This paper presents a novel method utilizing Sequential Structure-Associative Knowledge Graphs (SSAKGs) to address the challenges of sequence storage and retrieval in applications such as anomaly detection, behavior prediction, and genetic information analysis. SSAKGs encode sequences as trended tournaments, with nodes representing objects and edges defining their order. We develop four ordering algorithms (Simple Sort, Node Ordering, Enhanced Node Ordering, and Weighted Edges Node Ordering) and evaluate their performance using synthetic and real-world datasets (sentence sequences from the NLTK library and miRNA sequences). Precision, sensitivity, and specificity are used as evaluation metrics. SSAKGs exhibit a memory capacity that grows quadratically with graph size, require no learning, are flexible in context-based reconstruction, and offer high efficiency in sparse memory graphs. This provides a scalable solution for sequence-based memory operations with broad applications in computational neuroscience and bioinformatics.
