Comparative evaluation of machine learning algorithms for phishing site detection.

The advent of Internet technologies has resulted in the proliferation of electronic trading and the use of the Internet for electronic transactions, leading to a rise in unauthorized access to sensitive user information and the depletion of resources for enterprises. As a consequence, there has been a marked increase in phishing, which is now considered one of the most common types of online theft. Phishing attacks are typically directed towards obtaining confidential information, such as login credentials for online banking platforms and sensitive systems. The primary objective of such attacks is to acquire specific personal information to either use for financial gain or commit identity theft. Recent studies have been conducted to combat phishing attacks by examining domain characteristics such as website addresses, content on websites, and combinations of both approaches for the website and its source code. However, businesses require more effective anti-phishing technologies to identify phishing URLs and safeguard their users. The present research aims to evaluate the effectiveness of eight machine learning (ML) and deep learning (DL) algorithms, including support vector machine (SVM), k-nearest neighbors (KNN), random forest (RF), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), logistic regression (LR), convolutional neural network (CNN), and DL model and assess their performances in identifying phishing. This study utilizes two real datasets, Mendeley and UCI, employing performance metrics such as accuracy, precision, recall, false positive rate (FPR), and F-1 score. Notably, CNN exhibits superior accuracy, emphasizing its efficacy. Contributions include using purpose-specific datasets, meticulous feature engineering, introducing SMOTE for class imbalance, incorporating the novel CNN model, and rigorous hyperparameter tuning. The study demonstrates consistent model performance across both datasets, highlighting stability and reliability.

DeepSplice: a deep learning approach for accurate prediction of alternative splicing events in the human genome.

Alternative splicing (AS) is a crucial process in genetic information processing that generates multiple mRNA molecules from a single gene, producing diverse proteins. Accurate prediction of AS events is essential for understanding various physiological aspects, including disease progression and prognosis. Machine learning (ML) techniques have been widely employed in bioinformatics to address this challenge. However, existing models have limitations in capturing AS events in the presence of mutations and achieving high prediction performance. To overcome these limitations, this research presents deep splicing code (DSC), a deep learning (DL)-based model for AS prediction. The proposed model aims to improve predictive ability by investigating state-of-the-art techniques in AS and developing a DL model specifically designed to predict AS events accurately. The performance of the DSC model is evaluated against existing techniques, revealing its potential to enhance the understanding and predictive power of DL algorithms in AS. It outperforms other models by achieving an average AUC score of 92%. The significance of this research lies in its contribution to identifying functional implications and potential therapeutic targets associated with AS, with applications in genomics, bioinformatics, and biomedical research. The findings of this study have the potential to advance the field and pave the way for more precise and reliable predictions of AS events, ultimately leading to a deeper understanding of genetic information processing and its impact on human physiology and disease.

Stochastic forecasting of variable small data as a basis for analyzing an early stage of a cyber epidemic.

Security Information and Event Management (SIEM) technologies play an important role in the architecture of modern cyber protection tools. One of the main scenarios for the use of SIEM is the detection of attacks on protected information infrastructure. Consorting that ISO 27001, NIST SP 800-61, and NIST SP 800-83 standards objectively do not keep up with the evolution of cyber threats, research aimed at forecasting the development of cyber epidemics is relevant. The article proposes a stochastic concept of describing variable small data on the Shannon entropy basis. The core of the concept is the description of small data by linear differential equations with stochastic characteristic parameters. The practical value of the proposed concept is embodied in the method of forecasting the development of a cyber epidemic at an early stage (in conditions of a lack of empirical information). In the context of the research object, the stochastic characteristic parameters of the model are the generation rate, the death rate, and the independent coefficient of variability of the measurement of the initial parameter of the research object. Analytical expressions for estimating the probability distribution densities of these characteristic parameters are proposed. It is assumed that these stochastic parameters of the model are imposed on the intervals, which allows for manipulation of the nature and type of the corresponding functions of the probability distribution densities. The task of finding optimal functions of the probability distribution densities of the characteristic parameters of the model with maximum entropy is formulated. The proposed method allows for generating sets of trajectories of values of characteristic parameters with optimal functions of the probability distribution densities. The example demonstrates both the flexibility and reliability of the proposed concept and method in comparison with the concepts of forecasting numerical series implemented in the base of Matlab functions.

U-Net-Based Models towards Optimal MR Brain Image Segmentation.

Brain tumor segmentation from MRIs has always been a challenging task for radiologists, therefore, an automatic and generalized system to address this task is needed. Among all other deep learning techniques used in medical imaging, U-Net-based variants are the most used models found in the literature to segment medical images with respect to different modalities. Therefore, the goal of this paper is to examine the numerous advancements and innovations in the U-Net architecture, as well as recent trends, with the aim of highlighting the ongoing potential of U-Net being used to better the performance of brain tumor segmentation. Furthermore, we provide a quantitative comparison of different U-Net architectures to highlight the performance and the evolution of this network from an optimization perspective. In addition to that, we have experimented with four U-Net architectures (3D U-Net, Attention U-Net, R2 Attention U-Net, and modified 3D U-Net) on the BraTS 2020 dataset for brain tumor segmentation to provide a better overview of this architecture's performance in terms of Dice score and Hausdorff distance 95%. Finally, we analyze the limitations and challenges of medical image analysis to provide a critical discussion about the importance of developing new architectures in terms of optimization.

An intuitionistic approach for the predictability of anti-angiogenic inhibitors in cancer diagnosis.

