சுருக்கம்

Employing Machine Learning To Determine Higher Lifetime Cancer Risks Caused By Crop Residue Utilised As Construction and Building Materials

Arjun Gupta

Recycling agricultural waste in recycling increases the circular economy and environmental sustainability. However, agricultural by-products made from recycling agricultural waste materials include naturally occurring radionuclides that pose a threat to both the environment and human health. In order to prioritise their specialised functions, this article presents a review of the pertinent research on the radiological characteristics of agricultural by products (such as rice husk ash, mussel shell, palm oil clinker, and palm oil fuel ash). As a result, the analysed agricultural by products’ absorbed gamma dose rates, yearly effective dose rates, and extra lifetime cancer risks were calculated. Several machine learning techniques were used to train, validate, and test the specific concentrations of substances, AGDR, AEDR, and ECLR. All agricultural by products that were analysed had their radiological qualities evaluated, and it was determined that none of them It also appeared in previous studies where the main sources of human exposure were reported to be 226Ra, 232Th, and 40K in building and construction materials. Mehta and co[1]. For example, one of the primary findings from the NORM databases stated that around 85% of the garbage had an increased amount of building materials, which produced about 42% of the waste with an excessive gamma dose rate below the permissible range. In an identical example Miranda Rather verified that natural radiation sources account for 70% of the radiation dosage that people inhale. As a result, radon and its products irradiate the cells of the pulmonary system and distribute underneath creating leukaemia and anaemia, and building occupants and potential users are exposed to both internal and external radiation fromNORsfromdirectgammaradiationfromradionuclidesamateedrials us for devevOther cancers including those of the liver, bone, the liver, skin, lung, and kidney, which account for 314% of lung cancer cases and result in 20,000 mortality annually in Europe.Overall, resources must be assessed for potential radioactive materials to show that users can choose their use wisely and reduce any hazards.Relevant research have revealed that some building materials hold a higher lifetime cancer risk than the UNSCEAR world population weighted average, possibly presenting an intrinsic cancer risk. In addition to the data mentioned earlier, it has been discovered that the risk of cancer rises with prolonged contact to these substances.

It becomes very difficult to disregard some recycled waste materials’ viability given the health dangers that they pose.A review of the radioactive danger of all lopment is pertinent and merits investigationfrom the standpoint of radiatection.A growing numer of people are using technology and science to sole challenges.tion pro% of all lung cancers, equivalent to 20,000 deaths annually in Europe . Overall, resources must be evaluated for some building materials surpasses the world population-weighted average by UNSCEAR indicating that potential users have increases with increasing exposure time to these materials. Pereira and Bravo. It operates neurons like Brasov. The machine learning algorithm consists of input compressive strength-based concrete using machine learning models. Strength compared to support vector machine. Yet modelled and Niedostatkiewicz (2019) utilized the state-of-the-art achievements [3]. In machine learning techniques for concrete mix design the results that can be used in practical applications. Predicted alligator and longitudinal cracking of the asphalt mix design using Ml this is the rationale for this investigation. This paper provides a comprehensive assessment of agricultural by products with particular attention to the specific activities of 226Ra, 232Th and 40K. These radionuclides were used to determine the potential hazards from the use of studied agricultural by products. These 226Ra, 232Th, 40K, AGDRin, AGDRex, AEDRin, and André) using the Support Learning Machine (SVM), Neural Networks (NN), Ensemble Trees (ET), regression [4].