|
| References | Technique | Goal/objective and limitations |
|
| [11] | IoT-based sensors with Waspmote microcontroller and ZigBee Pro communicator | Reducing the overall cost of operation by finding the best route for garbage collecting vehicles |
| [12] | IoT-based sensors with MSP430 microcontroller |
| [13] | IoT-based sensors with Arduino Uno microcontroller |
| [14] |
| [17] | Integration of IoT and AWS Google computer engine |
| [15] | IoT-based sensors with Raspberry Pi microcontroller | Elimination of human contact by automating the opening and closing of the smart bin |
| [16] | IoT-based sensors with Raspberry Pi microcontroller | Movable and self-opening and closing smart bin to avoid human interaction and maintain hygiene |
| [20] | IoT-based movable bin with L298 N motor driver |
| [21] | Integration of IoT and machine learning algorithm (fuzzy logic) | Select the best site for bin installation based on real-time space and population density in the area |
| [22] | Integration of IoT and machine learning algorithm (linear regression) | Predict the fill-up time of a particular bin |
| [18] | Integration of IoT and (RFID) radio frequency identification | Increase utilization of bin by rewarding points based on weight |
| [23] | Integration of IoT and blockchain |
| [24] | IoT and tensor flow | Waste classification into biodegradable and non-biodegradable waste |
| [25] | Faster region CNN |
| [27] | Identification of e-waste and its subsequent categorization |
| [28] | Recognition of street litter and categorization |
| [29] | Detection of garbage for street cleanliness evaluation |
| [30] | Separation of biodegradable and non-biodegradable waste |
| [31] | YOLOv2 and YOLOv3 CNN | Classification of garbage container after detection |
| [32] | YOLOv3 and YOLOv3 Tiny-CNN | Segregation of waste for recycling and reuse or for disposal |
| [33] | YOLOv2 CNN | Classifying battery-containing devices, detecting batteries, and recognizing battery structures |
|
