Search

This paper presents a low-power RF receiver/transmitter front-end for 2.4-GHz-band IEEE 802.15.4 standard in 0.18-[micro]m CMOS technology. An RF receiver comprises a single-ended low-noise amplifier, a quadrature passive mixer, and a transimpedance amplifier. A current-mode passive mixer showing a very good 1/f noise performance is adopted to convert an RF signal directly to a baseband signal. Moreover, this type of passive mixer shows high-linearity performance, leading to overall RF receiver linearity improvement. A low-power, high-linearity transmitter front-end is implemented by using a passive mixer and two-stage driver amplifier in which the first stage is a conventional cascode amplifier and the second stage uses a folded cascode one. The receiver front-end achieves 30-dB voltage conversion gain, 7.3-dB noise figure with 1/f noise corner frequency of 70 kHz, -8-dBm input third-order intercept point, and +40-dBm input second-order intercept point. The transmitter front-end shows 12-dB power conversion gain, 0-dBm output power with 10-dBm output third-order intercept point, and -30-dB local-oscilator suppression. The receiver and transmitter front-end dissipate 3.5 and 3 mA from a 1.8-V supply, respectively. Index Terms--CMOS radio, dc offset, driver amplifier (DA), IEEE 802.15.4 transceiver, low-noise amplifier (LNA), low power, 1/f noise, passive mixer, transceiver front-end.

Stroke is the third highest cause of death worldwide after cancer and heart disease, and the number of stroke diseases due to aging is set to at least triple by 2030. As the top three causes of death worldwide are all related to chronic disease, the importance of healthcare is increasing even more. Models that can predict real-time health conditions and diseases using various healthcare services are attracting increasing attention. Most diagnosis and prediction methods of stroke for the elderly involve imaging techniques such as magnetic resonance imaging (MRI). It is difficult to rapidly and accurately diagnose and predict stroke diseases due to the long testing times and high costs associated with MRI. Thus, in this paper, we design and implement a health monitoring system that can predict the precursors of stroke diseases in the elderly in real time during daily walking. First, raw electroencephalography (EEG) data from six channels were preprocessed via Fast Fourier Transform (FFT). The raw EEG power values were then extracted from the raw spectra: alpha (α), beta (β), gamma (γ), delta (δ), and theta (θ) as well as the low β , high β , and θ to β ratio, respectively. The experiments in this paper confirm that the important features of EEG biometric signals alone during walking can accurately determine stroke precursors and occurrence in the elderly with more than 90% accuracy. Further, the Random Forest algorithm with quartiles and Z-score normalization validates the clinical significance and performance of the system proposed in this paper with a 92.51% stroke prediction accuracy. The proposed system can be implemented at a low cost, and it can be applied for early disease detection and prediction using the precursor symptoms of real-time stroke. Furthermore, it is expected that it will be able to detect other diseases such as cancer and heart disease in the future. [ABSTRACT FROM AUTHOR]

Stroke is a leading cause of disabilities in adults and the elderly which can result in numerous social or economic difficulties. If left untreated, stroke can lead to death. In most cases, patients with stroke have been observed to have abnormal bio-signals (i.e., ECG). Therefore, if individuals are monitored and have their bio-signals measured and accurately assessed in real-time, they can receive appropriate treatment quickly. However, most diagnosis and prediction systems for stroke are image analysis tools such as CT or MRI, which are expensive and difficult to use for real-time diagnosis. In this paper, we developed a stroke prediction system that detects stroke using real-time bio-signals with artificial intelligence (AI). Both machine learning (Random Forest) and deep learning (Long Short-Term Memory) algorithms were used in our system. EMG (Electromyography) bio-signals were collected in real time from thighs and calves, after which the important features were extracted, and prediction models were developed based on everyday activities. Prediction accuracies of 90.38% for Random Forest and of 98.958% for LSTM were obtained for our proposed system. This system can be considered an alternative, low-cost, real-time diagnosis system that can obtain accurate stroke prediction and can potentially be used for other diseases such as heart disease. [ABSTRACT FROM AUTHOR]

