Identification of brain tumors and accurate grading at an early stage are crucial in cancer diagnosis, as a timely diagnosis can increase the chances of survival. Considering the challenges and risks of tumor biopsies, noninvasive imaging procedures such as Magnetic Resonance Imaging (MRI) are extensively used in analyzing brain tumors. Recent advances in the field of medical imaging with deep learning using three dimensional (3D) MRI is aiding the clinical experts significantly in the diagnosis of brain tumor. In this study, three BraTS MRI datasets named BraTS 2018, BraTS 2019 and BraTS 2020 are employed to classify brain tumor into high-grade glioma (HGG) and low-grade glioma (LGG) where each of the datasets contains four different sequences of 3D MRI brain images named T1-weighted MRI (T1), T1-weighted MRI with contrast enhancement (T1ce), T2-weighted MRI (T2), and Fluid Attenuated Inversion Recovery (FLAIR) for a single patient. This research is composed of two approaches where, in the first part, we propose a hybrid deep learning model named TimeDistributed-CNN-LSTM (TD-CNN-LSTM) combining 3D Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) where each layer of the architecture is wrapped with a TimeDistributed function. The objective of developing the hybrid model is to consider all the four 3D MRI sequences of each patient as a single input data because every sequence contains necessary information on tumor that can have an impact on improving cancer detection performance. However, interpreting all the MRI sequences together with optimal performance especially in 3D is quite challenging. Therefore, the model is developed with optimal configuration based on highest accuracy performing ablation study for layer architecture and hyper-parameters. In the second part, a 3D CNN model is trained respectively with each of the MRI sequences to compare the performance with TD-CNN-LSTM model. In this regard, for both of the models, BraTS 2018 and BraTS 2019 are combined to increase the number of images and used as train dataset where BraTS 2020 dataset is employed as the test dataset. Moreover, before training the models the datasets is preprocessed to ensure the highest performance. Our results of these two approaches demonstrate that the TD-CNN-LSTM network outperforms 3D CNN achieving the highest test accuracy of 98.90%. Later, to evaluate the performance consistency, the TD-CNN-LSTM model is evaluated with K-fold cross validation using different k values. The approach of putting together all the MRI sequences at a time using hybrid CNN-LSTM approach with good generalization capability to classify brain tumor can be used effectively in future Computer Aided Diagnosis (CAD) based research which can aid radiologists in medical diagnostics.

With the popularity of Internet of Things (IoT) technology, the security of the IoT network has become an important issue. Traditional intrusion detection systems have their limitations when applied to the IoT network due to resource constraints and the complexity. This research focusses on the design, implementation and testing of an intrusion detection system which uses a hybrid placement strategy based on a multi-agent system, blockchain and deep learning algorithms. The system consists of the following modules: data collection, data management, analysis, and response. The National security lab–knowledge discovery and data mining NSL-KDD dataset is used to test the system. The results demonstrate the efficiency of deep learning algorithms when detecting attacks from the transport layer. The experiment indicates that deep learning algorithms are suitable for intrusion detection in IoT network environment.

Data analysis in modern times involves working with large volumes of data, including time-series data. This type of data is characterized by its high dimensionality, enormous volume, and the presence of both noise and redundant features. However, the "curse of dimensionality" often causes issues for learning approaches, which can fail to capture the temporal dependencies present in time-series data. To address this problem, it is essential to reduce dimensionality while preserving the intrinsic properties of temporal dependencies. This will help to avoid lower learning and predictive performances. This study presents twelve different dimensionality reduction algorithms that are specifically suited for working with time-series data and fall into different categories, such as supervision, linearity, time and memory complexity, hyper-parameters, and drawbacks.

Phishing is a pervasive form of cybercrime where malicious websites deceive users into revealing sensitive information, e.g., passwords and credit card details. Despite advances in cybersecurity, accurately detecting phishing websites remains challenging due to the absence of universally accepted identification parameters. This study introduces a novel feature selection method, Rough Set Theory-based Hybrid Feature Selection (RSTHFS), to enhance phishing website detection using Machine Learning (ML) techniques. Our approach was evaluated using three diverse datasets containing 2,456, 10,000, and 88,647 instances. The RSTHFS method demonstrated a significant improvement by maintaining an average accuracy rate of 95.48% while reducing the number of features by 69.11% on average. Performance was further assessed using three advanced classifiers: Light Gradient-Boosting Machine (LightGBM), Random Forest (RF), and Categorical Boosting (CatBoost), with CatBoost emerging as the most efficient, achieving the highest accuracy. Additionally, RSTHFS reduced the runtime by 61.43%, highlighting its efficiency. These findings indicate that RSTHFS is not only effective in identifying phishing websites but also accelerates ML processes, providing a reliable and swift approach to feature selection. This work contributes to the field by presenting a robust methodology that enhances the accuracy and speed of phishing detection systems.

Background: Relational agents (RAs) have shown effectiveness in various health interventions with and without doctors and hospital facilities. In situations such as a pandemic like the COVID-19 pandemic when health care professionals (HCPs) and facilities are unable to cope with increased demands, RAs may play a major role in ameliorating the situation. However, they have not been well explored in this domain.Objective: This study aimed to design a prototypical RA in collaboration with COVID-19 patients and HCPs and test it with the potential users, for its ability to deliver services during a pandemic.Methods: The RA was designed and developed in collaboration with people with COVID-19 (n=21) and 2 groups of HCPs (n=19 and n=16, respectively) to aid COVID-19 patients at various stages by performing 4 main tasks: testing guidance, support during self-isolation, handling emergency situations, and promoting postrecovery mental well-being. A design validation survey was conducted with 98 individuals to evaluate the usability of the prototype using the System Usability Scale (SUS), and the participants provided feedback on the design. In addition, the RA’s usefulness and acceptability were rated by the participants using Likert scales.Results: In the design validation survey, the prototypical RA received an average SUS score of 58.82. Moreover, 90% (88/98) of participants perceived it to be helpful, and 69% (68/98) of participants accepted it as a viable alternative to HCPs. The prototypical RA received favorable feedback from the participants, and they were inclined to accept it as an alternative to HCPs in non-life-threatening scenarios despite the usability rating falling below the acceptable threshold.Conclusions: Based on participants’ feedback, we recommend further development of the RA with improved automation and emotional support, ability to provide information, tracking, and specific recommendations.