A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization

Abstract

Security has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovative automatic Front Door Security (FDS) algorithm that uses Human Activity Recognition (HAR) to detect four different security threats at the front door from a real-time video feed with 73.18% accuracy. The activities are recognized using an innovative combination of GoogleNet-BiLSTM hybrid network. This network receives the video feed from the CCTV camera and classifies the activities. The proposed algorithm uses this classification to alert any attempts to break the door by kicking, punching, or hitting. Furthermore, the proposed FDS algorithm is effective in detecting gun violence at the front door, which further strengthens security. This Human Activity Recognition (HAR)-based novel FDS algorithm demonstrates the potential of ensuring better safety with 71.49% precision, 68.2% recall, and an F1-score of 0.65.

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

“…The proposed HAAS model uses a Convolutional Neural Network (CNN) specially designed to optimize CT images with minimal cloud resources. However, the literature review demonstrates that the machine learning model cannot perform well if the datasets are rich enough [36] . That is why data processing is essential in any machine learning-based approach [37] .…”

PersoNet: A Novel Framework for Personality Classification-Based Apt Customer Service Agent Selection

“…Moreover, MBTI text samples x i vary in length n i . LSTMs are a type of Recurrent Neural Network (RNN) that handles variable-length sequences without requiring the sequence length n to be fixed, unlike traditional feed-forward neural networks [34]. The MBTI dataset contains 16 been coupled with a Softmax layer to produce probability distributions across these 16 classes according to equation 19 where W and b are trainable parameters, and h ni is the final hidden state incorporating both forward and backward information.…”

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

“…These evaluation metrics are calculated using True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN) values from the confusion matrix illustrated in figure 7 [71]. The accuracy, precision, recall (sensitivity), and F1 Score are defined by equations 30, 31, 32, and 33, respectively [72].…”