Recognition of inscribed cursive Pashtu numeral through optimized deep learning.

Pashtu is one of the most widely spoken languages in south-east Asia. Pashtu Numerics recognition poses challenges due to its cursive nature. Despite this, employing a machine learning-based optical character recognition (OCR) model can be an effective way to tackle this issue. The main aim of the study is to propose an optimized machine learning model which can efficiently identify Pashtu numerics from 0-9. The methodology includes data organizing into different directories each representing labels. After that, the data is preprocessed i.e., images are resized to 32 × 32 images, then they are normalized by dividing their pixel value by 255, and the data is reshaped for model input. The dataset was split in the ratio of 80:20. After this, optimized hyperparameters were selected for LSTM and CNN models with the help of trial-and-error technique. Models were evaluated by accuracy and loss graphs, classification report, and confusion matrix. The results indicate that the proposed LSTM model slightly outperforms the proposed CNN model with a macro-average of precision: 0.9877, recall: 0.9876, F1 score: 0.9876. Both models demonstrate remarkable performance in accurately recognizing Pashtu numerics, achieving an accuracy level of nearly 98%. Notably, the LSTM model exhibits a marginal advantage over the CNN model in this regard.

Saraiki language characters dataset (SLCD).

About 26 million people worldwide use the Saraiki language [1]. In the southern part of Punjab and Sindh, Saraiki language is extensively spoken. One of the most important Saraiki cultural hubs is Dera Ghazi Khan. In Dera Ghazi Khan, the Saraiki language is spoken by over 90 % of the population. Calligraphers use a sophisticated script to write this language. Despite the vast body of Optical Character Recognition (OCR) literature and research dedicated to other languages, a fully functional OCR system is still needed for Saraiki language [2,3]. This work presents a genuine dataset of Saraiki handwritten characters, consisting of 50,000 scanned photos, and makes it accessible to the public for use. All of the photographs include handwritten text contributed by teachers and students from Pak-Austria Fachhochschule for Applied Sciences and Technology, Pakistan. Around 1000 people, roughly half men and half women, contributed in writing this text. For scientific research, the dataset will be made accessible to the general public.

Biosynthesized Silver Nanoparticles Using Alnus nitida Leaf Extract as a Potential Antioxidant and Anticancer Agent.

Biogenic synthesis of silver nanoparticles (AgNPs) using plant extracts is gaining attention as a substitute to the conventional physical and chemical synthesis methods. This study reports a facile, cost-effective, and ecofriendly synthesis of AgNPs using leaf extract of Alnus nitida (A. nitida) and their antioxidant and antiproliferative activities. The biosynthesized AgNPs were characterized using various analytical techniques including UV-visible spectroscopy, energy-dispersive spectrometry, scanning electron microscopy (SEM), Fourier transform infrared (FTIR), X-ray diffraction (XRD), and dynamic light scattering. The antioxidant and cytotoxic potential of the extract and AgNPs was evaluated using different in vitro models. The UV-vis analysis revealed a surface plasmon resonance peak of 400 nm corresponding to the synthesis of AgNPs. SEM analysis confirmed the formation of heterogeneously dispersed particles of nano size, while the XRD and FTIR spectra confirmed the crystallinity and existence of different functional groups that helped in capping and stability of AgNPs. The antioxidant activity of AgNPs and extract, studied by 1,1-diphenyl 2-picryl hydrazyl (DPPH), fluorescence recovery after photobleaching (FRAP), 2, 2'-azino-bis-3-ethylbenzothiazoline-6-sulfonic acid (ABTS), and H2O2 scavenging assays, showed a dose-dependent effect. The AgNPs at 1000 µg/mL significantly scavenged DPPH, FRAP, ABTS, and H2O2 by 66.45, 74.65, 78.81, and 72.56% with an average IC50 value of 33.31, 18.50, 16.46, and 15.65 µg/mL, respectively. The cytotoxic potential investigated by MTT assay revealed promising antiproliferative effects against different cancer cell lines. The IC50 values of AgNPs on MDA-MB-231, A549, and Hep-G2 cells were 14.88, 3.6, and 5.38 µg/mL, respectively. The results showed that AgNPs were more effective against lung and hepatocellular carcinoma. The selectivity index showed that AgNPs remained highly selective in retarding the growth of A549 and Hep-G2 cells as compared to normal cell lines HPAEpiC and HRPTEpiC. Overall, this study showed that biosynthesized AgNPs were associated with considerable antioxidant and cytotoxic effects. Our work suggests that A. nitida-mediated AgNPs should be evaluated further in order to develop safe and effective formulations for the treatment of different degenerative diseases.

