This paper proposes a novel framework for deep learning-based anomaly identification in videos using the squirrel search algorithm (SSA) and bidirectional long short-term memory (BiLSTM). The SSA, inspired by the foraging behavior of flying squirrels, enhances the exploration and exploitation capabilities of the optimization process. The BiLSTM, a type of recurrent neural network, is used to classify anomalies by processing sequences of frames. The framework combines these techniques to accurately identify abnormal activities in surveillance footage. The method was tested on several benchmark datasets, demonstrating superior performance with an area under the curve (AUC) score of 93.1%. The paper also discusses the benefits of using BiLSTM over traditional unidirectional LSTM models and highlights the importance of feature selection. Overall, the proposed framework provides a highly precise tool for identifying abnormal human behavior in surveillance videos.This paper proposes a novel framework for deep learning-based anomaly identification in videos using the squirrel search algorithm (SSA) and bidirectional long short-term memory (BiLSTM). The SSA, inspired by the foraging behavior of flying squirrels, enhances the exploration and exploitation capabilities of the optimization process. The BiLSTM, a type of recurrent neural network, is used to classify anomalies by processing sequences of frames. The framework combines these techniques to accurately identify abnormal activities in surveillance footage. The method was tested on several benchmark datasets, demonstrating superior performance with an area under the curve (AUC) score of 93.1%. The paper also discusses the benefits of using BiLSTM over traditional unidirectional LSTM models and highlights the importance of feature selection. Overall, the proposed framework provides a highly precise tool for identifying abnormal human behavior in surveillance videos.