One of the challenges faced by traditional intrusion detection systems based on machine learning or deep learning is instability when dealing with unbalanced network traffic, leading to failure in detecting certain attacks (minority classifications). Additionally, they struggle with multi-stage attacks, resulting in an increase in false alarms. This paper presents a hierarchical intrusion detection system supported by a Prediction Verification Layer (PVL) and a Feature Inheritance Mechanism (FIM). Where PVL contributes to documenting the system’s final decision and increasing sensitivity to minority attacks, FIM also helps in inheriting features from previous layers and correcting errors as much as possible. Additionally, it allows for ad

An intrusion detection system (IDS) is key to having a comprehensive cybersecurity solution against any attack, and artificial intelligence techniques have been combined with all the features of the IoT to improve security. In response to this, in this research, an IDS technique driven by a modified random forest algorithm has been formulated to improve the system for IoT. To this end, the target is made as one-hot encoding, bootstrapping with less redundancy, adding a hybrid features selection method into the random forest algorithm, and modifying the ranking stage in the random forest algorithm. Furthermore, three datasets have been used in this research, IoTID20, UNSW-NB15, and IoT-23. The results are compared with the three datasets men

With the rapid development of computers and network technologies, the security of information in the internet becomes compromise and many threats may affect the integrity of such information. Many researches are focused theirs works on providing solution to this threat. Machine learning and data mining are widely used in anomaly-detection schemes to decide whether or not a malicious activity is taking place on a network. In this paper a hierarchical classification for anomaly based intrusion detection system is proposed. Two levels of features selection and classification are used. In the first level, the global feature vector for detection the basic attacks (DoS, U2R, R2L and Probe) is selected. In the second level, four local feature vect

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

The complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra

Some of the main challenges in developing an effective network-based intrusion detection system (IDS) include analyzing large network traffic volumes and realizing the decision boundaries between normal and abnormal behaviors. Deploying feature selection together with efficient classifiers in the detection system can overcome these problems.  Feature selection finds the most relevant features, thus reduces the dimensionality and complexity to analyze the network traffic.  Moreover, using the most relevant features to build the predictive model, reduces the complexity of the developed model, thus reducing the building classifier model time and consequently improves the detection performance.  In this study, two different sets of select

Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep lea

Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi