Search

Objective: To compare the efficacy of Cprofloxacin 0.6% ear drops versus oral Cprofloxacin in achieving the dry ears in chronic suppurative otitis media patients presenting at a tertiary care hospital, Islamabad Pakistan. Study Design: Quasi-experimental study. Place and Duration of Study: Department of Otorhinolaryngology and Head and Neck Surgery, Pakistan Institute of Medical Sciences, Islamabad Pakistan, from Jun 2022 to Dec 2022. Methodology: The study recruited 130 patients with unilateral or bilateral chronic ear discharge, of either gender, aged 12-60 years, and divided them into two groups of 65 each. Group-A received topical Cprofloxacin 0.6% in a dose of four drops three times per day, while Group-B, 65 patients received oral Cprofloxacin 500 mg twice daily. Otoscopy was used to monitor patients for two weeks following dry ear treatment. Results: The mean age of participants was 29.70±9.03 years and most patients were males (60%). Post-treatment results of Group-A revealed that there were 11(16.9%) subjects with ear discharge. The rest 54(83.1%) had no ear discharge. In Group-B, there were 46(70.8%) subjects with ear discharge. The rest 19(29.2%) had no ear discharge. A statistically significant (p=0.001) difference in efficacy was observed between both groups. Conclusion: Topical Cprofloxacin 0.6% given 6 drops twice daily for two weeks is a better choice in medical management of CSOM than oral Cprofloxacin 500mg twice daily in terms of resolution of ear discharge.

Introduction and Objectives: Hepatorenal syndrome (HRS) is a serious complication of cirrhosis treated with various medications. We aim to evaluate terlipressin and albumin's effectiveness and safety compared to albumin and noradrenaline in adult hepatorenal disease patients. Materials and Methods: Clinical trials from four databases were included. Cochrane's approach for calculating bias risk was utilized. We rated the quality evaluation by Grading of Recommendations Assessment, Development, and Evaluation (GRADE). We included the following outcomes: serum creatinine (mg/dl), urine output (ml/24 h), mean arterial pressure (mmHg), reversal rate of HRS, mortality rate, blood plasma renin activity (ng/ml/h), plasma aldosterone concentration (pg/ml), urine sodium (mEq/l), and creatinine clearance (ml/min). Results: Our analysis of nine clinical studies revealed that the noradrenaline group was associated with higher creatinine clearance (MD = 4.22 [0.40, 8.05]), (P = 0.03). There were no significant differences in serum creatinine levels (MD = 0.03 [-0.07, 0.13]), urinary sodium (MD = -1.02 [-5.15, 3.11]), urine output (MD = 32.75 [-93.94, 159.44]), mean arterial pressure (MD = 1.40 [-1.17, 3.96]), plasma renin activity (MD = 1.35 [-0.17, 2.87]), plasma aldosterone concentration (MD = 55.35 [-24.59, 135.29]), reversal rate of HRS (RR = 1.15 [0.96, 1.37]), or mortality rate (RR = 0.87 [0.74, 1.01]) between the two groups (p-values > 0.05). Conclusions: Noradrenaline is a safe alternative medical therapy for HRS.

Unmanned aerial vehicles (UAVs) have revolutionized various industries by providing efficient and automated flight capabilities. However, reliance on GPS and traditional navigation systems poses challenges in scenarios where signal interference or failures occur. In this research, we present a novel computer-vision-based method to enhance UAV navigation, enabling accurate height and location estimation. Our approach utilizes a sophisticated network that leverages a pair of images to estimate UAV height. The pyramid stereo-matching network is employed to extract robust image features and generate a disparity map. Subsequently, a custom network processes and convolves these data, employing diverse computer vision techniques to achieve precise height estimation. To evaluate the effectiveness of our proposed method, we collected a comprehensive dataset by conducting flights with a Phantom 4 Pro drone over the NUST Main campus, H-12 Islamabad. The dataset encompasses images captured at 10 different heights, spanning from 100 to 280 m, with flights evenly spaced 20 m apart. In rigorous evaluations, our approach demonstrates promising results compared to existing methods. By liberating UAVs from reliance on GPS, this vision-based 3-D localization technique holds immense potential to ensure successful flights even in challenging environments.

