Search

Abstract This study evaluates the efficacy of discrete bacterial consortia in bioremediating sandy loamy soil deliberately contaminated with 20 mg/kg of chlorantraniliprole (CAP). It monitors alterations in total bacterial populations and CO2 emissions, tracking residual CAP levels through UV scanning and HPLC analysis. Six active bacterial degraders (four Bacillus strains (B. subtilis subsp. subtilis AZFS3, B. pumilus AZFS5, B. mojavensis AZFS15, and B. paramycoides AZFS18), one Alcaligenes strain (A. aquatilis KZFS11), and one Pseudomonas strain (P. aeruginosa KZFS4)) were used in single or combined preparations and grown on trypticase soy broth for 24 h at 30 °C before preparing the inoculants and adjusting the bacterial cell count to 107 CFU/dwt g soil. The bacterial consortia were added to the CAP-contaminated soil and incubated for 20 days at 30 °C. The di-, tetra-, and hexa-bacterial consortia recorded the highest levels of viable bacteria, reaching their peak after 3 to 11 days of incubation. Then, they declined to the minimum levels at the end of the 20 days, which coincided with their complete removal of CAP from the soil. At the end of the incubation period (20 days), the CAP was mainly biodegraded, scoring biodegradation rates of 90.05%, 93.65%, and 98.65% for T3, T4, and T5, respectively. This concurred with the highest average CO2 production. Based on the results of the HPLC analysis, the hexa-bacterial consortium T5 demonstrated the highest rate of CAP biodegradation (99.33%) after a 20-day incubation period, resulting in the lowest residual level of CAP in the soil (0.67%). Bioinformatic analysis predicted that the CAP biodegradation pathway reached CO2 and H2O. Under optimized conditions, the hexa-bacteria consortium is the most effective CAP biodegraded and is recommended as an eco-friendly treatment for eliminating CAP pollution in the field.

Abstract Facial Emotion Recognition (FER) is a very challenging task due to the varying nature of facial expressions, occlusions, illumination, pose variations, cultural and gender differences, and many other aspects that cause a drastic degradation in quality of facial images. In this paper, an anti-aliased deep convolution network (AA-DCN) model has been developed and proposed to explore how anti-aliasing can increase and improve recognition fidelity of facial emotions. The AA-DCN model detects eight distinct emotions from image data. Furthermore, their features have been extracted using the proposed model and numerous classical deep learning algorithms. The proposed AA-DCN model has been applied to three different datasets to evaluate its performance: The Cohn-Kanade Extending (CK+) database has been utilized, achieving an ultimate accuracy of 99.26% in (5 min, 25 s), the Japanese female facial expressions (JAFFE) obtained 98% accuracy in (8 min, 13 s), and on one of the most challenging FER datasets; the Real-world Affective Face (RAF) dataset; reached 82%, in low training time (12 min, 2s). The experimental results demonstrate that the anti-aliased DCN model is significantly increasing emotion recognition while improving the aliasing artifacts caused by the down-sampling layers.

Abstract In this paper, based on facial landmark approaches, the possible vulnerability of ensemble algorithms to the FGSM attack has been assessed using three commonly used models: convolutional neural network-based antialiasing (A_CNN), Xc_Deep2-based DeepLab v2, and SqueezeNet (Squ_Net)-based Fire modules. Firstly, the three individual deep learning classifier-based Facial Emotion Recognition (FER) classifications have been developed; the predictions from all three classifiers are then merged using majority voting to develop the HEM_Net-based ensemble model. Following that, an in-depth investigation of their performance in the case of attack-free has been carried out in terms of the Jaccard coefficient, accuracy, precision, recall, F1 score, and specificity. When applied to three benchmark datasets, the ensemble-based method (HEM_Net) significantly outperforms in terms of precision and reliability while also decreasing the dimensionality of the input data, with an accuracy of 99.3%, 87%, and 99% for the Extended Cohn-Kanade (CK+), Real-world Affective Face (RafD), and Japanese female facial expressions (Jaffee) data, respectively. Further, a comprehensive analysis of the drop in performance of every model affected by the FGSM attack is carried out over a range of epsilon values (the perturbation parameter). The results from the experiments show that the advised HEM_Net model accuracy declined drastically by 59.72% for CK + data, 42.53% for RafD images, and 48.49% for the Jaffee dataset when the perturbation increased from A to E (attack levels). This demonstrated that a successful Fast Gradient Sign Method (FGSM) can significantly reduce the prediction performance of all individual classifiers with an increase in attack levels. However, due to the majority voting, the proposed HEM_Net model could improve its robustness against FGSM attacks, indicating that the ensemble can lessen deception by FGSM adversarial instances. This generally holds even as the perturbation level of the FGSM attack increases.

Firms in the Gulf region are predominantly governed by the entrepreneurial model where royal ownerships/management dominants. Using a Panel Regression Model in a sample of 202 firms across six countries in the Gulf Cooperating Council (GCC), this paper assesses the direct effect of corporate cash holdings on firms’ financial objectives or performance, and also how managerial entrenchments directly affect corporate cash holdings in GCC. It further tests the moderation and interaction effects of managerial entrenchments on the relationship between cash-holdings and firms’ financial performance. The research concludes that the effect of corporate cash holdings on firms’ performance is negative, especially for absolute and relatively liquidity firms. This proofs the U-shape hypothesis of cash holdings. Also, the results show that different managerial entrenchment variables have different effects on corporate financial performance or objectives. Furthermore, the moderation and interaction effects of managerial entrenchment on the relationship between cash holding and firms’ financial performance (i.e. ROA and ROE) are inconsistent. These findings show randomness in how managerial entrenchment affects firms’ performance in the GCC region. However, the interaction between cash and leverage is consistently positive on shareholders wealth (i.e. ROE) for all liquidity thresholds. This highlights the benefits of debts in corporate financing.

Abstract Acetamiprid (ACDP) is a widely used neonicotinoid insecticide that is popular for its efficacy in controlling fleas in domestic settings and for pets. Our study aims to offer a comprehensive examination of the toxicological impacts of ACDP and the prophylactic effects of cinnamon nanoemulsions (CMNEs) on the pathological, immunohistochemical, and hematological analyses induced by taking ACDP twice a ‎week for 28 days. Forty healthy rats were divided into four groups (n = 10) at random; the first group served as control rats; the second received CMNEs (2 mg/Kg body weight); the third group received acetamiprid (ACDP group; 21.7 mg/Kg body weight), and the fourth group was given both ACDP and CMNEs by oral gavage. Following the study period, tissue and blood samples were extracted and prepared for analysis. According to a GC-MS analysis, CMNEs had several bioactive ingredients that protected the liver from oxidative stress by upregulating antioxidant and anti-inflammatory agents. Our findings demonstrated that whereas ACDP treatment considerably boosted white blood cells (WBCs) and lymphocytes, it significantly lowered body weight gain (BWG), red blood cells (RBCs), hemoglobin (Hb), hematocrit (HCT), and platelets (PLT). ACDP notably reduced antioxidant enzyme activities: superoxide dismutase (SOD), glutathione peroxidase (GPx), and catalase (CAT) and elevated hydrogen peroxide and malondialdehyde levels compared with other groups. ACDP remarkably raised alanine aminotransferase (ALT), aspartate amino transaminase (AST), and alkaline phosphatase (ALP) levels. Moreover, the histopathological and immunohistochemistry assays discovered a severe toxic effect on the liver and kidney following ACDP delivery. Furthermore, cyclooxygenase 2 (COX-2) + immunoexpression was enhanced after treatment with CMNEs. All of the parameters above were returned to nearly normal levels by the coadministration of CMNEs. The molecular docking of cinnamaldehyde with COX-2 also confirmed the protective potential of CMNEs against ACDP toxicity. Our findings highlighted that the coadministration of CMNEs along with ACDP diminished its toxicity by cutting down oxidative stress and enhancing antioxidant capacity, demonstrating the effectiveness of CMNEs in lessening ACDP toxicity.

The author posits that the establishment of a blockchain-based health data marketplace where EHR, IoMT, and wearable-derived data can be monetized by selling it to data consumers like medical professionals, researchers, regulators, third-party (e.g., AI service providers) and policymakers can solve this data centralization problem.

Meiosis is a critical process in sexual reproduction, and errors during this cell division can significantly impact fertility. Successful meiosis relies on the coordinated action of numerous genes involved in DNA replication, strand breaks, and subsequent rejoining. DNA topoisomerase enzymes play a vital role by regulating DNA topology, alleviating tension during replication and transcription. To elucidate the specific function of DNA topoisomerase 1α ( $AtTOP1 \alpha$AtTOP1α ) in male reproductive development of Arabidopsis thaliana, we investigated meiotic cell division in Arabidopsis flower buds. Combining cytological and biochemical techniques, we aimed to reveal the novel contribution of $AtTOP1 \alpha$AtTOP1α to meiosis. Our results demonstrate that the absence of $AtTOP1 \alpha$AtTOP1α leads to aberrant chromatin behavior during meiotic division. Specifically, the top1α1 mutant displayed altered heterochromatin distribution and clustered centromere signals at early meiotic stages. Additionally, this mutant exhibited disruptions in the distribution of 45s rDNA signals and a reduced frequency of chiasma formation during metaphase I, a crucial stage for genetic exchange. Furthermore, the atm-2×top1α1 double mutant displayed even more severe meiotic defects, including incomplete synapsis, DNA fragmentation, and the presence of polyads. These observations collectively suggest that $AtTOP1 \alpha$AtTOP1α plays a critical role in ensuring accurate meiotic progression, promoting homologous chromosome crossover formation, and potentially functioning in a shared DNA repair pathway with ATAXIA TELANGIECTASIA MUTATED (ATM) in Arabidopsis microspore mother cells.

Dorsal hand vein (DHV) recognition is a burgeoning biometric technology that has recently garnered considerable attention. This article uses image processing and deep learning to present a novel DHV recognition approach. It involves detecting and identifying the unique patterns present in the DHV. The proposed system begins with the preprocessing mechanism that is applied to enhance the quality of the acquired images, including contrast enhancement and noise reduction, by using some filters such as Median and Contrast Limited Adaptive Histogram Equalization (CLAHE). Next, a deep learning model, such as a convolutional neural network (CNN), is employed to automatically abstract discriminative features from the preprocessed vein images. The empirical outcomes prove the influence and reliability of the proposed technique for vein recognition, making it a promising solution for biometric authentication systems. Compared with traditional CNN, the proposed approach shows good accuracy and classification rate results. The suggested model achieved a high recognition rate accuracy, recall, precious, and f-score of 99.7%,97%,96%, and 96%, respectively, and a recognition time of about 1283.45 s. To enrich the model’s capability for feature recognition and reduce recognition time, decrease the intricacy of learning and the connectivity CNN structure, an alternative approach based on Restricted Boltzmann Machines (RBM) was assessed. This strategy exhibits superior accuracy in comparison to other contemporary algorithms. The proposed RBM achieved a high recognition rate accuracy, recall, precious, and f-score of 99.9%,99%,99%, and 99%, respectively, and a recognition time of about 137.235s.

The need for non-interactive human recognition systems to ensure safe isolation between users and biometric equipment has been exposed by the COVID-19 pandemic. This study introduces a novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication (MSDCS-PHGA). The proposed MSDCS-PHGA involves segmenting, preprocessing, and resizing silhouette images into three scales. Gait features are extracted from these multi-scale images using custom convolutional layers and fused to form an integrated feature set. This multi-scaled deep convolutional approach demonstrates its efficacy in gait recognition by significantly enhancing accuracy. The proposed convolutional neural network (CNN) architecture is assessed using three benchmark datasets: CASIA, OU-ISIR, and OU-MVLP. Moreover, the proposed model is evaluated against other pre-trained models using key performance metrics such as precision, accuracy, sensitivity, specificity, and training time. The results indicate that the proposed deep CNN model outperforms existing models focused on human gait. Notably, it achieves an accuracy of approximately 99.9% for both the CASIA and OU-ISIR datasets and 99.8% for the OU-MVLP dataset while maintaining a minimal training time of around 3 min.

