"""
纺织传感器系统架构

论文使用的纺织传感器配置
"""
TEXTILE_SENSOR_CONFIG = {
    'ecg': {
        'type': '1-lead textile ECG',
        'electrodes': '织物电极（嵌入飞行服）',
        'position': '胸部前方',
        'sampling_rate': 500,  # Hz
        'signal_quality_hypoxia': 93.4,  # %可用
        'signal_quality_gforce': 90.4,
    },
    'respiration': {
        'type': '织物胸廓张力带',
        'position': '胸部环绕',
        'sampling_rate': 100,  # Hz
        'signal_quality_hypoxia': 70.7,
        'signal_quality_gforce': 81.3,
    },
    'environmental': {
        'altitude': '低压舱模拟',
        'g_force': '人体离心机',
        'oxygen_level': '缺氧条件',
    }
}

"""
ECG信号质量评估框架

论文方法：信号质量分级
"""
import numpy as np

class ECGSignalQualityAssessor:
    """
    ECG信号质量评估器
    
    分级标准：
    - Class A: 可用（可提取HR/HRV）
    - Class B: 部分可用（可提取HR，HRV不可靠）
    - Class C: 不可用
    """
    
    QUALITY_THRESHOLDS = {
        'class_a': {'snr': 15, 'r_peak_detectable': True},
        'class_b': {'snr': 8, 'r_peak_detectable': True},
        'class_c': {'snr': 5, 'r_peak_detectable': False},
    }
    
    def assess(self, ecg_signal, condition='normal'):
        """
        评估ECG信号质量
        
        Args:
            ecg_signal: shape=(n_samples,)
            condition: 'normal'/'hypoxia'/'gforce'
            
        Returns:
            quality_class: str, 'A'/'B'/'C'
            features: dict
        """
        # SNR计算
        signal = np.max(np.abs(ecg_signal))
        noise = np.std(ecg_signal - self._denoise(ecg_signal))
        snr = 20 * np.log10(signal / (noise + 1e-10))
        
        # R波检测
        r_peaks = self._detect_r_peaks(ecg_signal)
        r_detectable = len(r_peaks) > len(ecg_signal) / (500 * 2)  # 至少0.5Hz
        
        # 分类
        if snr >= 15 and r_detectable:
            return 'A', {'snr': snr, 'n_peaks': len(r_peaks)}
        elif snr >= 8 and r_detectable:
            return 'B', {'snr': snr, 'n_peaks': len(r_peaks)}
        else:
            return 'C', {'snr': snr, 'n_peaks': len(r_peaks)}
    
    def _denoise(self, signal):
        """简单去噪"""
        from scipy.signal import medfilt
        return medfilt(signal, kernel_size=51)
    
    def _detect_r_peaks(self, signal):
        """R波检测"""
        from scipy.signal import find_peaks
        return find_peaks(signal, distance=250, height=0.5*np.max(signal))[0]


# 论文结果复现
MILITARY_RESULTS = {
    'hypoxia': {
        'ecg_class_a': 93.4,  # % Class A
        'ecg_class_b_or_below': 6.6,
        'resp_usable': 70.7,
        'resp_unusable': 29.3,
    },
    'gforce': {
        'ecg_class_a': 90.4,
        'ecg_class_b_or_below': 9.6,
        'resp_usable': 81.3,
        'resp_unusable': 18.7,
    }
}