Abstract Green purchase behavior in Pakistan faces challenges due to lack of awareness, limited availability, and greenwashing by companies that demand use of online environmental platforms. The study aims to examine the effect of Online Environmental Platforms Service on green purchase behaviors of customers who intend to buy green energy products. Moreover, the indirect effects of environmental attitude, price sensitivity and impulsiveness are examined as mediators. The relationships are examined in light of theory of planned behavior. The data from a sample of 301 customers were gathered using a closed-ended questionnaire. The customers aged between 30 and 50 years were considered for the study. The findings unequivocally reveal that the provision of online environmental platforms has a profound effect on the ecological shopping inclinations of customers. The green purchase behavior of consumers is amplified, as is their green purchase attitude and consumer impulsiveness. However, an alert emerges—price sensitivity, despite its noteworthy impact on consumer behavior, curiously, impedes actual green purchasing. Investigating deeper, it becomes apparent that the remarkable impact of online environmental platforms is mediated by two factors: the green consumer attitude and consumer impulsiveness. These two factors act as conduits for the transmission of the influence of the online platforms, empowering consumers to make eco-conscious decisions. The marketers can enhance green purchase behaviors among customers by making effective use of the online environmental platform services. The Online Environmental Platforms Services can enhance sales and can be an effective strategy for high profits.

Hyperspectral Imaging (HSI) uses large portions of the electromagnetic spectrum to obtain information from images that would be very difficult to get otherwise. An important task in forensic analysis of documents is to extract signatures for authentication. Signatures in documents often overlap with other parts of a document such as typed text or stamps and hence it is difficult to retrieve them. In this work we present a novel algorithm for recovering signatures from hyperspectral images of documents where signatures overlap typed text, seals, stamps, or other images. We used pure pixel index approaches to analyze the hyper-pixels corresponding to regions where overlaps occur and spectral classification methods to analyze the extracted channels’ information and to separate the overlapping signatures. We used the structural similarity index to validate the extracted signatures. Our experimental results highlight the capability of the proposed algorithm to recover signatures with great precision in HSI document images.

Solar energy has emerged as a viable and competitive renewable resource due to its abundance and cost-effectiveness. To meet the global energy demands, there is a growing need for efficient devices with unique compositions. In this study, we designed and analyzed a perovskite solar cell (PSC) incorporating methylammonium tin iodide (CH3NH3SnI3) as the active optical absorber material, tin iodide (SnO2) as the electron transport layer (ETL), and copper thiocyanate (CuSCN) as the hole transport layer (HTL) using SCAPS-1D software for numerical investigations. Subsequently, the optimized outcomes were implemented in the PVSyst software package to derive the characteristics of a solar module based on the proposed novel solar cell composition. The objective of our research was to enhance the stability of solar cell for use in solar module. This was achieved by optimizing the thicknesses of the compositional layers which resulted in the enhancement of excess electron and hole mobilities and a reduction in defect densities, thereby leading to an improvement in the device performance. The optimization of excess electron and hole mobilities, as well as defect densities, was conducted to improve the device performance. SCAPS calculations indicated that the perovskite absorber layer (CH3NH3SnI3) may achieve the best possible performance with a maximum optimized thickness of 3.2 μm. The optimized thickness value for CuSCN-HTL and SnO2-ETL were found to be 0.07 μm and 0.05 μm respectively resulting in a maximum power conversion efficiency (PCE) of 23.57%. Variations in open circuit voltage (Voc), short circuit current (Jsc), fill factor (FF %), and quantum efficiency (QE) associated with the optimized thickness values of all layers in the ITO/SnO2/CH3NH3SnI3/CuSCN/Mo composition were critically analyzed. The use of these input parameters resulted in power creation of 557.4 W for a module consisting of 72 cells with an annual performance ratio of 80.3%. These recent investigations are expected to be effective in the design and fabrication of eco-friendly and high-performance solar cells in terms of efficiency.

Online learning provides flexibility and convenience to students, however, it also presents various challenges, such as technostress. Technostress is the psychological discomfort or stress experienced by individuals due to the use of technology, particularly when they cannot cope with its demands. Students’ technostress levels can have a negative impact on their online learning experiences. Drawing from the Community of Inquiry (CoI) framework, the study investigates the moderating impact of instructor and university support on technostress and the quality of online learning relationship in university students. Data were collected from 392 university students taking one or more online courses. Results reveal that technostress has a negative impact on the quality of online learning. However, this negative impact is mitigated in the presence of support from the instructor and the university separately and jointly. The study makes an important contribution to the growing body of knowledge by identifying instructor support and university support as important contributors to the communities of inquiry in an online educational setting.

