Academia.eduAcademia.edu

Figure 10 – uploaded by IOSR Journals

See full PDFdownloadDownload figure
A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI The waste segregator has been successfully implemented for segregation of waste into biodegradable and non- biodegradable waste at a domestic level. However, the noise can be eliminated from the sensor modules to increase the accuracy and efficiency of the system. This system has its own limitations. It can segregate only one type of waste at a time since having different types of wastes at once can create problems in effectively segregating. Thus, improvements can be made to segregate mixed type of waste by the use of buffer spaces. the iterative data-driven methodology for achieving the highest performance where first the existing solution to the problem was assessed, second this solution was optimised using the collected dataset, next, machine learning algorithms were applied to the problem, and finally, the feature engineering was used to find if additional features would improve the results. (Random Forest) allowed significantly improving the performance reaching the accuracy of 99:1 % and the recall of 98:2 %.

Figure 10 A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI The waste segregator has been successfully implemented for segregation of waste into biodegradable and non- biodegradable waste at a domestic level. However, the noise can be eliminated from the sensor modules to increase the accuracy and efficiency of the system. This system has its own limitations. It can segregate only one type of waste at a time since having different types of wastes at once can create problems in effectively segregating. Thus, improvements can be made to segregate mixed type of waste by the use of buffer spaces. the iterative data-driven methodology for achieving the highest performance where first the existing solution to the problem was assessed, second this solution was optimised using the collected dataset, next, machine learning algorithms were applied to the problem, and finally, the feature engineering was used to find if additional features would improve the results. (Random Forest) allowed significantly improving the performance reaching the accuracy of 99:1 % and the recall of 98:2 %.

Related Figures (10)

