Automated fruit classification is a stimulating problem in the fruit growing and retail industrial chain as it assists fruit growers and supermarket owners to recognize variety of fruits and the status of the container or stock to increase business profit and production efficacy. As a result, intelligent systems using machine learning and computer vision approaches were explored for ripeness grading, fruit defect categorization, and identification over the last few years. Recently, deep learning (DL) methods for classifying fruits led to promising performance that effectively extracts the feature and carries out an end-to-end image classification. This paper introduces an Automated Fruit Classification using Hyperparameter Optimized Deep Transfer Learning (AFC-HPODTL) model. The presented AFC-HPODTL model employs contrast enhancement as a pre-processing step which helps to enhance the quality of images. For feature extraction, the Adam optimizer with deep transfer learning-based DenseNet169 model is used in which the Adam optimizer fine-tunes the initial values of the DenseNet169 model. Moreover, a recurrent neural network (RNN) model is utilized for the identification and classification of fruits. At last, the Aquila optimization algorithm (AOA) is exploited for optimal hyperparameter tuning of the RNN model in such a way that the classification performance gets improved. The design of Adam optimizer and AOA-based hyperparameter optimizers for DenseNet and RNN models show the novelty of the work. The performance validation of the presented AFC-HPODTL model is carried out utilizing a benchmark dataset and the outcomes report the promising performance over its recent state-of-the-art approaches.
fruit classificationhyperparameter optimizationrecurrent neural networkstransfer learning
The applications of bioactive compounds from medicinal plants as therapeutic drugs are largely increasing. The present study selected the bioactive compounds from Acacia concinna (A. concinna) and Citrus limon (C. limon) to assess their phytochemicals, proteins, and biological activity. The plant material was collected, and extraction performed as per the standard procedure. Qualitative analysis was undertaken, and identification of functional organic groups was performed by FTIR and HPLC. Antibacterial, anticancer, antioxidant, antihyperglycemic, antihyperlipidemic, and inhibition kinetics studies for enzymes were performed to assess the different biological activities. Flavonoids and phenols were present in a significant amount in both the selected plants. A. concinna showed significant antimicrobial activity against Z. mobilis, E. coli, and S. aureus, with minimum inhibition zones (MIZ) of 24, 22, and 20 mm, respectively. C. limon strongly inhibited all the tested pathogenic bacteria with maximum and minimum MIZ of 32 and 17 mm. A. concinna silver nanoparticles also exhibited potent antimicrobial activity. Both extracts showed substantial antioxidant, antihyperlipidemic, antidiabetic, anticancer (MCF-7), and anti-urease (antiulcer) properties. To conclude, these plants can be used to treat hyperlipidemia, diabetes, cancer, and gastrointestinal ulcers. They can also serve as antimicrobial and antioxidant agents. Thus, the studied plants must be exploited cost-effectively to generate therapeutic drugs for various diseases.
Journal of Enzyme Inhibition and Medicinal Chemistry · مجلد 37 (1) · 563-572
On account of its crucial role in the virus life cycle, SARS-COV-2 NSP13 helicase enzyme was exploited as a promising target to identify a novel potential inhibitor using multi-stage structure-based drug discovery approaches. Firstly, a 3D pharmacophore was generated based on the collected data from a protein-ligand interaction fingerprint (PLIF) study using key interactions between co-crystallised fragments and the NSP13 helicase active site. The ZINC database was screened through the generated 3D-pharmacophore retrieving 13 potential hits. All the retrieved hits exceeded the benchmark score of the co-crystallised fragments at the molecular docking step and the best five-hit compounds were selected for further analysis. Finally, a combination between molecular dynamics simulations and MM-PBSA based binding free energy calculations was conducted on the best hit (compound FWM-1) bound to NSP13 helicase enzyme, which identified FWM-1 as a potential potent NSP13 helicase inhibitor with binding free energy equals −328.6 ± 9.2 kcal/mol.
