Search

Intrusion detection systems (IDS) play a critical role in ensuring the security and integrity of computer networks. There is a constant demand for the development of powerful, novel, and generalized methods for IDS that can accurately detect and classify intrusions. In this study, we aim to evaluate the benefits of linear classifiers (LC) and nonlinear classifiers (NLC) in IDS. We employed ten machine learning (ML) classifiers, consisting of five LC and five NLC. These classifiers underwent cross-validation for performance evaluation, unseen analysis, statistical tests, and power analysis on measuring the minimum sample size. Four hypotheses were formulated and validated on five processed intrusion attack datasets. NLC outperformed LC, with a mean accuracy (ACC)/area-under-the-curve (AUC) increase of 22.26%/20.3% on the WUSTL-EHMS dataset, with improvements of ACC/AUC by 5.5%/2.3% on the UNSW-NB15 dataset. In the unseen analysis, NLC achieved an ACC/AUC increase of 21.9%/21.8% when trained on WUSTL-EHMS and tested on UNSW-NB15. Lastly, when using a mixed dataset of WUSTL-EHMS and UNSW-NB15, NLC demonstrated an ACC/AUC increase of 11.67%/5.5%. The model performed well in cross-validation protocols, and the statistical tests yielded significant p-values. NLC provides generalized and robust solutions to detect intrusion attacks, ensuring the integrity and security of computer networks.

A substantial portion of the worldwide population relies on wheat as a foundational dietary staple. However, the increased occurrence and severity of drought and heat stress events due to climate change pose significant threats to wheat production. The physiological and biochemical responses of wheat to drought and heat stress (HS) varied and had unfavorable impacts on plant growth, as well as grain yield and quality. Understanding these responses is crucial for developing effective mitigation strategies. The high temperature during grain synthesis alters the synthesis and proportion of major chemical constituents in the grain, thereby affecting its functionality and suitability for processing into various products. Developing drought-tolerant and heat-resistant wheat varieties through marker-assisted breeding and genetic engineering are two modern strategies that effectively combat temperature stress. Additionally, agronomic practices such as improved irrigation methods, crop rotation, and precision farming are common approaches to enhance wheat resilience under stress conditions. This review serves as a valuable resource for researchers, agronomists, policymakers, and processors by providing a comprehensive overview of the effects of drought and HS on wheat growth and its grain quality and by offering insights into promising strategies for sustainable wheat production and its processing. Adapting and implementing these strategies are essential steps towards ensuring global food security, safeguarding the livelihoods of wheat-growing farmers, and shedding light on changes in the composition and functionality of wheat grain that are useful for the food industry.

Abstract The wheatgrass and pulse microgreens have gained popularity for their concentrated phytochemical content. However, the variability in growth parameters and compositional constituents of wheatgrass and pulse microgreens is dependent on the prevailing environmental conditions. Nowadays, wheatgrass and pulse microgreens are used as culinary sources or incorporated into various food products and consumed by a large proportion of the global population. Therefore, it is necessary to review the impact of growth conditions to meet the increased demand. This will allow breeders to adjust their cultivation techniques according to consumer preferences for specific nutritional components. This systematic review seeks to provide an analysis of the available literature on the variation in growth and compositions of wheatgrass and pulse microgreens as the influence of diverse growing conditions. The growth of wheatgrass and pulse microgreens can be influenced by a range of growth conditions, such as variations in light intensity, temperature, nutrient availability, and cultivation techniques. The variation in growth and compositional components, in terms of proximate composition and certain constituents such as chlorophyll, antioxidants, minerals, phenolic compounds, and secondary metabolites, is discussed in relation to the changing cultivation parameters as published in recent studies. However, this review only covers the compositional make‐up of wheatgrass and pulse microgreens. There remains a need to summarize the compositional profiles of other microgreen species under various conditions. Ultimately, this review illuminates the promise of emerging superfoods and underscores how their growth and composition can vary depending on cultivation methods, ultimately impacting their capacity to promote health. In addition, there is a need to establish dose–response relationships to address various diseases. Therefore, additional research may be warranted.

Abstract Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint’s GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.

Summary: Background: The field of precision medicine endeavors to transform the healthcare industry by advancing individualised strategies for diagnosis, treatment modalities, and predictive assessments. This is achieved by utilizing extensive multidimensional biological datasets encompassing diverse components, such as an individual's genetic makeup, functional attributes, and environmental influences. Artificial intelligence (AI) systems, namely machine learning (ML) and deep learning (DL), have exhibited remarkable efficacy in predicting the potential occurrence of specific cancers and cardiovascular diseases (CVD). Methods: We conducted a comprehensive scoping review guided by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. Our search strategy involved combining key terms related to CVD and AI using the Boolean operator AND. In August 2023, we conducted an extensive search across reputable scholarly databases including Google Scholar, PubMed, IEEE Xplore, ScienceDirect, Web of Science, and arXiv to gather relevant academic literature on personalised medicine for CVD. Subsequently, in January 2024, we extended our search to include internet search engines such as Google and various CVD websites. These searches were further updated in March 2024. Additionally, we reviewed the reference lists of the final selected research articles to identify any additional relevant literature. Findings: A total of 2307 records were identified during the process of conducting the study, consisting of 564 entries from external sites like arXiv and 1743 records found through database searching. After 430 duplicate articles were eliminated, 1877 items that remained were screened for relevancy. In this stage, 1241 articles remained for additional review after 158 irrelevant articles and 478 articles with insufficient data were removed. 355 articles were eliminated for being inaccessible, 726 for being written in a language other than English, and 281 for not having undergone peer review. Consequently, 121 studies were deemed suitable for inclusion in the qualitative synthesis. At the intersection of CVD, AI, and precision medicine, we found important scientific findings in our scoping review. Intricate pattern extraction from large, complicated genetic datasets is a skill that AI algorithms excel at, allowing for accurate disease diagnosis and CVD risk prediction. Furthermore, these investigations have uncovered unique genetic biomarkers linked to CVD, providing insight into the workings of the disease and possible treatment avenues. The construction of more precise predictive models and personalised treatment plans based on the genetic profiles of individual patients has been made possible by the revolutionary advancement of CVD risk assessment through the integration of AI and genomics. Interpretation: The systematic methodology employed ensured the thorough examination of available literature and the inclusion of relevant studies, contributing to the robustness and reliability of the study's findings. Our analysis stresses a crucial point in terms of the adaptability and versatility of AI solutions. AI algorithms designed in non-CVD domains such as in oncology, often include ideas and tactics that might be modified to address cardiovascular problems. Funding: No funding received.

Scientific evidence has demonstrated that biofuels have the ability to reduce environmental contamination, hence addressing the underlying causes of potential disasters. Renewable fuels produced from biological resources provide flexible solutions for several aspects of crisis management, such as supplying energy for emergency generators, fuelling transportation fleets, and offering heating and cooking options. Empirical evidence supports the notion that biofuels effectively reduce carbon and sulphur emissions. Notably, certain biofuels, such as algal biodiesel, have the capacity to mitigate 0.6% of carbon dioxide output. Cities, such as Delhi, that are contaminated by the consumption of fossil fuels have a scarcity of breathing oxygen during the winter and elevated ambient temperatures during the summer. These pioneers cause inundation and tempests in vulnerable regions. The lessons acquired from various locations highlight the importance of cooperation, enhancing capabilities, and providing governmental support in order to replicate and expand successful models. To optimize the advantages of biofuels in crisis management, it is crucial to prioritize research and development projects, involve stakeholders, and raise awareness. The role of national and international policy is vital in providing incentives for the production and use of biofuels, while technical advancements are key in shaping the future of sustainability and efficiency. Communities may utilize the ideas of sustainability and resilience to leverage the transformational potential of biofuels in order to construct societies that are safer, more environmentally friendly, and better equipped to withstand challenges.

Hardness of wheat endosperm is a physical property that depends on the genetic makeup of the grain and varies amongst different types/varieties. It is associated with proteins, particularly 14–15 kDa friabilins, which exist in higher amounts at the surface of starch in soft wheat grains while either absent or occur in smaller quantities on granules of hard wheat varieties. The storage proteins in hard wheat flours exhibit a higher proportion of polymeric proteins, β-sheets and β-turns. Soft wheat starches show lower crystallinity, amylose-lipid complex content and proportion of A-type granules (disk or lenticular-shaped granules with diameter >10 µm) while higher gelatinisation temperatures, swelling, breakdown susceptibility and retrogradation than hard wheat starches. Flours from hard and soft wheat also differ for processing and end-use quality based on differences in dough rheological properties, solvent retention capacities and particle size.