Background and aims: Acute calculous cholecystitis (ACC) represents about one-third of all surgical emergencies. The gold standard management of ACC is laparoscopic cholecystectomy. Although cholecystectomy is a safe procedure, it may be dangerous and contraindicated in patients with complex comorbidities. Endoscopic transpapillary gallbladder stenting (ETGBS) and drainage had been widely used to manage patients suffering from ACC with comorbidities. Methods: We searched PubMed, SCOPUS, Web of Science, and Cochrane Library for relevant studies assessing the use of ETGBS in patients suffering from ACC with various comorbidities. Risk of bias assessment was performed using the National Institues of Health (NIH) tool. We included the following outcomes: clinical success, technical success, late complications, and pancreatitis. Results: We included seven studies that met our inclusion criteria. We found that the pooled proportion of clinical success, technical success, late complications, and pancreatitis was [91.3%, 95% confidence interval (CI) (86.8%, 95.9%)], [92.8%, 95% CI (89%, 96.5%)], [5.4%, 95% CI (2.9%, 7.9%)], and [3.5%, 95% CI (1.2%, 5.8%)], respectively. Conclusion: We found that an ETGBS was an effective and well-tolerated method for the treatment of cholecystitis, especially in high-risk individuals.

Abstract Deep exploration of histone occupancy and covalent post-translational modifications (e.g., acetylation, methylation) is essential to decode gene expression regulation, chromosome packaging, DNA damage, and transcriptional activation. Existing computational approaches are unable to precisely predict histone occupancy and modifications mainly due to the use of sub-optimal statistical representation of histone sequences. For the establishment of an improved histone occupancy and modification landscape for multiple histone markers, the paper in hand presents an end-to-end computational multi-paradigm framework “Histone-Net”. To learn local and global residue context aware sequence representation, Histone-Net generates unsupervised higher order residue embeddings (DNA2Vec) and presents a different application of language modelling, where it encapsulates histone occupancy and modification information while generating higher order residue embeddings (SuperDNA2Vec) in a supervised manner. We perform an intrinsic and extrinsic evaluation of both presented distributed representation learning schemes. A comprehensive empirical evaluation of Histone-Net over ten benchmark histone markers data sets for three different histone sequence analysis tasks indicates that SuperDNA2Vec sequence representation and softmax classifier-based approach outperforms state-of-the-art approach by an average accuracy of 7%. To eliminate the overhead of training separate binary classifiers for all ten histone markers, Histone-Net is evaluated in multi-label classification paradigm, where it produces decent performance for simultaneous prediction of histone occupancy, acetylation, and methylation.

Inorganic metal halide perovskite materials have attracted remarkable attention as light harvesters because of their promising optoelectronic merits and photovoltaic features like tunable band gaps, high charge carrier mobilities and greater absorption coefficients. In order to explore new inorganic perovskite materials for use in optoelectronic devices Potassium Tin Chloride (KSnCl3) has been experimentally synthesized using a supersaturated recrystallization technique at ambient conditions. The resultant nanoparticle (NP) specimens were analyzed for optical and structural properties by characteristic available techniques including scanning electron microscopy (SEM), energy dispersive X-ray spectroscopy (EDX) and UV visible spectroscopy. Experimental investigations about structure reveals that KSnCl3 crystallizes in orthorhombic phase with particle size of 400–500 nm. SEM showed better crystallization and EDX confirmed the accurate structural composition. UV–Visible analysis indicated a prominent absorption peak at 504 nm, and the band gap is 2.70 eV. Theoretical investigations of KSnCl3 were also carried out via AB-initio calculations in Wein2k simulation program using modified Becke Johnson (mBJ) and generalized gradient approximations (GGA). Optical properties like extinction coefficient k (ω), complex parts of dielectric constant (ε1, ε2), reflectivity R (ω), refractive index n (ω), optical conductivity L (ω) and absorption coefficient α (ω) were examined and it was observed that . theoretical investigations were consistent with experimental findings. Incorporation of KSnCl3 as an absorber material along with single walled carbon nanotubes as p-type materials in (AZO/IGZO/KSnCl3/CIGS/SWCNT/Au) solar cell configuration have been investigated by SCAPS-1D simulation package. Open circuit voltage (Voc) of 0.9914 V, short circuit current density (Jsc) of 47.32067 mA/cm2 and a remarkable efficiency of 36.823% with has been predicted. Thermally stable KSnCl3 may become potential source in manufacturing of photovoltaic and optoelectronic applications on large scale.

