fix citation issue

paper/paper.md

@@ -25,7 +25,7 @@ Deep Waste is a mobile application that leverages state-of-the art computer visi
 
 # Statement of need
 
-The escalating global waste crisis, projected to surge by 70% by 2050 without intervention [@kaza_what_2018], demands innovative solutions. Diverse waste management techniques, from source reduction to education initiatives, strive to combat this issue [@mridha_intelligent_2021; @mridha_intelligent_2021]. Yet, the absence of a standardized waste classification system results in regional disparities [@ferronato_waste_2019], emphasizing the need for efficient waste identification, crucial for integrated solid waste management [@fadhullah_household_2022].
+The escalating global waste crisis, projected to surge by 70% by 2050 without intervention [@kaza_what_2018], demands innovative solutions. Diverse waste management techniques, from source reduction to education initiatives, strive to combat this issue [@mridha_intelligent_2021]. Yet, the absence of a standardized waste classification system results in regional disparities [@ferronato_waste_2019], emphasizing the need for efficient waste identification, crucial for integrated solid waste management [@fadhullah_household_2022].
 
 Recent advancements leverage deep learning models to streamline waste sorting and management [@liu_image_2022]. These models, like RWNet and ConvoWaste, exhibit high accuracy, emphasizing the role of accurate waste disposal in mitigating climate change and reducing greenhouse gas emissions. Some studies incorporate IoT and waste grid segmentation to classify and segregate waste items in real time [@m_technical_2023].