Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models.

Phishing is one of the most dangerous attacks targeting individuals, organizations, and nations. Although many traditional methods for email phishing detection exist, there is a need to improve accuracy and reduce false-positive rates. Our work investigates one-dimensional CNN-based models (1D-CNNPD) to detect phishing emails in order to address these challenges. Additionally, further improvement is achieved with the augmentation of the base 1D-CNNPD model with recurrent layers, namely, LSTM, Bi-LSTM, GRU, and Bi-GRU, and experimented with the four resulting models. Two benchmark datasets were used to evaluate the performance of our models: Phishing Corpus and Spam Assassin. Our results indicate that, in general, the augmentations improve the performance of the 1D-CNNPD base model. Specifically, the 1D-CNNPD with Bi-GRU yields the best results. Overall, the performance of our models is comparable to the state of the art of CNN-based phishing email detection. The Advanced 1D-CNNPD with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. We observe that increasing model depth typically leads to an initial performance improvement, succeeded by a decline. In conclusion, this study highlights the effectiveness of augmented 1D-CNNPD models in detecting phishing emails with improved accuracy. The reported performance measure values indicate the potential of these models in advancing the implementation of cybersecurity solutions to combat email phishing attacks.

Role of Optimization in RNA-Protein-Binding Prediction.

RNA-binding proteins (RBPs) play an important role in regulating biological processes, such as gene regulation. Understanding their behaviors, for example, their binding site, can be helpful in understanding RBP-related diseases. Studies have focused on predicting RNA binding by means of machine learning algorithms including deep convolutional neural network models. One of the integral parts of modeling deep learning is achieving optimal hyperparameter tuning and minimizing a loss function using optimization algorithms. In this paper, we investigate the role of optimization in the RBP classification problem using the CLIP-Seq 21 dataset. Three optimization methods are employed on the RNA-protein binding CNN prediction model; namely, grid search, random search, and Bayesian optimizer. The empirical results show an AUC of 94.42%, 93.78%, 93.23% and 92.68% on the ELAVL1C, ELAVL1B, ELAVL1A, and HNRNPC datasets, respectively, and a mean AUC of 85.30 on 24 datasets. This paper's findings provide evidence on the role of optimizers in improving the performance of RNA-protein binding prediction.

Molecular Identification of Newly Recorded Louse Columbicola tschulyschman Eichler (Phthiraptera: Philopteridae) From Saudi Arabia With a Note on Genus Columbicola spp. Phylogeny.

Chewing lice comprise a large group of ectoparasites that colonize and adversely affect several domestic and wild birds including pigeons. In Saudi Arabia, there is a lack of studies describing such ectoparasites and their infestation rates. Through this work, a new record, Columbicola, tschulyschman Eichler (C. tschulyschman Eichler) was collected from domestic pigeons (Columba livia domestica, Linnaeus). The collected C. tschulyschman Eichler was morphologically identified based on specific taxonomic keys. Mitochondrial (COI) and nuclear (EF-1α) gene fragments were used for molecular identification and phylogenetic reconstruction. In this study, the C. tschulyschman Eichler accounted for around 69.40%. To our knowledge, this is the first report of C. tschulyschman Eichler in Riyadh, Saudi Arabia. To improve the tree topology and differentiate between genera, further studies should utilize the 16s rRNA.

Optimal Deep Transfer Learning-Based Human-Centric Biomedical Diagnosis for Acute Lymphoblastic Leukemia Detection.