This study examines the effect of technostress on teachers’ quality of work life and job performance. A moderated mediation model is proposed and tested based on the transactional model of stress and coping. This study proposes organizational flexibility as the boundary condition—a first-level moderator—and quality of work life as the explanatory variable. A sample of 199 university teachers who worked from home or used the hybrid teaching mode was selected. Data were collected through closed-ended questionnaires. Structural equation modeling (SEM) and the Hayes PROCESS Macro (extension in SPSS) were used for hypothesis testing. The results found that the three dimensions of technostress (Techno complexity, Techno invasion, and Techno overload) negatively and significantly affect teachers’ quality of work life. However, there are significant positive direct effects of these three dimensions of technostress on employee performance and significant negative indirect effects on performance through quality of work life. Organizational flexibility acts as a significant moderator, where a low value of organizational flexibility enhances the negative relationship between technostress and quality of work life. In contrast, high values of organizational flexibility convert the significant negative relationship into an insignificant impact. The university management must take measures to overcome technostress among teachers by showing flexibility.

One of the major reasons of death worldwide is Cardiovascular diseases. One of its type is Arrhythmia in which normal rhythm of heart is varied due to damage in heart muscles and electrolyte imbalance. To study cardiovascular disease, Electrocardiogram (ECG) signal is used that plays a significant role in identifying Arrhythmia. By using a combination of Multivariate Empirical Mode Decomposition (MEMD) and Artificial Neural Network (ANN), a hybrid technique is proposed in this research work to detect and classify Arrhythmia. MEMD, a promising technique that is used nowadays for denoising of multichannel signals, is used in this work. Two main features, i.e., RR interval and Heart Rate are extracted from the ECG signal for the detection of Arrhythmia. Using these features, Arrhythmia is classified into Tachycardia and Bradycardia. Classification is done using pattern recognition of ANN in which Multilayer feed forward neural network is used and trained through Back Propagation Algorithm. Results that are achieved using proposed technique is compared with previous existing techniques as in 2016 (Discrete Wavelet Transform) DWT and ANN gave 87.01% and in 2018 (Empirical Mode Decomposition) EMD and (Linear Discriminant Analysis) LDA gave 87% accuracy. As compare to these techniques, the proposed technique results show that it is an efficient technique that gives better accuracy of 89.8%.

Subcellular localization of Ribonucleic Acid (RNA) molecules provide significant insights into the functionality of RNAs and helps to explore their association with various diseases. Predominantly developed single-compartment localization predictors (SCLPs) lack to demystify RNA association with diverse biochemical and pathological processes mainly happen through RNA co-localization in multiple compartments. Limited multi-compartment localization predictors (MCLPs) manage to produce decent performance only for target RNA class of particular sub-type. Further, existing computational approaches have limited practical significance and potential to optimize therapeutics due to the poor degree of model explainability. The paper in hand presents an explainable Long Short-Term Memory (LSTM) network “EL-RMLocNet”, predictive performance and interpretability of which are optimized using a novel GeneticSeq2Vec statistical representation learning scheme and attention mechanism for accurate multi-compartment localization prediction of different RNAs solely using raw RNA sequences. GeneticSeq2Vec generates optimized statistical vectors of raw RNA sequences by capturing short and long range relations of nucleotide k-mers. Using sequence vectors generated by GeneticSeq2Vec scheme, Long Short Term Memory layers extract most informative features, weighting of which on the basis of discriminative potential for accurate multi-compartment localization prediction is performed using attention layer. Through reverse engineering, weights of statistical feature space are mapped to nucleotide k-mers patterns to make multi-compartment localization prediction decision making transparent and explainable for different RNA classes and species. Empirical evaluation indicates that EL-RMLocNet outperforms state-of-the-art predictor for subcellular localization prediction of 4 different RNA classes by an average accuracy figure of 8% for Homo Sapiens species and 6% for Mus Musculus species. EL-RMLocNet is freely available as a web server at (https://sds_genetic_analysis.opendfki.de/subcellular_loc/).