SARS-CoV-2nsp13 helicasehelicase inhibitorsstructure-based drug design
Breast cancer is the major cause behind the death of women worldwide and is responsible for several deaths each year. Even though there are several means to identify breast cancer, histopathological diagnosis is now considered the gold standard in the diagnosis of cancer. However, the difficulty of histopathological image and the rapid rise in workload render this process time-consuming, and the outcomes might be subjected to pathologists' subjectivity. Hence, the development of a precise and automatic histopathological image analysis method is essential for the field. Recently, the deep learning method for breast cancer pathological image classification has made significant progress, which has become mainstream in this field. This study introduces a novel chaotic sparrow search algorithm with a deep transfer learning-enabled breast cancer classification (CSSADTL-BCC) model on histopathological images. The presented CSSADTL-BCC model mainly focused on the recognition and classification of breast cancer. To accomplish this, the CSSADTL-BCC model primarily applies the Gaussian filtering (GF) approach to eradicate the occurrence of noise. In addition, a MixNet-based feature extraction model is employed to generate a useful set of feature vectors. Moreover, a stacked gated recurrent unit (SGRU) classification approach is exploited to allot class labels. Furthermore, CSSA is applied to optimally modify the hyperparameters involved in the SGRU model. None of the earlier works have utilized the hyperparameter-tuned SGRU model for breast cancer classification on HIs. The design of the CSSA for optimal hyperparameter tuning of the SGRU model demonstrates the novelty of the work. The performance validation of the CSSADTL-BCC model is tested by a benchmark dataset, and the results reported the superior execution of the CSSADTL-BCC model over recent state-of-the-art approaches.
breast cancer classificationhistopathological imagestransfer learninghyperparameter optimization
In recent years, human action recognition is modeled as a spatial-temporal video volume. Such aspects have recently expanded greatly due to their explosively evolving real-world uses, such as visual surveillance, autonomous driving, and entertainment. Specifically, the spatio-temporal interest points (STIPs) approach has been widely and efficiently used in action representation for recognition. In this work, a novel approach based on the STIPs is proposed for action descriptors i.e., Two Dimensional-Difference Intensity Distance Group Pattern (2D-DIDGP) and Three Dimensional-Difference Intensity Distance Group Pattern (3D-DIDGP) for representing and recognizing the human actions in video sequences. Initially, this approach captures the local motion in a video that is invariant to size and shape changes. This approach extends further to build unique and discriminative feature description methods to enhance the action recognition rate. The transformation methods, such as DCT (Discrete cosine transform), DWT (Discrete wavelet transforms), and hybrid DWT+DCT, are utilized. The proposed approach is validated on the UT-Interaction dataset that has been extensively studied by past researchers. Then, the classification methods, such as Support Vector Machines (SVM) and Random Forest (RF) classifiers, are exploited. From the observed results, it is perceived that the proposed descriptors especially the DIDGP based descriptor yield promising results on action recognition. Notably, the 3D-DIDGP outperforms the state-of-the-art algorithm predominantly.
human action recognitionspatio-temporal interest pointsvideo feature extractiondiscrete wavelet transform
Frontiers in Pharmacology · مجلد 12 · 770762-770762
Tuberculosis (TB) is the leading cause of death from a single infectious agent. The estimated total global TB deaths in 2019 were 1.4 million. The decline in TB incidence rate is very slow, while the burden of noncommunicable diseases (NCDs) is exponentially increasing in low- and middle-income countries, where the prevention and treatment of TB disease remains a great burden, and there is enough empirical evidence (scientific evidence) to justify a greater research emphasis on the syndemic interaction between TB and NCDs. The current study was proposed to build a disease-gene network based on overlapping TB with NCDs (overlapping means genes involved in TB and other/s NCDs), such as Parkinson’s disease, cardiovascular disease, diabetes mellitus, rheumatoid arthritis, and lung cancer. We compared the TB-associated genes with genes of its overlapping NCDs to determine the gene-disease relationship. Next, we constructed the gene interaction network of disease-genes by integrating curated and experimentally validated interactions in humans and find the 13 highly clustered modules in the network, which contains a total of 86 hub genes that are commonly associated with TB and its overlapping NCDs, which are largely involved in the Inflammatory response, cellular response to cytokine stimulus, response to cytokine, cytokine-mediated signaling pathway, defense response, response to stress and immune system process. Moreover, the identified hub genes and their respective drugs were exploited to build a bipartite network that assists in deciphering the drug-target interaction, highlighting the influential roles of these drugs on apparently unrelated targets and pathways. Targeting these hub proteins by using drugs combination or drug repurposing approaches will improve the clinical conditions in comorbidity, enhance the potency of a few drugs, and give a synergistic effect with better outcomes. Thus, understanding the Mycobacterium tuberculosis (Mtb) infection and associated NCDs is a high priority to contain its short and long-term effects on human health. Our network-based analysis opens a new horizon for more personalized treatment, drug-repurposing opportunities, investigates new targets, multidrug treatment, and can uncover several side effects of unrelated drugs for TB and its overlapping NCDs.