Effect of Ajwa date pits powder (Phoenix dactylifera L.) on body composition, lipid profile and blood pressure in patients with hyperlipidemia: A randomized clinical trial.

Objective: To evaluate the effect of Ajwa dates pit powder (ADP) on lipid profile, body composition and blood pressure in patients with hyperlipidemia. Materials and Methods: This randomized controlled clinical study was carried out on 40 patients with total cholesterol >200 mg/dl, triglycerides >150 mg/dl and BMI >25, of either sex, aged 30-50 years, who were recruited through written consent. The patients were divided into two groups (n=20 each): the ADP and the control group (CG). All patients received the doctor's prescribed class A statin (Rosuvastatin/ Atorvastatin) 10 mg/day, while 2.7 g ADP was given on daily basis before breakfast with lukewarm water for 40 days and the control group received the same amount of wheat flour. Body composition, blood pressure and lipid profile were determined at baseline, and after 20 and 40 days. Data were analyzed by using SPSS and GraphPad Prism. Results: ADP significantly reduced body weight (p<0.001), BMI (p<0.001), fat mass, body fat percentage, visceral fat area and waist circumference compared to the control group. Similarly, ADP significantly (p=0.000) decreased the serum level of total cholesterol and low-density lipoprotein. Conclusion: ADP may have the potential to improve dyslipidemia and obesity.

Antioxidant and Anti-inflammatory Activities of Rumex acetosa

Rumex acetosa is a folk medicine for gastritis and gastric ulcers. In our previous study, the ethanol extract of R. acetosa inhibited gastric ulcers and protected gastric tissue in mice induced with HCl/ethanol from gastric ulcers. Moreover, we isolated six anthraquinone compounds from this plant and evaluated their antiHelicobacter pylori activity. Therefore, this study was conducted to identify further the related antioxidant and anti-inflammatory activities and the bioactive constituents. Five fractions of n-hexane, methylene chloride, ethyl acetate, n-butanol, and aqueous fractions were obtained from the total ethanolic extract from whole parts of R. acetosa that had exhibited antioxidant and anti-inflammatory activities. The ethyl acetate fraction contained the highest total phenol and flavonoid contents among the five fractions and exhibited the most potent antioxidant effect on 2,2-diphenyl-1-picrylhydrazyl radical scavenging assay. Among the six compounds, emodin showed the most potent antioxidant activity. Next, we induced inflammation in the LPS-induced RAW 264.7 cell line. The methylene chloride fraction showed the strongest reducing nitric oxide production activity among the fractions. In addition, the methylene chloride fraction suppressed the phosphorylation of ERK and JNK, and the expression of cyclooxygenase-2 in a dose-dependent manner. These physiological activities of the fraction and the compounds could be involved in the anti-gastric ulcer activity of R. acetosa

Pashtu Language Digits Dataset.

Pashtu is a language spoken by 50 million people in the world [1]. It is the national language of Afghanistan and also spoken in the two largest provinces of Pakistan. It is a language written in complex way by calligraphers. Instead of enormous literature and research work in Optical Character Recognition for other languages of the world, this language still requires a mature optical character recognition system [2], [3]. A real dataset of Pashtu digits having 50000 scanned images is introduced and made publically available in this paper. All the digits in the images are handwritten images written and collected from faculty members, staff, and students of the Pak-Austria Fachhochschule, Institute of Applied Sciences and Technology, Pakistan. A total of 1250 candidates appeared in writing the text, out of which half are male and half female. The dataset will be publically available for research purposes.