Hyperspectral data analysis is being utilized as an effective and compelling tool for image processing, providing unprecedented levels of information and insights for various applications. In this manuscript, we have compiled and presented a comprehensive overview of recent advances in hyperspectral data analysis that can provide assistance for the development of customized techniques for hyperspectral document images. We review the fundamental concepts of hyperspectral imaging, discuss various techniques for data acquisition, and examine state-of-the-art approaches to the preprocessing, feature extraction, and classification of hyperspectral data by taking into consideration the complexities of document images. We also explore the possibility of utilizing hyperspectral imaging for addressing critical challenges in document analysis, including document forgery, ink age estimation, and text extraction from degraded or damaged documents. Finally, we discuss the current limitations of hyperspectral imaging and identify future research directions in this rapidly evolving field. Our review provides a valuable resource for researchers and practitioners working on document image processing and highlights the potential of hyperspectral imaging for addressing complex challenges in this domain.

The purpose of this paper was to examine the extent to which green HRM impacts the pro-environmental behavior of employees via the mediation of Green Entrepreneurship and the moderation of Green Self-Efficacy in the hospitality sector of Pakistan. Research design included questionnaires and the study setting was cross-sectional. Respondents of the study were 4 and 5-star hotel employees of Islamabad city of Pakistan. However, a 205-sample size was taken from the population to collect primary data for deriving results. Data were collected from 205 hotel employees, and there were no incomplete data. Using SEM through Smart PLS 3.2.7, finally, 205 responses were analyzed. The results of the analysis showed that GHRM positively impacts the pro-environmental behavior of employees. Results show that there is a significant mediation of Green Entrepreneurship and a significant moderation of Green Self-Efficacy, respectively. This study fulfills the gaps in literature and provides pioneering inputs as there is a lack of studies in green HRM field, especially in the hospitality sector of Pakistan. This study enhances the knowledge in the green HRM field. Besides, this study also contributes practically and provides various inputs to hospitality sectors that how effective environmental performance can be enhanced by effectively incorporating green practices in the HR policies of organizations. This study is significant as it contributes to both theory and practice by providing fresh insights on green HRM.

The organizational sustainability heavily depends upon employee performance. The aim of the study is to examine the relationship of organizational justice and in-role employee performance. Moreover, the organizational embeddedness and employee advocacy are used as mediator and moderator, respectively. A sample of 402 medical doctors was selected from different hospitals using snow-ball sampling technique. Their responses were gathered through a closed-ended questionnaire. The data collected were analyzed using partial-least square method. The study shows that organizational justice in the organization increases the employees performance. Organizational embeddedness mediates their relation, whereas advocating the needs of the employees moderates their relation. We have contributed to the existing theoretical model proposed in earlier literature by comprehensively analyzing the organizational justice impact on the in-role performance, i.e. by including the interactional justice impact as well. Furthermore, we also propose to include the role of employees’ advocacy in enhancing the in-role performance of the employees. The hospital managers can enhance employees’ in-role performance by treating them fairly; apply same rules without any bias, while developing open communication with them. These measures can be further improved by providing support. The cross-sectional nature of the study may restrict the generalizability of results.

Summary: Protein-protein interaction (PPI) prediction is essential to understand the functions of proteins in various biological processes and their roles in the development, progression, and treatment of different diseases. To perform economical large-scale PPI analysis, several artificial intelligence-based approaches have been proposed. However, these approaches have limited predictive performance due to the use of in-effective statistical representation learning methods and predictors that lack the ability to extract comprehensive discriminative features. The paper in hand generates statistical representation of protein sequences by applying transfer learning in an unsupervised manner using FastText embedding generation approach. Furthermore, it presents “ADH-PPI” classifier which reaps the benefits of three different neural layers, long short-term memory, convolutional, and self-attention layers. Over two different species benchmark datasets, proposed ADH-PPI predictor outperforms existing approaches by an overall accuracy of 4%, and matthews correlation coefficient of 6%. In addition, it achieves an overall accuracy increment of 7% on four independent test sets. Availability: ADH-PPI web server is publicly available at https://sds_genetic_analysis.opendfki.de/PPI/

This study aims to investigate the impact of exposure to terrorism on post-traumatic stress disorder and employee performance, and to determine whether social support acts as a boundary condition that can attenuate the adverse effects of PTSD on employee performance. The study used a cross-sectional sample of 178 university teachers who had experienced a terrorist attack. Data was collected using closed-ended questionnaires and analyzed using PROCESS Macro). The results found a negative and significant relationship between exposure to terrorism, post-traumatic disorder, and employees’ performance. Moreover, it was also found that social support helps attenuate the negative impact of PTSD on performance levels. This study adds to the existing body of knowledge by exploring the relationship between terrorism exposure, PTSD, employee performance, and the potential mitigating effects of social support.

