PRE2022 3 Group3

Group members

Name	Student id	Major
Luta Iulia Andreea	1671685	BCS
Sonia Roberta Maxim	1675656	BCS
Marie Spreen	1909983
Fenna Schipper	1625624	BPT
Hakim Agni	1430149	BCS
Lazgin Mamo	1502506
Dhruv Manohar	1568868

Brainstorming:

- Greenhouse robot

- Piano playing robot

- Drone that detect quality of snow in order to estimate risk of avalanches

- Drones that detect people stuck in places?

- Robot that helps elderly people with education

- Sorting robot for recycling

- Bed that closes in case of eg. earthquakes

Final Idea choice:

Sorting robot for recycling

- Targeting private homes (individual Trashcans with inbuilt sorting function)

-> using affordable materials

-> trash "compression"

- Targeting companies (Sorting arms, larger scale)

- ML approaches for Material classification

Paper about Material Classification with Machine Learning:

https://www.intechopen.com/chapters/75628

The literature review depicted the support vector machine (SVM) and artificial neural network (ANN) techniques as more effective than other ML techniques for material classification. The last section of this chapter includes a python-based ANN model for material classification. This ANN model has been tested for construction items (brick, wood, concrete block, and asphalt) for training and prediction. Moreover, the predictive ANN model results have been shared for the readers, along with the resources and open-source web links.

-> Maybe we can apply this to waste-materials

Game Plan:

Week 01:

- research different areas of Problem

Literature study

Recycling of medical plastics - ScienceDirect [1]

Conclusion:

Plastics have revolutionized medical industry, especially the single use plastic. The common method adopted for disposing medical plastics is incineration that can lead to the release of toxic chemicals and gases. Many of the plastics end up in marine ecosystems detrimentally affecting their survival. Usually, medical plastics are assumed to be infectious and cannot be discarded with the common municipal waste. Moreover, lack of sufficient landfills available have persuaded mankind to think of sustainable recyclable options. Most of the medical plastics have the potential to be recycled back into the petrochemical industry as a feedstock for the production of new plastics or refined fuels. There should be better awareness about recycling possibilities among the healthcare workers and the commitment to collect and recycle the plastic wastes is essential for a sustainable future. Most importantly the plastic devices should be designed such that it is easily recyclable. The outbreak of Covid 19 has increased our dependence on plastics in an unpredictable manner. The outcome would be drastic, finally affecting our future generations. Urgent measures should be taken to properly segregate, sterilize and recycle medical plastics. Multilayer plastics can be replaced by single layer plastics wherever possible. Current recycling strategies can be scaled up and integrated with new sustainable alternatives. This can reduce the accumulation of plastic waste to a certain extend.

Improving waste separation in hospitals - insights for intervention design | Project | BehaviourWorks Australia [2]

Findings:

• One key influence was their access to the appropriate bins. Sometimes bins were placed far away in a corner, blocked by equipment or another (less appropriate) bin would be closer. With regards to recycling, we also learned that available recycling streams in the operating suites not only differed between hospitals but also between rooms within a hospital operating suite. This was sometimes due to a lack of space, where another bin simply wouldn’t fit into an already crowded room.
• We also found out that often by default large rather than small clinical waste bags were used in the operating rooms (even though exceptions exist).
• Time could work as a barrier or facilitator depending on whether nurses felt they had sufficient time to sort waste or had more pressing tasks to attend.
• Nurses’ self-assessed knowledge on correct waste sorting behaviour was fairly high, however, there was still room for improvement.
• Waste support staff also played a role in nurses’ waste separation behaviour. Nurses relied on support staff to line bins appropriately, empty them when full and transport waste out of the operating suite. Unsurprisingly, nurses also identified their colleagues as another key social influence.
• While nurses recognised the positive outcomes of reducing landfill and materials being reused if recycled, they expressed some lack of trust in the overall recycling process, wondering if the items they placed in the recycling bin would actually get recycled once they left the operating suite or the hospital.