Human-centric biomedical diagnosis (HCBD) becomes a hot research topic in the healthcare sector, which assists physicians in the disease diagnosis and decision-making process. Leukemia is a pathology that affects younger people and adults, instigating early death and a number of other symptoms. Computer-aided detection models are found to be useful for reducing the probability of recommending unsuitable treatments and helping physicians in the disease detection process. Besides, the rapid development of deep learning (DL) models assists in the detection and classification of medical-imaging-related problems. Since the training of DL models necessitates massive datasets, transfer learning models can be employed for image feature extraction. In this view, this study develops an optimal deep transfer learning-based human-centric biomedical diagnosis model for acute lymphoblastic detection (ODLHBD-ALLD). The presented ODLHBD-ALLD model mainly intends to detect and classify acute lymphoblastic leukemia using blood smear images. To accomplish this, the ODLHBD-ALLD model involves the Gabor filtering (GF) technique as a noise removal step. In addition, it makes use of a modified fuzzy c-means (MFCM) based segmentation approach for segmenting the images. Besides, the competitive swarm optimization (CSO) algorithm with the EfficientNetB0 model is utilized as a feature extractor. Lastly, the attention-based long-short term memory (ABiLSTM) model is employed for the proper identification of class labels. For investigating the enhanced performance of the ODLHBD-ALLD approach, a wide range of simulations were executed on open access dataset. The comparative analysis reported the betterment of the ODLHBD-ALLD model over the other existing approaches.

Incremental Ant-Miner Classifier for Online Big Data Analytics.

Internet of Things (IoT) environments produce large amounts of data that are challenging to analyze. The most challenging aspect is reducing the quantity of consumed resources and time required to retrain a machine learning model as new data records arrive. Therefore, for big data analytics in IoT environments where datasets are highly dynamic, evolving over time, it is highly advised to adopt an online (also called incremental) machine learning model that can analyze incoming data instantaneously, rather than an offline model (also called static), that should be retrained on the entire dataset as new records arrive. The main contribution of this paper is to introduce the Incremental Ant-Miner (IAM), a machine learning algorithm for online prediction based on one of the most well-established machine learning algorithms, Ant-Miner. IAM classifier tackles the challenge of reducing the time and space overheads associated with the classic offline classifiers, when used for online prediction. IAM can be exploited in managing dynamic environments to ensure timely and space-efficient prediction, achieving high accuracy, precision, recall, and F-measure scores. To show its effectiveness, the proposed IAM was run on six different datasets from different domains, namely horse colic, credit cards, flags, ionosphere, and two breast cancer datasets. The performance of the proposed model was compared to ten state-of-the-art classifiers: naive Bayes, logistic regression, multilayer perceptron, support vector machine, K*, adaptive boosting (AdaBoost), bagging, Projective Adaptive Resonance Theory (PART), decision tree (C4.5), and random forest. The experimental results illustrate the superiority of IAM as it outperformed all the benchmarks in nearly all performance measures. Additionally, IAM only needs to be rerun on the new data increment rather than the entire big dataset on the arrival of new data records, which makes IAM better in time- and resource-saving. These results demonstrate the strong potential and efficiency of the IAM classifier for big data analytics in various areas.

Molecular Detection of Tick-Borne Rickettsial Pathogens Associated with the Arabian Camel (Camelus dromedarius) in Riyadh and the Eastern Region, Saudi Arabia.

BACKGROUND: In Saudi Arabia, records on molecular identification of tick-borne infections in camels are relatively scarce; few molecular epidemiological studies have been conducted. OBJECTIVE: This study aimed to find Anaplasma species and Piroplasma spp. in camels from Riyadh and the Eastern Region, Saudi Arabia. ANIMALS: A total of 1369 blood samples were collected from camels from Riyadh and the Eastern Region and analyzed for the DNA of Anaplasma and Piroplasma species by polymerase chain reaction (PCR). RESULTS: Piroplasma spp. infection was not observed in any of the blood samples. 616 camels (44.99%) were found to be positive for Anaplasma infection by PCR targeting the 16S rRNA and COX1 genes. Six Anaplasma sequences for the 16S rRNA gene (OK481101-OK481106) were deposited in GenBank and six for the COX1 gene (OK490994-OK490999). They showed 98.3% and 62.7% similarities with Anaplasma marginale (A. marginale) detected in Kenya and Brazil, respectively. Phylogenetic studies revealed that the 12 sequences reported in this study were closely related; they were found in the same cluster as A. marginale isolates previously recorded in South Africa, Brazil, USA, China, and Israel. CONCLUSION: Finally, 12 Anaplasma sequences closely related to A. marginale were detected in camels in Riyadh and the Eastern Region, Saudi Arabia. Camels in these areas were confirmed to be free of Piroplasma.

