Search

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits and vegetables is a key challenge in maintaining agricultural products. Due to the similarity in disease colour, texture, and shape, it is difficult to recognize manually. Also, this process is time-consuming and requires an expert person. We proposed a novel deep learning and optimization framework for apple and cucumber leaf disease classification to consider the above challenges. In the proposed framework, a hybrid contrast enhancement technique is proposed based on the Bi-LSTM and Haze reduction to highlight the diseased part in the image. After that, two custom models named Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA) are proposed and trained on the selected datasets. After the training, testing images are employed, and deep features are extracted from the self-attention layer. Deep extracted features are fused using a concatenation approach that is further optimized in the next step using an improved human learning optimization algorithm. The purpose of this algorithm was to improve the classification accuracy and reduce the testing time. The selected features are finally classified using a shallow wide neural network (SWNN) classifier. In addition to that, both trained models are interpreted using an explainable AI technique such as LIME. Based on this approach, it is easy to interpret the inside strength of both models for apple and cucumber leaf disease classification and identification. A detailed experimental process was conducted on both datasets, Apple and Cucumber. On both datasets, the proposed framework obtained an accuracy of 94.8% and 94.9%, respectively. A comparison was also conducted using a few state-of-the-art techniques, and the proposed framework showed improved performance. [ABSTRACT FROM AUTHOR]

Objectives: To elucidate the burden and clinico-epidemiological attributes of congenital and hereditary anomalies (CA) in the extended Peshawar Valley of Pakistan. Method: This is a multicenter cross sectional study carried out in Buner, Charsadda, Mardan, Nowshera, Peshawar and Swabi districts, during 2017-2021. The pediatric and adult patients with CA were recruited from hospitals, public places and through door-to-door surveys. The anomalies were classified with the help of specialized clinicians. Descriptive statistics was employed. Results: In this study, 1065 independent subjects with certain types of CA from independent households were included. The index males were 71%; the majority of subjects originated from rural areas (72%), and spoke Pashto (96%). The CA were categorized into 10 major and at least 104 minor categories. There was highest representation of neurological disorders, n=375 (proportion.: 0.352; 95% CI: 0.323-0.381), followed by limb defects (n=281; prop.: 0.264), sensorineural defects (n=128; prop.: 0.120), musculoskeletal defects (n=84; prop.: 0.079), visual impairments (n=67; prop.: 0.063), hemoglobinopathies (n=40; prop.: 0.038), ectodermal disorders (n=34; prop.: 0.032), cardiovascular anomalies (n=19; prop.: 0.018), and orofacial anomalies (n=19; prop). Among the neurological disorder, intellectual disabilities and cerebral palsy were highly prevalent. The majority of the cases had a sporadic presentation (68%), and isolated occurrence (72%), whereas parental consanguinity was witnessed in 58% of cases. Conclusion: A wide range of CA were witnessed in this cohort with a preponderance of neurological disorders. The majority of the anomalies are of severe nature rendering a high morbidity burden in the population and requiring early detection, intervention and management. [ABSTRACT FROM AUTHOR]

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits and vegetables is a key challenge in maintaining agricultural products. Due to the similarity in disease colour, texture, and shape, it is difficult to recognize manually. Also, this process is time-consuming and requires an expert person. We proposed a novel deep learning and optimization framework for apple and cucumber leaf disease classification to consider the above challenges. In the proposed framework, a hybrid contrast enhancement technique is proposed based on the Bi-LSTM and Haze reduction to highlight the diseased part in the image. After that, two custom models named Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA) are proposed and trained on the selected datasets. After the training, testing images are employed, and deep features are extracted from the self-attention layer. Deep extracted features are fused using a concatenation approach that is further optimized in the next step using an improved human learning optimization algorithm. The purpose of this algorithm was to improve the classification accuracy and reduce the testing time. The selected features are finally classified using a shallow wide neural network (SWNN) classifier. In addition to that, both trained models are interpreted using an explainable AI technique such as LIME. Based on this approach, it is easy to interpret the inside strength of both models for apple and cucumber leaf disease classification and identification. A detailed experimental process was conducted on both datasets, Apple and Cucumber. On both datasets, the proposed framework obtained an accuracy of 94.8% and 94.9%, respectively. A comparison was also conducted using a few state-of-the-art techniques, and the proposed framework showed improved performance. [ABSTRACT FROM AUTHOR]

We study the existence of fixed points, local stability analysis, bifurcation sets at fixed points, codimension‐one and codimension‐two bifurcation analysis, and chaos control in a predator‐prey model with Holling types I and III functional responses. It is proven that the model has a trivial equilibrium point for all involved parameters but interior and semitrivial equilibrium solutions under certain model parameter conditions. Furthermore, local stability at trivial, semitrivial, and interior equilibria using the theory of linear stability is investigated. We have also explored the bifurcation sets for trivial, semitrivial, and interior equilibria and proved that flip bifurcation occurs at semitrivial equilibrium. Furthermore, it is also proven that Neimark–Sacker bifurcation as well as flip bifurcation occurs at an interior equilibrium solution, and in addition, at the same equilibrium solution, we also studied codimension‐two 1 : 2 strong resonance bifurcation. Then, OGY and hybrid control strategies are employed to manage chaos in the model under study, which arises from Neimark–Sacker and flip bifurcations, respectively. We have also examined the preservation of the positive solution of the understudied model. Finally, numerical simulations are given to verify the theoretical results. [ABSTRACT FROM AUTHOR]

Osteoporosis is primarily associated with bone loss, but changes in bone tissue matrix composition and osteocyte mechanotransduction have also been identified. However, the molecular mechanisms underlying these changes and their relation to bone loss are not fully understood. The objectives of this study were to (1) conduct comprehensive temporal gene expression analyses on cortical bone tissue from ovariectomized rats, with a specific focus on genes known to govern matrix degradation, matrix production, and mechanotransduction, and (2) correlate these findings with bone mass, trabecular and cortical microarchitecture, and mineral and matrix composition. Microarray data revealed 35 differentially expressed genes in the cortical bone tissue of the ovariectomized cohort. We report that catabolic gene expression abates after the initial accelerated bone loss period, which occurs within the first 4 wk of estrogen deficiency. However, in long-term estrogen deficiency, we report increased expression of genes associated with extracellular matrix deposition (Spp1, COL1A1, COL1A2, OCN) and mechanotransduction (Cx43) compared with age-matched controls and short-term estrogen deficiency. These changes coincided with increased heterogeneity of mineral-to-matrix ratio and collagen maturity, to which extracellular matrix markers COL1A1 and COL1A2 were positively correlated. Interestingly, mineral heterogeneity and collagen maturity, exhibited a negative correlation with PHEX and IFT88, associated with mechanosensory cilia formation and Hedgehog (Hh) signaling. This study provides the first insight into the underlying mechanisms governing secondary mineralization and heterogeneity of matrix composition of bone tissue in long-term estrogen deficiency. We propose that altered mechanobiological responses in long-term estrogen deficiency may play a role in these changes. Graphical Abstract [ABSTRACT FROM AUTHOR]