Deciphering the influence: academic stress and its role in shaping learning approaches among nursing students: a cross-sectional study.

BACKGROUND: Nursing education presents unique challenges, including high levels of academic stress and varied learning approaches among students. Understanding the relationship between academic stress and learning approaches is crucial for enhancing nursing education effectiveness and student well-being. AIM: This study aimed to investigate the prevalence of academic stress and its correlation with learning approaches among nursing students. DESIGN AND METHOD: A cross-sectional descriptive correlation research design was employed. A convenient sample of 1010 nursing students participated, completing socio-demographic data, the Perceived Stress Scale (PSS), and the Revised Study Process Questionnaire (R-SPQ-2 F). RESULTS: Most nursing students experienced moderate academic stress (56.3%) and exhibited moderate levels of deep learning approaches (55.0%). Stress from a lack of professional knowledge and skills negatively correlates with deep learning approaches (r = -0.392) and positively correlates with surface learning approaches (r = 0.365). Female students showed higher deep learning approach scores, while male students exhibited higher surface learning approach scores. Age, gender, educational level, and academic stress significantly influenced learning approaches. CONCLUSION: Academic stress significantly impacts learning approaches among nursing students. Strategies addressing stressors and promoting healthy learning approaches are essential for enhancing nursing education and student well-being. NURSING IMPLICATION: Understanding academic stress's impact on nursing students' learning approaches enables tailored interventions. Recognizing stressors informs strategies for promoting adaptive coping, fostering deep learning, and creating supportive environments. Integrating stress management, mentorship, and counseling enhances student well-being and nursing education quality.

A Partially Flipped Physiology Classroom Improves the Deep Learning Approach of Medical Students.

This study aimed to compare the impact of the partially flipped physiology classroom (PFC) and the traditional lecture-based classroom (TLC) on students' learning approaches. The study was conducted over five months at Xiangya School of Medicine from February to July 2022 and comprised 71 students majoring in clinical medicine. The experimental group (n = 32) received PFC teaching, while the control group (n = 39) received TLC. The Revised Two-Factor Study Process Questionnaire (R-SPQ-2F) was used to assess the impact of different teaching methods on students' learning approaches. After the PFC, students got significantly higher scores on deep learning approach (Z=-3.133, P<0.05). Conversely, after the TLC, students showed significantly higher scores on surface learning approach (Z=-2.259, P<0.05). After the course, students in the PFC group scored significantly higher in deep learning strategy than those in the TLC group (Z=-2.196, P<0.05). The PFC model had a positive impact on the deep learning motive and strategy, leading to an improvement in the deep approach, which is beneficial for the long-term development of students. In contrast, the TLC model only improved the surface learning approach. The study implies that educators should consider implementing PFC to enhance students' learning approaches.

A Review of Machine Learning Approaches for the Personalization of Amplification in Hearing Aids.

This paper provides a review of various machine learning approaches that have appeared in the literature aimed at individualizing or personalizing the amplification settings of hearing aids. After stating the limitations associated with the current one-size-fits-all settings of hearing aid prescriptions, a spectrum of studies in engineering and hearing science are discussed. These studies involve making adjustments to prescriptive values in order to enable preferred and individualized settings for a hearing aid user in an audio environment of interest to that user. This review gathers, in one place, a comprehensive collection of works that have been conducted thus far with respect to achieving the personalization or individualization of the amplification function of hearing aids. Furthermore, it underscores the impact that machine learning can have on enabling an improved and personalized hearing experience for hearing aid users. This paper concludes by stating the challenges and future research directions in this area.

Discovering the Learning Gradient of Students' Preferences for Learning Environment.

The aim of this study was to examine the effects of online learning self-regulation on learning outcomes during the COVID-19 pandemic lockdown among university college students. Quantitative k-means cluster analysis was used to examine the relationship among students in three different clusters based on their preferences toward online learning. The results indicated that online learning self-regulation had a significant positive effect on learning outcomes due to the shift to online learning. Thus, we identified a "learning gradient" among students, showing that cluster 1 students (preferences for 100% online) have the most positive preferences toward online teaching and the highest degree of self-regulation and learning outcome, cluster 2 students (moderate preferences for both physical and online teaching) are mixed (both positive and negative experiences) and moderate self-regulation and learning outcomes while cluster 3 students (preferences for physical classroom teaching) have the most negative preferences and the lowest self-regulation and learning outcome. The results from this study show that students' self-regulated learning strategies during online teaching environments are important for their learning outcomes and that cluster 1 and 2 students especially profited from the more flexible online learning environment with organized and deep learning approaches. Cluster 3 students need more support from their educators to foster their self-regulation skills to enhance their learning outcomes in online teaching environments.

Removal of hazardous textile dye from simulated wastewater by municipal organic solid waste charcoal using machine learning approaches: Kinetics, isotherm, and thermodynamics.

This study focuses on the probable use of municipal organic solid waste charcoal (MOSWC) as an adsorbent for Methyl orange (MO) adsorption. The prepared MOSWC is characterized by FE-SEM and FT-IR. Batch adsorption experiments were conducted with the influencing of different operational conditions namely time of contact (1-180 min), adsorbate concentration (60-140 mg/L), adsorbent dose (1-5 g/L), pH (3-11), and temperature (25-60 °C). The high coefficient value (R2 = 0.96) of the process optimization model suggests that this model was significant, where pH and adsorbent dose expressively stimulus adsorption efficiency including 40.11 mg/g at pH (3), MO concentration (100 mg/L), and MOSWC dose (1 g/L). Furthermore, the machine learning approaches (ANN and BB-RSM) revealed a good association between the tested and projected values. The highest monolayer adsorption capacity of MO was 90.909 mg/g. Pseudo-second-order was the well-suited kinetics, where Langmuir isotherm could explain better for equilibrium adsorption data. Thermodynamic study shows MO adsorption is favourable, exothermic, and spontaneous. Finally, this study indicates that MOSWC could be a potential candidate for the adsorption of MO from wastewater.

Exploring the Influence of Cognitive and Ecological Dynamics Approaches on Countermovement Jumping Enhancement: A Comparative Training Study.

Countermovement jumping (CMJ) and free-arm countermovement jumping (CMJFA) express the explosive-elastic force of the lower limbs. Strategies to enhance performance in both types of jumping can be categorized into cognitive and ecological-dynamic approaches. However, the effectiveness of these approaches in improving CMJ and CMJFA remains incompletely understood. This study aims to investigate the impact of training protocols based on the two approaches to improving CMJ. Thirty-six subjects with an average age of 26 years were selected and divided into two groups: the ecological-dynamic group (EDG) and the cognitive group (CG). For 12 weeks, both groups followed separate protocols of three weekly one-hour sessions. EDG group followed a protocol focused on circle time. The CG group followed an instructor-led training protocol. Incoming and outgoing flight heights were measured. Pre and post-intervention differences within and between groups were assessed using t-tests for dependent and independent samples, respectively (p ≤ 0.05). CG demonstrated a 12.2% increase in CMJ and a 7.8% improvement in CMJFA, while EDG showed a 10.2% increase in CMJ and 19.5% progress in CMJFA. No statistically significant differences (p > 0.05) were observed between the groups in the improvement of CMJ; statistically significant differences (p < 0.05) were found in the improvement of CMJFA in favor of EDG.

Predicting outcome with Intranasal Esketamine treatment: A machine-learning, three-month study in Treatment-Resistant Depression (ESK-LEARNING).

Treatment-resistant depression (TRD) represents a severe clinical condition with high social and economic costs. Esketamine Nasal Spray (ESK-NS) has recently been approved for TRD by EMA and FDA, but data about predictors of response are still lacking. Thus, a tool that can predict the individual patients' probability of response to ESK-NS is needed. This study investigates sociodemographic and clinical features predicting responses to ESK-NS in TRD patients using machine learning techniques. In a retrospective, multicentric, real-world study involving 149 TRD subjects, psychometric data (Montgomery-Asberg-Depression-Rating-Scale/MADRS, Brief-Psychiatric-Rating-Scale/BPRS, Hamilton-Anxiety-Rating-Scale/HAM-A, Hamilton-Depression-Rating-Scale/HAMD-17) were collected at baseline and at one month/T1 and three months/T2 post-treatment initiation. We trained three different random forest classifiers, able to predict responses to ESK-NS with accuracies of 68.53% at T1 and 66.26% at T2 and remission at T2 with 68.60% of accuracy. Features like severe anhedonia, anxious distress, mixed symptoms as well as bipolarity were found to positively predict response and remission. At the same time, benzodiazepine usage and depression severity were linked to delayed responses. Despite some limitations (i.e., retrospective study, lack of biomarkers, lack of a correct interrater-reliability across the different centers), these findings suggest the potential of machine learning in personalized intervention for TRD.

The approaches and motivations to learning of student nurses: a phenomenological study.

This research study was undertaken to elicit a group of final-year student nurses' perceptions of their motivations and approaches to learning, and the implications of their views. It is important to explore this subject because students' motivations and approaches to learning can potentially impact patient care. This study was part of a larger research project. The sample consisted of 18 final-year student nurses at a large UK university. Students completed semi-structured interviews that used a qualitative constructivist approach to explore their educational experience. Students described what motivated them to learn, and how they approached their learning because of their understanding of which subjects they believed were and were not important. Students felt that clinical skills were the most important subjects, and topics such as health promotion, law and ethics, were less important and therefore they approached these subjects in a superficial way, learning just enough to pass their course. Clinical skills were perceived as more useful because they would be used directly in clinical practice. The findings of this study are significant to inform nurse educators as they plan curricula and provide an insight into what may potentially adversely affect patient care when students become registered nurses.

Learning Approaches: Cross-Cultural Differences (Spain-Argentina) and Academic Achievement in College Students.

Learning approaches describe the students' degree of cognitive commitment to learning in diverse types of academic tasks and educational environments. Even though from a micro-level perspective different profiles of approaches have been identified in high-achievement undergraduates attending several majors, such profiles have not been examined from a macro-level approach in terms of distinct educational cultures. Therefore, the research involved two studies conducted on undergraduates from Argentina and Spain: The first one was aimed at analyzing the psychometric features of the Approaches and Study Skills Inventory for Students (ASSIST) whereas the second was focused on examining the learning approaches profiles of high and low achievers attending the same major (Psychology) in two different educational cultures (Spain and Argentina). The scale's original internal structure, examined on a sample of 400 participants (50% Spanish), was verified except for one item, which was fatherly eliminated. The resulting structure was tested and proven verified in a new sample (N = 1,334; 58.3% Spanish) by confirmatory factor analysis, factorial invariance, and internal consistency studies. External validity evidence was examined as well. Additionally, norms to be used in the professional field were calculated.Profiles of learning approaches by academic achievement from each country were examined by latent class analysis. In both cases, high achievers reported higher and more frequent use of the Deep and Strategic approaches and lower and less frequent usage of the Surface one. Further studies should replicate these analyses in undergraduates attending other majors in order to test the hypothesis sustaining these findings' generalization.

Learning Approaches: Cross-Cultural Differences (Spain–Argentina) and Academic Achievement in College Students

Learning approaches describe the students’ degree of cognitive commitment to learning in diverse types of academic tasks and educational environments. Even though from a micro-level perspective different profiles of approaches have been identified in high-achievement undergraduates attending several majors, such profiles have not been examined from a macro-level approach in terms of distinct educational cultures. Therefore, the research involved two studies conducted on undergraduates from Argentina and Spain: The first one was aimed at analyzing the psychometric features of the Approaches and Study Skills Inventory for Students (ASSIST) whereas the second was focused on examining the learning approaches profiles of high and low achievers attending the same major (Psychology) in two different educational cultures (Spain and Argentina). The scale’s original internal structure, examined on a sample of 400 participants (50% Spanish), was verified except for one item, which was fatherly eliminated. The resulting structure was tested and proven verified in a new sample (N = 1,334; 58.3% Spanish) by confirmatory factor analysis, factorial invariance, and internal consistency studies. External validity evidence was examined as well. Additionally, norms to be used in the professional field were calculated.Profiles of learning approaches by academic achievement from each country were examined by latent class analysis. In both cases, high achievers reported higher and more frequent use of the Deep and Strategic approaches and lower and less frequent usage of the Surface one. Further studies should replicate these analyses in undergraduates attending other majors in order to test the hypothesis sustaining these findings’ generalization. (AU)