Identification of Theileria spp. in sheep and goats from Jeddah, Saudi Arabia, using molecular techniques.

BACKGROUND: Thileriosis is a tick -born disease caused by hemoprotozoan parasites which has global veterinary and economic implications. METHODS: Blood samples were collected from 216 sheep and 83 goats from Jeddah, Saudi Arabia, were analyzed to determine whether the animals were infected with Theileria spp. parasites. The parasites were detected using a polymerase chain reaction (PCR) targeting the gene of 18S rRNA followed by sequencing. RESULTS: According to obtained findings, Theileria spp. were detected in sheep (57.8%, 48/83) and goats (51.9%, 112/216). Phylogenetic analysis to sequence data showed that T. ovis identified in this study were found to be closely connected to an isolate from Turkey, with 84.4-99.8% pairwise identity and 52.35-99.79% coverage.

Empirical Evaluation of Alternative Time-Series Models for COVID-19 Forecasting in Saudi Arabia.

COVID-19 is a disease-causing coronavirus strain that emerged in December 2019 that led to an ongoing global pandemic. The ability to anticipate the pandemic's path is critical. This is important in order to determine how to combat and track its spread. COVID-19 data is an example of time-series data where several methods can be applied for forecasting. Although various time-series forecasting models are available, it is difficult to draw broad theoretical conclusions regarding their relative merits. This paper presents an empirical evaluation of several time-series models for forecasting COVID-19 cases, recoveries, and deaths in Saudi Arabia. In particular, seven forecasting models were trained using autoregressive integrated moving average, TBATS, exponential smoothing, cubic spline, simple exponential smoothing Holt, and HoltWinters. The models were built using publicly available daily data of COVID-19 during the period of 24 March 2020 to 5 April 2021 reported in Saudi Arabia. The experimental results indicate that the ARIMA model had a smaller prediction error in forecasting confirmed cases, which is consistent with results reported in the literature, while cubic spline showed better predictions for recoveries and deaths. As more data become available, a fluctuation in the forecasting-accuracy metrics was observed, possibly due to abrupt changes in the data.

A deep learning approach to predict blood-brain barrier permeability.

The blood-brain barrier plays a crucial role in regulating the passage of 98% of the compounds that enter the central nervous system (CNS). Compounds with high permeability must be identified to enable the synthesis of brain medications for the treatment of various brain diseases, such as Parkinson's, Alzheimer's, and brain tumors. Throughout the years, several models have been developed to solve this problem and have achieved acceptable accuracy scores in predicting compounds that penetrate the blood-brain barrier. However, predicting compounds with "low" permeability has been a challenging task. In this study, we present a deep learning (DL) classification model to predict blood-brain barrier permeability. The proposed model addresses the fundamental issues presented in former models: high dimensionality, class imbalances, and low specificity scores. We address these issues to enhance the high-dimensional, imbalanced dataset before developing the classification model: the imbalanced dataset is addressed using oversampling techniques and the high dimensionality using a non-linear dimensionality reduction technique known as kernel principal component analysis (KPCA). This technique transforms the high-dimensional dataset into a low-dimensional Euclidean space while retaining invaluable information. For the classification task, we developed an enhanced feed-forward deep learning model and a convolutional neural network model. In terms of specificity scores (i.e., predicting compounds with low permeability), the results obtained by the enhanced feed-forward deep learning model outperformed those obtained by other models in the literature that were developed using the same technique. In addition, the proposed convolutional neural network model surpassed models used in other studies in multiple accuracy measures, including overall accuracy and specificity. The proposed approach solves the problem inevitably faced with obtaining low specificity resulting in high false positive rate.

A Convolutional Neural Network for Improved Anomaly-Based Network Intrusion Detection.

Cybersecurity protects and recovers computer systems and networks from cyber attacks. The importance of cybersecurity is growing commensurately with people's increasing reliance on technology. An anomaly detection-based network intrusion detection system is essential to any security framework within a computer network. In this article, we propose two models based on deep learning to address the binary and multiclass classification of network attacks. We use a convolutional neural network architecture for our models. In addition, a hybrid two-step preprocessing approach is proposed to generate meaningful features. The proposed approach combines dimensionality reduction and feature engineering using deep feature synthesis. The performance of our models is evaluated using two benchmark data sets, namely the network security laboratory-knowledge discovery in databases data set and the University of New South Wales Network Based 2015 data set. The performance is compared with similar deep learning approaches in the literature, as well as state-of-the-art classification models. Experimental results show that our models achieve good performance in terms of accuracy and recall, outperforming similar models in the literature.

