CCChing-Yao Chou

Ching-Yao Chou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ching-Yao Chou has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Accumulated Polar Feature-Based Deep Learning for Efficient and Lightweight Automatic Modulation Classification With Channel Compensation Mechanism

    by Chieh-Fang Teng, Ching-Yao Chou, Chun-Hsiang Chen, An-Yeu Wu

    In next-generation communications, massive machine-type communications (mMTC) induce severe burden on base stations. To address such an issue, automatic modulation classification (AMC) can help to reduce signaling overhead by blindly recognizing the modulation types without handshaking. Thus, it plays an important role in future intelligent modems. The emerging deep learning (DL) technique stores intelligence in the network, resulting in superior performance over traditional approaches. However, DL-based approaches suffer from heavy training overhead, memory overhead, and computational complexity, which severely hinder practical applications for resource-limited scenarios, such as Internet-of-Things (IoT) networks and unmanned aerial vehicle (UAV)-aided systems. Furthermore, the overhead of online retraining under time-varying fading channels has not been studied in the prior arts. In this work, an accumulated polar feature-based DL with a channel compensation mechanism is proposed to cope with the aforementioned issues. Firstly, the simulation results show that learning features from the polar domain with historical data information can approach near-optimal performance while reducing training overhead by 99.8 times. Secondly, the proposed neural network-based channel estimator (NN-CE) can learn the channel response and compensate for the distorted channel with 13% improvement. Moreover, in applying this lightweight NN-CE in a time-varying fading channel, two efficient mechanisms of online retraining are proposed, which can reduce transmission overhead and retraining overhead by 90% and 76%, respectively. Finally, the performance of the proposed approach is evaluated and compared with prior arts on a public dataset to demonstrate its great efficiency and lightness. The lightweight and efficient learning features of the proposed mechanism will be very attractive for future resource-constrained/aware IoT and Vehicle-to-Everying (V2X) applications.


  • A Tri-Mode Compressed Analytics Engine for Low-Power AF Detection With On-Demand EKG Reconstruction

    by Kuan-Chun Chen, Ching-Yao Chou, An-Yeu Wu

    Compressive sensing (CS) is a novel technique to realize the low-power designs for sensor nodes and reduce overall transmission power in a wireless sensor network. The reconstruction engines using CS techniques have also been widely explored to realize real-time processing. However, for the applications of physiological signal monitoring, we are also concerned about physiological conditions. Moreover, in most cases, we are more interested in those high-risk signals, such as paroxysmal atrial fibrillation (AF), that the syndrome happened occasionally. Therefore, lots of computational efforts are wasted if we fully reconstruct those normal signals that are irrelevant to diseases. In this article, we present a tri-mode CS-based compressed analytics (CA) engine that is fabricated in 40-nm CMOS technology and this engine can realize CA, on-demand reconstruction, and full reconstruction in a hardware sharing manner. With CA, we can classify high-risk signals directly in the compressed domain. While the on-demand reconstruction can avoid unnecessary energy consumption of reconstructing these normal sinus rhythm (NSR) signals. Hence, by adopting on-demand reconstruction, the area-energy efficiency (AEE) of this engine can be 3.22-to-67.57x better compared with state-of-the-art designs. In summary, the proposed 2.41-mm² tri-mode CA engine has more comprehensive functionalities, but is more lightweight for medical telemonitoring applications.


  • Low-Complexity On-Demand Reconstruction for Compressively Sensed Problematic Signals

    by Ching-Yao Chou, Kai-Chieh Hsu, Bo-Hong Cho, Kuan-Chun Chen, An-Yeu Andy Wu

    Compressed Sensing (CS) is a revolutionary technology for realizing low-power sensor nodes through sub-Nyquist sampling, and the CS reconstruction engines have been widely studied to fulfill the energy efficiency for real-time processing. However, in most cases, we only want to analyze the problematic signals which account for a very low percentage. Therefore, large efforts will be wasted if we recover uninterested signals. On the other hand, in order to identify the high-risk signals, additional hardware and computation overhead are required for classification other than CS reconstruction. In this paper, to achieve low-complexity on-demand CS reconstruction, we propose a two-stage classification-aided reconstruction (TS-CAR) framework. The compressed signals can be classified with a sparse coding based classifier, which provides the hardware sharing potential with reconstruction. Furthermore, to accelerate the reconstruction speed, a cross-domain sparse transform is applied from classification to reconstruction. TS-CAR is implemented in electrocardiography based atrial fibrillation (AF) detection. The average computational cost of TS-CAR is 2.25× fewer compared to traditional frameworks when AF percentage is among 10% to 50%. Finally, we implement TS-CAR in TSMC 40 nm technology. The post-layout results show that the proposed intelligent CS reconstruction engine can provide a competitive area- and energy-efficiency compared to state-of-the-art CS and machine learning engines.


  • Open Access

    Compressed-Domain ECG-Based Biometric User Identification Using Compressive Analysis

    by Ching-Yao Chou, Yo-Woei Pua, Ting-Wei Sun, An-Yeu (Andy) Wu

    Nowadays, user identification plays a more and more important role for authorized machine access and remote personal data usage. For reasons of privacy and convenience, biometrics-based user identification, such as iris, fingerprint, and face ID, has become mainstream methods in our daily lives. However, most of the biometric methods can be easily imitated or artificially cracked. New types of biometrics, such as electrocardiography (ECG), are based on physiological signals rather than traditional biological traits. Recently, compressive sensing (CS) technology that combines both sampling and compression has been widely applied to reduce the power of data acquisition and transmission. However, prior CS-based frameworks suffer from high reconstruction overhead and cannot directly align compressed ECG signals. In this paper, in order to solve the above two problems, we propose a compressed alignment-aided compressive analysis (CA-CA) algorithm for ECG-based biometric user identification. With CA-CA, it can avoid reconstruction and extract information directly from CS-based compressed ECG signals to reduce overall complexity and power. Besides, CA-CA can also align the compressed ECG signals in the eigenspace-domain, which can further enhance the precision of identifications and reduce the total training time. The experimental result shows that our proposed algorithm has a 94.16% accuracy based on a public database of 22 people.


  • Robust and Lightweight Ensemble Extreme Learning Machine Engine Based on Eigenspace Domain for Compressed Learning

    by Huai-Ting Li, Ching-Yao Chou, Yi-Ta Chen, Sheng-Hui Wang, An-Yeu Wu

    Compressive sensing (CS) is applied to electrocardiography (ECG) telemonitoring system to address the energy constraint of signal acquisition in sensors. In addition, on-sensor-analysis transmitting only abnormal data further reduces the energy consumption. To combine both advantages, ``On-CS-sensor-analysis'' can be achieved by compressed learning (CL), which analyzes signals directly in compressed domain. Extreme learning machine (ELM) provides an effective solution to achieve the goal of low-complexity CL. However, single ELM model has limited accuracy and is sensitive to the quality of data. Furthermore, hardware non-idealities in CS sensors result in learning performance degradation. In this work, we propose the ensemble of sub-eigenspace-ELM (SE-ELM), including two novel approaches: 1) We develop the eigenspace transformation for compressed noisy data, and further utilize a subspace-based dictionary to remove the interferences, and 2) Hardware-friendly design for ensemble of ELM provides high accuracy while maintaining low complexity. The simulation results on ECG-based atrial fibrillation show the SE-ELM can achieve the highest accuracy with 61.9% savings of the required multiplications compared with conventional methods. Finally, we implement this engine in TSMC 90 nm technology. The postlayout results show the proposed CL engine can provide competitive area- and energy-efficiency compared to existing machine learning engines.


  • Variation-Aware Reliable Many-Core System Design by Exploiting Inherent Core Redundancy

    by Huai-Ting Li, Ching-Yao Chou, Yuan-Ting Hsieh, Wei-Ching Chu, An-Yeu Wu

    Reliability issues are more severe in multi/many-core systems because of the integration of more devices in advanced technology nodes. To achieve robust computing in nanoscale designs, many circuit-level and architecture-level redundancy techniques had been proposed, which pose large fixed silicon area overhead and a lack of flexibility. In recent years, some methods have exploited the “inherent core redundancy” of many-core systems to implicitly implement N-modular redundant (NMR) subsystems to achieve area-efficient fault-tolerant computing. However, while facing the different levels of soft error rate, task vulnerability, and task significance in the many-core system, existing core-level redundancy methods become ineffective. To achieve robust computation in many-core systems with intercore variations and mixed workloads, we propose a variation-aware core-level redundancy scheme. Two novel approaches are presented in this scheme: 1) we construct NMR tables that store the degree of redundancy using mathematical models for systems affected by these variations and 2) we dynamically allocate each replicated task to a proper core with variation-aware mapping algorithms to achieve high reliability. Based on a modified multicore simulator, Sniper-Transient Error Process Variation (TEVR), the experimental results show that the proposed scheme can increase the reliability by 47.92% and achieve the energy saving of 39% compared with conventional core-level redundancy methods.