1,721,080 research outputs found
On-Chip Epilepsy Detection: Where Machine Learning Meets Patient-Specific Healthcare
No full textDetecting epileptic seizure from EEG/iEEG is challenging due to each patient's onset pattern being very different from each other. To detect such onsets (in real time), the hardware must learn each patient's ictal pattern from the EEG/iEEG traces. This paper describes feature extraction and usage of Support Vector Machine (SVM)-based classifiers to achieve a patient-specific seizure detection System-on-Chip (SoC). Linear SVM (LSVM), Non-Linear SVM (NLSVM), and the Dual Detector Architecture (D(2)A)-SVM are described and compared. We show that when there are a limited number of training sets, the D(2)A-SVM classifier performs well while minimizing the hardware cost. The SoC is implemented and verified.N
Energy-Efficient AI at the edge for Biomedical Applications
No full textThis paper presents a AI-on-the-edge System-on-Chip (SoC) for biomedical applications. For ambulatory tracking and effective treatment of neurological disorders such as seizure and epilepsy, long-term monitoring wearable SoCs is essential to 'close the loop'. To satisfy the wearable form factor, the design challenges at techniques of feature extraction and classification to improve seizure detection accuracy at the Digital Back-End (DBE) must be addressed at a system perspective. Furthermore, future trends of the epilepsy tracking system are discussed.N
Body Coupled Communication: Towards Energy-Efficient Body Area Network Applications
No full textBody Coupled Communication (BCC) utilizes human body itself as a communication medium to provide energy-efficient connectivity between nodes on or around the body. Although BCC is an attractive way for composing a Body Area Network (BAN), the BCC still has several challenges to overcome to be commercially viable. These challenges include 1) varying channel gain over space, time and subject, 2) varying environment, and 3) stringent power consumption requirements. This paper reviews the issues related to BCC, and several efforts to overcome such issues. An example application that benefits from BCC is also discussed.N
Planar-Fabric Circuit Board and Silicon-on-Clothes for wearable healthcare applications
No full textThis paper introduces two emerging wearable technologies: Planar-Fabric Circuit Board (P-FCB) and Silicon-on-Clothes (SoC). P-FCB enables fabric itself to become a circuit board and it maximizes wearer's comfort and safety. Discrete components and dry fabric electrodes made out of P-FCB is discussed and their electrical characteristics are shown. SoC directly integrates silicon chip onto P-FCB to form a system. With these technologies, an example patch sensor is also presented. ©2010 IEEE.N
Area and Energy-Efficient Multi-Channel Instrumentation Amplifiers for Biomedical Applications
No full textRecent biomedical circuit and system often adopt multi-channel instrumentation amplifiers (IA). For such a multichannel environment, the IA should not only consider traditional specifications such as accurate gain, low noise, low power, and offset mitigation but also meet the additional requirements, including small area and small between-channel mismatch. This paper reviews the design requirements and technics for the multichannel IAs targeting biomedical applications, with several implementation examples. It includes Channel-Sharing IA, Orthogonal Frequency-Chopping IA, Group-Chopping IA, and Intrinsic-Feedback Capacitor IA.N
Energy-Efficient Body Area Network Transceiver Using Body-Coupled Communication
No full textThis chapter addresses the challenges and design strategies in body area network (BAN) transceivers. Stringent energy constraint in BAN application means the transceiver circuit must operate in energy-efficient manner. Yet the human body absorbing majority of radio frequency (RF) energy makes the RF-based transceivers unattractive for BAN applications. In this chapter, we discuss an alternative solution which utilizes the human body itself as a communication medium namely the body-coupled communication (BCC).N
Body Area Network: Connecting and powering things together around the human body
No full textA body area network (BAN) provides connectivity and power among on-body/in-body sensors and is an attractive means for realizing the 'human intranet' for health-care, medical, or multimedia applications around the human body [1], [2]. As shown in Figure 1, compared to a WLAN or a wireless personal area network (WPAN), it targets a much smaller range (∼2 m) with greater energy efficiency.N
Body-Coupled Powering for Wearables
No full textProviding power to body-worn sensors and nodes is challenging. Energy Harvesting (EH) often faces source-destination location mismatch issues. Batteries are bulky and lead to "battery anxiety" as the number of nodes increases. Body-Coupled Power (BCP) Transfer and Energy Harvesting, on the other hand, uses the human body as a coupling medium to effectively distribute power on/around the human body. With the BCP, energy harvesters can be used without location constraints, and a single power source can provide power to multiple wearables around the body.N
Body-coupled wireless power transfer and energy harvesting for wearables
No full textWith the growing number of wearables, providing power to the wearables around the body is becoming challenging. Using batteries for each node is inconvenient due to charging overhead. RF-based wireless power transfer (WPT) is limited by the human-body shadowing effect. Many energy harvesting (EH) methods such as PV/tribo/piezoelectric/thermoelectric harvesters have their own limitations when it comes to the wearables. This paper introduces the human body-coupled wireless power transfer/energy harvesting, namely the Body-Coupled Powering (BCP), which overcomes the issues with conventional RF-WPT or EH methods.N
- …