Experimentation and Mathematical Modelling of Process Parameters for Prevention of Infectious Disease Caused by Staphylococcus aureus Bacteria in Indoor Environment.

Performance optimization using process parameters of an indoor air filtration system is a requirement that has to be established through experimental and analytical means for increasing machine efficacy. A closed casing containing a motor-driven blower is placed in a glass-encapsulated control volume. Air flows axially through an inlet filter and is thrown radially by the blower. In the radial path, air is treated with free radicals from the UVC-irradiated nano-TiO2 coated in the inner wall of casing. A known quantity of Staphylococcus aureus bacteria is populated (Courtesy: EFRAC Laboratories) in the glass-encapsulated control volume. The bacterial colony count is measured at different time intervals after the machine is switched on. Machine learning approaches are applied to develop a hypothesis space and the hypothesis based on best R2 score is used as a fitness function in genetic algorithm to find the optimal values of input parameters. The present research aims to determine the optimum time for which the setup is operated, the optimum air flow velocity in the chamber, the optimum setup-chamber-turning-radius affecting the air flow chaos, and the optimum UVC tube wattage, which when maintained yields the maximum reduction in bacterial colony count. The optimal values of the process parameters were obtained from genetic algorithm using the hypothesis obtained from multivariate polynomial regression. A reduction of 91.41% in bacterial colony count was observed in the confirmation run upon running the air filter in the optimal condition.

Artificial intelligence in timber forensics employing DNA barcode database.

Extreme difficulties in species identification of illegally sourced wood with conventional tools have accelerated illicit logging activities, leading to the destruction of natural resources in India. In this regard, the study primarily focused on developing a DNA barcode database for 41 commercial timber tree species which are highly vulnerable to adulteration in south India. The developed DNA barcode database was validated using an integrated approach involving wood anatomical features of traded wood samples collected from south India. Traded wood samples were primarily identified using wood anatomical features using IAWA list of microscopic features for hardwood identification. Consortium of Barcode of Life (CBOL) recommended barcode gene regions (rbcL, matK & psbA-trnH) were employed for developing DNA barcode database. Secondly, we employed artificial intelligence (AI) analytical platform, Waikato Environment for Knowledge Analysis (WEKA) for analyzing DNA barcode sequence database which could append precision, speed, and accuracy for the entire identification process. Among the four classification algorithms implemented in the machine learning algorithm (WEKA), best performance was shown by SMO, which could clearly allocate individual samples to their respective sequence database of biological reference materials (BRM) with 100 % accuracy, indicating its efficiency in authenticating the traded timber species. Major advantage of AI is the ability to analyze huge data sets with more precision and also provides a large platform for rapid authentication of species, which subsequently reduces human labor and time. Supplementary Information: The online version contains supplementary material available at 10.1007/s13205-023-03604-0.

Machine learning approaches and non-linear processing of extracted components in frontal region to predict rTMS treatment response in major depressive disorder.

Predicting the therapeutic result of repetitive transcranial magnetic stimulation (rTMS) treatment could save time and costs as ineffective treatment can be avoided. To this end, we presented a machine-learning-based strategy for classifying patients with major depression disorder (MDD) into responders (R) and nonresponders (NR) to rTMS treatment. Resting state EEG data were recorded using 32 electrodes from 88 MDD patients before treatment. Then, patients underwent 7 weeks of rTMS, and 46 of them responded to treatment. By applying Independent Component Analysis (ICA) on EEG, we identified the relevant brain sources as possible indicators of neural activity in the dorsolateral prefrontal cortex (DLPFC). This was served through estimating the generators of activity in the sensor domain. Subsequently, we added physiological information and placed certain terms and conditions to offer a far more realistic estimation than the classic EEG. Ultimately, those components mapped in accordance with the region of the DLPFC in the sensor domain were chosen. Features extracted from the relevant ICs time series included permutation entropy (PE), fractal dimension (FD), Lempel-Ziv Complexity (LZC), power spectral density, correlation dimension (CD), features based on bispectrum, frontal and prefrontal cordance, and a combination of them. The most relevant features were selected by a Genetic Algorithm (GA). For classifying two groups of R and NR, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) were applied to predict rTMS treatment response. To evaluate the performance of classifiers, a 10-fold cross-validation method was employed. A statistical test was used to assess the capability of features in differentiating R and NR for further research. EEG characteristics that can predict rTMS treatment response were discovered. The strongest discriminative indicators were EEG beta power, the sum of bispectrum diagonal elements in delta and beta bands, and CD. The Combined feature vector classified R and NR with a high performance of 94.31% accuracy, 92.85% specificity, 95.65% sensitivity, and 92.85% precision using SVM. This result indicates that our proposed method with power and nonlinear and bispectral features from relevant ICs time-series can predict the treatment outcome of rTMS for MDD patients only by one session pretreatment EEG recording. The obtained results show that the proposed method outperforms previous methods.

Does a deep learning inventory predict knowledge transfer? Linking student perceptions to transfer outcomes.

Students are often encouraged to learn 'deeply' by abstracting generalizable principles from course content rather than memorizing details. So widespread is this perspective that Likert-style inventories are now routinely administered to students to quantify how much a given course or curriculum evokes deep learning. The predictive validity of these inventories, however, has been criticized based on sparse empirical support and ambiguity in what specific outcome measures indicate whether deep learning has occurred. Here we further tested the predictive validity of a prevalent deep learning inventory, the Revised Two-Factor Study Process Questionnaire, by selectively analyzing outcome measures that reflect a major goal of medical education-i.e., knowledge transfer. Students from two undergraduate health sciences courses completed the deep learning inventory before their course's final exam. Shortly after, a random subset of students rated how much each final exam item aligned with three task demands associated with transfer: (1) application of general principles, (2) integration of multiple ideas or examples, and (3) contextual novelty. We then used these ratings from students to examine performance on a subset of exam items that were collectively perceived to demand transfer. Despite good reliability, the resulting transfer outcomes were not substantively predicted by the deep learning inventory. These findings challenge the validity of this tool and others like it.

A systematic review: Chest radiography images (X-ray images) analysis and COVID-19 categorization diagnosis using artificial intelligence techniques.

COVID-19 pandemic created a turmoil across nations due to Severe Acute Respiratory Syndrome Corona virus-1(SARS - Co-V-2). The severity of COVID-19 symptoms is starting from cold, breathing problems, issues in respiratory system which may also lead to life threatening situations. This disease is widely contaminating and transmitted from man-to-man. The contamination is spreading when the human organs like eyes, nose, and mouth get in contact with contaminated fluids. This virus can be screened through performing a nasopharyngeal swab test which is time consuming. So the physicians are preferring the fast detection methods like chest radiography images and CT scans. At times some confusion in finding out the accurate disorder from chest radiography images can happen. To overcome this issue this study reviews several deep learning and machine learning procedures to be implemented in X-ray images of chest. This also helps the professionals to find out the other types of malfunctions happening in the chest other than COVID-19 also. This review can act as a guidance to the doctors and radiologists in identifying the COVID-19 and other types of viruses causing illness in the human anatomy and can provide aid soon.

Prediction of Autogenous Shrinkage of Concrete Incorporating Super Absorbent Polymer and Waste Materials through Individual and Ensemble Machine Learning Approaches.

