Search Results (14)

Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks. Full article

Series arc faults on the DC side of photovoltaic (PV) systems are a critical hazard that can trigger system fires. Conventional contact-based detection methods suffer from cumbersome installation and high retrofit cost, whereas existing non-contact approaches mostly rely on megahertz-level high-frequency sampling and therefore require expensive radio-frequency instrumentation or high-performance computing platforms. As a result, it remains difficult to simultaneously achieve strong interference immunity and real-time performance on low-cost embedded devices with limited resources. To address this engineering paradox between high-frequency sampling and constrained computational capability, this paper proposes a fully embedded, non-contact arc fault detection system based on a 12–80 kHz low-frequency sub-band selection strategy. By exploiting the physical characteristic of broadband energy elevation induced by arc faults, the proposed strategy avoids dependence on high-bandwidth hardware. Guided by this strategy, a Moebius-topology coaxial shielded loop antenna is employed as the near-field sensor, while an ultra-simplified passive analog front end is constructed directly by using the on-chip programmable gain amplifier and analog-to-digital converter of the microcontroller unit, enabling efficient signal acquisition and fast Fourier transform processing within the target sub-band. To cope with complex background noise in the low-frequency range, an environment-adaptive baseline mechanism based on exponential moving average and exponential absolute deviation is developed for dynamic decoupling. In addition, a lightweight INT8-quantized multilayer perceptron is introduced as a nonlinear auxiliary module, thereby forming a robust hybrid decision architecture with complementary rule-based and artificial intelligence components. Experimental results show that, under the tested household, laboratory, and PV-site conditions, the proposed system achieved an overall detection rate of 97%, while the remaining 3% mainly corresponded to failed ignition or non-sustained arc attempts rather than persistent false triggering during normal monitoring. Full article

This paper proposes a novel sound source localization system that combines parametric homomorphic deconvolution with neural network regression to estimate the angle of arrival from a single-channel signal. The system uses an analog adder to sum signals from three spatially arranged microphones, reducing system hardware complexity and requiring the estimation of time delays from a single-channel signal. Time delay features are extracted through parametric homomorphic deconvolution methods—Yule–Walker, Prony, and Steiglitz–McBride—and input to multilayer perceptrons configured with various structures. Simulations confirm that Steiglitz–McBride provides the sharpest and most accurate predictions with reduced model order, while Yule–Walker shows slightly better performance than Prony at higher orders. A hybrid learning strategy that combines synthetic and real-world data improves generalization and robustness across all angles. Experimental validations in an anechoic chamber support the simulation results, showing high correlation and low deviation values, especially with the Steiglitz–McBride method. The proposed sound source localization system demonstrates a compact and scalable design suitable for real-time and resource-constrained applications and provides a promising platform for future extensions in complex environments and broader signal interpretation domains. Full article

In this study, our primary focus is the biomimetic design and rigorous evaluation of an economically viable and portable ‘e-nose’ system, tailored for the precise detection of a broad range of volatile organic compounds (VOCs) in local Thai craft spirits. This e-nose system is innovatively equipped with cost-efficient metal oxide gas sensors and a temperature/humidity sensor, ensuring comprehensive and accurate sensing. A custom-designed real-time data acquisition system is integrated, featuring gas flow control, humidity filters, dual sensing/reference chambers, an analog-to-digital converter, and seamless data integration with a laptop. Deep learning, utilizing a multilayer perceptron (MLP), is employed to achieve highly effective classification of local Thai craft spirits, demonstrated by a perfect classification accuracy of 100% in experimental studies. This work underscores the significant potential of biomimetic principles in advancing cost-effective, portable, and analytically precise e-nose systems, offering valuable insights into future applications of advanced gas sensor technology in food, biomedical, and environmental monitoring and safety. Full article

This paper proposes methods for Machine Learning (ML)-based Beam Alignment (BA), using low-complexity ML models, and achieves a small pilot overhead. We assume a single-user massive mmWave MIMO, Uplink, using a fully analog architecture. Assuming large-dimension codebooks of possible beam patterns at $UE$ and $BS$, this data-driven and model-based approach aims to partially and blindly sound a small subset of beams from these codebooks. The proposed BA is blind (no CSI), based on Received Signal Energies (RSEs), and circumvents the need for exhaustively sounding all possible beams. A sub-sampled subset of beams is then used to train several ML models such as low-rank Matrix Factorization (MF), non-negative MF (NMF), and shallow Multi-Layer Perceptron (MLP). We provide an extensive mathematical description of these models and the algorithms for each of them. Our extensive numerical results show that, by sounding only $10\%$ of the beams from the $UE$ and $BS$ codebooks, the proposed ML tools are able to accurately predict the non-sounded beams through multiple transmitted power regimes. This observation holds as the codebook sizes at $UE$ and $BS$ vary from $128\times 128$ to $1024\times 1024$. Full article

