{"doi":"10.1145/3764924.3770901","title":"An Algorithm for Feature Based Segmentation of Contiguous Area in a Community to Locate Underserved Areas","abstract":"Identification of the largest contiguous area in a community, using a map, is an important task to identify underserved areas in a community. However, this can be a significant challenge in geospatial computation. The current algorithms typically work on the pixel values of the images to perform segmentation. The research problem is that few algorithms exist that utilize features at a location and can scale well. Features are aspects of a map that can sometimes be seen through satellite imaging, but at other times can include, for example, the number of restaurants in a community. The easiest way to express a feature in a map is a binary value, (presence/absence or above/below a threshold value) at a position. An existing algorithm, Kadane's algorithm, results in a rectangular contiguous area that cannot be applied in many real-world large-scale applications without losing granularity. The Union-Find with Connected Component Labeling algorithm works accurately, but takes lot of time. This paper examines various alternative approaches and presents a novel application that results in a non-rectangular contiguous area, from a binary matrix of a geospatial feature. Spatial join is performed with the feature dataset for generating the matrix. We use a depth-first search traversal with a 4-way tree-based data structure to recursively explore connected cells. The algorithm limits redundant traversal, isolates disjoint regions and selects the largest connected component. So, our contribution is a geospatial system algorithm that is faster while matching a perfect accuracy. This work has broader impacts for identification of coverage of various features, such as demographic, atmospheric and epidemiological characteristics, in a computationally efficient manner.","journal":null,"year":2025,"id":579318,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.951,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1489531,"name":"Devesh Sarda","orcid":"0009-0007-7499-3235","position":1,"is_corresponding":false},{"id":1339026,"name":"Udaysinh Rathod","orcid":"0009-0002-5391-2436","position":2,"is_corresponding":false},{"id":1339027,"name":"Mridula Mavuri","orcid":"0009-0001-2768-4815","position":3,"is_corresponding":false},{"id":1339024,"name":"Subhajit Chakrabarty","orcid":"0000-0003-0818-3190","position":0,"is_corresponding":true}],"reference_count":11,"raw_metadata":null,"created_at":"2026-07-19T02:58:30.282164Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}