{"id":9107,"date":"2024-02-05T11:39:55","date_gmt":"2024-02-05T19:39:55","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=9107"},"modified":"2025-04-24T17:03:19","modified_gmt":"2025-04-24T17:03:19","slug":"room-occupancy-detection","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\/","title":{"rendered":"Room Occupancy Detection"},"content":{"rendered":"\n
\"a<\/figure>\n\n\n\n

This project aims to predict whether a room is occupied based on the data collected from the sensors. The data set is collected from the UCI Machine Learning Repository. The data set contains 7 attributes: date, temperature, humidity, light, CO2, humidity ratio, and occupancy. The data set is divided into 2 data sets for training and testing. It provides experimental data for binary classification (room occupancy of an office room) from Temperature, Humidity, Light, and CO2. Ground-truth occupancy was obtained from time-stamped pictures that were taken every minute.<\/p>\n\n\n\n

Data Dictionary<\/h3>\n\n\n\n
\"\"\/
Figure 1: Data Dictionary of the dataset<\/figcaption><\/figure>\n\n\n\n

 <\/p>\n\n\n\n

Importing the required libraries<\/p>\n\n\n\n

import<\/span> numpy as<\/span> np\nimport<\/span> pandas as<\/span> pd\nimport<\/span> matplotlib.pyplot as<\/span> plt\nimport<\/span> seaborn as<\/span> sns<\/span><\/pre>\n\n\n\n
Loading two datasets and combining them into one dataset<\/p>\n\n\n\n
#loading the datasets<\/span>\ndf1 = pd.read_csv('datatest.csv'<\/span>)\ndf2 = pd.read_csv('datatraining.csv'<\/span>)<\/span><\/pre>\n\n\n\n
Combining the datasets<\/p>\n\n\n\n
df = pd.concat([df1,df2])\ndf.head()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 2: Data frame<\/figcaption><\/figure>\n\n\n\n
Data Preprocessing<\/h3>\n\n\n\n
Checking the number of rows and columns in the dataset<\/p>\n\n\n\n
#number of rows and columns<\/span>\ndf.shape<\/span><\/pre>\n\n\n\n
Checking for null\/missing values<\/p>\n\n\n\n
df.isnull().sum<\/span>()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 3: null value count<\/figcaption><\/figure>\n\n\n\n
Checking for duplicate values<\/p>\n\n\n\n
df.duplicated().sum<\/span>()\n=> 27<\/span><\/span><\/pre>\n\n\n\n
The dataset has 27 duplicate values. I will drop these duplicate values.<\/p>\n\n\n\n
#removing the duplicate values<\/span>\ndf.drop_duplicates(inplace=True<\/span>)<\/span><\/pre>\n\n\n\n
Checking the data types of each column<\/p>\n\n\n\n
#checking data types<\/span>\ndf.dtypes<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 4: Dataset datatypes<\/figcaption><\/figure>\n\n\n\n
Since the column date has an object datatype, I am converting it to the datetime datatype.<\/p>\n\n\n\n
#converting the date and time to datetime format<\/span>\ndf['date'<\/span>] = pd.to_datetime(df['date'<\/span>])<\/span><\/pre>\n\n\n\n
Descriptive Statistics<\/p>\n\n\n\n
#checking the descriptive statistics<\/span>\ndf.describe()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 5: Descriptive Statistics<\/figcaption><\/figure>\n\n\n\n
Exploratory Data Analysis<\/h3>\n\n\n\n
In the exploratory data analysis, we will be looking at the distribution of the data, along with the time series of the data. We will also be looking at the correlation between the variables.<\/p>\n\n\n\n
Visualizing the Temperature Fluctuations Over Time<\/h4>\n\n\n\n
#lineplot for temperature changes for time<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.lineplot(x='date'<\/span>,y='Temperature'<\/span>,data=df)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 6: Temperature vs. Time Graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The spikes in the graph indicate that the room temperature increases suddenly, which might be due to the presence of people in the room. The room’s temperature may increase due to the heat emitted by the human body.<\/p>\n\n\n\n
Visualizing the Humidity Fluctuations Over Time<\/h4>\n\n\n\n
#lineplot for humidity changes for time<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.lineplot(x='date'<\/span>,y='Humidity'<\/span>,data=df)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 7: Humidity vs. Time Graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The line graph between the 3rd and 6th of February is similar to the temperature graph, possibly due to the presence of people in the room. However, from the 7th of February onwards, there has been a significant rise in the humidity levels, which might be due to the cleaning of the room or a change in the weather conditions. Room cleaning, such as sweeping the floor, might be the reason for the sudden rise in the humidity levels. But it couldn’t explain the increase in the humidity levels near the 10th of February.<\/p>\n\n\n\n
