Search

Parallel to the rapid growth of the population, the rate of consumption is increasing all over the world; this causes significant increases in the amount of waste. Thanks to the recycling of waste, not only environmental pollution is prevented but also a great contribution to the economy is made. One of the basic conditions for ensuring maximum performance in recycling processes is the classification of wastes according to their contents. At this stage, minimizing the human factor is an important issue in terms of time, labor, and performance of recycling facilities. In this research, paper, glass, plastic, and organic waste pictures obtained from the external environment were classified with the help of machine learning techniques. In classification, four- and five-layer deep convolutional neural networks algorithms were used. According to the results of the research, five-layer architecture was able to distinguish the wastes with a 70% accuracy rate. In the research, as the number of layers decreased, the performance values of the networks decreased. In the four-layer architecture, wastes could be separated by a rate of 61.67%. In both network architectures, the accuracy rate in differentiating plastic wastes from other wastes was found to be lower. The accuracy rate in the classification of plastic wastes was determined as 37% and 56.7% in four-layer and five-layer DCNN architectures, respectively. In the research, organic wastes were distinguished with higher accuracy compared to other wastes. The accuracy rate in the classification of organic wastes was determined as 83% and 76.7% in four- and five-layered DCNN architectures, respectively. [ABSTRACT FROM AUTHOR]

Highlights: [•] Paper reviews data on material recycling used in LCAs of waste management systems. [•] In total 366 datasets, from 1980 to 2010, covering 14 materials, were evaluated. [•] Totals for emissions of CO2-equivalent were compared to illustrate variations. [•] The choice of dataset is crucial for the outcome of an LCA on waste management. [•] Recycling in general showed lower emission of CO2/kg material than primary production. [ABSTRACT FROM AUTHOR]

Abstract: This paper reports the results of a multilevel structure equation model predicting general and fraction specific self-reported recycling behaviour. The model was tested on a sample of 697 undergraduate students from four Norwegian universities who each reported their degree of participation in the local recycling schemes for paper/cardboard, glass, metal, and plastic. It was demonstrated that variance in recycling behaviour can be divided into a smaller general part that is relatively stable across waste fractions and a specific part that depends on the respective fraction. General recycling behaviour is well predicted by intentions to recycle and recycling habits, whereas perceived behavioural control is to a large extend fraction specific and influences the fraction specific recycling. Perceived behavioural control mediates the influence of the recycling scheme type, distance to recycling containers, and transport mode used to reach the recycling containers. [Copyright &y& Elsevier]

The article reports that the New Zealand government, through Environment Minister David Benson-Pope, congratulated the country's paper sector for meeting the paperboard recycling target two years ahead of schedule. The sector registered a 72% recovery rate of paperboard packaging ahead of the 2008 target year. He emphasized that the country's recycling targets are comparable with the rates being achieved overseas. Benson-Pope said that the national targets for the recovery of aluminum, glass, steel, and plastic are all proceeding towards their 2008 targets.