This descriptive study was conducted to evaluate the factors affecting the quality of online learning of Pakistani students during the COVID-19 pandemic. Developing economies such as Pakistan present a unique context to online education as there is limited access to technology, ITC services, and the internet for the general public. This paper integrates the factors affecting the online learning process of students while taking the situational factors as a boundary condition (moderating variable). Data were collected through a Appendix Questionnaire administered to students studying in different universities in Pakistan. Stepwise linear regression and PROCESS Macro by Hayes (2013) was used for data analysis. Results revealed that university support, instructors’ support, and motivational factors predicted the quality of online learning. The situational factors negatively influenced the relationship of instructors’ support and motivational factors and the quality of online learning. University support and the quality of online learning relationships were not moderated by situational factors.

Small non-coding RNAs (ncRNAs) are attracting increasing attention as they are now considered potentially valuable resources in the development of new drugs intended to cure several human diseases. A prerequisite for the development of drugs targeting ncRNAs or the related pathways is the identification and correct classification of such ncRNAs. State-of-the-art small ncRNA classification methodologies use secondary structural features as input. However, such feature extraction approaches only take global characteristics into account and completely ignore co-relative effects of local structures. Furthermore, secondary structure based approaches incorporate high dimensional feature space which is computationally expensive. The present paper proposes a novel Robust and Precise ConvNet (RPC-snRC) methodology which classifies small ncRNAs into relevant families by utilizing their primary sequence. RPC-snRC methodology learns hierarchical representation of features by utilizing positioning and information on the occurrence of nucleotides. To avoid exploding and vanishing gradient problems, we use an approach similar to DenseNet in which gradient can flow straight from subsequent layers to previous layers. In order to assess the effectiveness of deeper architectures for small ncRNA classification, we also adapted two ResNet architectures having a different number of layers. Experimental results on a benchmark small ncRNA dataset show that the proposed methodology does not only outperform existing small ncRNA classification approaches with a significant performance margin of 10% but it also gives better results than adapted ResNet architectures. To reproduce the results Source code and data set is available at https://github.com/muas16/small-non-coding-RNA-classification.

Solar energy is free from noise and environmental pollution. It could be used to replace non-renewable sources such as fossil fuels, which are in limited supply and have negative environmental impacts. The first generation of solar cells was made from crystalline silicon. They were relatively efficient, however very expensive because they require a lot of energy to purify the silicon. Nowadays, the production of solar cells has been improved since the first generation (thin-film solar cells, dye-sensitized solar cells, perovskite solar cells, and organic solar cells). In this work, the development of solar cells was discussed. The advantages, limitations, challenges, and future trends of these solar cells were also reported. Lastly, this article emphasized the various practices to promote solar energy and highlighted the power conversion efficiency of the fabricated devices.

The wide-spread usage of ciprofloxacin (CIP) resulted in its presence in different parts of the ecosystem. Thus, a simple, reliable, on-spot detection method for CIP is required in environmental context. Herein, a colorimetric assay is developed for the detection of CIP based on the branched polyethyleneimine (PEI) conjugated silver nanoparticles (PEI-AgNPs). AgNPs are prepared using PEI as stabilizing agent following a simple one-pot two-phase procedure. The prepared PEI-AgNPs are subsequently used for an efficient and selective detection of CIP. The characteristic yellow colour of PEI-AgNPs changed to colourless when CIP was added which was further confirmed by quenching in the intensity of the SPR (surface plasmon resonance) band (hypochromic shift). The proposed method is efficient for the quantitation of CIP in a linear dynamic range (LDR) of 0.1–200 µM with a limit of detection (LOD) of 0.038 µM, and limit of quantification (LOQ) of 0.12 µM. The developed method is selective, efficient, and sensitive to CIP in the presence of numerous interfering species and in real biological, environmental, and commercial pharmaceutical samples. Excellent performance of the proposed method compared to UV-Vis spectroscopy and UPLC in environmental, biological, and commercial pharmaceutical samples is demonstrated.

