how can I correct predict error in matlab

I coded a source-destination direct link and predicted the received data at the destination using Matlab.It gives an error as "Error using predict ,No valid system or dataset was specified"

1.I generated data set as below as you mentioned.

    clear all;close all;clc;
    bits = randi([0 1], 1000, 1); % generate random bits
    bpsk = 2*bits - 1; % BPSK modulation
    snr = 10; % signal-to-noise ratio in dB
    noisy_bpsk = awgn(bpsk, snr); % add noise to the signal
    newdata = [bpsk ,noisy_bpsk];
    writematrix(newdata, 'tx_rx_data.csv'); %Writing data to .csv file 

2.Training the model with the generated dataset. I used support vector machines.

    %Prepare the dataset
    tx_rx_data = readmatrix('tx_rx_data.csv');
    %Assigning data to X and Y variables
    X = tx_rx_data(:,1);
    Y = tx_rx_data(:,2);
    rand = randperm(10^2);%Generate random nums is equal to rows
                          %divide the data for traing and testing
    Xtr = X(rand(1:length(rand)*0.8) ,:);% 80% for training
    Ytr = Y(rand(1:length(rand)*0.8) ,:);% 80% for training
    Xtest = X(rand(1:length(rand)*0.2) ,:);% 20% for testing
    Ytest = Y(rand(1:length(rand)*0.2) ,:);% 20% for testing
    model_tx_rx_data = fitcecoc(Xtr , Ytr); %used support vector machines
    save model_tx_rx_data;%save the model
                          %Testing the model
    result = predict(model_tx_rx_data , Xtest);
    accuracy =  (sum(result == Ytest)/length(Ytest))*100;
    sp = sprintf("Test Accuracy  = %0.2f" , accuracy);
    disp(sp);

Test Accuracy  = 0.00

3.Testing new data.

    bits = randi([0 1], 1000, 1); % generate random bits
    bpsk = 2*bits - 1; % BPSK modulation
    snr = 10; % signal-to-noise ratio in dB
    noisy_bpsk = awgn(bpsk, snr); % add noise to the signal
    rx_symbols = noisy_bpsk;

    decodedData = real(rx_symbols) ; %Decoder output
                                    %Prepare the dataset for real data
    TrainedmodelRx_data = readmatrix('tx_rx_data.csv');

    %Assigning data to variable
    TrainedmodelRx_data = Trainedmodel_data(:,2);

Unrecognized function or variable 'Trainedmodel_data'.

    %use the trained model to predict the data at Rx
    ML_predicted_receivedData = predict(TrainedmodelRx_data , decodedData);
 
    %TrainedmodelRx_data - Output of the trained model
    %decodedData - output from the decoder at Rx

When I run "Testing new data" file , there is an error "Error using predict, No valid system or dataset was specified. can you tell me the reason for it. Thank you

[Walter Roberson]

    clear all;close all;clc;
    bits = randi([0 1], 1000, 1); % generate random bits
    bpsk = 2*bits - 1; % BPSK modulation
    snr = 10; % signal-to-noise ratio in dB
    noisy_bpsk = awgn(bpsk, snr); % add noise to the signal
    newdata = [bpsk ,noisy_bpsk];
    writematrix(newdata, 'tx_rx_data.csv'); %Writing data to .csv file 
    
    %Prepare the dataset
    tx_rx_data = readmatrix('tx_rx_data.csv');
    %Assigning data to X and Y variables
    X = tx_rx_data(:,1);
    Y = tx_rx_data(:,2);
    rand = randperm(10^2);%Generate random nums is equal to rows
                          %divide the data for traing and testing
    Xtr = X(rand(1:length(rand)*0.8) ,:);% 80% for training
    Ytr = Y(rand(1:length(rand)*0.8) ,:);% 80% for training
    Xtest = X(rand(1:length(rand)*0.2) ,:);% 20% for testing
    Ytest = Y(rand(1:length(rand)*0.2) ,:);% 20% for testing
    model_tx_rx_data = fitcecoc(Xtr , Ytr); %used support vector machines
    save model_tx_rx_data;%save the model
                          %Testing the model
    result = predict(model_tx_rx_data , Xtest);
    accuracy =  (sum(result == Ytest)/length(Ytest))*100;
    sp = sprintf("Test Accuracy  = %0.2f" , accuracy);
    disp(sp);

Test Accuracy  = 5.00

    
    bits = randi([0 1], 1000, 1); % generate random bits
    bpsk = 2*bits - 1; % BPSK modulation
    snr = 10; % signal-to-noise ratio in dB
    noisy_bpsk = awgn(bpsk, snr); % add noise to the signal
    rx_symbols = noisy_bpsk;

    decodedData = real(rx_symbols) ; %Decoder output
                                    %Prepare the dataset for real data
    TrainedmodelRx_data = readmatrix('tx_rx_data.csv');

    %Assigning data to variable
    TrainedmodelRx_data = TrainedmodelRx_data(:,2);

    %use the trained model to predict the data at Rx
    ML_predicted_receivedData = predict(TrainedmodelRx_data , decodedData);

Warning: Data sample time is assumed to be 1 seconds. To specify a different value for the data sample time consider providing data using a timetable or an iddata object.

Error using predict
The "InterSample" property must be a cell array of size Nu-by-Ne, where Nu = number of inputs and Ne = number of experiments in the data set.

 
    %TrainedmodelRx_data - Output of the trained model
    %decodedData - output from the decoder at Rx
    

[Kasun Wickramarathna]

Hi Walter Roberson ,

Thank you very much for the answer.I am still begineer for this area .I checked the dimensions , type of data etc.I could not find the solution.Can you please show me where is the error.

Thank you

[Walter Roberson]

Earlier you had

    model_tx_rx_data = fitcecoc(Xtr , Ytr); %used support vector machines
    %...
    result = predict(model_tx_rx_data , Xtest);

so predict() is being invoked on the result of fitcecoc.

Later you have

    TrainedmodelRx_data = readmatrix('tx_rx_data.csv');
    TrainedmodelRx_data = TrainedmodelRx_data(:,2);

    ML_predicted_receivedData = predict(TrainedmodelRx_data , decodedData);

so predict() is being invoked on numeric data.

predict() is a generally a method of a class -- model_tx_rx_data is a particular class, and the predict() method of that class is being invoked.

When you try to predict() passing in numeric data, you get a completely different predict() that is useless to you.

[Kasun Wickramarathna]

Hi Walter Roberson ,

Thank you for the clarification.It worked.