This study utilizes Mentha piperita (MI) for the first time to investigate the uptake and translocation of chlorpyrifos (CPF; 10 µg g−1) from soil, introducing a new approach to improve the efficacy of this technique, which includes using biosurfactants (Bacillus subtilis and Pseudomonas aeruginosa) at 107 CFU/mL to degrade CPF under greenhouse conditions. Moreover, antioxidant enzymes, including superoxide dismutase (SOD) and peroxidase (Prx), and oxidative stress due to hydrogen peroxide (H2O2) and malondialdehyde (MDA) in MI roots and leaves were evaluated under CPF stress. Our results demonstrated that amending soil with MI and B. subtilis followed by P. aeruginosa significantly reduced CPF levels in the soil (p > 0.05) and enhanced CPF concentrations in MI roots and leaves after 1, 3, 7, 10, and 14 days of the experiment. Furthermore, CPF showed its longest half-life (t1/2) in soil contaminated solely with CPF, lasting 15.36 days. Conversely, its shortest half-life occurred in soil contaminated with CPF and treated with MI along with B. subtilis, lasting 4.65 days. Soil contaminated with CPF and treated with MI and P. aeruginosa showed a half-life of 7.98 days. The half-life (t1/2) of CPF-contaminated soil with MI alone was 11.41 days. A batch equilibrium technique showed that B. subtilis is better than P. aeruginosa for eliminating CPF from soil in In vitro experiments. Notably, CPF-polluted soil treated with coadministration of MI and the tested bacteria improved the activities of SOD and Prx and reduced H2O2 and MDA compared with CPF-polluted soil treated with MI alone. Our findings demonstrated that using B. subtilis and P. aeruginosa as biosurfactants to augment phytoremediation represents a commendable strategy for enhancing the remediation of CPF contamination in affected sites while reducing the existence of harmful pesticide remnants in crop plants.

Recently, Machine Learning (ML)-based solutions have been widely adopted to tackle the wide range of security challenges that have affected the progress of the Internet of Things (IoT) in various domains. Despite the reported promising results, the ML-based Intrusion Detection System (IDS) proved to be vulnerable to adversarial examples, which pose an increasing threat. In fact, attackers employ Adversarial Machine Learning (AML) to cause severe performance degradation and thereby evade detection systems. This promoted the need for reliable defense strategies to handle performance and ensure secure networks. This work introduces RobEns, a robust ensemble framework that aims at: (i) exploiting state-of-the-art ML-based models alongside ensemble models for IDSs in the IoT network; (ii) investigating the impact of evasion AML attacks against the provided models within a black-box scenario; and (iii) evaluating the robustness of the considered models after deploying relevant defense methods. In particular, four typical AML attacks are considered to investigate six ML-based IDSs using three benchmarking datasets. Moreover, multi-class classification scenarios are designed to assess the performance of each attack type. The experiments indicated a drastic drop in detection accuracy for some attempts. To harden the IDS even further, two defense mechanisms were derived from both data-based and model-based methods. Specifically, these methods relied on feature squeezing as well as adversarial training defense strategies. They yielded promising results, enhanced robustness, and maintained standard accuracy in the presence or absence of adversaries. The obtained results proved the efficiency of the proposed framework in robustifying IDS performance within the IoT context. In particular, the accuracy reached 100% for black-box attack scenarios while preserving the accuracy in the absence of attacks as well.

Introduction To investigate the short-term effect of Maitland mobilization on lumbar proprioception, pain intensity, and functional disability in patients with chronic nonspecific low back pain (CNSLBP). Methods Fifty-four subjects aged 18–30 years old with CNSLBP were randomly assigned into two groups. The experimental group received a selected exercise program (stretching, strengthening, and lumbar stabilization exercises) and Maitland posterior-anterior vertebral mobilization three sessions /week, whereas the control group received exercises only. Lumbar repositioning error (LRE), pain intensity, and function disability were measured using an isokinetic dynamometer, visual analog scale (VAS), and the Arabic version of the Oswestry Disability Index (ODI), respectively. Measurements were taken at baseline and four weeks after intervention. Results Within-group analysis showed a significant decrease in LRE, VAS, and ODI after treatment ( p < 0.001). Between-group analysis revealed a significant difference between groups post-intervention favoring the Maitland mobilization group ( p < 0.001) where the mean differences at 95% confidence interval were (–2.10, –1.36) for LRE, (–34.53, –25.61) for VAS and (–9, –7.07) for ODI. Conclusions Maitland lumbar mobilization is effective in improving lumbar proprioception, pain intensity, and functional disability in patients with CNSLBP.

Brain tumor diagnosis traditionally relies on the manual examination of magnetic resonance images (MRIs), a process that is prone to human error and is also time consuming. Recent advancements leverage machine learning models to categorize tumors, such as distinguishing between “malignant” and “benign” classes. This study focuses on the supervised machine learning task of classifying “firm” and “soft” meningiomas, critical for determining optimal brain tumor treatment. The research aims to enhance meningioma firmness detection using state-of-the-art deep learning architectures. The study employs a YOLO architecture adapted for meningioma classification (Firm vs. Soft). This YOLO-based model serves as a machine learning component within a proposed CAD system. To improve model generalization and combat overfitting, transfer learning and data augmentation techniques are explored. Intra-model analysis is conducted for each of the five YOLO versions, optimizing parameters such as the optimizer, batch size, and learning rate based on sensitivity and training time. YOLOv3, YOLOv4, and YOLOv7 demonstrate exceptional sensitivity, reaching 100%. Comparative analysis against state-of-the-art models highlights their superiority. YOLOv7, utilizing the SGD optimizer, a batch size of 64, and a learning rate of 0.01, achieves outstanding overall performance with metrics including mean average precision (99.96%), precision (98.50%), specificity (97.95%), balanced accuracy (98.97%), and F1-score (99.24%). This research showcases the effectiveness of YOLO architectures in meningioma firmness detection, with YOLOv7 emerging as the optimal model. The study’s findings underscore the significance of model selection and parameter optimization for achieving high sensitivity and robust overall performance in brain tumor classification.

With the growing use of digital technologies, the vision of a predictive, preventive and personalised healthcare system, commonly termed healthcare 4.0, is becoming tangible. However, the manifestation of healthcare 4.0 relies on empowering patients as active stakeholders of the healthcare system and transforming traditionally siloed data repositories into accessible ones. Combining blockchain-like distributed technology and Airbnb-like sharing economy model, this paper proposes a digital health data marketplace (DHDM) through which patients, as the data producer, can sell their health data to data consumers like medical practitioners, researchers, policymakers and machine learning algorithm developers without compromising privacy and security. In conjunction with the Welsh Secure Anonymised Information Linkage (SAIL) Databank, a traditional centralised and siloed data repository, DHDM was evaluated in a simulated environment to understand the technical feasibility, regulation compliance and, most importantly, the impact of such marketplace on healthcare 4.0 transformation.

