The rapid development of artificial intelligence (AI) has accelerated the progression of IoT technology into the smart era. Integrating AI processing capabilities into IoT devices to create smart sensing systems holds significant promise. In this work, we propose a distributed-centralized heterogeneous architecture that enables efficient multitask processing for smart sensing. This architecture improves the operational efficiency of sensing systems and enhances the deployment scalability through collaborative computing across end, edge, and center nodes. Specifically, we partition the network in traditional centralized sensing systems into several parts and perform algorithm-hardware co-design for each part on its respective deployment platform. We developed a sample design to validate the proposed architecture. By implementing a lightweight image encoder, we achieved an 88x reduction in encoder parameters and up to 9873x energy gain, facilitating deployment on resource-constrained devices. Experimental results demonstrate that the proposed architecture effectively reduces overall energy consumption by 0.0573x to 0.0889x, while maintaining robust multitask inference capabilities. Moreover, energy consumption reductions of 2.88x to 3.22x on edge nodes and 6311.56x to 10037.23x on end nodes were observed.

Noise is one of the most common and significant factors leading to image degradation. In recent years, due to the rapid development of neural networks, the performance of denoising algorithms has seen a substantial improvement. However, state-of-the-art denoising models often entail large-scale models and heavy computational requirements, making deployment challenging. Additionally, we have observed that the location of denoisers in the entire image processing pipeline has a significant impact on resource consumption and denoising effectiveness. Deploying the denoiser closer to the image acquisition stage will be more effective in separating noise from the image. In this paper, we propose a near-sensor compute-in-memory macro for visual perception denoising (Denoise on Sensor, DoS) along with its corresponding Edge Denoise U-net (EDU) architecture. DoS employs a mixed-signal circuit implementation for neural network inference, offering a notable advantage in terms of high speed and low power consumption compared to FPGA or GPU based approaches, making it feasible to deploy denoising tasks at the near-sensor edge. The simulation results show that the energy efficiency of DoS can reach 21.98 TOPS/W, and EDU deployed on DoS can achieve around 30dB PSNR and 0.83 SSIM on KODAK, BSD300 and SET14 datasets.

Due to the susceptibility to nothing-at-stake and long-range attacks, the Proof-of-Stake consensus faces challenges in securely and efficiently confirming blocks. We propose a new Proof-of-Stake consensus, Voted Weightest Sub-Tree(VWeiST) consensus. It assigns weights to each block through voting, and nodes confirm blocks by calculating the probability that each block's weight can be exceeded by other competitors. We employ a multi-round voting approach, where a small number of nodes are randomly selected as the committee nodes to vote in each round. This approach results in particularly low communication overhead per block, allowing for scalability to a large number of nodes. Compared to other consensus, our mechanism requires fewer rounds of voting to confirm a block, offering advantages in throughput and transaction latency. In the experiments, VWeiST achieves latency and round reductions down to 40% and 29% of the comparison method's levels at most. Furthermore, we theoretically prove that the consensus ensures liveness and probabilistic safety.

Blockchain, a widely utilized distributed ledger technology, faces the scalability challenge. State sharding has emerged as a promising solution for addressing this challenge. However, conventional state allocation solutions often face two major obstacles: a high ratio of cross-shard transactions and an unbalanced workload distribution, due to their reliance on a simple and fixed assignment of states to shards. The former increases the overall workload on the system, while the latter reduces resource utilization. Both factors significantly impact system performance. Moreover, our key observation is that the collection of smart contract transactions can be represented as a hypergraph network by analyzing their characteristics. Therefore, this study proposes HyperChain, a novel dynamic state sharding protocol that integrates a hypergraph partition algorithm. HyperChain aims to reduce the ratio of cross-shard transactions and balance workload distribution, thereby achieving improved throughput and reduced transaction latency in smart contract blockchain systems. Our experiments demonstrate that the proposed HyperChain exhibits superior performance than other solutions in terms of cross-shard transaction ratio, workload balance, throughput, and transaction latency.

Emotion is a human attitude experience and corresponding behavioral response to objective things. Effective emotion recognition is important for the intelligence and humanization of brain-computer interface (BCI). Although deep learning has been widely used in emotion recognition in recent years, emotion recognition based on electroencephalography (EEG) is still a challenging task in practical applications. Herein, we proposed a novel hybrid model that employs generative adversarial networks to generate potential representations of EEG signals while combining graph convolutional neural networks and long short-term memory networks to recognize emotions from EEG signals. Experimental results on DEAP and SEED datasets show that the proposed model achieved the promising emotion classification performance compared with the state-of-the-art methods.

In this paper, we present and evaluate an approach to incremental dialogue act (DA) segmentation and classification.Our approach utilizes prosodic, lexico-syntactic and contextual features, and achieves an encouraging level of performance in offline corpus-based evaluation as well as in simulated human-agent dialogues.Our approach uses a pipeline of sequential processing steps, and we investigate the contribution of different processing steps to DA segmentation errors.We present our results using both existing and new metrics for DA segmentation.The incremental DA segmentation capability described here may help future systems to allow more natural speech from users and enable more natural patterns of interaction.