Electronic nose (E-nose) systems have become popular in food and fruit quality evaluation because of their rapid and repeatable availability and robustness. In this paper, we propose an E-nose system ...that has potential as a non-destructive system for monitoring variation in the volatile organic compounds produced by fruit during the maturing process. In addition to the E-nose system, we also propose a camera system to monitor the peel color of fruit as another feature for identification. By incorporating E-nose and camera systems together, we propose a non-destructive solution for fruit maturity monitoring. The dual E-nose/camera system presents the best Fisher class separability measure and shows a perfect classification of the four maturity stages of a banana: Unripe, half-ripe, fully ripe, and overripe.
This study proposes an output capacitor-less linear regulator with high power supply rejection (PSR) for a wireless power transmission system. To achieve high PSR with a noisy input voltage, a fully ...integrated linear regulator with its reference circuit supplied by the output voltage is proposed. The proposed technique can isolate the reference circuit from the noisy <inline-formula> <tex-math notation="LaTeX">\text{V}_{IN} </tex-math></inline-formula>, thereby reducing the requirements of the conventional bulky low-pass filter loading the reference voltage node while achieving superior PSR performance. The regulator uses an N-type pass transistor and a dual-feedback structure to achieve wideband ripple-filtering and fast transient responses. The proposed regulator is compatible with typical biomedical implants requiring a 10mA load current at 1.1V output voltage while consuming a total quiescent current of <inline-formula> <tex-math notation="LaTeX">276~\mu </tex-math></inline-formula> A. A PSR performance was measured to be −48 and −56 dB against the <inline-formula> <tex-math notation="LaTeX">\text{V}_{IN} </tex-math></inline-formula> and charge pump at 10 MHz, respectively. The unity gain bandwidth (UGB) of the regulator was 291MHz. The proposed regulator was fabricated using commercial TSMC 0.18-<inline-formula> <tex-math notation="LaTeX">\mu \text{m} </tex-math></inline-formula> CMOS technology with an area of 0.1054 mm 2 including the reference circuit.
The tutorial explores key security and functional safety challenges for Artificial Intelligence (AI) in embedded automotive systems, including aspects from adversarial attacks, long life cycles of ...products, and limited energy resources of automotive platforms within safety-critical environments in diverse use cases. It provides a set of recommendations for how the security and safety engineering of machine learning can address these challenges. It also provides an overview of contemporary security and functional safety engineering practices, encompassing up-to-date legislative and technical prerequisites. Finally, we identify the role of AI edge processing in enhancing security and functional safety within embedded automotive systems.
Inspired by the human brain, spiking neuron networks are promising to realize energy-efficient and low-latency neuromorphic computing. However, even state-of-the-art silicon neurons are orders of ...magnitude worse than biological neurons in terms of area and power consumption due to the limitations. Moreover, limited routing in typical CMOS processes is another challenge for realizing the fully-parallel high-throughput synapse connections compared to biological synapses. This paper presents an SNN circuit that utilizes resource-sharing techniques to address the two challenges. Firstly, a comparator sharing neuron circuit with a background calibration technique is proposed to shrink the size of a single neuron without performance degradation. Secondly, a time-modulated axon-sharing synapse system is proposed to realize a fully-parallel connection with limited hardware overhead. To validate the proposed approaches, a CMOS neuron array is designed and fabricated under a 55-nm process. It consists of 48 LIF neurons with 3125 neurons/mm<inline-formula><tex-math notation="LaTeX">{^{_{2}}}</tex-math></inline-formula> area density, power consumption of 5.3 pJ/spike, and equivalent 2304 fully parallel synapses providing a unit throughput of 5500 events/s/neuron. It proves the proposed approaches are promising to realize a high-throughput high-efficiency SNN with CMOS technology.
Traditional casting methods are losing their appeal due to poor working conditions. Integrating additive manufacturing into traditional Casting is a popular solution. Among the seven additive ...manufacturing categories, binder jet 3D printing is most suitable for 3D printing sand molds. However, issues like waste management and environmental problems in binder jetting need to be solved. The investigation proves that utilizing recycled sand as a raw material for 3D printing sand products can reduce the environmental impacts associated with binder jet 3D printing while achieving adequate mechanical properties. This study shows that recycled sand can produce mechanical properties comparable to new sand, while reducing waste and environmental impact. The study examines samples of new sand and recycled sand obtained from one to nine cycles of recycling. It reveals that the compressive and flexural strengths of sand recycled one to three times outperform new sand, while surface hardness remains unaffected by the recycling cycle. However, the permeability of the sand decreases as the number of recycling cycles increases. Recycled sand required less binder and hardener, which reduced costs and improved the environmental impact. This study highlights the importance of waste management and sustainability in 3D-printed sand mold processes and offers a promising solution for recycled sand powders in binder jetting.
An Adjustable Dual-Output Current Mode MOSFET-Only Filter Akbari, Meysam; Hussein, Safwan Mawlood; Hashim, Yasir ...
IEEE transactions on circuits and systems. II, Express briefs,
06/2021, Letnik:
68, Številka:
6
Journal Article
Recenzirano
This brief presents an adjustable third-order filter without employing passive elements. The proposed filter combines two low-pass and band-pass MOSFET-only topologies to configure a dual-output ...structure, while the transconductances and parasitic gate-source capacitances of the transistors act as the required passive elements. The main core of the proposed filter contains just 3 transistors that with the elimination of passive elements results in a small silicon area and low power consumption. The proposed filter benefits from low-input and high-output impedances that is an advantage for cascading in current-mode systems. Moreover, a kind of self-biasing topology is used to configure the proposed filter in which a control voltage is provided to move the center frequency of both outputs in a wide frequency range. The proposed circuit was fabricated using TSMC 0.18 μm CMOS process. Experimental and simulation results at a supply voltage of 1.8 V show a bandwidth range from 38.1 MHz to 99.5 MHz for a capacitive load bigger than 15 pF, while the average power consumption is 435 μW. It occupies a silicon area of just 43 μm ×86 μm.