Enevo one is a comprehensive logistics solution that saves time, money and the environment. It uses wireless sensors to measure and forecast the fill-level of waste containers and generates smart collection plans using the most efficient schedules and routes. The solution provides up to 50% in direct cost savings. Receive automatically generated schedules and optimised routes which take into account an extensive set of parameters future fill level projections, truck availability, traffic information, road restrictions, container and content types the vehicle can collect etc. New schedules and routes are planned not only looking at the current situation, but considering the future outlook as well. Enevo using WSN and Ultrasound sensor for measuring the fill level of waste container [3].
Enevo one is a comprehensive logistics solution that saves time, money and the environment. It uses wireless sensors to measure and forecast the fill-level of waste containers and generates smart collection plans using the most efficient schedules and routes. The solution provides up to 50% in direct cost savings. Receive automatically generated schedules and optimised routes which take into account an extensive set of parameters future fill level projections, truck availability, traffic information, road restrictions, container and content types the vehicle can collect etc. New schedules and routes are planned not only looking at the current situation, but considering the future outlook as well. Enevo using WSN and Ultrasound sensor for measuring the fill level of waste container [3].
It comprises the use of biosensor sensor and weight sensor along with height sensor to sense the run over of the waste in the waste bin and the intensity of pollution caused by undesired poisonous gases from the waste bins. Afterwards, these sensors are fed to the controller to help the GSM module to send the notification to the respective authority about the status of waste bin. SENS Dumper rs wii SENS dumpster filling level monitoring SENS dumpster is an innovative device that monitors the filling level of a dumpster. SENS dumpster works with any kind of waste and fits to any type of dumpster. It makes use of a volumetric sensor that provides information of the level of filing of a dumpsters. SENS dumpster can be applied to any kind of waste, and a temperature sensor is able to detect significant temperature increases that may result in fire. SENS dumpster is a fully ZigBee wireless device that can be integrated to any ZigBee network deployment within the smart-city. BIO Sensor (load sensor)
It comprises the use of biosensor sensor and weight sensor along with height sensor to sense the run over of the waste in the waste bin and the intensity of pollution caused by undesired poisonous gases from the waste bins. Afterwards, these sensors are fed to the controller to help the GSM module to send the notification to the respective authority about the status of waste bin. SENS Dumper rs wii SENS dumpster filling level monitoring SENS dumpster is an innovative device that monitors the filling level of a dumpster. SENS dumpster works with any kind of waste and fits to any type of dumpster. It makes use of a volumetric sensor that provides information of the level of filing of a dumpsters. SENS dumpster can be applied to any kind of waste, and a temperature sensor is able to detect significant temperature increases that may result in fire. SENS dumpster is a fully ZigBee wireless device that can be integrated to any ZigBee network deployment within the smart-city. BIO Sensor (load sensor)
Fig 3 SENS dumpster wireless device to monitor filling level of dumpster. PROPOSED SYSTEM: However, the quality of filling level predictions will determine the efficiency of a Smart Waste Management system. There are several technical challenges for achieving a high quality predictions. Our analysis of an operating Smart Waste Management system revealed that one of these challenges is a problem of an accurate detection of a container being emptied using the measurements from a sensor mounted on top of a container. As it is demonstrated in, the quality of filling level predictions depends on the correct detection of emptying. Inaccurate detections devalue filling level predictions; therefore, detection of container emptying is an integral step in obtaining qualitative predictions. Therefore, this article applies the proposed methodology to the problem of the emptying detection. Moreover, this study for the first time draws attention to the challenges and importance of the emptying detection for the functioning of Smart Waste Management systems.
Fig 3 SENS dumpster wireless device to monitor filling level of dumpster. PROPOSED SYSTEM: However, the quality of filling level predictions will determine the efficiency of a Smart Waste Management system. There are several technical challenges for achieving a high quality predictions. Our analysis of an operating Smart Waste Management system revealed that one of these challenges is a problem of an accurate detection of a container being emptied using the measurements from a sensor mounted on top of a container. As it is demonstrated in, the quality of filling level predictions depends on the correct detection of emptying. Inaccurate detections devalue filling level predictions; therefore, detection of container emptying is an integral step in obtaining qualitative predictions. Therefore, this article applies the proposed methodology to the problem of the emptying detection. Moreover, this study for the first time draws attention to the challenges and importance of the emptying detection for the functioning of Smart Waste Management systems.
A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI Fig 4. Proposed System Architecture diagram
A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI Fig 4. Proposed System Architecture diagram
International organization of Scientific Research
International organization of Scientific Research
A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI
A Structured Process for the Waste Disposal and Maximizing the Recycling of the Waste Using MI
Mr.Murali Krishna Vasantha Working as Asst.Professor, Department Of Computer Science and Engineering in Avanthi Institute of Engineering and Technology Cherukupalli(V), Near TagarapuvalsaBridge, Vizianagaram (Dist) - 531162,Andhra Pradesh. He has More than 11 Years of Teaching Experience in Various Colleges in Andhra Pradesh. His Area of interests include Machine’ Learning, Artificial intelligence, BlockchainTechnology,MEAN Stack,Data mining with Outlier Detection and Microsoft POWER BI Consulting Service . 3 q . é é \ Pheesetti Ganesh Holds a B.Tech Degree in Computer Science & Engineering from Welfare Institute of Science Technology And Management, PINAGADI , PENDURTHY, Vishakapatnam -531 173, Andhra Pradesh. He is presently Pursuing M.Tech (CSE) in Department of Computer Science and Engineering from Avanthi Institute of Engineering and Technology Cherukupalli(V), Near TagarapuvalsaBridge, Vizianagaram (Dist) - 531162,Andhra Pradesh. Area of interest include Full Stack Web application Development, Python Programming, Machine learning and Data science.
Mr.Murali Krishna Vasantha Working as Asst.Professor, Department Of Computer Science and Engineering in Avanthi Institute of Engineering and Technology Cherukupalli(V), Near TagarapuvalsaBridge, Vizianagaram (Dist) - 531162,Andhra Pradesh. He has More than 11 Years of Teaching Experience in Various Colleges in Andhra Pradesh. His Area of interests include Machine’ Learning, Artificial intelligence, BlockchainTechnology,MEAN Stack,Data mining with Outlier Detection and Microsoft POWER BI Consulting Service . 3 q . é é \ Pheesetti Ganesh Holds a B.Tech Degree in Computer Science & Engineering from Welfare Institute of Science Technology And Management, PINAGADI , PENDURTHY, Vishakapatnam -531 173, Andhra Pradesh. He is presently Pursuing M.Tech (CSE) in Department of Computer Science and Engineering from Avanthi Institute of Engineering and Technology Cherukupalli(V), Near TagarapuvalsaBridge, Vizianagaram (Dist) - 531162,Andhra Pradesh. Area of interest include Full Stack Web application Development, Python Programming, Machine learning and Data science.
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved