Short-term wind power forecasting through stacked and bi directional LSTM techniques.

Background: Computational intelligence (CI) based prediction models increase the efficient and effective utilization of resources for wind prediction. However, the traditional recurrent neural networks (RNN) are difficult to train on data having long-term temporal dependencies, thus susceptible to an inherent problem of vanishing gradient. This work proposed a method based on an advanced version of RNN known as long short-term memory (LSTM) architecture, which updates recurrent weights to overcome the vanishing gradient problem. This, in turn, improves training performance. Methods: The RNN model is developed based on stack LSTM and bidirectional LSTM. The parameters like mean absolute error (MAE), standard deviation error (SDE), and root mean squared error (RMSE) are utilized as performance measures for comparison with recent state-of-the-art techniques. Results: Results showed that the proposed technique outperformed the existing techniques in terms of RMSE and MAE against all the used wind farm datasets. Whereas, a reduction in SDE is observed for larger wind farm datasets. The proposed RNN approach performed better than the existing models despite fewer parameters. In addition, the approach requires minimum processing power to achieve compatible results.

A CNN based m5c RNA methylation predictor.

Post-transcriptional modifications of RNA play a key role in performing a variety of biological processes, such as stability and immune tolerance, RNA splicing, protein translation and RNA degradation. One of these RNA modifications is m5c which participates in various cellular functions like RNA structural stability and translation efficiency, got popularity among biologists. By applying biological experiments to detect RNA m5c methylation sites would require much more efforts, time and money. Most of the researchers are using pre-processed RNA sequences of 41 nucleotides where the methylated cytosine is in the center. Therefore, it is possible that some of the information around these motif may have lost. The conventional methods are unable to process the RNA sequence directly due to high dimensionality and thus need optimized techniques for better features extraction. To handle the above challenges the goal of this study is to employ an end-to-end, 1D CNN based model to classify and interpret m5c methylated data sites. Moreover, our aim is to analyze the sequence in its full length where the methylated cytosine may not be in the center. The evaluation of the proposed architecture showed a promising results by outperforming state-of-the-art techniques in terms of sensitivity and accuracy. Our model achieve 96.70% sensitivity and 96.21% accuracy for 41 nucleotides sequences while 96.10% accuracy for full length sequences.

A novel CT image de-noising and fusion based deep learning network to screen for disease (COVID-19).

A COVID-19, caused by SARS-CoV-2, has been declared a global pandemic by WHO. It first appeared in China at the end of 2019 and quickly spread throughout the world. During the third layer, it became more critical. COVID-19 spread is extremely difficult to control, and a huge number of suspected cases must be screened for a cure as soon as possible. COVID-19 laboratory testing takes time and can result in significant false negatives. To combat COVID-19, reliable, accurate and fast methods are urgently needed. The commonly used Reverse Transcription Polymerase Chain Reaction has a low sensitivity of approximately 60% to 70%, and sometimes even produces negative results. Computer Tomography (CT) has been observed to be a subtle approach to detecting COVID-19, and it may be the best screening method. The scanned image's quality, which is impacted by motion-induced Poisson or Impulse noise, is vital. In order to improve the quality of the acquired image for post segmentation, a novel Impulse and Poisson noise reduction method employing boundary division max/min intensities elimination along with an adaptive window size mechanism is proposed. In the second phase, a number of CNN techniques are explored for detecting COVID-19 from CT images and an Assessment Fusion Based model is proposed to predict the result. The AFM combines the results for cutting-edge CNN architectures and generates a final prediction based on choices. The empirical results demonstrate that our proposed method performs extensively and is extremely useful in actual diagnostic situations.

AIEE active sensors for fluorescence enhancement based detection of Ni2+ in living cells: Mechanofluorochromic and photochromic properties with reversible sensing of acid and base.

Stimuli responsive sensors QI 1 and QI 2 were rationally developed which exhibited diverse features of mutable mechanofluorochromism, reversible photochromism, solvatochromism, aggregation induced emission enhancement (AIEE), and metal ion sensing. After observing the exceptional structural property relationship, sensors were applied for reversible colorimetric and fluorometric determination of Ni2+ with low detection limits of 12 and 17 nM, respectively. Fluorescence emission enhancement based Ni2+ sensing was induced by chelation enhanced fluorescence (CHEF) mechanism. CHEF is triggered by the inhibition of excited state intramolecular proton transfer (ESIPT) and -C=N isomerization. The proposed Ni2+ sensing mechanism was investigated through 1H NMR, FT-IR titration, theoretical studies, and Jobs plots. Further, the developed sensors successfully demonstrated the selective acid-base induced absorption/emission switching through reversible ring-opening/closing and keto-enol tautomerization, evidenced by 1H NMR titration experiments. Additionally, the sensitivity of the sensor QI 1 towards Ni2+ was effectively mimicked in live MCF-7 cells and industrial effluents. Furthermore, monitoring of Ni2+ ions was also accessed through inexpensive and portable sensors' coated fluorescent films. Finally, an INHIBIT logic gate was fabricated imputing Ni2+ and EDTA as input signals to electronically scrutinize the targeted Ni2+.

The prevalence of foot ulcers in diabetic patients in Pakistan: A systematic review and meta-analysis.

We aimed to determine the pooled prevalence of diabetic foot ulcers in Pakistan. MEDLINE (PubMed), Web of Science, Google scholars, and local databases were systematically searched for studies published up to August 10, 2022, on the prevalence of foot ulcers among diabetic patients in Pakistan. Random-effects meta-analysis was used to generate summary estimates. Subgroup analysis and meta-regression models were used to address the issue of high heterogeneity. Two authors independently identified eligible articles, collected data, and performed a risk of bias analysis. Twelve studies were included in the meta-analysis (14201, range 230-2199, diabetic patients), of which 7 were of "high" quality. The pooled prevalence of diabetic foot ulcers was 12.16% (95% CI: 5.91-20.23%). We found significant between-study heterogeneity (I2 = 99.3%; p < 0.001) but no statistical evidence of publication bias (p = 0.8544). Subgroup meta-analysis found significant differences in foot ulcer prevalence by publication year and by the duration of diabetes. An increasing trend was observed during the last two decades, with the prevalence of diabetic foot ulcers being the highest in the latest period from 2011 to 2022 (19.54%) than in the early 2000 s (4.55%). This study suggests that the prevalence of diabetic foot ulcers in Pakistan is relatively high, with significant variation between provinces. Further study is required to identify ways for early detection, prevention, and treatment in the population.

Multiclass Cancer Prediction Based on Copy Number Variation Using Deep Learning.

DNA copy number variation (CNV) is the type of DNA variation which is associated with various human diseases. CNV ranges in size from 1 kilobase to several megabases on a chromosome. Most of the computational research for cancer classification is traditional machine learning based, which relies on handcrafted extraction and selection of features. To the best of our knowledge, the deep learning-based research also uses the step of feature extraction and selection. To understand the difference between multiple human cancers, we developed three end-to-end deep learning models, i.e., DNN (fully connected), CNN (convolution neural network), and RNN (recurrent neural network), to classify six cancer types using the CNV data of 24,174 genes. The strength of an end-to-end deep learning model lies in representation learning (automatic feature extraction). The purpose of proposing more than one model is to find which architecture among them performs better for CNV data. Our best model achieved 92% accuracy with an ROC of 0.99, and we compared the performances of our proposed models with state-of-the-art techniques. Our models have outperformed the state-of-the-art techniques in terms of accuracy, precision, and ROC. In the future, we aim to work on other types of cancers as well.

A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates.

License plate localization is the process of finding the license plate area and drawing a bounding box around it, while recognition is the process of identifying the text within the bounding box. The current state-of-the-art license plate localization and recognition approaches require license plates of standard size, style, fonts, and colors. Unfortunately, in Pakistan, license plates are non-standard and vary in terms of the characteristics mentioned above. This paper presents a deep-learning-based approach to localize and recognize Pakistani license plates with non-uniform and non-standardized sizes, fonts, and styles. We developed a new Pakistani license plate dataset (PLPD) to train and evaluate the proposed model. We conducted extensive experiments to compare the accuracy of the proposed approach with existing techniques. The results show that the proposed method outperformed the other methods to localize and recognize non-standard license plates.

An atypical presentation of Salmonella enterica ser Dublin in an immunocompromised patient.

Mycotic aneurysms of the carotid artery are a rare entity that can be fatal if not diagnosed promptly. We present a 60-year-old man with a tender left-sided neck mass due to a ruptured aneurysm of the left internal carotid artery. Cultures taken intraoperatively grew Salmonella enterica ser Dublin.

Effect of co-application of wastewater and freshwater on the physiological properties and trace element content in Raphanus sativus: soil contamination and human health.

Nowadays, the use of wastewater for crop irrigation is increasing at global scale mainly due to freshwater scarcity and economic benefits. However, the presence of different types of pollutants including the trace elements (TEs) poses a serious threat to environmental and human health. This pot study evaluated the effect of alone and mixed irrigation water [wastewater (WW) with canal water (CW) and tube-well water (TW)] on TEs build-up in the soil, their soil-plant transfer and allied health hazards in District Vehari. The WW samples were mainly contaminated with Cd (0.03 mg/L), Cr (1.45 mg/L), Cu (0.35 mg/L) and Ni (0.40 mg/L). The CW contained high levels of Cr and Fe, while TW was contaminated with Pb and Cr. In soil, the concentrations of Cd, Fe and Mn exceeded their respective limit values for all the treatments. Among all the treatments, TEs concentration was found highest in WW-3 irrigated soil. Application of all the treatments resulted in TEs (Cu, 60.1 mg/kg; Cd, 8.2 mg/kg; Ni, 39.9 mg/kg; Fe, 4411 mg/kg; Zn, 111.3 mg/kg and Pb, 44.5 mg/kg) accumulation mainly in the edible parts of Raphanus sativus. Compared to other treatments, TW and TW + CW irrigated plants accumulated higher levels of TEs. Results showed linear trends among TEs accumulation and alterations in physiological attributes of R. sativus. High TEs accumulation in TW irrigated treatments (TW + WW-1 and TW + CW) caused maximum H2O2 production, lipid peroxidation and decline in plant pigments. Risk assessment parameters showed both carcinogenic and non-carcinogenic risks for all the irrigation treatments due to high TEs contents in edible tissues. It is concluded that alone or combined application of WW, TW and CW is not fit for vegetable irrigation, in the studied area, due to high TEs contents.

Synthesis, characterization and docking studies of amide ligands as anti-leishmanial agents.

Aim of this study was to synthesize new inhibitors on the basis of active site of aspartic protease enzyme and to evaluate their intended biological activity. A3D model of an enzyme was generated via homology modeling and series of novel amide ligands were synthesized by using a short high yield process, subsequently, analyzed in-silico and in-vitro anti-leishmanial activities. Characterization and identification was accomplished via NMR (H1& C13), infrared and mass spectroscopic techniques. Among all compound (4) was found to show significant activity (IC50 58±0.01) against Leishmania major (L. major) species. Furthermore, docking studies confirmed the inhibition of a targeted enzyme that supported the interaction of potent compound (4) with key residues (aspartic protease) via hydrogen bonds. Present study conferred about novel compound (4) as a promising compound to antagonize L. major activities in future.

Deep Learning Techniques for Diabetic Retinopathy Detection.

Diabetes occurs due to the excess of glucose in the blood that may affect many organs of the body. Elevated blood sugar in the body causes many problems including Diabetic Retinopathy (DR). DR occurs due to the mutilation of the blood vessels in the retina. The manual detection of DR by ophthalmologists is complicated and time-consuming. Therefore, automatic detection is required, and recently different machine and deep learning techniques have been applied to detect and classify DR. In this paper, we conducted a study of the various techniques available in the literature for the identification/classification of DR, the strengths and weaknesses of available datasets for each method, and provides the future directions. Moreover, we also discussed the different steps of detection, that are: segmentation of blood vessels in a retina, detection of lesions, and other abnormalities of DR.

Vicissitudes in polyphenolic extract-based high internal phase creams (HIPCs)- effect of storage temperature dependent characteristics.

The purpose of this investigation was to evaluate the vicissitudes in polyphenolic extract- based high internal phase creams (HIPCs) and effect of storage temperature dependent characteristics. Rheological parameters, that is, power law and IPC analysis with its physical characteristics were exploredat different storage temperatures (8°, 25°, 40° and 40° with 75% relative humidity- RH) with different time intervals up to 2 months of newly formulated poly-phenolic extract- based high internal phase cream and its comparison with base. Polyphenolic- based HIPCs showed non-Newtonian-pseudo plastic tendencies in vicissitudes with time and storage temperatures. Data analysis with Power Law and IPC paste was found to fit to all the rheograms. Flow index, shear sensitivity factor, consistency Index and 10 RPM of freshly prepared HIPCs with and without encapsulated polyphenolic extract were found to be 0.5,0.53, 386.4 cP, and 432.9 cP, respectively.The viscosities were fallen with rise in shear stress.There was no change in color, electrical conductivity, liquefaction and phase separation after centrifugation in any sample of polyphenolic extract-based HIPCs and its base. Polyphenolic- based extract HIPCs behaved non-Newtonian- pseudo plastic tendencies and showed stability up to 2 months and can be directed absolutely to shield skin against ultraviolet radiation (UV) intervened oxidative mutilation.

Analgesic Effect Of Direct Breastfeeding During BCG Vaccination In Healthy Neonates.

BACKGROUND: Pain during painful procedures in neonates has far reaching consequences. In developed countries many non-pharmacological interventions are used for neonatal pain reduction. Breast feeding has been proved to be an effective analgesic during mild to moderate painful procedures in neonates. METHODS: The study, randomized controlled trial was conducted in CMH, Quetta. The study period extended from June to November 2015. Neonates included in the experimental group were breastfeed during BCG vaccination and neonates in the control group were provided with routine care. Duration of cry with needle insertion was recorded with a digital stopwatch till the baby is silent for more than 5 seconds. RESULTS: The mean crying duration in experimental group was significantly less than control group. In experimental group mean crying duration was 16.48s (12.76) whereas in control group mean crying duration was 34.93 s(45.26). Statistically significant difference was observed between the mean crying times of the two groups (p<0.05). CONCLUSIONS: Mean duration of crying with breastfeeding is shorter than without breast feeding during BCG immunization. Breast feeding reduces pain during minor painful procedures in neonates.

Burkholderia Lethal Factor 1, a Novel Anti-Cancer Toxin, Demonstrates Selective Cytotoxicity in MYCN-Amplified Neuroblastoma Cells.

Immunotoxins are being investigated as anti-cancer therapies and consist of a cytotoxic enzyme fused to a cancer targeting antibody. All currently used toxins function via the inhibition of protein synthesis, making them highly potent in both healthy and transformed cells. This non-specific cell killing mechanism causes dose-limiting side effects that can severely limit the potential of immunotoxin therapy. In this study, the recently characterised bacterial toxin Burkholderia lethal factor 1 (BLF1) is investigated as a possible alternative payload for targeted toxin therapy in the treatment of neuroblastoma. BLF1 inhibits translation initiation by inactivation of eukaryotic initiation translation factor 4A (eIF4A), a putative anti-cancer target that has been shown to regulate a number of oncogenic proteins at the translational level. We show that cellular delivery of BLF1 selectively induces apoptosis in neuroblastoma cells that display MYCN amplification but has little effect on non-transformed cells. Future immunotoxins based on this enzyme may therefore have higher specificity towards MYCN-amplified cancer cells than more conventional ribosome-inactivating proteins, leading to an increased therapeutic window and decreased side effects.

Neonatal Pain And Preventive Strategies: An Experience In A Tertiary Care Unit.

BACKGROUND: Little is known about neonatal pain in Pakistan. So, to know about neonatal pain, its scoring and the effectiveness of oral dextrose in neonatal pain management we carried this study in neonatal intensive care unit (NICU) of military hospital (MH) Rawalpindi. METHODS: This randomized control trial was carried out in NICU of MH, Rawalpindi from Jan to Dec 2013. Total of 252 babies were enrolled in the study. We assessed neonatal pain by using Modified Behavioural Pain Scale (MBPS). Babies were given 10% dextrose and sterile water two minutes before a painful procedure and pain assessment was done after the procedure. The different painful procedures included, heel prick, nasogastric (NG) tube insertion, cannulation, catheterization and venepuncture for blood sampling. RESULTS: A total of 252 babies were enrolled in the study. Of these 139 (55%) were male and 113 (45%) were female babies. Painful procedures included heel lancing 120 (48%), I/V cannulations 60 (24%), venepuncture 40 (16%), NG insertion 26 (10%) and Foley catheterization 6 (2%). Mean MBPS score with 10% dextrose and sterile water were 4.31 and 6.26 respectively and the difference between two was significant statically. CONCLUSIONS: Oral dextrose is a cheap and easily available solution and can be used in neonatal pain management during various painful procedures.

Identification of microRNA precursors using reduced and hybrid features.

MicroRNAs (also called miRNAs) are a group of short non-coding RNA molecules. They play a vital role in the gene expression of transcriptional and post-transcriptional processes. However, abnormality of their expression has been observed in cancer, heart diseases and nervous system disorders. Therefore for basic research and microRNA based therapy, it is imperative to separate real pre-miRNAs from false ones (hairpin sequences similar to pre-miRNA stem loops). Different conservation and machine learning methods have been applied for the identification of miRNAs. However, machine learning algorithms have gained more popularity than conservative based algorithms in terms of sensitivity and overall performance. Due to the avalanche of RNA sequences discovered in a post-genomic age, it is necessary to construct a predictor for the identification of pre-microRNAs in humans. We have developed a predictor called MicroR-Pred in which the RNA sequences are formulated by a hybrid feature vector. The novelty of the new predictor is in the use of the partial least squares technique followed by the Random Forest and SVM (Support Vector Machine) algorithms for dimension reduction and classification. The performance of the MicroR-Pred model is quite promising compared to other state-of-the-art miRNA predictors. It has achieved 88.40% and 93.90% accuracies for RF and SVM.

Risk Factors Associated with Thyroid Carcinoma in North Pakistan.

BACKGROUND: Epidemiological data on thyroid cancer and associated risk factors are scarce in our setting. The present study was therefore designed to gather data which could be helpful in providing insights to thyroid physicians and surgeons for better management of affected patients. PURPOSE: To determine the frequency of carcinoma thyroid among patients presenting with goiter and its association with TSH, Tg/ATg and other demographic factors. MATERIALS AND METHODS: A total of 73 adult patients of either gender with solitary solid cold nodules and/or multi-ndoular goiter (MNG) with predominant solid cold nodules were enrolled. All surgically resected samples were sent for histopathology. The frequency of thyroid cancer and its subtypes was noted and tested for association with gender, age (< or ≥40 years), recent increase in swelling size, TSH, Tg and ATg. RESULTS: Thyroid cancer was diagnosed in 26% (n=19) of the patients, 14 (73.7%) being diagnosed with papillary thyroid cancer and 5 (26.3%) with follicular thyroid cancer. No other subtypes were noted. Presence of thyroid cancer was significantly associated with recent increase in swelling size and higher TSH Values mean TSH values (P<0.05). No significant association was found with gender, age, Tg and ATg values (P>0.05). CONCLUSIONS: Overall percentage of thyroid cancer in our study sample was found to be 26%, with a predominance of papillary over follicular lesions. Rates were significantly higher in patients who had history of recent increase in swelling size and higher and higher pre-surgery TSH values.

CONGENITAL MALARIA.

Neonates with congenital malaria may present with non-specific signs and symptoms which may be mistaken for neonatal sepsis and inborn error of metabolism resulting in delay of diagnosis.and significant mortality and morbidity. Here we present a unique case of 25 days old premature female baby who was diagnosed to have mixed malarial infection. Despite standard treatment the patient was not responding well and was also diagnosed to have congenital adrenal hyperplasia.

Importance of microscopic stool examination in patients with diarrhoea.

BACKGROUND: Loose motion is a common symptom in patients reporting to our hospital. As it is a small set up where only facility for microscopic stool examination is available, we designed this study to know how much microscopic stool examination can help us in management of patients with diarrhoea. METHODS: This cross-sectional descriptive study was conducted from January 2010 to April 2012, at Thall Scout Hospital, Hangoo, Khyber Pukhtoon Khwa, Pakistan. All the patients presenting with acute diarrhoea were included in the study. Patients older than 12 years of age were labelled as adults and those 12 years or younger as child. Stool specimens were collected using proper procedure and were examined microscopically. RESULTS: Of 494 stool specimens examined, 117 (23.68%) were positive for parasites or their ova, 34 (6.88%) had numerous pus and red blood cells and 343 (69.43%) patients had only stool of loose/soft consistency. Of 117 stool specimens positive for parasites, Giardia lamblia was detected in 67 (57.26%) patients, Entamoeba histolytica in 22 (18.80%) patients, H. nana in 10 (8.55%) patients, Tenea saginata in 8(6.84%) patients, hook worm in 6 (5.13%) patients, ascarids in 2 (1.71%) and Trichuris trichura in 2 (1.71%) patients. CONCLUSION: Among the parasitic causes of diarrhoea, giardia is the most common cause in our study with entameoba the second most common cause.

Low temperature conversion of plastic waste into light hydrocarbons.

Advance recycling through pyrolytic technology has the potential of being applied to the management of plastic waste (PW). For this purpose 1 l volume, energy efficient batch reactor was manufactured locally and tested for pyrolysis of waste plastic. The feedstock for reactor was 50 g waste polyethylene. The average yield of the pyrolytic oil, wax, pyrogas and char from pyrolysis of PW were 48.6, 40.7, 10.1 and 0.6%, respectively, at 275 degrees C with non-catalytic process. Using catalyst the average yields of pyrolytic oil, pyrogas, wax and residue (char) of 50 g of PW was 47.98, 35.43, 16.09 and 0.50%, respectively, at operating temperature of 250 degrees C. The designed reactor could work at low temperature in the absence of a catalyst to obtain similar products as for a catalytic process.