Clustering of multi-view data has got broad consideration of the researchers. Multi-view data is composed through different domain which shows the consistent and complementary behavior. The existing studies did not draw attention of over-fitting and sparsity among the diverse view, which is the considerable issue for getting the unique consensus knowledge from these complementary data. Herein article, a multi-view clustering approach is recommended to provide the consensus solution from the multi-view data. To accomplish this task, we exploit non-negative matrix factorized method to generate a cost function. Further, manifold learning model is used to build the graph through the nearest neighbor strategy, which is effective to save the geometrical design for data and feature matrix. Furthermore, the over-fitting problem, sparsity is handled through adaption of frobenious norm, and$L_{1}$-norm on basis and coefficient matrices. The whole formulation is done through the mathematical function, which is optimized through the iterative updating strategy to get the optimal solution. The computational experiment is carried on the available datasets to exhibits that the proposed strategy beats the current methodologies in terms of clustering execution.
IEEE Annual Computing and Communication Workshop and Conference (CCWC) · 0007-0011
Emails are frequently utilized as a way of personal and professional communication. Banking information, credit reports, login data, and other sensitive personal information are commonly transmitted over email. This makes them valuable to cybercriminals, who can exploit the knowledge for their gain. Phishing is a technique used by con artists to steal sensitive information from people by impersonating well-known sources. The sender of a phished email can persuade you to disclose personal information under pretenses. The detection of a phished email is treated as a classification problem in this research, and this paper shows how machine learning methods are used to categorize emails as phished or not. SVM classifier attains a maximum accuracy of 0.998 percent in email classification.
Frontiers in Pharmacology · مجلد 13 · 902207-902207
The present work investigates a blend of jack fruit mucilage (JFM) and okra mucilage (OKM) as promising mucoadhesive carriers for colon-specific delivery of a curcumin (CMN)-loaded mucoadhesive tablet (CMT) formulation. Formulation optimization was performed using central composite design (CCD) to further decipher the effect of varying proportions of the mucoadhesive carriers JFM and OKG on response factors such as drug release (% DR) and mucoadhesive strength (MA). The optimized formulation CMT (F14) demonstrated a favorable 54.35% in vitro release of CMN in 12 h with release kinetics resulting from a zero-order anomalous diffusion mechanism and MA of 34.1733 ± 1.26 g. Accelerated stability testing of CMT (F14) confirmed a shelf life of about 4.7 years. In vivo drug targeting studies performed using rabbit models in order to observe transit behavior (colon-specific delivery) of the dosage form were assessed by fluoroscopic images of the GI tract. Taking the results together, the results confirm that the combination of JFM and OKM could be exploited as an ideal mucoadhesive carrier for effective delivery of macromolecules to the colon.