The accurate prevention and control of pear tree diseases, especially the precise segmentation of leaf diseases, poses a serious challenge to fruit farmers globally. Given the possibility of disease areas being minute with ambiguous boundaries, accurate segmentation becomes difficult. In this study, we propose a pear leaf disease segmentation model named MFBP-UNet. It is based on the UNet network architecture and integrates a Multi-scale Feature Extraction (MFE) module and a Tokenized Multilayer Perceptron (BATok-MLP) module with dynamic sparse attention. The MFE enhances the extraction of detail and semantic features, while the BATok-MLP successfully fuses regional and global attention, striking an effective balance in the extraction capabilities of both global and local information. Additionally, we pioneered the use of a diffusion model for data augmentation. By integrating and analyzing different augmentation methods, we further improved the model’s training accuracy and robustness. Experimental results reveal that, compared to other segmentation networks, MFBP-UNet shows a significant improvement across all performance metrics. Specifically, MFBP-UNet achieves scores of 86.15%, 93.53%, 90.89%, and 0.922 on MIoU, MP, MPA, and Dice metrics, marking respective improvements of 5.75%, 5.79%, 1.08%, and 0.074 over the UNet model. These results demonstrate the MFBP-UNet model’s superior performance and generalization capabilities in pear leaf disease segmentation and its inherent potential to address analogous challenges in natural environment segmentation tasks. Full article

A programmable, energy-efficient analog hardware implementation of a multilayer perceptron (MLP) is presented featuring a highly programmable system that offers the user the capability to create an MLP neural network hardware design within the available framework. In addition to programmability, this implementation provides energy-efficient operation via analog/mixed-signal design. The configurable system is made up of 12 neurons and is fabricated in a standard 130 nm CMOS process occupying approximately 1 mm² of on-chip area. The system architecture is analyzed in several different configurations with each achieving a power efficiency of greater than 1 tera-operations per watt. This work offers an energy-efficient and scalable alternative to digital configurable neural networks that can be built upon to create larger networks capable of standard machine learning applications, such as image and text classification. This research details a programmable hardware implementation of an MLP that achieves a peak power efficiency of 5.23 tera-operations per watt while consuming considerably less power than comparable digital and analog designs. This paper describes circuit elements that can readily be scaled up at the system level to create a larger neural network architecture capable of improved energy efficiency. Full article

As a leading branch of deep learning, the convolutional neural network (CNN) is inspired by the natural visual perceptron mechanism of living things, showing great application in image recognition, language processing, and other fields. Photonics technology provides a new route for intelligent signal processing with the dramatic potential of its ultralarge bandwidth and ultralow power consumption, which automatically completes the computing process after the signal propagates through the processor with an analog computing architecture. In this paper, we focus on the key enabling technology of optical CNN, including reviewing the recent advances in the research hotspots, overviewing the current challenges and limitations that need to be further overcome, and discussing its potential application. Full article

This paper presents a BJT-based smart CMOS temperature sensor. The analog front-end circuit contains a bias circuit and a bipolar core; the data conversion interface features an incremental delta-sigma analog-to-digital converter. The circuit utilizes the chopping, correlated double sampling, and dynamic element matching techniques to mitigate the effects of process bias and nonideal device characteristics on measurement accuracy. Furthermore, based on the principle of charge conservation, the dynamic range utilization of the ADC increases. We propose a neural network that uses a multilayer convolutional perceptron to calibrate the sensor output results. Using the algorithm, the sensor achieves an inaccuracy of ±0.11 °C (3σ), exceeding the accuracy of ±0.23 °C (3σ) achieved without calibration. We implement the sensor in a 0.18 µm CMOS process, occupying an area of 0.42 mm². It achieves a resolution of 0.01 °C and has a conversion time of 24 ms. Full article