"""
汽车座椅纺织ECG方案

借鉴军用飞行服纺织传感器技术
"""
CAR_SEAT_ECG_DESIGN = {
    'electrode_type': '织物电极(碳纤维/银纤维)',
    'position': {
        'back_left': '座椅靠背左侧（接触左背）',
        'back_right': '座椅靠背右侧（接触右背）',
        'reference': '座椅坐垫（接触大腿）',
    },
    'advantages': [
        '无需用户佩戴任何设备',
        '自然接触（靠背+坐垫）',
        '不可见，美观',
        '可加热/通风不影响信号',
    ],
    'challenges': [
        '衣物厚度影响接触阻抗',
        '不同体型接触压力不同',
        '运动伪影（颠簸路面）',
        '长期使用磨损',
    ],
    'expected_performance': {
        'resting_hr_accuracy': '< 3 bpm',
        'hrv_accuracy': 'SDNN误差<10%',
        'stress_detection_accuracy': '~75%',
        'usable_time': '> 85%',
    }
}

class CarSeatECGMonitor:
    """
    汽车座椅ECG监测器
    
    硬件：
    - 3个织物电极（靠背左/靠背右/坐垫参考）
    - AD8232心率监测IC
    - BLE/MCU连接DMS处理器
    """
    
    def __init__(self):
        self.config = CAR_SEAT_ECG_DESIGN
        self.sampling_rate = 250  # Hz（汽车场景可降低）
        self.quality_assessor = ECGSignalQualityAssessor()
        
    def monitor(self, ecg_raw):
        """
        实时监测
        
        Args:
            ecg_raw: shape=(n_samples,), 座椅ECG原始信号
            
        Returns:
            vital_signs: dict
        """
        # 信号质量评估
        quality, metrics = self.quality_assessor.assess(ecg_raw)
        
        if quality == 'C':
            return {'status': 'unavailable', 'reason': 'poor_signal'}
        
        # 提取生命体征
        hr = self._estimate_hr(ecg_raw)
        hrv = self._estimate_hrv(ecg_raw)
        stress_prob = self._estimate_stress(hr, hrv)
        
        return {
            'heart_rate': hr,
            'hrv_sdnn': hrv,
            'stress_probability': stress_prob,
            'signal_quality': quality,
        }
    
    def _estimate_hr(self, ecg):
        """心率估计"""
        from scipy.signal import find_peaks
        peaks, _ = find_peaks(ecg, distance=100, height=0.3*np.max(ecg))
        if len(peaks) < 3:
            return None
        rr = np.diff(peaks) / self.sampling_rate
        hr = 60 / np.mean(rr)
        return hr
    
    def _estimate_hrv(self, ecg):
        """HRV(SDNN)估计"""
        from scipy.signal import find_peaks
        peaks, _ = find_peaks(ecg, distance=100, height=0.3*np.max(ecg))
        if len(peaks) < 5:
            return None
        rr = np.diff(peaks) / self.sampling_rate * 1000  # ms
        return np.std(rr)
    
    def _estimate_stress(self, hr, hrv):
        """压力估计（LF/HF代理）"""
        if hr is None or hrv is None:
            return 0.5  # 默认中等
        # 简化：HR高+HRV低 → 压力高
        stress = min(max((hr - 60) / (100 - 60), 0), 1)
        if hrv < 30:
            stress = min(stress + 0.2, 1.0)
        return stress

class SignalQualityGatedMonitoring:
    """
    信号质量门控监测系统
    
    原则：
    - 高质量信号 → 提取HRV，做精细分析
    - 中等质量信号 → 只提取HR，做粗略分析
    - 低质量信号 → 依赖其他传感器（DMS摄像头rPPG）
    """
    
    def __init__(self):
        self.ecg_quality = ECGSignalQualityAssessor()
        self.rppg_fallback = rPPGStressDetector()  # 降级方案
    
    def monitor(self, ecg_signal, video_frame):
        """多层级监测"""
        quality, _ = self.ecg_quality.assess(ecg_signal)
        
        if quality == 'A':
            # 高质量：ECG精细分析
            return self._ecg_full_analysis(ecg_signal)
        elif quality == 'B':
            # 中等：ECG粗略+视觉辅助
            return self._ecg_basic_plus_rppg(ecg_signal, video_frame)
        else:
            # 低质量：纯视觉rPPG
            return self.rppg_fallback.extract_rppg_signal(video_frame)