Health-care waste (who.int)[3]

Key facts

• Of the total amount of waste generated by health-care activities, about 85% is general, non-hazardous waste.
• The remaining 15% is considered hazardous material that may be infectious, toxic or radioactive.
• Every year an estimated 16 billion injections are administered worldwide, but not all of the needles and syringes are properly disposed of afterwards.
• Open burning and incineration of health care wastes can, under some circumstances, result in the emission of dioxins, furans, and particulate matter.
• Measures to ensure the safe and environmentally sound management of health care wastes can prevent adverse health and environmental impacts from such waste including the unintended release of chemical or biological hazards, including drug-resistant microorganisms, into the environment thus protecting the health of patients, health workers, and the general public.

A Study on AI‐based Waste Management Strategies for the COVID‐19 Pandemic - PMC (nih.gov)[4]

Conclusion

Overall, it can be seen that AI/ML‐based methods can be employed to improve the performance of several different activities in the waste management process that can provide a safe and scalable setup together with the physical measures as laid out in the discussion a long‐term waste management ‐strategy.

Hospital Waste Recycling: The Great Waste Recycling Revolution (tradebe.com) [5]

Waste produced by hospitals and other medical facilities is a largely invisible contributor to environmental degradation. However, when one considers the wide array of establishments that produce medical waste, and the use of single-use sterile equipment across these facilities, their impact quickly becomes apparent. An incredible amount of waste is produced by health clinics, nursing homes, medical research laboratories, dentists, offices, veterinary clinics, and of course hospitals. Incredibly, around 85% of hospital waste is non-hazardous and non-infectious, according to the World Health Organization. The majority of that waste is recyclable, highlighting the need for a robust hospital waste recycling initiative to prevent these safe waste materials from reaching landfills.

AGV Scheduling Optimization for Medical Waste Sorting System

Key facts:

• Traditional manual order picking is extremely susceptible to infection spread among workers and picking errors, while automated medical waste sorting systems can handle large volumes of medical waste efficiently and reliably. Medical waste is infectious, toxic, and hazardous, thus, the application of automated sorting systems can greatly reduce the infection rate of operators and improve the efficiency of medical waste disposal compared with traditional manual sorting.
• The disposal process of medical waste mainly includes classification and collection, transportation, and recycling.
• Due to the large amount of medical waste that needs to be sorted, medical waste recycling and processing centers (MWRPC) face the requirements for small orders, high volume, and strict work schedules, which are similar to e-commerce warehouses.
• The recent outbreak of the novel coronavirus has stimulated the demand for medical services and protective equipment, causing the amount of medical waste to increase exponentially.
• Medical waste is usually divided into five categories: infectious waste, pathological waste, injury waste, pharmaceutical waste, and chemical waste.
• A vertical sorting system might be an optimal solution for sorting medical waste.

Medical Waste-Sorting and Management Practices in Five Hospitals in Ghana

Hospital waste management in Ghana faces the risk of cross-contamination from the lack of thorough sorting of the waste at the points of generation. This has increased the potential for the spread of infections and chemical pollutant.

Conclusion:

A cross-sectional study of waste-sorting and management practices in five hospitals in Ghana has shown that even though there were attempts to segregate hospital waste, particularly in the high-risk areas, the lack of a uniform color coding and labeling system for the different categories of hospital waste affects the efficiency of collection and handling and the integrity of the final waste treatment processes. Significant differences in waste-sorting behavior among health staff were apparent only on the basis of occupation or work area. A number of incinerators for burning infectious waste are either not functioning or are operated outside their capacities or appropriate uses. Current incinerators are unable to inactivate pathogens. Chemical agents like PCDDs/Fs and PCBs are likely released in the exhausts, which calls for the need to install air pollution control devices (APCDs). It is recommended that refresher training courses are periodically organized for health workers to conscientize them on laboratory and general health safety. There is a need for an integrated approach to healthcare waste management in Ghana that will entail the coordinated efforts of the assemblies as well as the Ministry of Health and private companies contracted to collect, transport, and dispose of waste. Since 80–85% of wastes generated in health facilities are of no risk and comparable to domestic waste, they can be separated and handled together with the municipal waste streams while the infectious ones are treated specially, either on-site or sent to designated engineered incinerators.

Machine Learning and IoT-Based Waste Management Model

The waste-collecting trucks collect waste just once or twice in seven days. Due to improper waste collection practices, the waste in the dustbin is spread on the streets. Thus, to defeat this situation, an efficient solution for smart and effective waste management using machine learning (ML) and the Internet of Things (IoT) is proposed. In the proposed solution, there have used an Arduino UNO microcontroller, ultrasonic sensor, and moisture sensor. Using image processing, one can measure the waste index of a particular dumping ground. A hardware prototype is also developed for the proposed framework.

