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.

Autonomous exploration in unknown environments is a critical challenge in robotics, particularly for applications such as indoor navigation, search and rescue, and service robotics. Traditional exploration strategies, such as frontier-based methods, often struggle to efficiently utilize prior knowledge of structural regularities in indoor spaces. To address this limitation, we propose Mapping at First Sense, a lightweight neural network-based approach that predicts unobserved areas in local maps, thereby enhancing exploration efficiency. The core of our method, SenseMapNet, integrates convolutional and transformer-based architectures to infer occluded regions while maintaining computational efficiency for real-time deployment on resource-constrained robots. Additionally, we introduce SenseMapDataset, a curated dataset constructed from KTH and HouseExpo environments, which facilitates training and evaluation of neural models for indoor exploration. Experimental results demonstrate that SenseMapNet achieves an SSIM (structural similarity) of 0.78, LPIPS (perceptual quality) of 0.68, and an FID (feature distribution alignment) of 239.79, outperforming conventional methods in map reconstruction quality. Compared to traditional frontier-based exploration, our method reduces exploration time by 46.5% (from 2335.56s to 1248.68s) while maintaining a high coverage rate (88%) and achieving a reconstruction accuracy of 88%. The proposed method represents a promising step toward efficient, learning-driven robotic exploration in structured environments.

Sensing devices at edge nodes are usually resource-constrained, such as limited battery capacity and physical size. As a result, there is a substantial demand for enhancing energy efficiency in these devices, which can otherwise hinder the deployment of more complex neural networks. This work proposes an energy-efficient computing engine, which is equipped with appropriate computing power to deploy medium-size neural networks for smart sensing at near-sensor edge nodes. SRAM-based Compute-in-Memory (CIM) macro and end-to-end digital controller comprise the engine. We successfully prototyped this engine using an FPGA platform and conducted a demonstration of image classification on the CIFAR-10 dataset. Furthermore, we implement the above design on a TSMC 40nm process, with post-simulation results indicating an impressive throughput of 368.64GOPS and an energy efficiency of 25.7TOPS/W at 10MHz operating frequency, given the memory capacity is 576kb.

This paper proposes an in-situ self-powered BNN-based intelligent visual perception system that harvests light energy utilizing the indispensable image sensor itself. The harvested energy is allocated to the low-power BNN computation modules layer by layer, adopting a light-weighted duty-cycling-based energy scheduler. A software-hardware co-design method, which exploits the layer-wise error tolerance of BNN as well as the computing-error and energy consumption characteristics of the computation circuit, is proposed to determine the parameters of the energy scheduler, achieving high energy efficiency for self-powered BNN inference. Simulation results show that with the proposed inference-adaptive energy scheduling method, self-powered MNIST classification task can be performed at a frame rate of 4 fps if the harvesting power is 1μW, while guaranteeing at least 90% inference accuracy using binary LeNet-5 network.

DNS caches play an important role in DNS querying. However, the performance of DNS caches will be remarkably influenced by disposable domain names, which are generated by services of cloud storage, social networks, etc., and belong to a new class of misused case of DNS. In this paper, we proposed a novel solution named DC3(Domain Classification and Cascade Cache) to mitigate the negative impact. Domain Classification adopts a classifier which is based on a long short-term memory (LSTM) network to prevent disposable domains from being cached. Cascade Cache is a refined cascade LRU policy considering cache size allocation to process the remaining disposable domains. By querying the real DNS traces collected from a large ISP network, experiment results show that this solution can detect disposable domain names and mitigate their negative impacts on DNS caches effectively. Specifically, in our dataset, 67.4% of all distinct domain names are detected as disposable domain names. Correspondingly, when getting rid of them by using this solution, we can raise the cache hit rate more than double.

With the increasing capacity of wireless networks, more people would like to consume the 360-degree panoramic video (PV) in virtual reality (VR) applications as its immersive experience. However, due to the super-high resolution of the PV and the dynamic features of wireless networks, it is very difficult to efficiently deliver PVs over wireless networks. The traditionally independent PV encoding and networking sometimes also results in the PV quality deterioration since it neglects the harmony between the source encoding and networking. In this paper, a joint source encoding and networking optimization scheme is proposed to transmit the PV over LTE-A downlink. The PV encoding parameters during the source compression, the modulation and coding scheme (MCS), and relay selection during the networking are jointly considered to optimize the end-to-end PV quality. In addition, the video quality for region of interest (RoI, the possible viewport region) is enhanced by allowing a larger latency bound in the joint source encoding and networking optimization. Experimental results show that the proposed scheme achieves significant performance improvement for the quality of the received PV over traditional PV streaming approaches.