Chapattis have been a global dietary staple since ancient times serving as a primary source of carbohydrates, proteins, dietary fiber and minerals. The escalating prevalence of health challenges such as diabetes, cardiovascular diseases etc. driven by evolving lifestyles, environmental factors, underscores the urgent need for innovative chapatti formulations. To address current and future challenges effectively, there is a compelling requirement to explore novel formulations that not only maintain low glycemic-index and high protein content of chapattis but also enrich them with minerals, vitamins and dietary fibers. The review delves into key quality attributes that define the nutritional and textural characteristics of wheat including the presence of essential micronutrients and bioactive compounds to highlight the potential health benefits associated with regular consumption. The role of different processing parameters in enhancing the quality and shelf stability of wheat chapatti along with the critical aspect of utilizing additives, elucidating various factors influencing the preservation of wheat chapatti over time has been investigated. Furthermore, the findings offer practical insights for food industry professionals contributing to the overall improvement of global food security and dietary well-being.

Background and noveltyWhen RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections.MethodologyAnnotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland–Altman, and (iv) Correlation plots.ResultsAmong the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann–Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p

Abstract The distribution of A‐ and B‐type‐sized starch granules plays a deciding role in controlling the physicochemical, structural, morphological, and functional attributes of wheat starch. Starches of three Indian wheat varieties, viz. DBW 16, WH 147, and WH 542, were fractionated into A‐ and B‐type starch granules and further evaluated for their influence on various attributes of wheat starches using different analytical tools like X‐ray diffraction, scanning electron microscopy (SEM), differential scanning calorimetry, and rapid viscoanalyzer. SEM revealed that the size of large granules (A‐type) ranged from 12.6 to 36.4 µm and small granules (B‐type) varied from 2.53 to 7.52 µm. The amylose content was significantly higher for A‐type starch ranging from 26.6% to 29.68% than B‐type starch ranging from 19.20% to 22.38%. The highest swelling power was observed for B‐type granules, followed by native and A‐type granules, and similar trend was noticed for water absorption. Pasting viscosities of A‐type granules were higher than B‐type for starches of all wheat varieties. A higher pasting temperature was observed in B‐type starch granules, suggesting more resistance to swell during the heating process. X‐ray diffraction of wheat starches showed A‐type pattern of crystallinity, variety DBW 16 (27%) showed the highest relative crystallinity and intensities of peaks in comparison to varieties WH 147 (23.5%) and WH 542 (22.4% as observed in diffractograms and well supported by Fourier transforms infrared spectroscopy. Fractionated large granules of wheat starches exhibited a higher gelatinization temperature than smaller granules and native starches for all the varieties. It was also observed that A‐type granules had higher onset temperature comparatively, which suggested that high energy is required in gelatinization due to more ordered arrangement of starch molecules.

Cardiovascular disease (CVD) diagnosis and treatment are challenging since symptoms appear late in the disease’s progression. Despite clinical risk scores, cardiac event prediction is inadequate, and many at-risk patients are not adequately categorised by conventional risk factors alone. Integrating genomic-based biomarkers (GBBM), specifically those found in plasma and/or serum samples, along with novel non-invasive radiomic-based biomarkers (RBBM) such as plaque area and plaque burden can improve the overall specificity of CVD risk. This review proposes two hypotheses: (i) RBBM and GBBM biomarkers have a strong correlation and can be used to detect the severity of CVD and stroke precisely, and (ii) introduces a proposed artificial intelligence (AI)—based preventive, precision, and personalized (aiP3) CVD/Stroke risk model. The PRISMA search selected 246 studies for the CVD/Stroke risk. It showed that using the RBBM and GBBM biomarkers, deep learning (DL) modelscould be used for CVD/Stroke risk stratification in the aiP3 framework. Furthermore, we present a concise overview of platelet function, complete blood count (CBC), and diagnostic methods. As part of the AI paradigm, we discuss explainability, pruning, bias, and benchmarking against previous studies and their potential impacts. The review proposes the integration of RBBM and GBBM, an innovative solution streamlined in the DL paradigm for predicting CVD/Stroke risk in the aiP3 framework. The combination of RBBM and GBBM introduces a powerful CVD/Stroke risk assessment paradigm. aiP3 model signifies a promising advancement in CVD/Stroke risk assessment.

Background: There are several antibiotic resistance genes (ARG) for the Escherichia coli (E. coli) bacteria that cause urinary tract infections (UTI), and it is therefore important to identify these ARG. Artificial Intelligence (AI) has been used previously in the field of gene expression data, but never adopted for the detection and classification of bacterial ARG. We hypothesize, if the data is correctly conferred, right features are selected, and Deep Learning (DL) classification models are optimized, then (i) non-linear DL models would perform better than Machine Learning (ML) models, (ii) leads to higher accuracy, (iii) can identify the hub genes, and, (iv) can identify gene pathways accurately. We have therefore designed aiGeneR, the first of its kind system that uses DL-based models to identify ARG in E. coli in gene expression data. Methodology: The aiGeneR consists of a tandem connection of quality control embedded with feature extraction and AI-based classification of ARG. We adopted a cross-validation approach to evaluate the performance of aiGeneR using accuracy, precision, recall, and F1-score. Further, we analyzed the effect of sample size ensuring generalization of models and compare against the power analysis. The aiGeneR was validated scientifically and biologically for hub genes and pathways. We benchmarked aiGeneR against two linear and two other non-linear AI models. Results: The aiGeneR identifies tetM (an ARG) and showed an accuracy of 93% with area under the curve (AUC) of 0.99 (p < 0.05). The mean accuracy of non-linear models was 22% higher compared to linear models. We scientifically and biologically validated the aiGeneR. Conclusions: aiGeneR successfully detected the E. coli genes validating our four hypotheses.

Background and Motivation: Coronary artery disease (CAD) has the highest mortality rate; therefore, its diagnosis is vital. Intravascular ultrasound (IVUS) is a high-resolution imaging solution that can image coronary arteries, but the diagnosis software via wall segmentation and quantification has been evolving. In this study, a deep learning (DL) paradigm was explored along with its bias. Methods: Using a PRISMA model, 145 best UNet-based and non-UNet-based methods for wall segmentation were selected and analyzed for their characteristics and scientific and clinical validation. This study computed the coronary wall thickness by estimating the inner and outer borders of the coronary artery IVUS cross-sectional scans. Further, the review explored the bias in the DL system for the first time when it comes to wall segmentation in IVUS scans. Three bias methods, namely (i) ranking, (ii) radial, and (iii) regional area, were applied and compared using a Venn diagram. Finally, the study presented explainable AI (XAI) paradigms in the DL framework. Findings and Conclusions: UNet provides a powerful paradigm for the segmentation of coronary walls in IVUS scans due to its ability to extract automated features at different scales in encoders, reconstruct the segmented image using decoders, and embed the variants in skip connections. Most of the research was hampered by a lack of motivation for XAI and pruned AI (PAI) models. None of the UNet models met the criteria for bias-free design. For clinical assessment and settings, it is necessary to move from a paper-to-practice approach.

Introduction. Due to the increasing demand for natural and functional products, scientists together with industries are conducting research to improve the nutritional quality of food. One of the ways to enhance the functionality of food is to add fruits or vegetables to their formulations. In this study, we attempted to develop muffins fortified with Dacryodes macrophylla L. fruit as a value-added ingredient. Study objects and methods. Our study objects included D. macrophylla L. extract and six muffins: three eggless samples and three egg-containing samples. Each group included control and experimental samples. The experimental samples containing 0.5 and 1% of D. macrophylla L. extract instead of wheat flour were evaluated for muffin-making properties. All the samples were analyzed for their physicochemical, antioxidant, and sensory properties, as well as rheological parameters. Results and discussion. We found that D. macrophylla L. reduced the water activity, color values (L*, a*, b*), and firmness of muffins. It had no significant effect on baking loss, height, moisture, cohesiveness, springiness, gumminess or chewiness, but tended to decrease the specific volume of muffins. However, D. macrophylla L. fruit increased the specific gravity, improved rheology properties, and tended to increase adhesiveness and mineral contents. Na and K varied from 5.93 to 7.75 and 2.88 to 7.35 mg/g, respectively. Furthermore, D. macrophylla L. fruit significantly improved the muffins’ antioxidant activities. According to sensory evaluation, the muffins made with egg solids and 0.5% of D. macrophylla L. fruit had higher sensory scores than the other experimental samples. Conclusion. D. macrophylla L. fruit is a good potential ingredient for enriching muffins and developing new functional bakery products. However, further research is needed to improve the color reproduction of muffins and determine the optimal concentration of D. macrophylla L.

The present work evaluated nine diverse kidney bean accessions for colour, composition, digestibility, protein profile, starch crystallinity, techno-functional properties, pasting properties and microstructure with the objective of identifying key attributes affecting their digestibility and functionality. The accessions exhibited dry matter digestibility, resistant starch (RS) content, water absorption capacity, fat absorption capacity, emulsifying activity index (EAI), foaming capacity (FC) and foam stability (FS) of 14.6–47.2%, 32.0–50.5%, 1.7–2.7 g/g, 1.4–1.7 g/g, 50.1–70.1 m2/g, 70.8–98.3% and 82.4–91.3%, respectively. Starch-lipid complexes (SLC), proteins and non-starch carbohydrates contributed to lower starch and dry matter-digestibility. Principal component analysis revealed positive relation of emulsification, foaming and water absorption capacity with proteins, starch, RS and ash-content while negative with crystallinity and amount of lipids, non-starch carbohydrates and digestible starch. Hydration ability of proteins promoted foaming whereas flour with lower vicilins level was less surface active and exhibited the lowest EAI, FC and FS. Pasting temperature related positively with SLC, while average starch granule size was in strong positive relationship with RS content, peak viscosity and breakdown viscosity. The results could be useful for enhanced utilization of kidney beans in different foods.

Background: Cardiovascular disease (CVD) is challenging to diagnose and treat since symptoms appear late during the progression of atherosclerosis. Conventional risk factors alone are not always sufficient to properly categorize at-risk patients, and clinical risk scores are inadequate in predicting cardiac events. Integrating genomic-based biomarkers (GBBM) found in plasma/serum samples with novel non-invasive radiomics-based biomarkers (RBBM) such as plaque area, plaque burden, and maximum plaque height can improve composite CVD risk prediction in the pharmaceutical paradigm. These biomarkers consider several pathways involved in the pathophysiology of atherosclerosis disease leading to CVD. Objective: This review proposes two hypotheses: (i) The composite biomarkers are strongly correlated and can be used to detect the severity of CVD/Stroke precisely, and (ii) an explainable artificial intelligence (XAI)-based composite risk CVD/Stroke model with survival analysis using deep learning (DL) can predict in preventive, precision, and personalized (aiP3) framework benefiting the pharmaceutical paradigm. Method: The PRISMA search technique resulted in 214 studies assessing composite biomarkers using radiogenomics for CVD/Stroke. The study presents a XAI model using AtheroEdgeTM 4.0 to determine the risk of CVD/Stroke in the pharmaceutical framework using the radiogenomics biomarkers. Conclusions: Our observations suggest that the composite CVD risk biomarkers using radiogenomics provide a new dimension to CVD/Stroke risk assessment. The proposed review suggests a unique, unbiased, and XAI model based on AtheroEdgeTM 4.0 that can predict the composite risk of CVD/Stroke using radiogenomics in the pharmaceutical paradigm.

Background and motivation: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. Methodology: The system consists of a cascade of quality control, ResNet–UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL’s. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts—Croatia (80 COVID) and Italy (72 COVID and 30 controls)—leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. Results: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. Conclusion: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

Depression is increasingly prevalent, leading to higher suicide risk. Depression detection and sentimental analysis of text inputs in cross-domain frameworks are challenging. Solo deep learning (SDL) and ensemble deep learning (EDL) models are not robust enough. Recently, attention mechanisms have been introduced in SDL. We hypothesize that attention-enabled EDL (aeEDL) architectures are superior compared to attention-not-enabled SDL (aneSDL) or aeSDL models. We designed EDL-based architectures with attention blocks to build eleven kinds of SDL model and five kinds of EDL model on four domain-specific datasets. We scientifically validated our models by comparing “seen” and “unseen” paradigms (SUP). We benchmarked our results against the SemEval (2016) sentimental dataset and established reliability tests. The mean increase in accuracy for EDL over their corresponding SDL components was 4.49%. Regarding the effect of attention block, the increase in the mean accuracy (AUC) of aeSDL over aneSDL was 2.58% (1.73%), and the increase in the mean accuracy (AUC) of aeEDL over aneEDL was 2.76% (2.80%). When comparing EDL vs. SDL for non-attention and attention, the mean aneEDL was greater than aneSDL by 4.82% (3.71%), and the mean aeEDL was greater than aeSDL by 5.06% (4.81%). For the benchmarking dataset (SemEval), the best-performing aeEDL model (ALBERT+BERT-BiLSTM) was superior to the best aeSDL (BERT-BiLSTM) model by 3.86%. Our scientific validation and robust design showed a difference of only 2.7% in SUP, thereby meeting the regulatory constraints. We validated all our hypotheses and further demonstrated that aeEDL is a very effective and generalized method for detecting symptoms of depression in cross-domain settings.