Module 2: The Healthcare Waste Management System

A PowerPoint presentation about Waste Minimization in Health Facilities. For example:

• Inventory control in pharmacy and stockroom
• Employing reusable and recycled products
• Solvent recovery in the hospital laboratory
• Silver recovery in the x-ray department

Classification of Trash for Recyclability Status

Conclusion:

The classification of trash into various categories; glass, paper, plastic, cardboard, metal and trash, is possible through machine learning and computer vision algorithms. Trash classification based on images of trash has been trained using both a support vector machine (SVM) and a convolutional neural network (CNN). However, in order to create a more accurate system, there needs to be a continuously growing data source and the optimal hyperparameters for the CNN must still be found.

Sonia:

Managing barriers to recycling in the Operating Room, The American Journal of Surgery

• It is very often unclear which Operating room items are recyclable and the greatest barrier to recycling is lack of knowledge.
• Up to 90% of “red-bag” waste does not meet criteria for “red-bag” waste - common items are mistakenly disposed of in red bags are vent tubing, suction tubes, IV bags, foley bags, foley catheters, masks, casts and splints, urinals, and bedpans.
• Addressing this issues could significantly reduce waste and save a lot of money

A circular healthcare economy; a feasibility study to reduce surgical stainless steel waste, Sustainable Production and Consumption. Elsevier.

Talks about reducing surgical stainless steel waste by recycling and sterilizing it. Presents several statistics on this topic and an experiment which in the end proves that a circular approach towards reusing discarded hospital instruments and stainless steel waste is indeed feasible and furthermore, it saves money.

Where does hospital waste go? medical waste disposal explained, CleanRiver.

• 85% of hospital waste is noninfectious – most of these materials end up in landfills or get burned.  
• One of the biggest issues facing hospital waste challenges is “Over-classification” of waste related to “red bag” waste – they are filled incorrectly.“Over-classification” of waste refers to a large issue occurring in most medical facilities - regular waste, such as pop cans, bottles, paper, food waste, etc. end up being tossed in the “red bag” bins by patients or staff which are reserved to collect medical waste only.
• Problem: Red Bag waste can be up to 20X more expensive to haul than a hospital’s regular waste streams! Red bag waste is for anything contaminated with blood, infectious material, or other bodily fluids.

The recycling of medical waste (no date) Frst Solutions GmbH.

• 2 million tons of medical waste produces yearly – best way to deal with this: shredded then wet steam sterilization.

There are companies specializes in this:

1. AMB, a company based in Belgium
2. ECODAS based in France
3. WastinnovaIn, a company in Zimbabwe

A review on Medical Waste Management: Treatment, recycling, and disposal options, MDPI.

Lazgin :

•   the wastes from hospitals and health-care systems are not required to be treated to remove health-care chemicals. Municipal wastewater treatment plants are not designed to remove these chemicals and at best result in incomplete removal and lead to formation of transformation products, which may still be a concern in the environment. In some instances, the transformation products may even be more toxic than the parent compounds.
• Once released into the waste stream, the contaminants from health-care system are subject to several processes that affect how they move around the natural environment and how long they persist in the environment such as sorption, transformation, and degradation (both abiotic and biotic)
• Segregation and categorization of wastes are critical to minimize risk during handling and identify safe transport and treatment requirements.
• The concept of the “circular economy” is gradually being introduced across Europe. The circular economy moves away from a linear economy (make, use, and dispose) in theory enabling products and materials to last longer and virtually eliminating waste (The Waste and Resources Action Programme (WRAP), 2016).
• Identify if the waste needs to be classified—almost all health-care waste would need to be classified unless the material either is not waste or is identified in Article 2 of the Waste Framework Directive 2008/98/EC as being excluded as it is covered by other legislation
• Determine the chemical composition of the waste to determine if it has a hazardous property, which can be found through product manufacturer's safety data sheets,
• Assess the hazardous properties of the waste to see if it contains any of the following hazardous descriptions at relevant concentrations (Jones and Tansey, 2015): H1: Explosive H2: Oxidizing H3A: Highly flammable H3B: Flammable H4: Irritant H5: Harmful H6: Toxic H7: Carcinogenic H8: Corrosive H9: Infectious H10: Toxic for reproduction H11: Mutagenic H12: Substances that release toxic gases H13: Sensitizing H14: Ecotoxic

