The order of amino acids in a protein sequence enables the protein to acquire a conformation suitable for performing functions, thereby motivating the need to analyse these sequences for predicting functions. Although machine learning based approaches are fast compared to methods using BLAST, FASTA, etc., they fail to perform well for long protein sequences (with more than 300 amino acids). In this paper, we introduce a novel method for construction of two separate feature sets for protein using bi-directional long short-term memory network based on the analysis of fixed 1) single-sized segments and 2) multi-sized segments. The model trained on the proposed feature set based on multi-sized segments is combined with the model trained using state-of-the-art Multi-label Linear Discriminant Analysis (MLDA) features to further improve the accuracy. Extensive evaluations using separate datasets for biological processes and molecular functions demonstrate not only improved results for long sequences, but also significantly improve the overall accuracy over state-of-the-art method. The single-sized approach produces an improvement of +3.37% for biological processes and +5.48% for molecular functions over the MLDA based classifier. The corresponding numbers for multi-sized approach are +5.38% and +8.00%. Combining the two models, the accuracy further improves to +7.41% and +9.21% respectively.

As cities grapple with rising temperatures, the integration of urban greenery has gained recognition as a viable solution to mitigate these effects and enhance outdoor thermal conditions. This paper identifies widely used and emerging numerical models, highlights research gaps, and addresses key insights from the selected literature. Grounded in a PRISMA-based review, it offers insights to optimize strategies for mitigating urban heat islands and enhancing livability. The study explores synergies and trade-offs between green infrastructure and the built environment, aiming to provide insights into optimizing these elements for sustainable urban development. In this research, a mixed-methods approach was adopted by combining a systematic review and a bibliometric review using the PRISMA 2020 and VOSviewer 1.6.19 of 48 relevant studies. The PRISMA process led to the selection of the papers used for both the qualitative synthesis and bibliometric analysis. The results indicate a significant increase in research output in the last decades with a marked focus on green roofs, urban parks, and vertical greening systems. Our findings provide an elaborate conceptual framework that maps the interrelation between the research topics. Also, the study highlights existing research gaps in numerical modeling software for evaluating the cooling potential of urban greenery and its impact on thermal comfort across diverse urban contexts. The study recommends developing standardized frameworks and metrics for evaluating thermal comfort in urban areas, as well as suggesting that advancing numerical modeling software is essential to accurately simulate the complex interactions between urban greenery, microclimates, and urban forms.