The effectiveness of deep learning models depends on their architecture and topology. Thus, it is essential to determine the optimal depth of the network. In this paper, we propose a novel approach to learn the optimal depth of a stacked AutoEncoder, called Dynamic Depth for Stacked AutoEncoders (DDSAE). DDSAE learns in an unsupervised manner the depth of a stacked AutoEncoder while training the network model. Specifically, we propose a novel objective function, aside from the AutoEncoder’s loss function to optimize the network depth: The optimization of the objective function determines the layers’ relevance weights. Additionally, we propose an algorithm that iteratively prunes the irrelevant layers based on the learned relevance weights. The performance of DDSAE was assessed using benchmark and real datasets.

While the past 50 years have been categorized as the Information or Digital Age, the mass amounts of digitized data has been sorely underutilized. It was only recently through the COVID-19 pandemic that accelerated efforts were sought to harness this data with the use of blockchain technology in healthcare. Through the infrastructure and its tokenization applications, we can now effectively leverage healthcare data into more efficient business processes, secure better patient engagement and outcomes all while generating new revenue streams for an array of healthcare stakeholders. It is in compiling this stockpiled data into new, compliant business models and utilizing blockchain technology that we can reap the full potential of this era. Here are some predictions as to how we might set about these efforts in 2023.

Semi-supervised clustering typically relies on both labeled and unlabeled data to guide the learning process towards the optimal data partition and to prevent falling into local minima. However, researchers’ efforts made to improve existing semi-supervised clustering approaches are relatively scarce compared to the contributions made to enhance the state-of-the-art fully unsupervised clustering approaches. In this paper, we propose a novel semi-supervised deep clustering approach, named Soft Constrained Deep Clustering (SC-DEC), that aims to address the limitations exhibited by existing semi-supervised clustering approaches. Specifically, the proposed approach leverages a deep neural network architecture and generates fuzzy membership degrees that better reflect the true partition of the data. In particular, the proposed approach uses side-information and formulates it as a set of soft pairwise constraints to supervise the machine learning process. This supervision information is expressed using rather relaxed constraints named “should-link” constraints. Such constraints determine whether the pairs of data instances should be assigned to the same or different cluster(s). In fact, the clustering task was formulated as an optimization problem via the minimization of a novel objective function. Moreover, the proposed approach’s performance was assessed via extensive experiments using benchmark datasets. Furthermore, the proposed approach was compared to relevant state-of-the-art clustering algorithms, and the obtained results demonstrate the impact of using minimal previous knowledge about the data in improving the overall clustering performance.

The rapid development of Internet of Things (IoT) networks has revealed multiple security issues. On the other hand, machine learning (ML) has proven its efficiency in building intrusion detection systems (IDSs) intended to reinforce the security of IoT networks. In fact, the successful design and implementation of such techniques require the use of effective methods in terms of data and model quality. This paper encloses an empirical impact analysis for the latter in the context of a multi-class classification scenario. A series of experiments were conducted using six ML models, along with four benchmarking datasets, including UNSW-NB15, BOT-IoT, ToN-IoT, and Edge-IIoT. The proposed framework investigates the marginal benefit of employing data pre-processing and model configurations considering IoT limitations. In fact, the empirical findings indicate that the accuracy of ML-based IDS detection rapidly increases when methods that use quality data and models are deployed. Specifically, data cleaning, transformation, normalization, and dimensionality reduction, along with model parameter tuning, exhibit significant potential to minimize computational complexity and yield better performance. In addition, MLP- and clustering-based algorithms outperformed the remaining models, and the obtained accuracy reached up to 99.97%. One should note that the performance of the challenger models was assessed using similar test sets, and this was compared to the results achieved using the relevant pieces of research.

Internet of Things (IoT) technologies serve as a backbone of cutting-edge intelligent systems. Machine Learning (ML) paradigms have been adopted within IoT environments to exploit their capabilities to mine complex patterns. Despite the reported promising results, ML-based solutions exhibit several security vulnerabilities and threats. Specifically, Adversarial Machine Learning (AML) attacks can drastically impact the performance of ML models. It also represents a promising research field that typically promotes novel techniques to generate and/or defend against Adversarial Examples (AE) attacks. In this work, a comprehensive survey on AML attack and defense techniques is conducted for the years 2018–2022. The article investigates the employment of AML techniques to enhance intrusion detection performance within the IoT context. Additionally, it depicts relevant challenges that researchers aim to overcome to implement proper IoT-based security solutions. Thus, this survey aims to contribute to the literature by investigating the application of AML concepts within the IoT context. An extensive review of the current research trends of AML within IoT networks is presented. A conclusion is reached where several findings are reported including a shortage of defense mechanisms investigations, a lack of tailored IoT-based solutions, and the applicability of the existing mechanisms in both attack and defense scenarios.

Tax revenue represents an essential budget source for most countries around the world. Accordingly, the modernization of relevant technological infrastructure has become a key factor of tax administration strategy for improving tax collection efficiency. In particular, the fiscal consolidation of the Kingdom of Saudi Arabia has been supported by considerable development in tax policy and administration, aimed at raising more taxes from non-oil activities. In fact, non-Saudi investors are liable for income tax in Saudi Arabia. On the other hand, Saudi citizen investors (and citizens of the GCC countries) are liable for Zakat, an Islamic assessment. Typically, taxpayers are in charge of preparing and accurately reporting their Zakat declaration. This allows tax authorities to overview and audit their business activities. However, despite administration efforts to increase taxpayer compliance, considerable revenue remains at under-reporting risk. In this paper, we introduce a novel intelligent approach to support tax authority efforts in detecting under-reporting among Zakat payer declarations. In particular, the proposed solution aims at improving detection accuracy and determining the fraud cases that correspond to a higher revenue at risk. Specifically, we formulate Zakat under-reporting detection as a supervised machine learning task through the design of a deep neural network that performs simultaneous classification and regression tasks. In particular, the proposed network contains an input layer, five hidden layers, and two output layers for classification and regression. Zakat declarations are mapped into the predefined “under-reporting” or “actual declaration” classes. Moreover, the revenue at risk caused by the predicted fraud cases is learned by the designed model. This allows the proposed approach to prioritize the auditing of specific Zakat payers based on the corresponding predicted revenue at risk. A real dataset including 51,919 Zakat declarations was used to validate and assess the designed model. Further, the Synthetic Minority Oversampling Technique (SMOTE) boosted the proposed model performance in terms of classification and prioritization.