State of the art

Plastics have been revolutionizing the healthcare system for the last century. Their main advantage is the ease of sterilization compared to traditional materials used in healthcare such as ceramics, glass and metal. The latter materials needed time-consuming sterilization processes, steaming or autoclaving, whereas for plastics, there is a new technology used: gamma sterilization. A special place is occupied by single use plastics that offer an immense health benefit when it comes to maintaining a sterile environment. This was a crucial aspect during the COVID19 pandemic when single use plastic had become part of the daily life of healthcare workers. "There has been a dramatic demand for personal protective equipment (PPE). PPE which includes masks, safety goggles, face shields, hair covers etc. are all made of plastics like polyethylene terephthalate (PET),"

Machines developed that can separate 12 different types of plastic

Researchers from the Department of Biological and Chemical Engineering at Aarhus University have created a new camera technology that can differentiate among 12 types of plastic From these types, PVC, PP, PS, PE, PC, PET, PA12, ABS are frequently used in the healthcare system. For example, Polycarbonate (PC) is usually found in syringes, tubes and stents. The camera technology separates the different types of plastic based on their pure chemical composition. It uses a hyperspectral camera and machine learning algorithms to analyze the type of plastic directly on the conveyor belt.

In comparison, the current technology that usually uses near-infrared technology or density tests, can separate a much smaller variety of plastics and it is not as efficient.

Plastic classification via in-line hyperspectral camera analysis and unsupervised machine learning

Hyperspectral imaging with wavelengths from 955 to 1700 nm on thirteen different plastics analyzed by PCA has shown that the spectral range is sufficient to differentiate plastics. Unsupervised machine learning has proven to cluster the plastic types and the resulting loading matrix correctly classified unknown plastic samples.

Healthcare Plastics Recycling Council (HPRC)

The council showcases multiple case studies run in hospitals regarding plastic recycling. Even though multiple hospitals are planning and developing a recycling program, none of them had promising enough results to make a breakthrough.

• Chicago Regional Recycling Project: HPRC and Plastics Industry Association (PLASTISCS) are currently running a recycling program in the Chicago area. Participating hospitals are Advocate Illinois Masonic Medical Center, and NorthShore University Health System’s Evanston, Skokie, Glenbrook, and Highland Park Hospitals. The project includes various companies providing logistics and recycling support, sustainability management software service, financial support and specialized bags for collection and transportation of the plastic materials.
• Kaiser Permanente and Cleveland Clinic: the approach focuses on external waste recycling companies that will deal with sorting the mixed plastic waste. The programs are not yet running.
• Mayo Clinic: Mayo Clinic’s Healthcare Plastics Recycling Program began in 2013 and from 2016-2017 it saw a 78% increase in recycling the PP, PS and other types of plastic and a 9% increase in recycling PET AND HDPE plastics. The project involves the addition of a baler, a grinder and willing external plastic buyers.

TRASHBOT

Physical implementation of a autonomous sorting waste technology. Developed by cleanrobotics, the technology uses AI and computer vision to detect the recyclables and then applies machine learning algorithms to sort them and divert them into specific bins.

ECODAS & ECOSTERYL

Appendix

Logbook

Week	Name	Total	Breakdown of hours
1	Luta Iulia Andreea		Team formation
	Sonia Roberta Maxim		Team formation
	Marie Spreen		Team formation
	Fenna Schipper		Team formation
	Hakim Agni		Team formation
	Lazgin Mamo		Team formation
	Dhruv Manohar		Team formation
2	Luta Iulia Andreea	3	literature study
	Sonia Roberta Maxim
	Marie Spreen
	Fenna Schipper	6	literature study and meetings
	Hakim Agni
	Lazgin Mamo	6	Literature study (3hours) and meetings (3 hours)
	Dhruv Manohar
2+1/2	Luta Iulia Andreea	5	Research + State of the art
	Sonia Roberta Maxim	5	Research + State of the art
	Marie Spreen
	Fenna Schipper
	Hakim Agni
	Lazgin Mamo
	Dhruv Manohar

5. https://www.sciencedirect.com/science/article/pii/B9780444638571000012