Malignant cancer angiogenesis has historically attracted enormous scientific attention. Although angiogenesis is requisite for a child's development and conducive to tissue homeostasis, it is deleterious when cancer lurks. Today, anti-angiogenic biomolecular receptor tyrosine kinase inhibitors (RTKIs) to target angiogenesis have been prolific in treating various carcinomas. Angiogenesis is a pivotal component in malignant transformation, oncogenesis, and metastasis that can be activated by a multiplicity of factors (e.g., VEGF (Vascular endothelial growth factor), (FGF) Fibroblast growth factor, (PDGF) Platelet-derived growth factor and others). The advent of RTKIs, which primarily target members of the VEGFR (VEGF Receptor) family of angiogenic receptors has greatly ameliorated the outlook for some cancer forms, including hepatocellular carcinoma, malignant tumors, and gastrointestinal carcinoma. Cancer therapeutics have evolved steadily with active metabolites and strong multi-targeted RTK inhibitors such as E7080, CHIR-258, SU 5402, etc. This research intends to determine the efficacious anti-angiogenesis inhibitors and rank them by using the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE- II) decision-making algorithm. The PROMETHEE-II approach assesses the influence of growth factors (GFs) in relation to the anti-angiogenesis inhibitors. Due to their capacity to cope with the frequently present vagueness while ranking alternatives, fuzzy models constitute the most suitable tools for producing results for analyzing qualitative information. This research's quantitative methodology focuses on ranking the inhibitors according to their significance concerning criteria. The evaluation findings indicate the most efficacious and idle alternative for inhibiting angiogenesis in cancer.

Analysis of environmental factors using AI and ML methods.

The main goal of this research paper is to apply a deep neural network model for time series forecasting of environmental variables. Accurate forecasting of snow cover and NDVI are important issues for the reliable and efficient hydrological models and prediction of the spread of forest. Long Short Term Memory (LSTM) model for the time series forecasting of snow cover, temperature, and normalized difference vegetation index (NDVI) are studied in this research work. Artificial neural networks (ANN) are widely used for forecasting time series due to their adaptive computing nature. LSTM and Recurrent neural networks (RNN) are some of the several architectures provided in a class of ANN. LSTM is a kind of RNN that has the capability of learning long-term dependencies. We followed a coarse-to-fine strategy, providing reviews of various related research materials and supporting it with the LSTM analysis on the dataset of Himachal Pradesh, as gathered. Environmental factors of the Himachal Pradesh region are forecasted using the dataset, consisting of temperature, snow cover, and vegetation index as parameters from the year 2001-2017. Currently, available tools and techniques make the presented system more efficient to quickly assess, adjust, and improve the environment-related factors analysis.

Bulk Processing of Multi-Temporal Modis Data, Statistical Analyses and Machine Learning Algorithms to Understand Climate Variables in the Indian Himalayan Region.

Studies relating to trends of vegetation, snowfall and temperature in the north-western Himalayan region of India are generally focused on specific areas. Therefore, a proper understanding of regional changes in climate parameters over large time periods is generally absent, which increases the complexity of making appropriate conclusions related to climate change-induced effects in the Himalayan region. This study provides a broad overview of changes in patterns of vegetation, snow covers and temperature in Uttarakhand state of India through bulk processing of remotely sensed Moderate Resolution Imaging Spectroradiometer (MODIS) data, meteorological records and simulated global climate data. Additionally, regression using machine learning algorithms such as Support Vectors and Long Short-term Memory (LSTM) network is carried out to check the possibility of predicting these environmental variables. Results from 17 years of data show an increasing trend of snow-covered areas during pre-monsoon and decreasing vegetation covers during monsoon since 2001. Solar radiation and cloud cover largely control the lapse rate variations. Mean MODIS-derived land surface temperature (LST) observations are in close agreement with global climate data. Future studies focused on climate trends and environmental parameters in Uttarakhand could fairly rely upon the remotely sensed measurements and simulated climate data for the region.

Intellligent sustainable agricultural water practice using multi sensor spatiotemporal evolution.

The amount of water taken from non-renewable resources such as aquifers to fulfill irrigation requirements is rarely monitored, putting sustainable agriculture under threat in the face of changing climate. In the present research, an attempt was made to apply multi-sensor (Landsat suite, GRACE, GRACE-FO) satellite data to monitor spatiotemporal evolution of agriculture for the Al-Qassim region, Kingdom of Saudi Arabia (KSA). For this purpose, time series of NDVI (Normalized Difference Vegetation Index), SAVI (Soil-Adjusted Vegetation Index), and MSAVI2 (Modified Soil-Adjusted Vegetation 2) was utilized to assess vegetation pattern change in the study area. The present investigation used High-resolution Planetscope (PS) nanosatellite data to validate the vegetation results. Mann Kendall trend analysis and linear regression were performed to study the temporal pattern, and the relationship between vegetation, GRACE, and climate variables was performed from 1984 to 2020. Water extraction based on the averaged value of JPL GWS and CSR GWS showed a decreasing trend of -10.24 ± 1.4 mm/year from 2003-2020. The annual rainfall showed a decreasing trend, while the annual temperature showed an increasing trend from 1982-2020. The correlation of vegetation indices with rainfall of one-month lag showed a significantly better relationship of 0.74, 0.74, and 0.75, respectively, for NDVI, SAVI, and MSAVI2. The correlation between temperature and all three vegetation indices is a strong negative correlation: -0.85 for NDVI and -0.9 for SAVI and MSAVI.