The use of superabsorbent polymers, sometimes known as SAP, is a tremendously efficacious method for reducing the amount of autogenous shrinkage (AS) that occurs in high-performance concrete. This study utilizes support vector regression (SVR) as a standalone machine-learning algorithm (MLA) which is then ensemble with boosting and bagging approaches to reduce the bias and overfitting issues. In addition, these ensemble methods are optimized with twenty sub-models with varying the nth estimators to achieve a robust R2. Moreover, modified bagging as random forest regression (RFR) is also employed to predict the AS of concrete containing supplementary cementitious materials (SCMs) and SAP. The data for modeling of AS includes water to cement ratio (W/C), water to binder ratio (W/B), cement, silica fume, fly ash, slag, the filer, metakaolin, super absorbent polymer, superplasticizer, super absorbent polymer size, curing time, and super absorbent polymer water intake. Statistical and k-fold validation is used to verify the validation of the data using MAE and RMSE. Furthermore, SHAPLEY analysis is performed on the variables to show the influential parameters. The SVM with AdaBoost and modified bagging (RF) illustrates strong models by delivering R2 of approximately 0.95 and 0.98, respectively, as compared to individual SVR models. An enhancement of 67% and 63% in the RF model, while in the case of SVR with AdaBoost, it was 47% and 36%, in RMSE and MAE of both models, respectively, when compared with the standalone SVR model. Thus, the impact of a strong learner can upsurge the efficiency of the model.

Study of medical students' learning approaches and their association with academic performance and problem-solving styles.

BACKGROUND: Learners have various processing and understanding of the environment and issues and choose different strategies for problem-solving considering learning and studying approaches. The purpose of this study was to examine medical students' learning approaches and their association with academic performance and problem-solving styles. MATERIALS AND METHODS: This study was conducted using the descriptive-correlational method. The statistical population comprised medical students of Iran University of Medical Sciences during the academic year of 2019-2020. Of them, 168 subjects were chosen based on simple random sampling and Morgan Table. Study tools include the Standard Approaches and Study Skills Inventory for Students (ASSIST) Questionnaire, which includes 18 items and a Likert five-choice spectrum, and includes a deep, superficial, and strategic approach. Its reliability was determined by Cronbach's alpha of 0.81. Problem-Solving Style Questionnaire developed by Cassidy and Long was used. This instrument included 24 items and 6 components, and its reliability equaled 0.83, which was their grade point average. Data were analyzed using normality tests, paired t-test, Pearson correlation coefficient, and regression through SPSS 16 software. RESULTS: Results implied the positive and significant relationship between deep-strategic approaches, problem-solving styles, and academic performance of medical students (P < 0.001); furthermore, there was no significant difference between learning approaches based on gender (P > 0.001), while there was a significant difference between two groups in terms of problem-solving styles (P < 0.001). CONCLUSION: Because deep and strategic approaches predict academic performance and problem-solving styles, the diagnostic assessment must be done at the beginning of the educational process to determine the type of learners' approaches. Such an evaluation can be used to implement instructional strategies and educational designs to improve the academic performance of students.

A Pilot Study of Augmented Intelligence Risk-Based Stratification for Endocrine Surgical Waiting List Prioritisation.

Introduction The New Deal for Surgery report encouraged using new technology in healthcare to address the 377,689 patients in England awaiting National Health Service (NHS) hospital treatment in July 2022. During the pandemic's second wave, this pilot study investigated the utility of COMPASS Surgical List Triage (COMPASS SLT; C2-Ai, Cambridge, England), an augmented intelligence-based system, in assisting surgical decision-making on patient prioritisation. Data generated from COMPASS SLT was compared to data from the British Association of Endocrine and Thyroid Surgeons' (BAETS) and Federation of Surgical Specialties Associations' (FSSA) prioritisation guidance. Methods A cohort of thyroidectomy and parathyroidectomy patients on the surgical waiting list at Imperial College Healthcare NHS Trust, London, United Kingdom, was used. COMPASS SLT calculated individuals' mortality and significant morbidity risk (risk >2.5%). Significant morbidity risk was set at 2.5% or above following internal model validation, thus reducing the risk of model overfitting occurring with COMPASS SLT. The additional increase in mortality and morbidity due to treatment delay was calculated. Actual treatment time was aligned to the treatment delay (in weeks) experienced by each patient. Results Twenty-nine patients, with a median age of 43 years and a waiting time of 18 weeks at the onset of the second wave, were enrolled. Non-statistically significant differences (p=0.937) between the FSSA and BAETS classifications were identified. However, cohort size could promote a type II error. An increase in median mortality and morbidity risk (p<0.001) arising from treatment delay and decisions based on the FSSA and BAETS classifications were identified. Conclusion COMPASS SLT can supplement clinical decision-making. An augmented intelligence tool can provide clinicians objectivity and flexibility in prioritising patients, with information on individual morbidity and mortality.