Visualizing the Light Fluctuations Over Time<\/h4>\n\n\n\n
#lineplot for light changes for time<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.lineplot(x='date'<\/span>,y='Light'<\/span>,data=df)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 8: Light Intensity vs. Time Graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
Looking closely, we can see that the number of peaks in this graph and the temperature graph are the same. This indicates that the lights were turned on when a person was in the room. This is a good indicator of the occupancy of the room.<\/p>\n\n\n\n
Visualizing the CO2 Fluctuations Over Time<\/h4>\n\n\n\n
#lineplot for co2 changes for time<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.lineplot(x='date'<\/span>,y='CO2'<\/span>,data=df)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 9: CO2 Levels vs. Time graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The CO2 graph also shows the spikes in the CO2 levels, which indicates the presence of a person in the room, assuming that there is no other source of CO2 in the room. In addition, the spikes correspond with the temperature graph and light graph. However, from the 7th to the 9th of February, the CO2 levels were minimal, indicating that the room was not occupied during that time. This observation contradicts the humidity graph and temperature graph.<\/p>\n\n\n\n
Visualizing the Humidity Ratio Fluctuations Over Time<\/h4>\n\n\n\n
#lineplot for humidity ratio changes for time<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.lineplot(x='date'<\/span>,y='HumidityRatio'<\/span>,data=df)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 10: Humidity Ratio Vs Time graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The humidity ratio graph is quite similar to the humidity graph. The spikes in the graph indicate the presence of people in the room. Moreover, the same assumption is made about the humidity ratio after the 9th of February.<\/p>\n\n\n\n
Correlation Between the Variables<\/h3>\n\n\n\n
Correlation Heatmap<\/h4>\n\n\n\n
#correlation heatmap<\/span>\nplt.figure(figsize=(20<\/span>,10<\/span>))\nsns.heatmap(df.corr(),annot=True<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 11: Correlation Heatmap<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
There is a strong correlation between light and occupancy as well as between humidity and humidity ratio. The CO2 levels and temperature also show a strong correlation with the occupancy. However, the humidity and humidity ratio has little correlation with the occupancy.<\/p>\n\n\n\n
Temperature and Occupancy<\/h4>\n\n\n\n
#violinplot for temperature<\/span>\nsns.violinplot(y = df['Temperature'<\/span>],x = df['Occupancy'<\/span>])\nplt.xlabel('Occupancy'<\/span>)\nplt.ylabel('Temperature'<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 12: Temperature vs. Occupancy graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The temperature and occupancy graph shows that the room temperature increases when a person is in the room because of the heat emitted by the human body. The room’s temperature decreases when there is no person in the room. This proves the hypothesis regarding the peaks in the temperature graph.<\/p>\n\n\n\n
Light and Occupancy<\/h4>\n\n\n\n
#boxplot for light<\/span>\nsns.boxplot(y = df['Light'<\/span>],x = df['Occupancy'<\/span>])\nplt.xlabel('Occupancy'<\/span>)\nplt.ylabel('Light'<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 13: Light Intensity Vs Occupancy Graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The light intensity of the room increases when there is a person in the room. This is because the lights are turned on when a person is in the room. The light intensity of the room decreases when there is no person in the room. This proves the hypothesis regarding the peaks in the light graph. The outliers in the boxplot and the curves in the light graph might be due to sunlight entering the room.<\/p>\n\n\n\n