curcuminmucoadhesive tabletsokra mucilagecolon-targeted drug delivery
BACKGROUND: Bacterial ghosts are the evacuated bacterial cellular membranes from most of the genetic and protein contents which preserved their surface characters. Recently, bacterial ghosts exploited for different biomedical applications, for instance, vaccination. The purpose of this study is to measure the immunogenic protective response of bacterial ghosts of Salmonella Typhimurium in animals and to allow future testing this response in humans. The immunologic response was qualitatively, quantitatively, and functionally measured. We have measured the humoral and cellular immune responses, such as immunoglobulins elevation (IgG), increased granulocytes, serum antibacterial activity, clearance of virulence in feces and liver, and the survival rate. RESULTS: The bacterial ghosts' vaccine was able to protect 100% of subcutaneously vaccinated rats and 75% of adjuvant subcutaneously vaccinated rats. The lowest survival rate was in the orally vaccinated group (25%). The maximum level of serum IgG titers, as well as serum and feces bactericidal activity (100% eradication), was exhibited in the subcutaneously vaccinated group with adjuvant vaccines followed by the subcutaneously vaccinated one. Additionally, the highest granulocytes' number was observed in the adjuvant vaccine subcutaneously immunized group. The bacterial load in liver homogenate was eliminated in the subcutaneously vaccinated rats after the virulence challenge. CONCLUSIONS: The bacterial ghosts of Salmonella enterica serovar Typhimurium that prepared by Tween 80 Protocol showed an effective vaccine candidate that protected animals, eliminated the virulence in feces and liver. These findings show that chemically induced bacterial ghosts of Salmonella Typhimurium can be a promising vaccine.
IEEE Annual Computing and Communication Workshop and Conference (CCWC) · 0354-0358
Emails are frequently utilized as a way of personal and professional communication. Banking information, credit reports, login data, and other sensitive and personal information are frequently transmitted over email. This makes them valuable to cyber criminals, who can exploit the knowledge for their own gain. Phishing is a technique used by con artists to steal sensitive information from people by impersonating well-known sources. The sender of a phished email can persuade you to disclose personal information under false pretenses. The detection of a phished email is treated as a classification problem in this research, and this paper shows how machine learning methods are used to categorize emails as phished or not. LMT classifiers attain a maximum accuracy in email classification.
Journal of King Saud University - Science · مجلد 34 (6) · 102147-102147
Various protein/receptor targets have been discovered through in-silico research. They are expanding rapidly due to their extensive advantage of delivering new drug candidates more quickly, efficiently, and at a lower cost. The automation of organic synthesis and biochemical screening will lead to a revolution in the entire research arena in drug discovery. In this research article, a few fungal metabolites were examined through an in-silico approach which involves major steps such as (a) Molecular Docking Analysis, (b) Drug likeness and ADMET studies, and (c) Molecular Dynamics Simulation. Fungal metabolites were taken from Antibiotic Database which showed antiviral effects on severe viral diseases such as HIV. Docking, Lipinski's, and ADMET analyses investigated the binding affinity and toxicity of five metabolites: Chromophilone I, iso; F13459; Stachyflin, acetyl; A-108836; Integracide A (A-108835). Chromophilone I, iso was subjected to additional analysis, including a 50 ns MD simulation of the protein to assess the occurring alterations. This molecule's docking data shows that it had the highest binding affinity. ADMET research revealed that the ligand might be employed as an oral medication. MD simulation revealed that the ligand–protein interaction was stable. Finally, this ligand can be exploited to develop SARS-CoV-2 therapeutic options. Fungal metabolites that have been studied could be a potential source for future lead candidates. Further study of these molecules may result in creating an antiviral drug to battle the SARS-CoV-2 virus.
SARS-CoV-2RNA-dependent RNA polymerasefungal metabolitesantiviral drug discovery
Computer Systems Science and Engineering · مجلد 44 (3) · 2277-2292
Learning Management System (LMS) is an application software that is used in automation, delivery, administration, tracking, and reporting of courses and programs in educational sector. The LMS which exploits machine learning (ML) has the ability of accessing user data and exploit it for improving the learning experience. The recently developed artificial intelligence (AI) and ML models helps to accomplish effective performance monitoring for LMS. Among the different processes involved in ML based LMS, feature selection and classification processes find beneficial. In this motivation, this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring (GSO-MFWELM) technique for LMS. The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS. The proposed GSO-MFWELM technique involves GSO-based feature selection technique to select the optimal features. Besides, Weighted Extreme Learning Machine (WELM) model is applied for classification process whereas the parameters involved in WELM model are optimally fine-tuned with the help of Mayfly Optimization (MFO) algorithm. The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance. The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects. The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.