Viral-host protein protein interaction (PPI) analysis is essential to decode the molecular mechanism of viral pathogen and host immunity processes which eventually help to control viral diseases and optimize therapeutics. The state-of-the-art viral-host PPI predictor leverages unsupervised embedding learning technique (doc2vec) to generate statistical representations of viral-host protein sequences and a Random Forest classifier for interaction prediction. However, doc2vec approach generates the statistical representations of viral-host protein sequences by merely modelling the local context of residues which only partially captures residue semantics. The paper in hand proposes a novel technique for generating better statistical representations of viral and host protein sequences based on the infusion of comprehensive local and global contextual information of the residues. While local residue context aware encoding captures semantic relatedness and short range dependencies of residues. Global residue context aware encoding captures comprehensive long-range residues dependencies, positional invariance of residues, and unique residue combination distribution important for interaction prediction. Using concatenated rich statistical representations of viral and host protein sequences, a robust machine learning framework "LGCA-VHPPI" is developed which makes use of a deep forest model to effectively model complex non-linearity of viral-host PPI sequences. An in-depth performance comparison of the proposed LGCA-VHPPI framework with existing diverse sequence encoding schemes based viral-host PPI predictors reveals that LGCA-VHPPI outperforms state-of-the-art predictor by 6%, 2%, and 2% in terms of matthews correlation coefficient over 3 different benchmark viral-host PPI prediction datasets.

Excretion of heavy metals especially mercury (Hg2+) from the industries into the environment becomes a major global problem. In this context, mercury is a highly dangerous metal which poses serious impact on human health. In the present study, acridine- (ACR-) based silver nanoparticles (ACR-AgNPs) were prepared and employed as a nanosensor for effective detection and quantification of Hg2+ in tap water. Conjugation between ACR-based coating agent and silver was examined by UV-visible and FT-IR spectroscopy, while morphology and particle size were determined through atomic force microscopy (AFM), dynamic light scattering (DLS), and scanning electron microscopy (SEM). Furthermore, sensing behavior of nanosensor for metal ions was evaluated by mixing different metals such as Mn2+, Ni2+, Ba2+, Mg2+, Cr3+, Pb2+, Pd2+, Al3+, Sn2+, Fe2+, Co2+, Cu2+, Fe3+, Cd2+, and Hg2+with ACR-AgNPs. Among all the added metal ions, only Hg2+resulted in significant quenching in the absorption intensity of ACR-AgNPs. The limit of detection of the ACR-AgNP-based nanosensor was found to be 1.65 μM in a wide pH range (1-14). The proposed mercury sensor worked efficiently in the presence of other interfering agents such as other metal ions. Therefore, the synthesized ACR-AgNPs have proved to be an efficient and robust nanosensor for quantitative detection of Hg2+ in real sample analysis such as tap water. The proposed method does not require expensive instrumentation and trained manpower.

The incorporation of functionalized graphene oxide (GO) in mixed matrix membrane (MMM) is expected to greatly increase the permeability and selectivity for O2/N2 separation. In the present study, GO functionalized with 3- (Trimethoxysilyl) propyl methacrylate (TMOPMA) was used as inorganic filler and incorporated in to a PVC/pAMPS based MMM to increase the separation efficiency. Membranes of different compositions were synthesized and the best morphology was achieved with 0.5 g of PVC, 1.0 g of pAMPS and 0.015 g of filler. The synthesized membrane and inorganic filler were characterized using SEM, EDS, FTIR, Raman and XRD spectroscopy. Moreover, the gas permeation studies were performed to check the separation factor of synthesized membrane for O2/N2. The maximum permeability achieved for O2 and N2 was 4097 and 3373 barrers, respectively at 5 bar pressure. For the selectivity, a gradual increasing trend was observed with the increase in permeability. The maximum selectivity achieved was 1.215 at 5 bar pressure. The results revealed an increasing trend in selectivity with the increase in permeability of gases across the membrane with the increase in feed gas pressure.

In the current study, gold nanoparticles (AuC6NPs and AuC8NPs) were prepared through sodium borohydride reduction method by using Calix[6]rene and Calix[8]rene as a stabilizing agents. The synthesized AuNPs were screened for cytotoxic, phytotoxic, antifungal and antibacterial activities. The fabricated AuNPs were characterized by UV–visible spectroscopy, atomic force microscopy (AFM) and FTIR spectroscopy. Antibacterial activities of the AuNPs were tested against E. coli and S. aureus. The AuC6NPs were found to be effective against the growth of gram positive bacteria and inhibited the growth of S. aureus. AuC6NPs interact with bacterial cell and damaged cell membrane. Roughness of the bacterial surface and membrane rupture can be clearly observed by AFM images. The AuNPs possess insignificant antifungal activity against Aspergillus niger and Candida albicans. Moreover, AuC8NPs have significant phytotoxicity and moderate cytotoxicity. Keywords: Gold nanoparticles, S. aureus, E. coli, Antibacterial mechanism, Phytotoxicity, Cytotoxicity and atomic force microscopy