Artificial Intelligence Algorithm-Based Economic Denial of Sustainability Attack Detection Systems: Cloud Computing Environments.

Cloud computing is currently the most cost-effective means of providing commercial and consumer IT services online. However, it is prone to new flaws. An economic denial of sustainability attack (EDoS) specifically leverages the pay-per-use paradigm in building up resource demands over time, culminating in unanticipated usage charges to the cloud customer. We present an effective approach to mitigating EDoS attacks in cloud computing. To mitigate such distributed attacks, methods for detecting them on different cloud computing smart grids have been suggested. These include hard-threshold, machine, and deep learning, support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF) tree algorithms, namely convolutional neural network (CNN), and long short-term memory (LSTM). These algorithms have greater accuracies and lower false alarm rates and are essential for improving the cloud computing service provider security system. The dataset of nine injection attacks for testing machine and deep learning algorithms was obtained from the Cyber Range Lab at the University of New South Wales (UNSW), Canberra. The experiments were conducted in two categories: binary classification, which included normal and attack datasets, and multi-classification, which included nine classes of attack data. The results of the proposed algorithms showed that the RF approach achieved accuracy of 98% with binary classification, whereas the SVM model achieved accuracy of 97.54% with multi-classification. Moreover, statistical analyses, such as mean square error (MSE), Pearson correlation coefficient (R), and the root mean square error (RMSE), were applied in evaluating the prediction errors between the input data and the prediction values from different machine and deep learning algorithms. The RF tree algorithm achieved a very low prediction level (MSE = 0.01465) and a correlation R2 (R squared) level of 92.02% with the binary classification dataset, whereas the algorithm attained an R2 level of 89.35% with a multi-classification dataset. The findings of the proposed system were compared with different existing EDoS attack detection systems. The proposed attack mitigation algorithms, which were developed based on artificial intelligence, outperformed the few existing systems. The goal of this research is to enable the detection and effective mitigation of EDoS attacks.

A Proactive Recognition System for Detecting Commercial Vehicle Driver's Distracted Behavior.

Road traffic accidents regarding commercial vehicles have been demonstrated as an important culprit restricting the steady development of the social economy, which are closely related to the distracted behavior of drivers. However, the existing driver's distracted behavior surveillance systems for monitoring and preventing the distracted behavior of drivers still have some shortcomings such as fewer recognition objects and scenarios. This study aims to provide a more comprehensive methodological framework to demonstrate the significance of enlarging the recognition objects, scenarios and types of the existing driver's distracted behavior recognition systems. The driver's posture characteristics were primarily analyzed to provide the basis of the subsequent modeling. Five CNN sub-models were established for different posture categories and to improve the efficiency of recognition, accompanied by a holistic multi-cascaded CNN framework. To suggest the best model, image data sets of commercial vehicle driver postures including 117,410 daytime images and 60,480 night images were trained and tested. The findings demonstrate that compared to the non-cascaded models, both daytime and night cascaded models show better performance. Besides, the night models exhibit worse accuracy and better speed relative to their daytime model counterparts for both non-cascaded and cascaded models. This study could be used to develop countermeasures to improve driver safety and provide helpful information for the design of the driver's real-time monitoring and warning system as well as the automatic driving system. Future research could be implemented to combine the vehicle state parameters with the driver's microscopic behavior to establish a more comprehensive proactive surveillance system.