporal event-based streams. Despite their temporal nature and recent approaches advancements, these methods have predominantly been assessed on event-based classification tasks. In this paper, we explore the utility of SNNs for event-based tracking tasks. Specifically, we propose a brain-inspired adaptive Leaky Integrate-and-Fire neuron (BA-LIF) that can adaptively adjust the membrane time constant according to the inputs, thereby accelerating the leakage of meaningless noise features and reducing the decay of valuable information. SNNs composed of our proposed BA-LIF neurons can achieve high performance without a careful and time-consuming trial-by-error initialization on the membrane time constant. The adaptive capability of our network is further improved by introducing an extra temporal feature aggregator (TFA) that assigns attention weights over the temporal dimension. Extensive experiments on various event-based tracking datasets validate the effectiveness of our proposed method. We further validate the generalization capability of our method by applying it to other event-classification tasks.

In this paper, we propose a cooperative time synchronization (CTS) scheme for cell-free massive multiple-input multiple-output (MIMO) systems, where synchronization packets are jointly broadcast by a set of coordinated access points (APs). Thanks to multiple timestamps available at each target node, the proposed CTS scheme enables a much higher accuracy in clock parameters estimation than the conventional non-cooperative synchronization approaches. In addition to the clock parameters between the target nodes and their associated APs, the clock deviations among APs are also jointly estimated, where the clock deviations can be fed back to their associated APs via acknowledgment for further clock adjustment. Furthermore, to mitigate the impact on synchronization performance under the packet loss scenario, a matrix completion-based CTS (MC-CTS) algorithm is proposed that complements the lost timestamp information. Simulation results demonstrate that the proposed CTS scheme presents a robust performance against the clock deviations among coordinated APs with packet overhead of approximately 50% less than that of the non-broadcast synchronization approaches, and the proposed MC-CTS algorithm effectively enhances the estimation performance of clock parameters, compared to just utilizing the CTS algorithm. Hence, the proposed algorithms are particularly suitable for time-sensitive cell-free massive MIMO systems.

Most existing RGB-based trackers target low frame rate benchmarks of around 30 frames per second. This setting restricts the tracker's functionality in the real world, especially for fast motion. Event-based cameras as bioinspired sensors provide considerable potential for high frame rate tracking due to their high temporal resolution. However, event-based cameras cannot offer fine-grained texture information like conventional cameras. This unique complementarity motivates us to combine conventional frames and events for high frame rate object tracking under various challenging conditions. In this paper, we propose an end-to-end network consisting of multi-modality alignment and fusion modules to effectively combine meaningful information from both modalities at different measurement rates. The alignment module is responsible for cross-style and cross-frame-rate alignment between frame and event modalities under the guidance of the moving cues furnished by events. While the fusion module is accountable for emphasizing valuable features and suppressing noise information by the mutual complement between the two modalities. Extensive experiments show that the proposed approach outper-forms state-of-the-art trackers by a significant margin in high frame rate tracking. With the FE240Hz dataset, our approach achieves high frame rate tracking up to 240Hz.

Event cameras, or dynamic vision sensors, have recently achieved success from fundamental vision tasks to high-level vision researches. Due to its ability to asynchronously capture light intensity changes, event camera has an inherent advantage to capture moving objects in challenging scenarios including objects under low light, high dynamic range, or fast moving objects. Thus event camera are natural for visual object tracking. However, the current event-based trackers derived from RGB trackers simply modify the input images to event frames and still follow conventional tracking pipeline that mainly focus on object texture for target distinction. As a result, the trackers may not be robust dealing with challenging scenarios such as moving cameras and cluttered foreground. In this paper, we propose a distractor-aware event-based tracker that introduces transformer modules into Siamese network architecture (named DANet). Specifically, our model is mainly composed of a motion-aware network and a target-aware network, which simultaneously exploits both motion cues and object contours from event data, so as to discover motion objects and identify the target object by removing dynamic distractors. Our DANet can be trained in an end-to-end manner without any post-processing and can run at over 80 FPS on a single V100. We conduct comprehensive experiments on two large event tracking datasets to validate the proposed model. We demonstrate that our tracker has superior performance against the state-of-the-art trackers in terms of both accuracy and efficiency.

In industrial Internet of Things (IIoT), the existing access class barring (ACB) random access (RA) strategy suffers severe performance degradation with massive contention devices, due to high probability of access collision. In this paper, we propose a collision-aware (CA) ACB RA scheme by reusing the colliding preambles, to enhance the resource utilization. The proposed scheme employs dynamic adjustment of the ACB factor and the preamble resources for delay-sensitive and -non-sensitive devices, respectively. A joint optimization problem is formulated and solved to maximize the preamble utilization ratio (PAUR) subject to the delay constraints and the available preambles. The system performance is evaluated by a Markov Chain based analytical model. Simulation results verify the correctness of our analysis and also show that the proposed CA-ACB RA scheme significantly outperforms the existing ACB RA schemes in terms of PAUR, network throughput, and average access delay.

In this paper, by utilizing the temporal correlation of wireless channels, a hierarchical basis expansion model (HBEM) based estimation scheme is proposed for orthogonal frequency division multiplexing systems over doubly selective channel, where the complex exponential basis expansion model (CE-BEM) is used to extract the channel impulse response and the discrete Legendre polynomials BEM is used to refine the CE-BEM coefficients to improve the performance of channel estimation. We design a non-periodic sparse pilot pattern, and hence only scarce subcarriers of a small number of pilots are required for channel estimation, resulting a training overhead reduction of around 50% over the previous CE-BEM based schemes. A block-based signal space matching pursuit algorithm is proposed to enhance the estimation accuracy of CE-BEM coefficients. Furthermore, the proposed HBEM scheme enables a reduction in the number of estimated CE-BEM coefficients by more than 50%, compared to the previous work. A lower bound on the mean square error (MSE) of the proposed HBEM scheme is derived. Simulation results show that the proposed HBEM scheme significantly outperforms the previous CE-BEM based schemes in terms of MSE of channel estimation and bit error rate.

In this paper, we propose a novel cooperative time synchronization (CTS) scheme via broadcasting for time-sensitive cell-free (CF) massive multiple-input multiple-output (MIMO) networks, by allowing distributed access points (APs) to jointly broadcast synchronization messages to the target nodes. With the proposed CTS scheme, more timestamps from distributed APs are available to achieve higher synchronization accuracy over the conventional non-cooperative time synchronization approaches. Parameter estimation is conducted by maximum likelihood estimation of clock offset and clock skew under the Gaussian transmission delay model, and the corresponding Cramer-Rao lower bounds (CRLBs) are derived. In addition, the clock offset and skew deviations among APs are also estimated, which are fed back to APs for further clock adjustment. Thanks to the AP association scheme and broadcast characteristics, the proposed CTS scheme demonstrates robustness against clock parameter deviations, while at a relatively low overhead and computational complexity.

Age of information (AoI), which measures the freshness of information, is a critical performance metric of timesensitive applications of industrial Internet of things (IIoT) with short-packet transmission (SPT). In this paper, we investigate the suitability of predicting the status updates at source and sending them to destination in advance for AoI oriented SPT systems, in the presence of prediction error as well as transmission error. A predictive transmission scheme is proposed, where proactive transmission termination is adopted as soon as a prediction error is detected, and also multiple correlated features of the status is considered. A closed-form expression for the average AoI with respect to prediction horizon (related to prediction error probability) and blocklength (related to transmission error probability) is derived for the multi-feature source scenario. Also, the prediction error probability with respect to prediction horizon is derived in closed form. It is proved that the average AoI performance can benefit from status prediction, even under high prediction error probability. Simulation results demonstrate the correctness of the analytical results, and show that the proposed prediction scheme outperforms the prediction approach with no transmission termination, and there exists an optimal prediction horizon in terms of average AoI. A tight approximation of the optimal prediction horizon is derived for the special case of single-feature status, which achieves a near-optimal performance, with a much lower complexity than exhaustive search.

In this paper, an explainable artificial intelligence (AI) technique is employed to analyze the match style and gameplay of the national basketball association (NBA). A descriptive analysis on the evolution of the NBA gameplay is conducted by using clustering and principal component analysis. Supervised-learning based AI models (including the random forest and the feed-forward neural network) are applied to produce accurate predictions on NBA outcomes at a season-by-season and a month-by-month basis. To evaluate the interpretability of the established AI models, an explainable AI algorithm is utilized to deduce and assess the precise reasoning behind the model prediction based on the local interpretable model-agnostic explanation method. To illustrate its application potential, the method is applied to the open-source NBA data from 1980 to 2019. Experimental results demonstrate the effectiveness of the introduced explainable AI algorithm on predicting NBA outcomes with interpretation.

In this article, we investigate the grant-free communications with adaptive period for Industrial Internet of Things, where only a fraction of devices is active at a time. To the best of our knowledge, this is the first work to exploit the noncontinuous temporal correlation of the received signal for joint user activity detection (UAD), channel estimation, and signal detection, while all the previous work requires continuous transmission. Two schemes are proposed toward this purpose, namely, periodic block orthogonal matching pursuit (PBOMP) and periodic block sparse Bayesian learning (PBSBL), which outperform the previous schemes in terms of the success rate of UAD, bit error rate, and accuracy in period estimation and channel estimation. The Cramér–Rao lower bounds (CRLBs) of channel estimation by PBOMP and PBSBL are derived. It is shown that the two proposed approaches have close CRLBs and normalized mean-square error at high SNR.

Conventional request-grant based non-orthogonal multiple access (NOMA) incurs tremendous overhead and high latency. To enable grant-free access in NOMA systems, user activity detection (UAD) is essential. In this paper, we investigate compressive sensing (CS) aided UAD, by utilizing the property of quasi-time-invariant channel tap delays as the prior information. This does not require any prior knowledge of the number of active users like the previous approaches, and therefore is more practical. Two UAD algorithms are proposed, which are referred to as gradient based and time-invariant channel tap delays assisted CS (g-TIDCS) and mean value based and TIDCS (m-TIDCS), respectively. They achieve much higher UAD accuracy than the previous work at low signal-to-noise ratio (SNR). Based on the UAD results, we also propose a low-complexity CS based channel estimation scheme, which achieves higher accuracy than the previous channel estimation approaches.