Role of Neuropilin 1 in COVID-19 Patients with Acute Ischemic Stroke.

Severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) infection can trigger the adaptive and innate immune responses, leading to uncontrolled inflammatory reactions and associated local and systematic tissue damage, along with thromboembolic disorders that may increase the risk of acute ischemic stroke (AIS) in COVID-19 patients. The neuropilin (NRP-1) which is a co-receptor for the vascular endothelial growth factor (VEGF), integrins, and plexins, is involved in the pathogenesis of AIS. NRP-1 is also regarded as a co-receptor for the entry of SARS-CoV-2 and facilitates its entry into the brain through the olfactory epithelium. NRP-1 is regarded as a cofactor for binding of SARS-CoV-2 with angiotensin-converting enzyme 2 (ACE2), since the absence of ACE2 reduces SARS-CoV-2 infectivity even in presence of NRP-1. Therefore, the aim of the present study was to clarify the potential role of NRP-1 in COVID-19 patients with AIS. SARS-CoV-2 may transmit to the brain through NRP-1 in the olfactory epithelium of the nasal cavity, leading to different neurological disorders, and therefore about 45% of COVID-19 patients had neurological manifestations. NRP-1 has the potential capability to attenuate neuroinflammation, blood-brain barrier (BBB) permeability, cerebral endothelial dysfunction (ED), and neuronal dysfunction that are uncommon in COVID-19 with neurological involvement, including AIS. Similarly, high NRP-1 serum level is linked with ED, oxidative stress, and the risk of pulmonary thrombosis in patients with severe COVID-19, suggesting a compensatory mechanism to overcome immuno-inflammatory disorders. In conclusion, NRP-1 has an important role in the pathogenesis of COVID-19 and AIS, and could be the potential biomarker linking the development of AIS in COVID-19. The present findings cannot provide a final conclusion, and thus in silico, experimental, in vitro, in vivo, preclinical, and clinical studies are recommended to confirm the potential role of NRP-1 in COVID-19, and to elucidate the pharmacological role of NRP-1 receptor agonists and antagonists in COVID-19.

Silver and gold nanoparticles induced differential antimicrobial potential in calli cultures of Prunella vulgaris.

BACKGROUND: Prunella vulgaris is medicinally important plant containing high-valued chemical metabolites like Prunellin which belong to family Lamiaceae and it is also known as self-heal. In this research, calli culture were exposed to differential ratios of gold (Au) and silver (Ag) nanoparticles (1:1, 1:2, 1:3, 2:1 and 3:1) along with naphthalene acetic acid (2.0 mg NAA) to investigate its antimicrobial potential. A well diffusion method was used for antimicrobial properties. RESULTS: Here, two concentrations (1 and 2 mg/6 µl) of all treated calli cultures and wild plants were used against Escherichia coli, Pseudomonas aeruginosa, Salmonella typhi, Bacillus atrophaeus, Bacillus subtilis, Agrobacterium tumefaciens, Erwinia caratovora and Candida albicans. Dimethyl sulfoxide (DMSO) and antibiotics were used as negative and positive controls. Here, the calli exposed to gold (Au) nanoparticles (NPs) and 2.0 mg naphthalene acetic acid (NAA) displayed the highest activity (25.7 mm) against Salmonella typhi than other extracts, which was considered the most susceptible species, while Agrobacterium tumefaciens and Candida albicans was the most resistance species. A possible mechanism of calli induced nanoparticles was also investigated for cytoplasmic leakage. CONCLUSION: From the above data it is concluded that Prunella vulgaris is medicinally important plant for the development of anti-microbial drugs using nanotechnology and applicable in various pharmaceutical research.

Evaluation of in-vitro and in-vivo antimicrobial potential of Typha elephantina leaves extracts using Cyprinus carpio as a research model.