Prevalence Rate and Molecular Characteristics of Oestrus ovis L. (Diptera, Oestridae) in Sheep and Goats from Riyadh, Saudi Arabia.

Heads of sheep (n = 600) and goats (n = 800) slaughtered at Al-Aziziah Abattoir in Riyadh, Saudi Arabia, were inspected for the presence of O. ovis larvae (L). Heads were split along the longitudinal axes, and larvae (L1, L2, and L3) were gathered. The infestation rate was significantly higher in goats (44.5%; 356/800) than that in sheep (22.3%; 134/600). Out of the 151 collected larvae from sheep, 0% were L1, 1.3% were L2, and 98.7% were L3. Out of the total of 468 larvae from goats, 0% were L1, 1.2% were L2, and 98.8% were L3. The infestation rate was significantly higher in males than that in females. Myiasis-causing larvae collected from Riyadh, Saudi Arabia, were authenticated as O. ovis, according to morphological characteristics. Polymerase chain reaction (PCR) amplification of a partial fragment (600 bp) of the mitochondrial cytochrome c oxidase subunit I (mtCOI) gene further confirmed the species. Phylogenetic analysis based on the partial mtCOI gene sequence demonstrated that 23 unique sequences showed high similarity based on nucleotide pairs of O. ovis accessions retrieved from GenBank.

Machine learning approaches in COVID-19 diagnosis, mortality, and severity risk prediction: A review.

The existence of widespread COVID-19 infections has prompted worldwide efforts to control and manage the virus, and hopefully curb it completely. One important line of research is the use of machine learning (ML) to understand and fight COVID-19. This is currently an active research field. Although there are already many surveys in the literature, there is a need to keep up with the rapidly growing number of publications on COVID-19-related applications of ML. This paper presents a review of recent reports on ML algorithms used in relation to COVID-19. We focus on the potential of ML for two main applications: diagnosis of COVID-19 and prediction of mortality risk and severity, using readily available clinical and laboratory data. Aspects related to algorithm types, training data sets, and feature selection are discussed. As we cover work published between January 2020 and January 2021, a few key points have come to light. The bulk of the machine learning algorithms used in these two applications are supervised learning algorithms. The established models are yet to be used in real-world implementations, and much of the associated research is experimental. The diagnostic and prognostic features discovered by ML models are consistent with results presented in the medical literature. A limitation of the existing applications is the use of imbalanced data sets that are prone to selection bias.

Molecular Identification of Trypanosoma evansi Isolated from Arabian Camels (Camelus dromedarius) in Riyadh and Al-Qassim, Saudi Arabia.

We analyzed the blood from 400 one-humped camels, Camelus dromedarius (C. dromedarius), in Riyadh and Al-Qassim, Saudi Arabia to determine if they were infected with the parasite Trypanosoma spp. Polymerase chain reaction (PCR) targeting the internal transcribed spacer 1 (ITS1) gene was used to detect the prevalence of Trypanosoma spp. in the camels. Trypanosoma evansi (T. evansi) was detected in 79 of 200 camels in Riyadh, an infection rate of 39.5%, and in 92 of 200 camels in Al-Qassim, an infection rate of 46%. Sequence and phylogenetic analyses revealed that the isolated T. evansi was closely related to the T. evansi that was detected in C. dromedarius in Egypt and the T. evansi strain B15.1 18S ribosomal RNA gene identified from buffalo in Thailand. A BLAST search revealed that the sequences are also similar to those of T. evansi from beef cattle in Thailand and to T. brucei B8/18 18S ribosomal RNA from pigs in Nigeria.

Early Detection of Red Palm Weevil, Rhynchophorus ferrugineus (Olivier), Infestation Using Data Mining.