Abstract Background Phytochromes are plant photoreceptors that have long been associated with photomorphogenesis in plants; however, more recently, their crucial role in the regulation of variety of abiotic stresses has been explored. Chilling stress is one of the abiotic factors that severely affect growth, development, and productivity of crops. In the present work, we have analyzed and compared physiological, biochemical, and molecular responses in two contrasting phytochrome mutants of tomato, namely aurea (aur) and high pigment1 (hp1), along with wild-type cultivar Micro-Tom (MT) under chilling stress. In tomato, aur is phytochrome-deficient mutant while hp1 is a phytochrome-sensitive mutant. The genotype-specific physiological, biochemical, and molecular responses under chilling stress in tomato mutants strongly validated phytochrome-mediated regulation of abiotic stress. Results Here, we demonstrate that phytochrome-sensitive mutant hp1 show improved performance compared to phytochrome-deficient mutant aur and wild-type MT plants under chilling stress. Interestingly, we noticed significant increase in several photosynthetic-related parameters in hp1 under chilling stress that include photosynthetic rate, stomatal conductance, stomatal aperture, transpiration rate, chlorophyll a and carotenoids. Whereas most parameters were negatively affected in aur and MT except a slight increase in carotenoids in MT plants under chilling stress. Further, we found that PSII quantum efficiency (Fv/Fm), PSII operating efficiency (Fq′/Fm′), and non-photochemical quenching (NPQ) were all positively regulated in hp1, which demonstrate enhanced photosynthetic performance of hp1 under stress. On the other hand, Fv/Fm and Fq′/Fm′ were decreased significantly in aur and wild-type plants. In addition, NPQ was not affected in MT but declined in aur mutant after chilling stress. Noticeably, the transcript analysis show that PHY genes which were previously reported to act as molecular switches in response to several abiotic stresses were mainly induced in hp1 and repressed in aur and MT in response to stress. As expected, we also found reduced levels of malondialdehyde (MDA), enhanced activities of antioxidant enzymes, and higher accumulation of protecting osmolytes (soluble sugars, proline, glycine betaine) which further elaborate the underlying tolerance mechanism of hp1 genotype under chilling stress. Conclusion Our findings clearly demonstrate that phytochrome-sensitive and phytochrome-deficient tomato mutants respond differently under chilling stress thereby regulating physiological, biochemical, and molecular responses and thus establish a strong link between phytochromes and their role in stress tolerance.

The present paper proposes a new methodology for license plate (LP) recognition in the state of the art of image processing algorithms and an optimized neutrosophic set (NS) based on genetic algorithm (GA). First of all, we have performed some image processing techniques such as edge detection and morphological operations in order to utilize the (LP) localization. In addition, we have extracted the most salient features by implementing a new methodology using (GA) for optimizing the (NS) operations. The use of (NS) decreases the indeterminacy on the (LP) images. Moreover, k-means clustering algorithm has been applied to segment the (LP) characters. Finally, we have applied connected components labeling analysis (CCLA) algorithm for identifying the connected pixel regions and grouping the appropriate pixels into components to extract each character effectively. Several performance indices have been calculated in order to measure the system efficiency such as accuracy, sensitivity, specificity, dice, and jaccard coefficients. Moreover, we have created a database for all detected and recognized (LP) for testing purposes. Experimental results show that the proposed methodology has the ability to be suitable for both (Arabic –Egyptian) and English (LP). The proposed system achieves high degree of recognition accuracy for the whole system according to the following case studies; (i) for a high resolution Egyptian (LP), the proposed system achieves about 96.67% accuracy of correct recognition, (ii) for a low resolution-corrupted English (LP), the proposed system achieves about 94.27% accuracy. In addition, we have applied the proposed system on some sort of image disturbance i.e. (flash in image, external noise, and illumination variation), the proposed system achieves about 92.5% accuracy of correct identification. However, traditional methods achieve about 79% accuracy of correct identification in the presence of such image degradations. This reflects how the proposed system is generalized, optimized, and proposes high degree of recognition accuracy.

During the COVID-19 pandemic, we witnessed how sharing of biological and biomedical data have facilitated the researchers, medical practitioners and policymakers to tackle the pandemic at a global scale. Despite the growing use of EHR by medical practitioners and wearable digital gadgets by individuals, 80% of the health and medical data remain unused, adding little value to the researchers and medical practitioners. Legislative constraints related to health data sharing, centralised siloed design of traditional data management systems and most importantly, lack of incentivisation models are thought to be the underpinning bottlenecks for sharing health data. With the advent of the General Data Protection Regulation (GDPR) of the EU and the development of technologies like blockchain and distributed ledger technologies (DLT), it is now possible to create a new paradigm of data sharing by changing the incentivisation model from current authoritative or altruistic form to a shared economic model where financial incentivisation will be the main driver for data sharing. This can be achieved by setting up a digital health data marketplace (DHDM). Here we reviewed papers that proposed technical models or implemented frameworks that use blockchain-like technologies for health data. We seek to understand and compare different technical challenges associated with implementing and optimising the DHDM operation outlined in these papers. We also examined the legal limitations in the context of European Union and other countries such as the USA to accommodate any compliance requirement for such a marketplace. Last but not least, we reviewed papers that investigated the short, medium and long terms socioeconomic impact of such a marketplace on a wide range of stakeholders.

The urgent need to reduce greenhouse gas emissions has prompted the exploration of cleaner energy options such as renewable energy resources (RES) and electric vehicles (EVs). With the increasing use of RES and EVs, there are new opportunities and challenges for the stakeholders involved, and traditional centralized power system management methods are insufficient to handle the complexity. The energy management of photovoltaic (PV)-based parking lots is one of the challenges tackled in recent research. The main obstacle in applying previous research is the elimination of the utility objectives from the energy management models. This paper proposes an energy management framework that enables the integration of PV-based parking lots in a smart grid environment, considering the satisfaction of the utilities as a key player. The proposed framework is modeled using an optimization software package (GAMS), and the results are compared with two different cases to ensure its feasibility and effectiveness. The proposed model succeeded in taking the utilities satisfaction into account by managing the charging and discharging of the EVs.

Solenostemma argel (Delile) Hayne is a desert plant that survives harsh environmental conditions with several vital medicinal properties. Salt stress is a major constraint limiting agricultural production around the globe. However, response mechanisms behind the adaptation of S. argel plants to salt stress are still poorly understood. In the current study, we applied an omics approach to explore how this plant adapts to salt stress by integrating transcriptomic and metabolomic changes in the roots and leaves of S. argel plants under salt stress. De novo assembly of transcriptome produced 57,796 unigenes represented by 165,147 transcripts/isoforms. A total of 730 differentially expressed genes (DEGs) were identified in the roots (396 and 334 were up- and down-regulated, respectively). In the leaves, 927 DEGs were identified (601 and 326 were up- and down-regulated, respectively). Gene ontology and Kyoto Encyclopedia of Genes And Genomes pathway enrichment analyses revealed that several defense-related biological processes, such as response to osmotic and oxidative stress, hormonal signal transduction, mitogen-activated protein kinase signaling, and phenylpropanoid biosynthesis pathways are the potential mechanisms involved in the tolerance of S. argel plants to salt stress. Furthermore, liquid chromatography-tandem mass spectrometry was used to detect the metabolic variations of the leaves and roots of S. argel under control and salt stress. 45 and 56 critical metabolites showed changes in their levels in the stressed roots and leaves, respectively; there were 20 metabolites in common between the roots and leaves. Differentially accumulated metabolites included amino acids, polyamines, hydroxycinnamic acids, monolignols, flavonoids, and saccharides that improve antioxidant ability and osmotic adjustment of S. argel plants under salt stress. The results present insights into potential salt response mechanisms in S. argel desert plants and increase the knowledge in order to generate more tolerant crops to salt stress.

The design of AC filters must meet the criteria of harmonic distortion mitigation and reactive power support in various operating modes. The stringent reactive power-sharing requirements currently lead to sophisticated filter schemes with high component ratings. In this regard, triple-tuned filters (TTFs) have good potential in harmonic mitigation of a broad range of harmonics. In the literature, the TTF design has been presented using a parametric method, assuming that the TTF is equivalent to a three-arm single-tuned filter (TASTF). However, no direct methods of designing it or finding its optimal parameters have been provided. This paper presents novel mathematical designs of TTFs. Three different design methods are considered—the direct triple-tuned filter (DTTF) design method, as a TASTF, and a method based on the equivalence between the two design methods called the equivalence hypothesis method to design the triple-tuned filter (EHF). The parameters of the three proposed design methods are optimized based on the minimization of a proposed multi-objective function using a recent metaheuristic algorithm called artificial rabbits optimization (ARO) to mitigate harmonics, improve power quality, and minimize power losses in an exemplary system presented in IEEE STD-519. Further, the system’s performance has been compared to the system optimized by the ant lion optimizer (ALO) and whale optimization algorithm (WOA) to validate the effectiveness of the proposed design. Simulation results emphasized harmonics mitigation in the system, the system losses reduction, and power quality improvement with lower reactive power filter ratings than conventional single and double-tuned filters.

In this paper, we propose two novel Adaptive Neural Network Approaches (ANNAs), which are intended to automatically learn the optimal network depth. In particular, the proposed class-independent and class-dependent ANNAs address two main challenges faced by typical deep learning paradigms. Namely, they overcome the problems of setting the optimal network depth and improving the model interpretability. Specifically, ANNA approaches simultaneously train the network model, learn the network depth in an unsupervised manner, and assign fuzzy relevance weights to each network layer to better decipher the model behavior. In addition, two novel cost functions were designed in order to optimize the layer fuzzy relevance weights along with the model hyper-parameters. The proposed ANNA approaches were assessed using standard benchmarking datasets and performance measures. The experiments proved their effectiveness compared to typical deep learning approaches, which rely on empirical tuning and scaling of the network depth. Moreover, the experimental findings demonstrated the ability of the proposed class-independent and class-dependent ANNAs to decrease the network complexity and build lightweight models for less overfitting risk and better generalization.

Automatic speaker verification (ASV) systems play a prominent role in the security field due to the usability of voice biometrics compared to alternative biometric authentication modalities. Nevertheless, ASV systems are susceptible to malicious voice spoofing attacks. In response to such threats, countermeasures have been devised to prevent breaches and ensure the safety of user data by categorizing utterances as either genuine or spoofed. In this paper, we propose a new voice spoofing countermeasure that seeks to improve the generalization of supervised learning models. This is accomplished by alleviating the problem of intraclass variance. Specifically, the proposed approach addresses the generalization challenge by splitting the classification problem into a set of local subproblems in order to lessen the supervised learning task. The system outperformed existing state-of-the-art approaches with an EER of 0.097% on the ASVspoof challenge corpora related to replaying spoofing attacks.

Boosting the sales of e-commerce services is guaranteed once users find more items matching their interests in a short amount of time. Consequently, recommendation systems have become a crucial part of any successful e-commerce service. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems in recent years. This growing interest is due to security concerns over collecting personalized user behavior data, especially due to recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with their preferences. Our extensive experiments investigate baseline techniques (e.g., nearest neighbors and pattern mining algorithms) and deep learning approaches (e.g., recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most scenarios. However, we found that these models suffer more in the case of long sessions when there exists drift in user interests, and when there are not enough data to correctly model different items during training. Our study suggests that using the hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.