This article presents a computing-in-memory (CIM) structure aimed at improving the energy efficiency of edge devices running multi-bit multiply-and-accumulate (MAC) operations. The proposed scheme ...includes a 6T SRAM-based CIM (SRAM-CIM) macro capable of: 1) weight-bitwise MAC (WbwMAC) operations to expand the sensing margin and improve the readout accuracy for high-precision MAC operations; 2) a compact 6T local computing cell to perform multiplication with suppressed sensitivity to process variation; 3) an algorithm-adaptive low MAC-aware readout scheme to improve energy efficiency; 4) a bitline header selection scheme to enlarge signal margin; and 5) a small-offset margin-enhanced sense amplifier for robust read operations against process variation. A fabricated 28-nm 64-kb SRAM-CIM macro achieved access times of 4.1-8.4 ns with energy efficiency of 11.5-68.4 TOPS/W, while performing MAC operations with 4- or 8-b input and weight precision.
Although electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet been performed.
...Patients with lung cancer, as well as healthy control and diseased control groups, were prospectively recruited from two referral centers between 2019 and 2022. Deep learning models for detecting lung cancer with eNose breathprint were developed using training cohort from one site and then tested on cohort from the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) and Noise-Shift Augmentation (NSA) methods with or without fine-tuning was applied to improve performance.
In this study, 231 participants were enrolled, comprising a training/validation cohort of 168 individuals (90 with lung cancer, 16 healthy controls, and 62 diseased controls) and a test cohort of 63 individuals (28 with lung cancer, 10 healthy controls, and 25 diseased controls). The model has satisfactory results in the validation cohort from the same hospital while directly applying the trained model to the test cohort yielded suboptimal results (AUC, 0.61, 95% CI: 0.47─0.76). The performance improved after applying data augmentation methods in the training cohort (SDA, AUC: 0.89 0.81─0.97; NSA, AUC:0.90 0.89─1.00). Additionally, after applying fine-tuning methods, the performance further improved (SDA plus fine-tuning, AUC:0.95 0.89─1.00; NSA plus fine-tuning, AUC:0.95 0.90─1.00).
Our study revealed that deep learning models developed for eNose breathprint can achieve cross-site validation with data augmentation and fine-tuning. Accordingly, eNose breathprints emerge as a convenient, non-invasive, and potentially generalizable solution for lung cancer detection.
This study is not a clinical trial and was therefore not registered.
As the growing demand on artificial intelligence (AI) Internet-of-Things (IoT) devices, smart vision sensors with energy-efficient computing capability are required. This article presents a low-power ...and low-voltage dual mode 0.5-V computational CMOS image sensor (C 2 IS) with array-parallel computing capability for feature extraction using convolution. In the feature extraction mode, by applying the pulsewidth modulation (PWM) pixel and switch-current integration (SCI) circuit, the in-sensor eight-directional matrix-parallel multiply-accumulate (MAC) operation is realized. Furthermore, the analog-domain convolution-on-readout (COR) operation, the programmable <inline-formula> <tex-math notation="LaTeX">3\times3 </tex-math></inline-formula> kernel with ±3-bit weights, and the tunable-resolution column-parallel analog-to-digital converter (ADC) (1-8 bit) are implemented to achieve the real-time feature extraction without using additional memory and sacrificing frame rate. In the image capturing mode, the sensor provides the linear-response 8-bit raw image data. The C 2 IS prototype has been fabricated in the TSMC 0.18-<inline-formula> <tex-math notation="LaTeX">\mu \text{m} </tex-math></inline-formula> standard process technology and verified to demonstrate the raw and feature images at 480 frames/s with a power consumption of 77/<inline-formula> <tex-math notation="LaTeX">117~\mu \text{W} </tex-math></inline-formula> and the resultant FoM of 9.8/14.8 pJ/pixel/frame, respectively. The prototype sensor is used as a real-time edge feature detection frond-end camera and accompanied with a simplified convolutional neural network (CNN) architecture to demonstrate the hand gesture recognition. The prototype system achieves more than 95% validation accuracy.
In terms of electronic nose algorithms, data pre-processing and classifier type are the two main factors affecting gas classification results. In the early stage, data pre-processing mostly takes ...specific information from gas-reaction waveforms as features and uses machine learning algorithms, such as K-Nearest Neighbor(KNN) and Support Vector Machine(SVM), to classify the gas data. In recent years, some research has been done on using deep learning for gas classification. The data pre-processing takes the overall process of the gas reaction as a feature map, and the classifier uses Convolutional Neural Network(CNN) architecture to classify the gases, resulting in classification accuracy being significantly higher than those of traditional machine learning algorithms. In addition, external factors such as wind speed, and distance from the gas source are also important factors affecting gas classification. The objectives of this study are as follows: 1) improving the data pre-processing method and classifier structure in deep learning for gas analysis and 2) using hybrid deep neural networks with Multilayer Perceptron (MLP) for environment compensation to improve the sensor drift problem caused by external factors. This study used one open-source gas dataset, applied three data pre-processing methods and two deep learning architectures (GasNet, SimResNet-9) for gas analysis and comparison, selected the method with the best classification accuracy and used it in Deep Neural Networks with MLP environmental compensation to promote the accuracy of classification further by learning the relationship between external factors and gas data. The proposed SimResNet-10_X_MLP was used for data training and classification in this study, achieving a 95% classification accuracy.