We propose a new teacher–student framework (TSF)-based knowledge transfer method, in which knowledge in the form of dense flow across layers is distilled from a pre-trained “teacher” deep neural network (DNN) and transferred to another “student” DNN. In the case of distilled knowledge, multiple overlapped flow-based items of information from the pre-trained teacher DNN are densely extracted across layers. Transference of the densely extracted teacher information is then achieved in the TSF using repetitive sequential training from bottom to top between the teacher and student DNN models. In other words, to efficiently transmit extracted useful teacher information to the student DNN, we perform bottom-up step-by-step transfer of densely distilled knowledge. The performance of the proposed method in terms of image classification accuracy and fast optimization is compared with those of existing TSF-based knowledge transfer methods for application to reliable image datasets, including CIFAR-10, CIFAR-100, MNIST, and SVHN. When the dense flow-based sequential knowledge transfer scheme is employed in the TSF, the trained student ResNet more accurately reflects the rich information of the pre-trained teacher ResNet and exhibits superior accuracy to the existing TSF-based knowledge transfer methods for all benchmark datasets considered in this study. [ABSTRACT FROM AUTHOR]

We devise a layer‐wise hint training method to improve the existing hint‐based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher‐student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively trains the student ResNet and incrementally employs hint‐based information extracted from the pretrained teacher ResNet containing several hint and guided layers. Next, typical softening factor‐based KD training is performed using the previously estimated hint‐based information. We compare the recognition accuracy of the proposed approach with that of KD training without hints, hint‐based KD training, and ResNet‐based layer‐wise pretraining using reliable datasets, including CIFAR‐10, CIFAR‐100, and MNIST. When using the selected multiple hint‐based information items and their layer‐wise transfer in the proposed method, the trained student ResNet more accurately reflects the pretrained teacher ResNet's rich information than the baseline training methods, for all the benchmark datasets we consider in this study. [ABSTRACT FROM AUTHOR]

In this article, we present a subcarrier demodulation structure to eliminate an undesirable DC-offset phenomenon, which may appear in the baseband of the reader receiver under passive radio frequency identification environment.To achieve the requirement, the primary feature of the proposed demodulation structure is to reconstruct the signal corrupted by the DC-offset phenomenon by creating peak signals from the corrupted signal. In the case of the Miller subcarrier signal, the phase inversion information in the symbol duration is used for generating the peak signal. It is shown that the proposed method can successfully detect valid data from the received signal, even when the received baseband signal is distorted by the DC-offset phenomenon. In addition, the performance of the proposed method is slightly better than or comparable to that of the well-known-matched filter-type baseband receiver in the band-limited channel environments. © 2011 Wiley Periodicals, Inc. Microwave Opt Technol Lett 53:1264-1272, 2011; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.25995 [ABSTRACT FROM AUTHOR]

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques. [ABSTRACT FROM AUTHOR]

A slot-fed U-slotted patch antenna is developed as an aperture-coupling structure, and is compared to the existing feed types. Its wideband mechanism is explained, and its samples for Ku- and S-bands are designed, simulated, and tested. A bandwidth of about 42% for VSWR less than 2:1; and 30.1% for -3 dB peak gain are obtained. ©1999 John Wiley & Sons, Inc. Microwave Opt Technol Lett 22: 378–381, 1999 [ABSTRACT FROM AUTHOR]

Recently, with the rapid change to an aging society and the increased interest in healthcare, disease prediction and management through various healthcare devices and services is attracting much attention. In particular, stroke, represented by cerebrovascular disease, is a very dangerous disease, in which death or mental and physical aftereffects are very large in adults and the elderly. The sequelae of such stroke diseases are very dangerous, because they make social and economic activities difficult. In this paper, we propose a new system to prediction and in-depth analysis stroke severity of elderly over 65 years based on the National Institutes of Health Stroke Scale (NIHSS). In addition, we use the algorithm of decision tree of C4.5, which is a methodology of prediction and analysis of machine learning techniques. The C4.5 decision trees are machine learning algorithms that provide additional in-depth rules of the execution mechanism and semantic interpretation analysis. Finally, in this paper, it is verified that the C4.5 decision tree algorithm can be used to classify and predict stroke severity, and to obtain additional NIHSS features reduction effects. Therefore, during the operation of an actual system, the proposed model uses only 13 features out of the 18 stroke scale features, including age, so that it can provide faster and more accurate service support. Experimental results show that the system enables this by reducing the patient NIH stroke scale measurement time and making the operation more efficient, with an overall accuracy, using the C4.5 decision tree algorithm, of 91.11%. [ABSTRACT FROM AUTHOR]