python实现基于TNDADATASET的人体行为识别

首先来看下TNDADATASET：

 随便打开一个文件简单看下如下所示：

 可以大概推测出来，这里面不同维度的数据集应该是由不同的穿戴式传感器采集得到的，最后一列的class表示的是当前的行为类型。

在我之前的博文里面已经做过了相关的工作了，如下：

《人体行为姿势识别数据集WISDM实践》

《UCI行为识别——Activity recognition with healthy older people using a batteryless wearable sensor Data Set》

所以这里我就不再赘述相关的背景内容性质的东西了，参考前面的文章就懂得这里应该如何来处理数据集了，首先是数据集加载解析处理：

def loadData(path):
    """
    加载解析数据
    """
    all_subject_data = []
    for i in os.listdir(path):
        subject_path = path + i
        subject_data = pd.read_csv(subject_path)
        subject_data.drop(
            index=list(subject_data[subject_data["class"] <= 3].index), inplace=True
        )
        all_subject_data.append(subject_data)
    all_subject_data = pd.concat(all_subject_data, axis=0)
    all_subject_data.drop(
        index=list(all_subject_data[all_subject_data["class"] == 0].index), inplace=True
    )
    X = all_subject_data[
        [
            "wri_Acc_X",
            "wri_Acc_Y",
            "wri_Acc_Z",
            "wri_Gyr_X",
            "wri_Gyr_Y",
            "wri_Gyr_Z",
            "wri_Mag_X",
            "wri_Mag_Y",
            "wri_Mag_Z",
            "ank_Acc_X",
            "ank_Acc_Y",
            "ank_Acc_Z",
            "ank_Gyr_X",
            "ank_Gyr_Y",
            "ank_Gyr_Z",
            "ank_Mag_X",
            "ank_Mag_Y",
            "ank_Mag_Z",
            "bac_Acc_X",
            "bac_Acc_Y",
            "bac_Acc_Z",
            "bac_Gyr_X",
            "bac_Gyr_Y",
            "bac_Gyr_Z",
            "bac_Mag_X",
            "bac_Mag_Y",
            "bac_Mag_Z",
        ]
    ]
    y = all_subject_data["class"]
    return X, y

因为原始数据集中类别不均衡的存在，这里我丢掉了1 2 3这几种类别的行为动作，保留了4 5 6 7 8这五种行为动作的数据。

当然了也是可以全部保留的，本质都是一个多分类的问题。

接下来是特征提取部分，这里我们主要实现了包括：李雅普诺夫指数、递归图特征、庞加莱图特征、拓扑特征、近似熵特征、样本熵特征、模糊熵特征等在内的众多特征提取计算方法，后期可以综合使用。

这里以李雅普诺夫指数为例，看下对应的核心特征提取实现如下：

def lypnf_feature(data):
    """
    李雅普诺夫指数  nolds库
    """
    featuress = []
    for j in tqdm(range(data.shape[0])):
        fea = []
        for i in range(data.shape[2]):
            data_ = data[j, :, i]
            feature = nolds.lyap_e(data_)
            fea = np.hstack((fea, feature))
        if j == 0:
            featuress = np.concatenate((featuress, fea))
        else:
            featuress = np.vstack((featuress, fea))
    return featuress

整体特征工程融合提取存储实现如下：

def buildFeature(dataDir="./TNDADATASET/"):
    """
    特征工程
    """
    data, label = load_data(dataDir)
    data_processed, label_processed = data_preprocesssing(data, label, 128, 64)
    # 特征提取
    in_data_rec = rec_feature(data_processed)
    print("in_data_rec shape:", in_data_rec.shape)
    in_data_poincare = poincare_feature(data_processed)
    print("in_data_poincare shape:", in_data_poincare.shape)
    in_data_topo = topo_feature(data_processed, 5, 5)
    print("in_data_topo shape:", in_data_topo.shape)
    in_data_lypnf = lypnf_feature(data_processed)
    print("in_data_lypnf shape:", in_data_lypnf.shape)
    m = 2
    in_data_apx = apx_feature(data_processed, m)
    print("in_data_apx shape:", in_data_apx.shape)
    m, n = 2, 2
    in_data_fuz = fuz_feature(data_processed, m, n)
    print("in_data_fuz shape:", in_data_fuz.shape)
    m = 1
    in_data_samp = samp_feature(data_processed, m)
    print("in_data_samp shape:", in_data_samp.shape)
    feature = {}
    feature["rec_feature"] = in_data_rec.tolist()
    feature["poincare_feature"] = in_data_poincare.tolist()
    feature["topo_feature"] = in_data_topo.tolist()
    feature["lypnf_feature"] = in_data_lypnf.tolist()
    feature["apx_feature"] = in_data_apx.tolist()
    feature["fuz_feature"] = in_data_fuz.tolist()
    feature["samp_feature"] = in_data_samp.tolist()
    feature["label"] = label_processed.tolist()
    with open("feature.json", "w") as f:
        f.write(json.dumps(feature))
    sample_num = in_data_rec.shape[0]
    rec = in_data_rec.tolist()
    poincare = in_data_poincare.tolist()
    topo = in_data_topo.tolist()
    lypnf = in_data_lypnf.tolist()
    apx = in_data_apx.tolist()
    fuz = in_data_fuz.tolist()
    samp = in_data_samp.tolist()
    labels = label_processed.tolist()
    result = []
    for i in range(sample_num):
        one_vec = rec[i] + poincare[i] + topo[i] + lypnf[i] + apx[i] + fuz[i] + samp[i]
        one_label = labels[i]
        one_vec.append(one_label)
        result.append(one_vec)
    print("result_shape: ", np.array(result).shape)
    with open("allfeature.json", "w") as f:
        f.write(json.dumps(result))

执行耗时较长，输出如下：

 得到所需的特征数据之后就可以构建模型来进行训练测试计算了。

这里的机器学习模型主要是基于sklearn库来进行快速地搭建使用，主要选择了：LR、RF、GBDT、SVM这四种经典的模型进行试验对比分析，如下所示：

 以LR模型为例，看下核心完整构建流程实现如下：

def lrModel(data='feature.json',rationum=0.30,model_path='lr.model'):
    '''
    逻辑回归模型
    '''
    with open(data) as f:
        data_list=json.load(f)
    x_list,y_list=[],[]
    for i in range(len(data_list)):
        y_list.append(data_list[i][-1]) 
        x_list.append(data_list[i][:-1])
    label=list(set(y_list))
    print('y_list: ',label)
    X_train,X_test,y_train,y_test=splitData(x_list, y_list,ratio=rationum)
    model=LogisticRegression()
    model=DecisionTreeClassifier()
    model.fit(X_train,y_train)
    #预测、分析
    y_pred=model.predict(X_test).tolist()
    plotConfusionMatrix(y_test,y_pred,label,save_path=saveDir+'LR.png')
    #计算模型在测试集上的得分
    accuracy=model.score(X_test,y_test)
    print('logisticRegressionModel model_score: ',accuracy)
    Precision,Recall,F1=calThree(y_test,y_pred)
    saveModel(model,save_path=model_path)
    result={}
    result['accuracy'],result['F_value']=accuracy,F1
    result['precision'],result['recall']=Precision,Recall
    print('type: ', type(y_test), type(y_pred))
    result['y_true'],result['y_pred']=y_test,y_pred
    return result

看下对比混淆矩阵，如下所示：

 可以看到：四种不同的模型整体的效果都是很不错的。

之后为了对比深度学习模型与机器学习模型的优劣，我又依次开发了：LSTM、CNN-LSTM、BILSTM三种模型库，时间问题就不再一一解释了，直接看最终的结果：