Present study investigate the in-vitro antibacterial and antifungal potential of Typha elephantina leaves aqueous extract (T. Eaq), ethanolic extract (T. Eeth) and methanolic extract (T. Emth) at different dosages against selected bacteria and fungi using dis diffusion method and Potato Dextrose Agar method. The study was also proceeded in- vivo against one strain of fungi (Aspergillus niger) using aqueous (T. Eaq) extract only. In-vitro study showed that Citrobacter freundii was highly sensitive while Salmonella typhimurium was the least among all. The antifungal activity was dose dependent and differs according to the fungal strain. Aspergillus niger was highly sensitive in order of aqueous extract (T. Eaq), ethanolic extract (T. Eeth) and methanolic extract (T.Emth), followed by Alterneria solani, Candida albicans and Aspergillus ustus. The in-vivo antifungal study was carried using Cyprinus carpio which were first infected with Aspergillus niger and then treated with (T. Eaq) at different doses. During in-vivo study various hematobiochemicl parameters and bio-accumulative stress of some heavy metals were assessed. Highly significant (P<0.05) remedial effects were observed at day 21st of treatment with extract at 100mg/ kg body weight. Differential accumulation was found i.e in skin the accumulation was highest followed by intestine gills and muscles tissues. Liver showed least accumulation.

Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network.

Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. PROBLEM: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. METHOD: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim's dataset to detect pilgrims from the surveillance cameras. These preprocessed salient frames are passed to a lightweight CNN model for spatial features extraction in the second step. In the third step, a Long Short Term Memory network (LSTM) is developed to extract temporal features. Finally, in the last step, in the case of violent activity or accidents, the proposed system will generate an alarm in real time to inform law enforcement agencies to take appropriate action, thus helping to avoid accidents and stampedes. RESULTS: We have conducted multiple experiments on two publicly available violent activity datasets, such as Surveillance Fight and Hockey Fight datasets; our proposed model achieved accuracies of 81.05 and 98.00, respectively.

In vivo laxative, anti-diarrheal, hepatoprotective and diuretic investigations of Sterculia diversifolia and its isolated compound.

OBJECTIVE: To investigated the laxative, anti-diarrheal, hepatoprotective and diuretic activity of Sterculia diversifolia and its isolated compounds. METHODS: The laxative activity was studied by counting wet stools while anti-diarrheal activity was performed by measuring gastrointestinal tract motility. Hepatoprotective activity was studied by biochemical and histo-pathological analysis while diuretic activity was performed by urine collection protocol. RESULTS: Doses of 30 and 100 mg/kg of crude methanolic extract of Sterculia diversifolia (MESD) stem bark and leaves, significantly (P < 0.05, P < 0.01) produced wet feces in subjects pretreated with atropine while 8-hydroxyquercetin and dihydroquercetin showed highly significant (P < 0.001) results by increasing fecal weight and water contents without producing diarrhea. MESD stem bark and leaves also dose-dependently lowered diarrhea while 8-hydroxyquercetin and dihydroquercetin showed highly significant (P < 0.001) results by producing shaped stools in mice. MESD, 8-hydroxyquercetin and dihydroquercetin offered significant protection against histopathological changes in the liver. Diuretic activity of Crude MESD stem bark and leaves extracts shows highly significant diuretic effect while dihydroquercetin showed better results than 8-hydroxyquercetin. CONCLUSION: It is concluded that Sterculia diversifolia and its isolated compounds bears laxative, anti-diarrheal, hepatoprotective and diuretic effects.

Mechanistic evaluation of a novel cyclohexenone derivative's functionality against nociception and inflammation: An in-vitro, in-vivo and in-silico approach.

The synthesis of a novel cyclohexanone derivative (CHD; Ethyl 6-(4-metohxyphenyl)-2-oxo-4-phenylcyclohexe-3-enecarboxylate) was described and the subsequent aim was to perform an in vitro, in vivo and in silico pharmacological evaluation as a putative anti-nociceptive and anti-inflammatory agent in mice. Initial in vitro studies revealed that CHD inhibited both cyclooxygenase-2 (COX-2) and 5-lipoxygenase (5-LOX) enzymes and it also reduced mRNA expression of COX-2 and the pro-inflammatory cytokines TNF-α and IL-1ß. It was then shown that CHD dose dependently inhibited chemically induced tonic nociception in the abdominal constriction assay and also phasic thermal nociception (i.e. anti-nociception) in the hot plate and tail immersion tests in comparison with aspirin and tramadol respectively. The thermal test outcomes indicated a possible moderate centrally mediated anti-nociception which, in the case of the hot plate test, was pentylenetetrazole (PTZ) and naloxone reversible, implicating GABAergic and opioidergic mechanisms. CHD was also effective against both the neurogenic and inflammatory mediator phases induced in the formalin test and it also disclosed anti-inflammatory activity against the phlogistic agents, carrageenan, serotonin, histamine and xylene compared with standard drugs in edema volume tests. In silico studies indicated that CHD possessed preferential affinity for GABAA, opioid and COX-2 target sites and this was supported by molecular dynamic simulations where computation of free energy of binding also favored the formation of stable complexes with these sites. These findings suggest that CHD has prospective anti-nociceptive and anti-inflammatory properties, probably mediated through GABAergic and opioidergic interactions supplemented by COX-2 and 5-LOX enzyme inhibition in addition to reducing pro-inflammatory cytokine expression. CHD may therefore possess potentially beneficial therapeutic effectiveness in the management of inflammation and pain.

Advances and Trends in Real Time Visual Crowd Analysis.

Real time crowd analysis represents an active area of research within the computer vision community in general and scene analysis in particular. Over the last 10 years, various methods for crowd management in real time scenario have received immense attention due to large scale applications in people counting, public events management, disaster management, safety monitoring an so on. Although many sophisticated algorithms have been developed to address the task; crowd management in real time conditions is still a challenging problem being completely solved, particularly in wild and unconstrained conditions. In the proposed paper, we present a detailed review of crowd analysis and management, focusing on state-of-the-art methods for both controlled and unconstrained conditions. The paper illustrates both the advantages and disadvantages of state-of-the-art methods. The methods presented comprise the seminal research works on crowd management, and monitoring and then culminating state-of-the-art methods of the newly introduced deep learning methods. Comparison of the previous methods is presented, with a detailed discussion of the direction for future research work. We believe this review article will contribute to various application domains and will also augment the knowledge of the crowd analysis within the research community.

PHND: Pashtu Handwritten Numerals Database and deep learning benchmark.

In this paper we introduce a real Pashtu handwritten numerals dataset (PHND) having 50,000 scanned images and make publicly available for research and scientific use. Although more than fifty million people in the world use this language for written and oral communication, no significant efforts are devoted to the Pashtu Optical Character Recognition (POCR). We present a new approach for Pahstu handwritten numerals recognition (PHNR) based on deep neural networks. We train Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) on high-frequency numerals for feature extraction and classification. We evaluated the performance of the proposed algorithm on the newly introduced Pashtu handwritten numerals database PHND and Bangla language number database CMATERDB 3.1.1. We obtained best recognition rate of 98.00% and 98.64% on PHND and CMATERDB 3.1.1. respectively.

A Multi-Task Framework for Facial Attributes Classification through End-to-End Face Parsing and Deep Convolutional Neural Networks.

Human face image analysis is an active research area within computer vision. In this paper we propose a framework for face image analysis, addressing three challenging problems of race, age, and gender recognition through face parsing. We manually labeled face images for training an end-to-end face parsing model through Deep Convolutional Neural Networks. The deep learning-based segmentation model parses a face image into seven dense classes. We use the probabilistic classification method and created probability maps for each face class. The probability maps are used as feature descriptors. We trained another Convolutional Neural Network model by extracting features from probability maps of the corresponding class for each demographic task (race, age, and gender). We perform extensive experiments on state-of-the-art datasets and obtained much better results as compared to previous results.

Carveol a Naturally-Derived Potent and Emerging Nrf2 Activator Protects Against Acetaminophen-Induced Hepatotoxicity.

Acetaminophen (N-acetyl p-aminophenol or APAP) is used worldwide for its antipyretic and anti-inflammatory potential. However, APAP overdose sometimes causes severe liver damage. In this study, we elucidated the protective effects of carveol in liver injury, using molecular and in silico approaches. Male BALB/c mice were divided into two experimental cohorts, to identify the best dose and to further assess the role of carveol in the nuclear factor E2-related factor; nuclear factor erythroid 2; p45-related factor 2 (Nrf2) pathway. The results demonstrated that carveol significantly modulated the detrimental effects of APAP by boosting endogenous antioxidant mechanisms, such as nuclear translocation of Nrf2 gene, a master regulator of the downstream antioxidant machinery. Furthermore, an inhibitor of Nrf2, called all-trans retinoic acid (ATRA), was used, which exaggerated APAP toxicity, in addition to abrogating the protective effects of carveol; this effect was accompanied by overexpression of inflammatory mediators and liver = 2ltoxicity biomarkers. To further support our notion, we performed virtual docking of carveol with Nrf2-keap1 target, and the resultant drug-protein interactions validated the in vivo findings. Together, our findings suggest that carveol could activate the endogenous master antioxidant Nrf2, which further regulates the expression of downstream antioxidants, eventually ameliorating the APAP-induced inflammation and oxidative stress.

Anti-Helicobacter pylori Activity of Compounds Isolated from Fraxinus mandshurica Bark

Helicobacter pylori is a well-known pathogen that is responsible for gastric disorders. Overcoming of the antibiotic-resistance is a main barrier to treat H. pylori infection. In our search for anti-H. pylori compounds from natural resources, bioactivity-guided isolation on the ethyl acetate fraction of Fraxinus mandshurica bark that had shown anti-H. pylori activity gave twelve compounds (1 - 12) of six coumarins, three phenylethanoids, two secoiridoids, and a lignan using silica gel column chromatography, Sephadex-LH 20, and recrystallization.The chemical structures were identified by spectroscopic data analysis, including 1D, 2D NMR, and mass spectrometry. Among them, compounds 2, 10, and 11 showed moderate growth inhibitory activity against three strains ofH. pylori, compared with positive controls of quercetin and metronidazole. Compounds 5, 6, 8, and 12 exhibited the inhibitory activity against strains 26695 or 43504. This is the first report on the anti-H. pylori activity of this plant and the isolated compounds.

FASSEG: A FAce semantic SEGmentation repository for face image analysis.

The FASSEG repository is composed by four subsets containing face images useful for training and testing automatic methods for the task of face segmentation. Threesubsets, namely frontal01, frontal02, and frontal03 are specifically built for performing frontal face segmentation. Frontal01 contains 70 original RGB images and the corresponding roughly labelledground-truth masks. Frontal02 contains the same image data, with high-precision labelled ground-truth masks. Frontal03 consists in 150 annotated face masks of twins captured in various orientations, illumination conditions and facial expressions. The last subset, namely multipose01, contains more than 200 faces in multiple poses and the corresponding ground-truth masks. For all face images, ground-truth masks are labelled on six classes (mouth, nose, eyes, hair, skin, and background).

A Unified Framework for Head Pose, Age and Gender Classification through End-to-End Face Segmentation.

Accurate face segmentation strongly benefits the human face image analysis problem. In this paper we propose a unified framework for face image analysis through end-to-end semantic face segmentation. The proposed framework contains a set of stack components for face understanding, which includes head pose estimation, age classification, and gender recognition. A manually labeled face data-set is used for training the Conditional Random Fields (CRFs) based segmentation model. A multi-class face segmentation framework developed through CRFs segments a facial image into six parts. The probabilistic classification strategy is used, and probability maps are generated for each class. The probability maps are used as features descriptors and a Random Decision Forest (RDF) classifier is modeled for each task (head pose, age, and gender). We assess the performance of the proposed framework on several data-sets and report better results as compared to the previously reported results.