An ongoing challenge in neural information processing is the following question: how do neurons adjust their connectivity to improve network-level task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning mechanism in specific brain regions, such as the basal ganglia, that actualizes learning. However, the exact nature of this mechanism remains unclear. Here, we investigate the use of universal synaptic-level algorithms in training connectionist models. Specifically, we propose an algorithm based on reinforcement learning (RL) to generate and apply a simple biologically-inspired synaptic-level learning policy for neural networks. In this algorithm, the action space for each synapse in the network consists of a small increase, decrease, or null action on the connection strength. To test our algorithm, we applied it to a multilayer perceptron (MLP) neural network model. This algorithm yields a static synaptic learning policy that enables the simultaneous training of over 20,000 parameters (i.e., synapses) and consistent learning convergence when applied to simulated decision boundary matching and optical character recognition tasks. The trained networks yield character-recognition performance comparable to identically shaped networks trained with gradient descent. The approach has two significant advantages in comparison to traditional gradient-descent-based optimization methods. First, the robustness of our novel method and its lack of reliance on gradient computations opens the door to new techniques for training difficult-to-differentiate artificial neural networks, such as spiking neural networks (SNNs) and recurrent neural networks (RNNs). Second, the method’s simplicity provides a unique opportunity for further development of local information-driven multiagent connectionist models for machine intelligence analogous to cellular automata. Full article

Perceptron is an essential element in neural network (NN)-based machine learning, however, the effectiveness of various implementations by circuits is rarely demonstrated from chip testing. This paper presents the measured silicon results for the analog perceptron circuits fabricated in a 0.6 $\mathsf{\mu }$m/±2.5 V complementary metal oxide semiconductor (CMOS) process, which are comprised of digital-to-analog converter (DAC)-based multipliers and phase shifters. The results from the measurement convinces us that our implementation attains the correct function and good performance. Furthermore, we propose the multi-layer perceptron (MLP) by utilizing analog perceptron where the structure and neurons as well as weights can be flexibly configured. The example given is to design a 2-3-4 MLP circuit with rectified linear unit (ReLU) activation, which consists of 2 input neurons, 3 hidden neurons, and 4 output neurons. Its experimental case shows that the simulated performance achieves a power dissipation of 200 mW, a range of working frequency from 0 to 1 MHz, and an error ratio within 12.7%. Finally, to demonstrate the feasibility and effectiveness of our analog perceptron for configuring a MLP, seven more analog-based MLPs designed with the same approach are used to analyze the simulation results with respect to various specifications, in which two cases are used to compare to their digital counterparts with the same structures. Full article

Image classification is one of the most important tasks in the digital era. In terms of cultural heritage, it is important to develop classification methods that obtain good accuracy, but also are less computationally intensive, as image classification usually uses very large sets of data. This study aims to train and test four classification algorithms: (i) the multilayer perceptron, (ii) averaged one dependence estimators, (iii) forest by penalizing attributes, and (iv) the k-nearest neighbor rough sets and analogy based reasoning, and compares these with the results obtained from the Convolutional Neural Network (CNN). Three types of features were extracted from the images: (i) the edge histogram, (ii) the color layout, and (iii) the JPEG coefficients. The algorithms were tested before and after applying the attribute selection, and the results indicated that the best classification performance was obtained for the multilayer perceptron in both cases. Full article

Detailed analysis of the function of multilayer perceptron (MLP) and its neurons together with the use of time-varying neurons allowed the authors to find an analogy with the use of structures of linear differential operators. This procedure allowed the construction of a group and a hypergroup of artificial neurons. In this article, focusing on semihyperstructures and using the above described procedure, the authors bring new insights into structures and hyperstructures of artificial neurons and their possible symmetric relations. Full article

This study examines an analog circuit comprising a multilayer perceptron neural network (MLPNN). This study proposes a low-power and small-area analog MLP circuit to implement in an E-nose as a classifier, such that the E-nose would be relatively small, power-efficient, and portable. The analog MLP circuit had only four input neurons, four hidden neurons, and one output neuron. The circuit was designed and fabricated using a 0.18 μm standard CMOS process with a 1.8 V supply. The power consumption was 0.553 mW, and the area was approximately 1.36 × 1.36 mm². The chip measurements showed that this MLPNN successfully identified the fruit odors of bananas, lemons, and lychees with 91.7% accuracy. Full article