Abstract Background Phenylephrine is the most commonly used vasopressor for prophylaxis against maternal hypotension during cesarean delivery; however, the best regimen for its administration is not well established. Although variable infusion protocols had been suggested for phenylephrine infusion, evidence-based evaluation of variable infusion regimens are lacking. The aim of this work is to compare variable infusion, fixed on-and-off infusion, and intermittent boluses of phenylephrine for prophylaxis against maternal hypotension during cesarean delivery. Methods A randomized controlled study was conducted, including full-term pregnant women scheduled for elective cesarean delivery. Participants were divided into three groups which received phenylephrine by either intermittent boluses (1.5 mcg/Kg phenylephrine), fixed on-and-off infusion (with a dose of 0.75 mcg/Kg/min), or variable infusion (with a starting dose of 0.75 mcg/Kg/min). The three groups were compared with regard to frequency of: maternal hypotension (primary outcome), second episode hypotension, reactive hypertension, and bradycardia. Other outcomes included heart rate, systolic blood pressure, physician interventions, and neonatal outcomes. Results Two-hundred and seventeen mothers were available for final analysis. The 2 infusion groups showed less incidence of maternal hypotension {26/70 (37%), 22/71 (31%), and (51/76 (67%)} and higher incidence of reactive hypertension compared to the intermittent boluses group without significant differences between the two former groups. The number of physician interventions was highest in the variable infusion group compared to the other two groups. The intermittent boluses group showed lower systolic blood pressure and higher heart rate compared to the two infusion groups; whilst the two later groups were comparable. Conclusion Both phenylephrine infusion regimens equally prevented maternal hypotension during cesarean delivery compared to intermittent boluses regimen. Due to higher number of physician interventions in the variable infusion regimen, the current recommendations which favor this regimen over fixed infusion regimen might need re-evaluation.

Atrial fibrillation (AF) is the most common cardiac arrhythmia. It increases the risk of stroke, dementia, and death; therefore, its timely diagnosis at an initial stage is crucial. Often wearable mobile devices are recommended for the primary detection of this life-threatening arrhythmia. Irregularity of the heartbeat duration, often measured through R-R intervals (RRI), has been intensively investigated during the past four decades for automatic detection of AF. However, little improvement has been made when the input signal (RRI tachogram) contains different types of arrhythmic rhythms. In this paper, we propose a neighborhood component analysis (NCA) based linear transformation of a window of RRI tachogram to improve the robustness of AF detection. Several state-of-the-art classification models are trained and tested using transformed signals, and AF detection performance are evaluated using the challenging MIT-BIH Arrhythmia Database containing various types of arrhythmic rhythms. The experimental results show significant improvement in AF detection performance using the transformed signals compared to those for signals in the original space and after linear-discriminant-analysis-based transformation. In particular, for the Naïve Bayesian classification of the transformed signals, we obtained 98.59% sensitivity, 99.91% specificity, 99.16% positive predictive value, and 99.79% accuracy. The proposed AF detection method outperforms the existing methods reported in the past four decades. Owing to the use of a short window of RRI tachogram (15 consecutive RRIs), the proposed method can be incorporated into a deployable mobile screening device for robust detection of AF.

The apodization function has a significant impact on the state of the art of group delay, dispersion compensation, and acceptable decrease in side lobes in the spectrum of Fiber Bragg Grating (FBG) reflection. Accordingly, the Bragg grating length would be considered the backbone parameter in order to achieve a distinguishable performance. Here, the utilization influence of the presence of FBG is considered a dispersion compensator. In addition, we have implemented a tuned uniform-apodized FBG methodology according to various apodization functions. Common apodization functions have been studied and tested effectively. Experimental results show that the proposed raised cosine apodized function has scored the highest reflectivity with 50% reduction in the side lobe level and the narrowest bandwidth among all tested functions. Moreover, simulations for this function were performed with various lengths of grating. It is demonstrated that the reflection spectrum value is fixed at 100% at grating lengths greater than or equal to 28 mm and the minimum dispersion value is realized.

Abstract Background Dexmedetomidine infusion improves oxygenation and lung mechanics in patients with chronic obstructive lung disease; however, its effect in patients with restrictive lung disease has not been thoroughly investigated yet. The aim of this work was to evaluate the effects of dexmedetomidine infusion on oxygenation and lung mechanics in morbidly obese patients with restrictive lung disease. Methods Forty-two morbidly obese patients scheduled for bariatric surgery were included in the study. Patients were randomized to receive either dexmedetomidine infusion at a bolus dose of 1mcg/Kg followed by infusion at 1 mcg/Kg/hour for 90 min (Dexmedetomidine group), or normal saline infusion (Control group). Both groups were compared with regard to: oxygenation {P/F ratio: PaO2/fraction of inspired oxygen (FiO2)}, lung compliance, dead space, plateau pressure, blood pressure, and heart rate. Results Dexmedetomidine group showed significant improvement of the PaO2/FiO2 ratio, and higher lung compliance compared to control group by the end of drug infusion. Dexmedetomidine group demonstrated decreased dead space, plateau pressure, blood pressure, and heart rate compared to control group by the end of drug infusion. Conclusion A 90-min dexmedetomidine infusion resulted in moderate improvement in oxygenation and lung mechanics in morbidly obese patients with restrictive lung disease. Trial registration clinicaltrials.gov: NCT02843698 on 20 July 2016.

The intention of this correction is to better explain how the published article [1] relates to the article [3], which was referenced in [1] but without sufficient delineation.

Nowadays, Internet of Things (IoT) technology has various network applications and has attracted the interest of many research and industrial communities. Particularly, the number of vulnerable or unprotected IoT devices has drastically increased, along with the amount of suspicious activity, such as IoT botnet and large-scale cyber-attacks. In order to address this security issue, researchers have deployed machine and deep learning methods to detect attacks targeting compromised IoT devices. Despite these efforts, developing an efficient and effective attack detection approach for resource-constrained IoT devices remains a challenging task for the security research community. In this paper, we propose an efficient and effective IoT botnet attack detection approach. The proposed approach relies on a Fisher-score-based feature selection method along with a genetic-based extreme gradient boosting (GXGBoost) model in order to determine the most relevant features and to detect IoT botnet attacks. The Fisher score is a representative filter-based feature selection method used to determine significant features and discard irrelevant features through the minimization of intra-class distance and the maximization of inter-class distance. On the other hand, GXGBoost is an optimal and effective model, used to classify the IoT botnet attacks. Several experiments were conducted on a public botnet dataset of IoT devices. The evaluation results obtained using holdout and 10-fold cross-validation techniques showed that the proposed approach had a high detection rate using only three out of the 115 data traffic features and improved the overall performance of the IoT botnet attack detection process.

