• Study Helper - Most people suffer from CVS problem nowadays. To help people avoid this situation, we want to build a fatigue detection system which help people more healthier with computer.Our project present a system which uses environment status (including sound, light, temperature) and Perclose data to predict the potential working time for people which help them to avoid the potential fatigue. 
• Item Tracker - RFID and Vision based solution to track household items.
• Smart Dining - Get Credits for Ordering Line-waiting Food When You Save Food In Dining Hall: (i)  Credit system will allow users to place orders online so that they don’t have to wait in line in person to have freshly cooked meals, e.g., pasta in Ferris Booth and breakfast in JJ’s place.;  (ii) Intelligent trash bin rewards users with credits if they throw empty plates. In this way, users will be encouraged to save food, and can use credits to save time later when in need.
• Smart Elevator System - As inspired by the elevators’ performance in Mudd Building, we observed the traveling times are usually long when multiple people step into the lobby at the same time due to random allocation. Hence, we improved office buildings’ elevator performance under such conditions. Furthermore, facial recognition was also incorporated by our system, which could implement floor selection and cooperate with security systems.
• Smart Home Monitor - In this project, we designed a smart Home Monitor that could measure, monitor and display the home condition, and improve the home security with face recognition remotely. Our main technical challenges are real-time temperature display in our website and face recognition implementation. We found a lot of relative resource online and compared different results to select the better one. Finally, we finished our project successfully with all of our features  working.
• Smart Street Light - Ultrasonic and Zigbee based traffic detecting system.
  In this project, we implement a Smart Street Light system, a ZigBee based vehicle speed detection and traffic condition monitor. The main contributions are: 1 . Connecting the distance sensors and converting distance information into speed information; 2. Connecting the motherboard with all child boards and use both P2P and broadcasting in the system at the same time; 3. Machine learning is used for traffic condition classification.
• A Buffet Monitoring System -  For a buffet, providing  adequate and fresh food is essential. In order to achieve this goal, the restaurant manager must monitor the food. In traditional approach, the manager must check the food condition at regular intervals, which may waste them a lot of time. If a system can monitor the food condition automatically and only alert the manager to replace or refill the food when it is necessary, it may help the buffet to save a lot of manpower, so that the manager can provide a better service to customers. 
• Gesture Control - This project’s goal is to make a deft gesture control device which could provide a user with some simple but direct functions such as controlling a slideshow presentation or other applications on IoT networks without the limitations of complex computations and camera view/quality. The project uses a combination of sensors (accelerometers, IMUs, gyros) to recognize gestures and subsequently control an application. Gesture recognition is implemented by running machine learning algorithm(s) to create suitable models for prediction. Depending on sophistication, gesture control can be used to dictate other IoT networks, robotics, or simply keyboard control.

• Because Your Next Job is Waiting - The first mobile app to connect with employers in real time. Face-to-Face interactions significantly improve one’s ability to judge whether a candidate is a good fit for a job. JustMeet is a mobile application that facilitates in-person interactions between employers and job-seekers. We use smartphone GPS to access user locations and push notifications to communicate between users. We provide a user-friendly application that runs on both IOS and Android. Employers can use the intuitive map interface to display and contact nearby applicants.
• Pet Home Companion - Pet Home Companion is an intelligent system that tracks and monitors the status of a pet, including weight, movement pattern, and daily activity in order to determine the nutrition feeding portion throughout the day. Our solution targets the pet owners that live a busy lifestyle or travel regularly that their pets need to be taken care of without involving the risk of pet sitting or pet boarding. The indoor localization system that we have implemented turned out to be fairly inaccurate, but we have then improved the accuracy significantly through fine-tuning the parameters through linear regression and using least square error solver for coordinate estimation. Finally, through intelligent data collection and processing, we were able to achieve intelligent nutrition feeding based on the weight, movement pattern and daily activity level of the pet.
• Safe Driver - The proposed system aims to make driving safer by alerting the vehicle operator of dangerous behavior that has taken focus away from the primary task of driving. Detecting driving engagement is inherently subjective and therefore complex. By combining several behaviors, including facial detection and certain body movements, we are able to monitor for several types of distracted behaviors. In doing so, we were able to alert drivers to significant deviations in normal driving behavior.
• Intelligent Shopping Cart - The Intelligent Shopping Cart is a smart consumer purchasing product that is designed to help shoppers fast-track their shopping experience. From the moment a shopper puts an item into the cart, the Intelligent Shopping Cart will automatically tracks all the information and ready for final checkout in a decentralized manner. The improvement in the shopping flow reduces shopping and checkout time. 
• Where to Eat at Columbia University Our Smart Dining Hall Recommendation app is an Android application that help users to know current menu, flow rate, and table availability in each three dining halls. It allows users to grade dishes, and later recommends dining hall according to current data to users.
• Lab Occupancy Monitoring System - A real-time occupancy prediction system and interface. Provides a reliable and accurate occupancy prediction.
  Choose the studying meeting place per your preference.
• Smart Refridgerator - Tons of fruit get rotten every day in our refrigerators,
  ​while 821 million people are hungry worldwide. Avoiding waste is a good way to make life better. Moreover, an unhealthy diet may do harm to our body. Our smart refrigerator can make recommendations about fruit recipes, thus help people stay in good health.
• Mindtis: Online ​Psychologist - We propose an emotion recognition system that utilizes machine learning techniques to classify positive and negative emotions and provides result visualizations and recommendations through a web application.
• Smart Fridge by Moha - We have designed a smart fridge that helps users to monitor and track the real-time status of the fridge and get recommendations on foods and recipes. The fridge recognizes every single food that users put in or retrieve out. On our App, users are able to see the real-time collections of current food inside the fridge with corresponding information including food image, weight, calories, expected expiration date as well as some physical stats inside the fridge like temperature and humidity. Also, there are some recommended recipes based on what food they currently have. 

The following companies have generously supported the course by donating development platforms, components and services:

• ​Intel: Intel Edison development kits and Grove starter kits
• Amazon: AWS Educate accounts for faculty and students
• Broadcom: Broadcom WICED sensors​