RESUMEN
The emerging expanding scope of the Internet of Things (IoT) necessitates robust intrusion detection systems (IDS) to mitigate security risks effectively. However, existing approaches often struggle with adaptability to emerging threats and fail to account for IoT-specific complexities. To address these challenges, this study proposes a novel approach by hybridizing convolutional neural network (CNN) and gated recurrent unit (GRU) architectures tailored for IoT intrusion detection. This hybrid model excels in capturing intricate features and learning relational aspects crucial in IoT security. Moreover, we integrate the feature-weighted synthetic minority oversampling technique (FW-SMOTE) to handle imbalanced datasets, which commonly afflict intrusion detection tasks. Validation using the IoTID20 dataset, designed to emulate IoT environments, yields exceptional results with 99.60% accuracy in attack detection, surpassing existing benchmarks. Additionally, evaluation on the network domain dataset, UNSW-NB15, demonstrates robust performance with 99.16% accuracy, highlighting the model's applicability across diverse datasets. This innovative approach not only addresses current limitations in IoT intrusion detection but also establishes new benchmarks in terms of accuracy and adaptability. The findings underscore its potential as a versatile and effective solution for safeguarding IoT ecosystems against evolving security threats.
RESUMEN
Background: Software process improvement (SPI) is an indispensable phenomenon in the evolution of a software development company that adopts global software development (GSD) or in-house development. Several software development companies do not only adhere to in-house development but also go for the GSD paradigm. Both development approaches are of paramount significance because of their respective advantages. Many studies have been conducted to find the SPI success factors in the case of companies that opt for in-house development. Still, less attention has been paid to the SPI success factors in the case of the GSD environment for large-scale software companies. Factors that contribute to the SPI success of small as well as medium-sized companies have been identified, but large-scale companies have still been overlooked. The research aims to identify the success factors of SPI for both development approaches (GSD and in-house) in the case of large-scale software companies. Methods: Two systematic literature reviews have been performed. An industrial survey has been conducted to detect additional SPI success factors for both development environments. In the subsequent step, a comparison has been made to find similar SPI success factors in both development environments. Lastly, another industrial survey is conducted to compare the common SPI success factors of GSD and in-house software development, in the case of large-scale companies, to divulge which SPI success factor carries more value in which development environment. For this reason, parametric (Pearson correlation) and non-parametric (Kendall's Tau correlation and the Spearman correlation) tests have been performed. Results: The 17 common SPI factors have been identified. The pinpointed common success factors expedite and contribute to SPI in both environments in the case of large-scale companies.
RESUMEN
Medical imaging is considered a suitable alternative testing method for the detection of lung diseases. Many researchers have been working to develop various detection methods that have aided in the prevention of lung diseases. To better understand the condition of the lung disease infection, chest X-Ray and CT scans are utilized to check the disease's spread throughout the lungs. This study proposes an automated system for the detection multi lung diseases in X-Ray and CT scans. A customized convolutional neural network (CNN) and two pre-trained deep learning models with a new image enhancement model are proposed for image classification. The proposed lung disease detection comprises two main steps: pre-processing, and deep learning classification. The new image enhancement algorithm is developed in the pre-processing step using k-symbol Lerch transcendent functions model which enhancement images based on image pixel probability. While, in the classification step, the customized CNN architecture and two pre-trained CNN models Alex Net, and VGG16Net are developed. The proposed approach was tested on publicly available image datasets (CT, and X-Ray image dataset), and the results showed classification accuracy, sensitivity, and specificity of 98.60%, 98.40%, and 98.50% for the X-Ray image dataset, respectively, and 98.80%, 98.50%, 98.40% for the CT scans dataset, respectively. Overall, the obtained results highlight the advantages of the image enhancement model as a first step in processing.
Asunto(s)
Aprendizaje Profundo , Enfermedades Pulmonares , Humanos , Rayos X , Radiografía , Tomografía Computarizada por Rayos X , Enfermedades Pulmonares/diagnóstico por imagenRESUMEN
The exponentially growing concern of cyber-attacks on extremely dense underwater sensor networks (UWSNs) and the evolution of UWSNs digital threat landscape has brought novel research challenges and issues. Primarily, varied protocol evaluation under advanced persistent threats is now becoming indispensable yet very challenging. This research implements an active attack in the Adaptive Mobility of Courier Nodes in Threshold-optimized Depth-based Routing (AMCTD) protocol. A variety of attacker nodes were employed in diverse scenarios to thoroughly assess the performance of AMCTD protocol. The protocol was exhaustively evaluated both with and without active attacks with benchmark evaluation metrics such as end-to-end delay, throughput, transmission loss, number of active nodes and energy tax. The preliminary research findings show that active attack drastically lowers the AMCTD protocol's performance (i.e., active attack reduces the number of active nodes by up to 10%, reduces throughput by up to 6%, increases transmission loss by 7%, raises energy tax by 25%, and increases end-to-end delay by 20%).