This paper offers a systemic review of the deep learning methods to detect violence on campus, which is a critical issue in intelligent surveillance to improve the student safety and prompt cut off of violent accidents. The review reviews studies published 2018-2025, concentrating on model structure to detect fights, bullying, vandalism, and aggressive behavior on problematic campuses due to occlusion and light variations and complicated human interactions. The research design includes a comparative study of different deep learning networks, such as CNNs, RNNs, 3D CNNs, attention-based networks, transformers, graph neural networks, neuro-fuzzy, and multimodal systems and federated learning methods. The paper also assesses benchmark

    Multivariate Non-Parametric control charts were used to monitoring the data that generated by using the simulation, whether they are within control limits or not. Since that non-parametric methods do not require any assumptions about the distribution of the data.  This research aims to apply the multivariate non-parametric quality control methods, which are Multivariate Wilcoxon Signed-Rank ( ) , kernel principal component analysis (KPCA) and k-nearest neighbor ( −

Dengue fever is a mosquito-borne viral infection that produces characteristic abnormalities in routine blood tests, yet these hematologic changes are typically analysed separately for each parameter rather than as a combined multivariate profile. This study investigated whether the joint hematologic profile of adult dengue patients in Bangladesh is systematically displaced from healthy adult reference values. We analysed a cohort of laboratory-confirmed adult dengue cases from a Bangladeshi hospital and focused on four core hematologic indices: haemoglobin, white blood cell count, platelet count, and platelet distribution width (PDW). External adult reference means were used to define a healthy location vector, and robust multivariate infer