CO2 and Occupancy<\/h4>\n\n\n\n
#violinlot for co2<\/span>\nsns.violinplot(y = df['CO2'<\/span>],x = df['Occupancy'<\/span>])\nplt.xlabel('Occupancy'<\/span>)\nplt.ylabel('CO2'<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 14: CO2 Levels Vs Occupancy Graph<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
The CO2 levels of the room increase when there is a person in the room because of the CO2 emitted by the human body. The CO2 levels of the room decrease when there is no person in the room. This proves the hypothesis regarding the peaks in the CO2 graph.<\/p>\n\n\n\n
From the above EDA, it is clear that the room’s temperature, light, and CO2 levels are good occupancy indicators. Therefore, we will be using these three variables for our classification model.<\/p>\n\n\n\n
Data Preprocessing 2<\/h3>\n\n\n\n
Dropping the columns to reduce the dataset dimensionality<\/p>\n\n\n\n
#dropping columns humidity, date and humidity ratio<\/span>\ndf.drop(['Humidity'<\/span>,'date'<\/span>,'HumidityRatio'<\/span>],axis=1<\/span>,inplace=True<\/span>)<\/span><\/pre>\n\n\n\n
df.head(10<\/span>)<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 15: Final Dataset<\/figcaption><\/figure>\n\n\n\n
Train Test Split<\/h3>\n\n\n\n
Splitting the dataset for training and testing the machine learning model<\/p>\n\n\n\n
from<\/span> sklearn.model_selection import<\/span> train_test_split\nx_train,x_test,y_train,y_test = train_test_split(df.drop(['Occupancy'<\/span>],axis=1<\/span>),df['Occupancy'<\/span>],test_size=0.2<\/span>,random_state=42<\/span>)<\/span><\/pre>\n\n\n\n
Model Building<\/h3>\n\n\n\n
Random Tree Classifier<\/h4>\n\n\n\n
from<\/span> sklearn.ensemble import<\/span> RandomForestClassifier\nrfc = RandomForestClassifier()\nrfc<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 16: Random Forest Classifier<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
Training the model<\/p>\n\n\n\n
#training the model<\/span>\nrfc.fit(x_train,y_train)\n#training accuracy<\/span>\nrfc.score(x_train,y_train)\n=> 0.96<\/span><\/span><\/pre>\n\n\n\n
Model Evaluation<\/h3>\n\n\n\n
Predicting values from the model<\/p>\n\n\n\n
rfc_pred = rfc.predict(x_test)<\/span><\/pre>\n\n\n\n
Confusion Matrix Heatmap<\/h4>\n\n\n\n
#confusion matrix heatmap<\/span>\nfrom<\/span> sklearn.metrics import<\/span> confusion_matrix\nsns.heatmap(confusion_matrix(y_test,rfc_pred),annot=True<\/span>)\nplt.ylabel('Predicted'<\/span>)\nplt.xlabel('Actual'<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 17: Confusion Matrix Heatmap<\/figcaption><\/figure>\n\n\n\n
Distribution Plot<\/h4>\n\n\n\n
#distribution plot for the predicted and actual values<\/span>\nax = sns.distplot(y_test,hist=False<\/span>,label='Actual'<\/span>, color='r'<\/span>)\nsns.distplot(rfc_pred,hist=False<\/span>,label='Predicted'<\/span>,color='b'<\/span>,ax=ax)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 18: Distribution Plot<\/figcaption><\/figure>\n\n\n\n
Classification Report<\/h4>\n\n\n\n
from<\/span> sklearn.metrics import<\/span> classification_report\nprint<\/span>(classification_report(y_test,rfc_pred))<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 19: Classification Report<\/figcaption><\/figure>\n\n\n\n
Model Metrics Evaluation<\/h4>\n\n\n\n
from<\/span> sklearn.metrics import<\/span> accuracy_score\nfrom<\/span> sklearn.metrics import<\/span> precision_score\nfrom<\/span> sklearn.metrics import<\/span> recall_score\nfrom<\/span> sklearn.metrics import<\/span> f1_score\n\nprint<\/span>('Accuracy Score : '<\/span> + str<\/span>(accuracy_score(y_test,rfc_pred)))\nprint<\/span>('Precision Score : '<\/span> + str<\/span>(precision_score(y_test,rfc_pred)))\nprint<\/span>('Recall Score : '<\/span> + str<\/span>(recall_score(y_test,rfc_pred)))\nprint<\/span>('F1 Score : '<\/span> + str<\/span>(f1_score(y_test,rfc_pred)))<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 20: Model Metrics<\/figcaption><\/figure>\n\n\n\n
Testing the Model on the New Dataset<\/h3>\n\n\n\n
Loading the dataset<\/p>\n\n\n\n
df_new = pd.read_csv('datatest2.csv'<\/span>)\ndf_new.head()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 21: Testing Dataset<\/figcaption><\/figure>\n\n\n\n
 <\/p>\n\n\n\n
Making similar changes to the testing dataset<\/p>\n\n\n\n