In the past 30 years, the red palm weevil (RPW), Rhynchophorus ferrugineus (Olivier), a pest that is highly destructive to all types of palms, has rapidly spread worldwide. However, detecting infestation with the RPW is highly challenging because symptoms are not visible until the death of the palm tree is inevitable. In addition, the use of automated RPW weevil identification tools to predict infestation is complicated by a lack of RPW datasets. In this study, we assessed the capability of 10 state-of-the-art data mining classification algorithms, Naive Bayes (NB), KSTAR, AdaBoost, bagging, PART, J48 Decision tree, multilayer perceptron (MLP), support vector machine (SVM), random forest, and logistic regression, to use plant-size and temperature measurements collected from individual trees to predict RPW infestation in its early stages before significant damage is caused to the tree. The performance of the classification algorithms was evaluated in terms of accuracy, precision, recall, and F-measure using a real RPW dataset. The experimental results showed that infestations with RPW can be predicted with an accuracy up to 93%, precision above 87%, recall equals 100%, and F-measure greater than 93% using data mining. Additionally, we found that temperature and circumference are the most important features for predicting RPW infestation. However, we strongly call for collecting and aggregating more RPW datasets to run more experiments to validate these results and provide more conclusive findings.

A Recurrent Neural Network model to predict blood-brain barrier permeability.

The rapid development of computational methods and the increasing volume of chemical and biological data have contributed to an immense growth in chemical research. This field of study is known as "chemoinformatics," which is a discipline that uses machine-learning techniques to extract, process, and extrapolate data from chemical structures. One of the significant lines of research in chemoinformatics is the study of blood-brain barrier (BBB) permeability, which aims to identify drug penetration into the central nervous system (CNS). In this research, we attempt to solve the problem of BBB permeability by predicting compounds penetration to the CNS. To accomplish this goal: (i) First, an overview is provided to the field of chemoinformatics, its definition, applications, and challenges, (ii) Second, a broad view is taken to investigate previous machine-learning and deep-learning computational models to solve BBB permeability. Based on the analysis of previous models, three main challenges that collectively affect the classifier performance are identified, which we define as "the triple constraints"; subsequently, we map each constraint to a proposed solution, (iii) Finally, we conclude this endeavor by proposing a deep learning based Recurrent Neural Network model, to predict BBB permeability (RNN-BBB model). Our model outperformed other studies from the literature by scoring an overall accuracy of 96.53%, and a specificity score of 98.08%. The obtained results confirm that addressing the triple constraints substantially improves the classification model capability specifically when predicting compounds with low penetration.

Identification of Sarcocystis Spp. in One-humped Camels (Camelus dromedarius) from Riyadh and Dammam, Saudi Arabia, via Histological and Phylogenetic Approaches.

Sarcocystis (S.) spp. are intracellular protozoan parasites that infect birds and animals, resulting in substantial commercial losses. Sarcocystis spp. have an indirect life cycle; canines and felines are known to act as final hosts, and numerous domestic and wild animals act as intermediate hosts. The presence of sarcocysts in camel meat may diminish its commercial quality. There is limited knowledge regarding the taxonomy and diagnosis of Sarcocystis spp. that infect camels in Saudi Arabia. In this study, transmission electron microscopy (TEM) revealed S. cameli and S. camelicanis (camelicanis) in Camelus (C.) dromedarius. This is the first report of S. camelicanis in Saudi Arabia and is considered a significant finding. Based on cytochrome c oxidase subunit I gene (COX1) sequences, two samples of Sarcocystis spp. isolated from C. dromedarius in Riyadh and Dammam were grouped with S. levinei hosted by Bubalus bubalis in India, S. rangi hosted by Rangifer tarandus in Norway, S. miescheriana hosted by Sus scrofa in Italy and S. fayeri hosted by Equus caballus in Canada. The sequences obtained in this study have been deposited in GenBank.

Analyzing Passive BCI Signals to Control Adaptive Automation Devices.

