The detection of primary user signals is essential for optimum utilization of a spectrum by secondary users in cognitive radio (CR). The conventional spectrum sensing schemes have the problem of missed detection/false alarm, which hampers the proper utilization of spectrum. Spectrum sensing through deep learning minimizes the margin of error in the detection of the free spectrum. This research provides an insight into using a deep neural network for spectrum sensing. A deep learning based model, “DLSenseNet”, is proposed, which exploits structural information of received modulated signals for spectrum sensing. The experiments were performed using RadioML2016.10b dataset and the outcome was studied. It was found that “DLSenseNet” provides better spectrum detection than other sensing models.

Cognitive radio has been proposed to improve spectrum utilization in wireless communication. Spectrum sensing is an essential component of cognitive radio. The traditional methods of spectrum sensing are based on feature extraction of a received signal at a given point. The development in artificial intelligence and deep learning have given an opportunity to improve the accuracy of spectrum sensing by using cooperative spectrum sensing and analyzing the radio scene. This research proposed a hybrid model of convolution and recurrent neural network for spectrum sensing. The research further enhances the accuracy of sensing for low SNR signals through transfer learning. The results of modelling show improvement in spectrum sensing using CNN-RNN compared to other models studied in this field. The complexity of an algorithm is analyzed to show an improvement in the performance of the algorithm.

Cervical cancer, arising from the cells of the cervix, the lower segment of the uterus connected to the vagina-poses a significant health threat. The microscopic examination of cervical cells using Pap smear techniques plays a crucial role in identifying potential cancerous alterations. While developed nations demonstrate commendable efficiency in Pap smear acquisition, the process remains laborious and time-intensive. Conversely, in less developed regions, there is a pressing need for streamlined, computer-aided methodologies for the pre-analysis and treatment of cervical cancer. This study focuses on the classification of squamous cells into five distinct classes, providing a nuanced assessment of cervical cancer severity. Utilizing a dataset comprising over 4096 images from SimpakMed, available on Kaggle, we employed ensemble technique which included the Convolutional Neural Network (CNN), AlexNet, and SqueezeNet for image classification, achieving accuracies of 90.8%, 92%, and 91% respectively. Particularly noteworthy is the proposed ensemble technique, which surpasses individual model performances, achieving an impressive accuracy of 94%. This ensemble approach underscores the efficacy of our method in precise squamous cell classification and, consequently, in gauging the severity of cervical cancer. The results represent a promising advancement in the development of more efficient diagnostic tools for cervical cancer in resource-constrained settings.

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving machine learning across decentralized healthcare systems. This study proposes a secure and adaptive FL framework tailored for multi-institutional healthcare environments, combining structured electronic health records (EHR) and real-world ICU datasets (MIMIC-III) to predict patient severity levels. The framework incorporates secure multiparty computation (SMPC) with Shamir’s Secret Sharing to ensure encrypted communication between clients and edge aggregators, preserving data confidentiality throughout the training process. A key enhancement in this work is the integration of a dynamic edge thresholding mechanism that filters client updates based on round-wise gradient variance. Unlike static thresholds, this adaptive strategy enables real-time decision-making to accept or reject updates, improving robustness against noisy or unstable contributions and simulating real-world client dropout. The system was evaluated on both synthetic and MIMIC-III datasets using CatBoost, XGBoost, and TabNet across multiple threshold configurations and client setups. Performance metrics were reported with statistical confidence, standard deviation and 95% confidence intervals across five independent runs per model. The proposed framework demonstrates high classification accuracy, scalability across clients, and improved resilience to data heterogeneity and communication noise. It further incorporates deployment-aware considerations such as latency, update frequency, and dropout tolerance, making it suitable for integration in production healthcare networks. Experimental results highlight that dynamic thresholding not only improves model convergence but also contributes to reliable, fault-tolerant learning under practical constraints.

Malware forensics is a field in digital forensics that is dedicated to collecting evidence of a malware attack on a system. Malware is also executable code, but unlike regular executables, it is designed to perform unauthorized actions on victim computers. Being an executable, the malware also performs designated tasks through several processes that can leave its traces (digital footprints) throughout different components of the operating system, such as registries, file systems, DLL calls, API calls, memory usage, CPU utilization, network traffic, etc. Some of these traces can exist even after the removal of the malware and can be used as evidence to verify the occurrence of an attack. The proposed malware forensic analysis technique combines both the static and dynamic features of the malware to trace its evidence. This information is collected using the Cuckoo sandbox, which executes the malware sample files in a virtual environment to generate a JSON-formatted analysis report. The Python script is used to extract the non-volatile features from the JSON format analysis report. However, combining both features results in a very long and sparse feature vector, which negatively affects the classifier’s performance. Therefore, the principal component analysis (PCA) algorithm is adopted to reduce the dimensionality of the feature vectors. The generated reduced dimensionality feature vectors are used to train the extreme learning machine (ELM). The ELM can be trained in a fraction of the time compared to the support vector machine (SVM), while achieving similar accuracy. This makes it a favorable choice, especially for malware forensic analysis, where the classifier needs to train with a large amount of data and requires quick decision-making capabilities. The performance of the proposed techniques is evaluated using 90 malicious code samples containing 41 Trojans, 28 worms, and 21 bots. To demonstrate the superiority of the proposed algorithm, a comparison with some state-of-the-art classification methods, named Hidden Markov Model (HMM), Support Vector Machine (SVM), Artificial Neural Network (ANN), and ELM, was also performed. The comparison results show that the proposed technique achieves approximately 11% higher precision, 10% higher recall, and a 10.5% higher F-score than the competitors.

Deep learning and self-supervised learning techniques have advanced, making it possible to diagnose medical images more accurately. Our goal in this work is to increase the accuracy of medical diagnosis using chest X-rays by utilising information distillation and model compression techniques. By extracting knowledge from a self-supervised model which is a teacher model (SWAV Model with ResNet-50 as backbone), we enhance inference speed and reduce the computational resources needed for correct diagnosis. Our strategy entails translating the knowledge acquired by self-supervised models to smaller, more efficient models without sacrificing accuracy. In addition, we look at how model compression and distillation affect the diagnosis’s interpretation. The results of this study may enhance medical diagnosis procedures and increase their accessibility in environments with limited resources. Our extensive experiments prove the efficacy with 97.34% accuracy for the student model with knowledge distillation.