#dropping columns humidity, date and humidity ratio<\/span>\ndf_new.drop(['Humidity'<\/span>,'date'<\/span>,'HumidityRatio'<\/span>],axis=1<\/span>,inplace=True<\/span>)\n\n#splitting the target variable<\/span>\nx = df_new.drop(['Occupancy'<\/span>],axis=1<\/span>)\ny = df_new['Occupancy'<\/span>]<\/span><\/pre>\n\n\n\n
Predicting the values from the test dataset<\/p>\n\n\n\n
#predicting the values<\/span>\npred = rfc.predict(x)<\/span><\/pre>\n\n\n\n
Confusion Matrix Heatmap<\/h4>\n\n\n\n
#confusion matrix heatmap<\/span>\nsns.heatmap(confusion_matrix(y,pred),annot=True<\/span>)\nplt.ylabel('Predicted'<\/span>)\nplt.xlabel('Actual'<\/span>)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 22: Confusion Matrix Heatmap<\/figcaption><\/figure>\n\n\n\n
Distribution Plot<\/h4>\n\n\n\n
#distribution plot for the predicted and actual values<\/span>\nax = sns.distplot(y,hist=False<\/span>,label='Actual'<\/span>, color='r'<\/span>)\nsns.distplot(pred,hist=False<\/span>,label='Predicted'<\/span>,color='b'<\/span>,ax=ax)\nplt.show()<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 23: Distribution Plot<\/figcaption><\/figure>\n\n\n\n
Classification Report<\/h4>\n\n\n\n
print<\/span>(classification_report(y,pred))<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 24: Classification Report<\/figcaption><\/figure>\n\n\n\n
Model Metrics<\/h4>\n\n\n\n
print<\/span>('Accuracy Score : '<\/span> + str<\/span>(accuracy_score(y,pred)))\nprint<\/span>('Precision Score : '<\/span> + str<\/span>(precision_score(y,pred)))\nprint<\/span>('Recall Score : '<\/span> + str<\/span>(recall_score(y,pred)))\nprint<\/span>('F1 Score : '<\/span> + str<\/span>(f1_score(y,pred)))<\/span><\/pre>\n\n\n\n
\"\"\/
Figure 25: Model Metrics<\/figcaption><\/figure>\n\n\n\n
Conclusion<\/h3>\n\n\n\n
The above models show that the Random Forest Classifier has the highest accuracy score of 98%. Therefore, we will use the Random Forest Classifier for our final model. The exploratory data analysis found that the change in room temperature, CO levels, and light intensity can be used to predict the room occupancy in place of humidity and humidity ratio.<\/p>\n","protected":false},"excerpt":{"rendered":"
This project aims to predict whether a room is occupied based on the data collected from the sensors. The data set is collected from the UCI Machine Learning Repository. The data set contains 7 attributes: date, temperature, humidity, light, CO2, humidity ratio, and occupancy. The data set is divided into 2 data sets for training […]<\/p>\n","protected":false},"author":120,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"customer_name":"","customer_description":"","customer_industry":"","customer_technologies":"","customer_logo":"","footnotes":""},"categories":[7],"tags":[],"coauthors":[217],"class_list":["post-9107","post","type-post","status-publish","format-standard","hentry","category-tutorials"],"yoast_head":"\nRoom Occupancy Detection - Comet<\/title>\n<meta name=\"description\" content=\"In this project, walk through a tutorial to detect room occupancy using machine learning. Learn more today.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Room Occupancy Detection\" \/>\n<meta property=\"og:description\" content=\"In this project, walk through a tutorial to detect room occupancy using machine learning. Learn more today.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\" \/>\n<meta property=\"og:site_name\" content=\"Comet\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cometdotml\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-05T19:39:55+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-24T17:03:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw\" \/>\n<meta name=\"author\" content=\"Sukhman Singh\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@Cometml\" \/>\n<meta name=\"twitter:site\" content=\"@Cometml\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sukhman Singh\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"12 minutes\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Room Occupancy Detection - Comet","description":"In this project, walk through a tutorial to detect room occupancy using machine learning. Learn more today.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection","og_locale":"en_US","og_type":"article","og_title":"Room Occupancy Detection","og_description":"In this project, walk through a tutorial to detect room occupancy using machine learning. Learn more today.","og_url":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection","og_site_name":"Comet","article_publisher":"https:\/\/www.facebook.com\/cometdotml","article_published_time":"2024-02-05T19:39:55+00:00","article_modified_time":"2025-04-24T17:03:19+00:00","og_image":[{"url":"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw","type":"","width":"","height":""}],"author":"Sukhman Singh","twitter_card":"summary_large_image","twitter_creator":"@Cometml","twitter_site":"@Cometml","twitter_misc":{"Written by":"Sukhman Singh","Est. reading time":"12 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#article","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\/"},"author":{"name":"Sukhman Singh","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/03fee0ceb719563b09dcf21796f85455"},"headline":"Room Occupancy Detection","datePublished":"2024-02-05T19:39:55+00:00","dateModified":"2025-04-24T17:03:19+00:00","mainEntityOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\/"},"wordCount":1075,"publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#primaryimage"},"thumbnailUrl":"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw","articleSection":["Tutorials"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection\/","url":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection","name":"Room Occupancy Detection - Comet","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#primaryimage"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#primaryimage"},"thumbnailUrl":"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw","datePublished":"2024-02-05T19:39:55+00:00","dateModified":"2025-04-24T17:03:19+00:00","description":"In this project, walk through a tutorial to detect room occupancy using machine learning. Learn more today.","breadcrumb":{"@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#primaryimage","url":"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw","contentUrl":"https:\/\/cdn-images-1.medium.com\/max\/800\/0*f4InbS30yYQNzidw"},{"@type":"BreadcrumbList","@id":"https:\/\/www.comet.com\/site\/blog\/room-occupancy-detection#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.comet.com\/site\/"},{"@type":"ListItem","position":2,"name":"Room Occupancy Detection"}]},{"@type":"WebSite","@id":"https:\/\/www.comet.com\/site\/#website","url":"https:\/\/www.comet.com\/site\/","name":"Comet","description":"Build Better Models Faster","publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.comet.com\/site\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.comet.com\/site\/#organization","name":"Comet ML, Inc.","alternateName":"Comet","url":"https:\/\/www.comet.com\/site\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","width":310,"height":310,"caption":"Comet ML, Inc."},"image":{"@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/cometdotml","https:\/\/x.com\/Cometml","https:\/\/www.youtube.com\/channel\/UCmN63HKvfXSCS-UwVwmK8Hw"]},{"@type":"Person","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/03fee0ceb719563b09dcf21796f85455","name":"Sukhman Singh","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/image\/cbb8e2cab1e32e43711b4e44c7711e76","url":"https:\/\/secure.gravatar.com\/avatar\/2e74502dcaa20f8fe126f4e1eef424b9227d93803c9cc857de010fbca0b41265?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2e74502dcaa20f8fe126f4e1eef424b9227d93803c9cc857de010fbca0b41265?s=96&d=mm&r=g","caption":"Sukhman Singh"},"url":"https:\/\/www.comet.com\/site\/blog\/author\/sukhmansinghbhogalgmail-com\/"}]}},"_links":{"self":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9107","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/users\/120"}],"replies":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/comments?post=9107"}],"version-history":[{"count":1,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9107\/revisions"}],"predecessor-version":[{"id":15392,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9107\/revisions\/15392"}],"wp:attachment":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media?parent=9107"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/categories?post=9107"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/tags?post=9107"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/coauthors?post=9107"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}