Brain computer interfaces are currently considered to greatly enhance assistive technologies and improve the experiences of people with special needs in the workplace. The proposed adaptive control model for smart offices provides a complete prototype that senses an environment's temperature and lighting and responds to users' feelings in terms of their comfort and engagement levels. The model comprises the following components: (a) sensors to sense the environment, including temperature and brightness sensors, and a headset that collects electroencephalogram (EEG) signals, which represent workers' comfort levels; (b) an application that analyzes workers' feelings regarding their willingness to adjust to a space based on an analysis of collected data and that determines workers' attention levels and, thus, engagement; and (c) actuators to adjust the temperature and/or lighting. This research implemented independent component analysis to remove eye movement artifacts from the EEG signals and used an engagement index to calculate engagement levels. This research is expected to add value to research on smart city infrastructures and on assistive technologies to increase productivity in smart offices.

Molecular Characterization of Sarcocystis Species Isolated from Sheep and Goats in Riyadh, Saudi Arabia.

Sarcocystosis is induced by species of Sarcocystis, which is an intracellular protozoan parasite in the phylum Apicomplexa. The diversity and importance of Sarcocystis species in sheep and goats in Saudi Arabia are poorly understood. In this study, the tongue, esophagus, heart, diaphragm, and skeletal muscles were collected from 230 sheep and 84 goats, and the tissues were examined for the presence of Sarcocystis species by macroscopic examination and light microscopy. Microscopic Sarcocystis species cysts were found in both sheep and goats. Transmission electron microscopy (TEM) revealed S. tenella in sheep and S. capracanis in goats. Sarcocystis species were confirmed for the first time in Saudi Arabian sheep and goats by molecular testing. S. capracanis was most closely related to S. tenella, with the COX1 sequences sharing 91.7% identity. A phylogenetic analysis produced similar results and indicated that the Sarcocystis isolates were within a group of Sarcocystis species in which dogs were the final host. Finally, the Sarcocystis species cysts from sheep and goats could be grouped together, indicating that they were strongly related.

Gene-based molecular characterization of cox1 and pnad5 in Hymenolepis nana isolated from naturally infected mice and rats in Saudi Arabia.

Mice and rats are animals commonly used in research and laboratory testing. Compared with other animal species, they harbor many more zoonotic agents. Hymenolepis nana (H. nana) is a common tapeworm that parasitizes both humans and rodents. Although this tapeworm is of socio-economic importance worldwide, information related to its mitochondrial genome is limited. The present study examined the sequence diversity of two mitochondrial (mt) genes, subunit I of cytochrome oxidase (cox1) and NADH dehydrogenase subunit 5 (pnad5), of H. nana in mice and rats from two geographical regions of Saudi Arabia (Makkah and Riyadh). Partial sequences of cox1 and pnad 5 from individual H. nana isolates were separately amplified using polymerase chain reaction (PCR) and sequenced. The GC contents of the sequences ranged between 31.6-33.5% and 27.2-28.6% for cox1 and pnad5, respectively. The genomic similarity among specimens determined via cox1 primer and pnad5 primer was 97.1% and 99.7%, respectively. Based on these primers, our data did not indicate any differences between H. nana from rat and mice isolates. Results demonstrated that the present species are deeply embedded in the genus Hymenolepis with close relationship to other Hymenolepis species, including H. nana as a putative sister taxon, and that the isolates cannot be categorized as belonging to two different groups with origins in Makkah and Riyadh.

Gene-based molecular analysis of COX1 in Echinococcus granulosus cysts isolated from naturally infected livestock in Riyadh, Saudi Arabia.

The diversity and importance of Echinococcus species in domesticated animals in Saudi Arabia are poorly understood. In this study, 108 singular (hydatid) cysts were collected from goats (n = 25), sheep (n = 56) and camels (n = 27). DNA was extracted from the protoscoleces of individual fertile cysts and used for polymerase chain reaction (PCR) amplification of mitochondrial subunit 1 of the cytochrome c oxidase 1 (cox1) gene. Amplicon sequencing results revealed the presence of Echinococcus granulosus sensustricto (s.s.) (genotypes G1-G3) in 16 of the17 sheep cysts and 2 of the 27 camel cysts.of these samples, 18 (2 camel and 16 sheep) were divided into genotypes G1, G2, and G3.