A precision-improved processing architecture of physical computing for energy-efficient SIFT feature extraction algorithm has been proposed in this paper. With the novel physical computing technology of active resistor network (PC: ARN), the SIFT algorithm could be processed in analog signal domain without synchronizing clock signals, which means the complex algorithm could be completed within the setup time of the circuit. Especially for the multi-scale Gaussian convolution of SIFT algorithm, an architecture of two-layer 1-dimension PC: ARN has been adopted to compute the horizontal and vertical 1-dimension gaussian filter, in which way higher accuracy can be obtained when compared with the results processed by a 2D active circuit network. A circuit-level simulation with 65nm CMOS technology has been carried out, which shows the energy consumption of gaussian pyramid multi-scale-filtering hardware architecture is about 25.3pJ, where the size of input frame is assigned as 256×256 pixels. Additionally, the average matching ratio in different image pairs is around 80%. Moreover, integrated into the dominating CMOS image sensor with column-parallel readout technology of analog-to-digital convertor, about 20× speedup can be achieved comparing with previous implementations with FPGA, GPU, etc.

Using spectral of broadband emissivity which was measured by Fourier Transform Infrared spectrometer (FTIR) over Taklimakan Desert and MODIS data, we developed an empirical regression equation to estimate the surface broadband emissivity for the spectral domains 8-13.5 μm by the MODIS data. The accuracy of the equation was verified by the observed FTIR data and the MODIS spectral library data, respectively. Root mean square errors (RMSE) of the equation were 0.0041 and 0.0081, respectively. Then, the superiority and defect of observed FTIR data and MODIS spectral library were analyzed by each other, we found the FTIR data is better than spectral library data. At last, we selected the optimal regression equation to estimate the surface broadband emissivity of Xinjiang, and characteristics of spatial distribution for the broadband emissivity over four deserts in Xinjiang were analyzed. The results illustrated that the emissivity over Taklimakan Desert and Culukekum Desert are highly homogenous due to their stable climate and arid condition, which range is 0.850-0.915. Gurbantonggut Desert is influenced by vegetation and soil humidity, which emissivity is not well-distributed, their range is 0.890-0.915. However, the distribution of emissivity over Kumtagh Desert is similar to its plume underlying surface, which range is 0.860-0.910.

Approximate computing technology has aroused growing interest in circuit and system design for its well-performed trade-off between output quality and performance. Numerous basic circuits and system design methodologies for approximate computing have been proposed. Considering that the existing methodologies for the evaluation of tradeoff between output quality and performance is time-consuming, this paper presents a fast design methodology for approximate accumulator based on statistical error model, in which the inexact multistage speculative adder is adopted and modeled for its advantage of compact error pattern. To validate the proposed methodology, Support Vector Machine(SVM) algorithm is analyzed and mapped to a hardware system composed of inexact and accurate computing circuits. Results show that our time for searching the optimal mapping circuits has been saved by 22.08% than functional-based simulation where the final approximate system design achieves 1.57× speedups with 8.56% accuracy degradation.

Multi-stage latency adders based on different prediction schemes have been proved promising to enhance the circuit performance with negligible overhead. This paper presents a novel predictor exploiting both the detection and the sequence-dependence between the successive calculations. The detection of carry-kill pattern of the input data can lower the probability of the operation with multiple clock cycles and the sequence-dependence between the successive calculations is adapted to eliminate redundant cycles. The improved predictors have been inserted into Ripple Carry Adder (RCA) and a multistage latency structure has been setup. Compared with the previous predictors, the proposed one could have the same function with less prediction bits, which results in more energy-efficiency. Simulation results show that 2.41X-3.05X speedups can be achieved than the non-prediction counterpart. Furthermore, a design flow and a method for error control are proposed when applying the adder to approximate computation so that more performance improvement could be obtained after trading off certain precision.

With the rapid development of XML language which has good flexibility and interoperability, more and more log files of software running information are represented in XML format, especially for Web services. Fault diagnosis by analyzing semi-structured and XML like log files is becoming an important issue in this area. For most related learning methods, there is a basic assumption that training data should be in identical structure, which does not hold in many situations in practice. In order to learn from training data in different structures, we propose a similarity-based Bayesian learning approach for fault diagnosis in this paper. Our method is to first estimate similarity degrees of structural elements from different log files. Then the basic structure of combined Bayesian network (CBN) is constructed, and the similarity-based learning algorithm is used to compute probabilities in CBN. Finally, test log data can be classified into possible fault categories based on the generated CBN. Experimental results show our approach outperforms other learning approaches on those training datasets which have different structures.