Detecting cognitive profiles is critical to efficient adaptive learning systems that automatically adjust the content delivered depending on the learner’s cognitive states and skills. This study explores electroencephalography (EEG) and facial expressions as physiological monitoring tools to build models that detect two cognitive states, namely, engagement and instantaneous attention, and three cognitive skills, namely, focused attention, planning, and shifting. First, while wearing a 14-channel EEG Headset and being videotaped, data has been collected from 127 subjects taking two scientifically validated cognitive assessments. Second, labeling was performed based on the scores obtained from the used tools. Third, different shallow and deep models were experimented in the two modalities of EEG and facial expressions. Finally, the best performing models for the analyzed states are determined. According to the used performance measure, which is the f-beta score with beta = 2, the best obtained results for engagement, instantaneous attention, and focused attention are EEG-based models with 0.86, 0.82, and 0.63 scores, respectively. As for planning and shifting, the best performing models are facial expressions-based models with 0.78 and 0.81, respectively. The obtained results show that EEG and facial expressions contain important and different cues and features about the analyzed cognitive states, and hence, can be used to automatically and non-intrusively detect them.

We propose a novel multiple query retrieval approach, named weight-learner, which relies on visual feature discrimination to estimate the distances between the query images and images in the database. For each query image, this discrimination consists of learning, in an unsupervised manner, the optimal relevance weight for each visual feature/descriptor. These feature relevance weights are designed to reduce the semantic gap between the extracted visual features and the user’s high-level semantics. We mathematically formulate the proposed solution through the minimization of some objective functions. This optimization aims to produce optimal feature relevance weights with respect to the user query. The proposed approach is assessed using an image collection from the Corel database.

The accurate estimation of measurements covariance is a fundamental problem in sensors fusion algorithms and is crucial for the proper operation of filtering algorithms. This paper provides an innovative solution for this problem and realizes the proposed solution on a 2D indoor navigation system for unmanned ground vehicles (UGVs) that fuses measurements from a MEMS-grade gyroscope, speed measurements and a light detection and ranging (LiDAR) sensor. A computationally efficient weighted line extraction method is introduced, where the LiDAR intensity measurements are used, such that the random range errors and systematic errors due to surface reflectivity in LiDAR measurements are considered. The vehicle pose change is obtained from LiDAR line feature matching, and the corresponding pose change covariance is also estimated by a weighted least squares-based technique. The estimated LiDAR-based pose changes are applied as periodic updates to the Inertial Navigation System (INS) in an innovative extended Kalman filter (EKF) design. Besides, the influences of the environment geometry layout and line estimation error are discussed. Real experiments in indoor environment are performed to evaluate the proposed algorithm. The results showed the great consistency between the LiDAR-estimated pose change covariance and the true accuracy. Therefore, this leads to a significant improvement in the vehicle’s integrated navigation accuracy.

This paper aimed at developing advanced Logit discrete choice models with several individual and mode attributes affecting the prediction of individual choice. The models have been applied to Port-Said (PS) city and have been used to investigate innovative transport systems such as Bus Rapid Transit (BRT) as a hypothetical mode situation beside the regular modes of transport (car and taxi). The methodology provides data collection of PS transportation mode system and develops Multinomial Logit Model (MNL), Nested Logit Model (NL), and Mixed Logit Model (MXL) using Visual-tm Software. The survey was formed by the Stated Preference (SP) technique conducted for individuals from all PS zones and the predictable travel mode choice behavior was analyzed. The findings showed that in PS, income is the most important attribute affecting the mode choice behavior model. The high values and positive signs of income parameters indicate that the higher income earners are more likely to use private car than taxi or bus. Contrary to most cases in developed countries, out-of-vehicle time that represents the accessibility shows higher impacts than the in-vehicle time as a result of poor access facilities in developing countries.

An Intrusion detection system is an essential security tool for protecting services and infrastructures of wireless sensor networks from unseen and unpredictable attacks. Few works of machine learning have been proposed for intrusion detection in wireless sensor networks and that have achieved reasonable results. However, these works still need to be more accurate and efficient against imbalanced data problems in network traffic. In this paper, we proposed a new model to detect intrusion attacks based on a genetic algorithm and an extreme gradient boosting (XGBoot) classifier, called GXGBoost model. The latter is a gradient boosting model designed for improving the performance of traditional models to detect minority classes of attacks in the highly imbalanced data traffic of wireless sensor networks. A set of experiments were conducted on wireless sensor network-detection system (WSN-DS) dataset using holdout and 10 fold cross validation techniques. The results of 10 fold cross validation tests revealed that the proposed approach outperformed the state-of-the-art approaches and other ensemble learning classifiers with high detection rates of 98.2%, 92.9%, 98.9%, and 99.5% for flooding, scheduling, grayhole, and blackhole attacks, respectively, in addition to 99.9% for normal traffic.

In many cities, worldwide, city centers are highly congested. The reason is that the Area Traffic Capacity (ATC) becomes constrained; i.e. the traffic and parking demands (mainly motorized), continually, increase within a finite roads’ and car parks’ capacity. The central Area Traffic Capacity (ATC) could be either the capacity of the internal road network, the parking capacity, or the capacity of the approach roads leading into the area. One of these three elements limits the overall traffic capacity. Therefore, the main objective of this paper is to develop a planning process which can be used as a tool for determining the ATC, and producing and evaluating different solutions (or scenarios) that can improve a central area traffic capacity. The proposed planning process is based on a combined analysis of traffic and parking situations which result from the travel demand and the traffic supply in a city center. If the travel demand is greater than the area traffic capacity, the process reflects feedback effects of parking and traffic situations on the desired supply or demand. Thus, it can be used to analyze different possible improving strategies, which might be needed to achieve favorable situations (formulating scenarios). The proposed planning process is then applied to estimate the area traffic capacity of Alexandria city center and to analyze the impacts of applying some traffic strategies in order to improve the ATC.

Cancer was initially considered a genetic disease. However, recent studies have revealed the connection between bacterial infections and growth of different types of cancer. The enteroinvasive strain of Mycoplasma hominis alters the normal behavior of host cells that may result in the growth of prostate cancer. The role of M. hominis in the growth and development of prostate cancer still remains unclear. The infection may regulate several factors that influence prostate cancer growth in susceptible individuals. The aim of this study was to predict M. hominis proteins targeted into the endoplasmic reticulum (ER) of the host cell, and their potential role in the induction of prostate cancer. From the whole proteome of M. hominis, 19 proteins were predicted to be targeted into the ER of host cells. The results of our study predict that several proteins of M. hominis may be targeted to the host cell ER, and possibly alter the normal pattern of protein folding. These predicted proteins can modify the normal function of the host cell. Thus, the intercellular infection of M. hominis in host cells may serve as a potential factor in prostate cancer etiology.