Traditional neural networks trained using point-based maximum likelihood estimation are deterministic models and have exhibited near-human performance in many image classification tasks. However, their insistence on representing network parameters with point-estimates renders them incapable of capturing all possible combinations of the weights; consequently, resulting in a biased predictor towards their initialisation. Most importantly, these deterministic networks are inherently unable to provide any uncertainty estimate for their prediction which is highly sought after in many critical application areas. On the other hand, Bayesian neural networks place a probability distribution on network weights and give a built-in regularisation effect making these models able to learn well from small datasets without overfitting. These networks provide a way of generating posterior distribution which can be used for model's uncertainty estimation. However, Bayesian estimation is computationally very expensive since it greatly widens the parameter space. This paper proposes a hybrid convolutional neural network which combines high accuracy of deterministic models with posterior distribution approximation of Bayesian neural networks. This hybrid architecture is validated on 13 publicly available benchmark classification datasets from a wide range of domains and different modalities like natural scene images, medical images, and time-series. Our results show that the proposed hybrid approach performs better than both deterministic and Bayesian methods in terms of classification accuracy and also provides an estimate of uncertainty for every prediction. We further employ this uncertainty to filter out unconfident predictions and achieve significant additional gain in accuracy for the remaining predictions.

This paper presents a Convolutional Neural Networks (CNN) based Unsupervised Curriculum Learning approach for the recognition of water bodies to overcome the stated challenges for remote sensing based RGB imagery. The unsupervised nature of the presented algorithm eliminates the need for labelled training data. The problem is cast as a two class clustering problem (water and non-water), while clustering is done on deep features obtained by a pre-trained CNN. After initial clusters have been identified, representative samples from each cluster are chosen by the unsupervised curriculum learning algorithm for fine-tuning the feature extractor. The stated process is repeated iteratively until convergence. Three datasets have been used to evaluate the approach and show its effectiveness on varying scales: (i) SAT-6 dataset comprising high resolution aircraft images, (ii) Sentinel-2 of EuroSAT, comprising remote sensing images with low resolution, and (iii) PakSAT, a new dataset we created for this study. PakSAT is the first Pakistani Sentinel-2 dataset designed to classify water bodies of Pakistan. Extensive experiments on these datasets demonstrate the progressive learning behaviour of UCL and reported promising results of water classification on all three datasets. The obtained accuracies outperform the supervised methods in domain adaptation, demonstrating the effectiveness of the proposed algorithm.

Technostress, a stressor, has implications for employee’s psychological states; however, flexibility like work from home can have positive outcomes, especially for instructors who have to teach and ensure social distance during COVID-19. The present study examined the relationship of technostress and employee performance while taking training and creative self-efficacy as boundary conditions. A sample of 222 university instructors, who worked from home or hybrid (home and workplace) during COVID-19 lockdown, was selected from Pakistan. The responses were recorded using a closed-ended questionnaire. Stepwise linear regression and PROCESS Macro by Hayes (2013) was used to analyze the data. It was revealed that technostress, instead of having adverse effects, had a positive effect on employee’s performance and both training and one’s creative self-efficacy significantly moderated the relationship. As the main finding, it was revealed that the employees continued to perform well despite the prevalence of technostress. The training and one’s creative self-efficacy were useful to control the technostress and maintain the performance of instructors during COVID-19. The university administrators and employees must take technology as a positive tool for performance. The training, along with creative self-efficacy, adds to the working capacity of employees and enhances their performance.

Employee performance is the backbone of achieving competitiveness and sustainability. This study aims to examine the impact of workplace incivility on employee performance. In addition, trust in supervisors is examined as a mediator. The conservation of resources (COR) theory and Maslow’s hierarchy of needs theory provided the grounds for developing the framework. The data were collected through closed-ended questionnaires and were analyzed using structural equation modeling with SmartPLS. The results affirmed that incivility is harmful to the performance of employees, and that trust in supervisors helps employees to perform well. The trust in the supervisor significantly mediates the incivility–performance relationship. The examination of the proposed model through the lens of two theories as well as the study of low-intensity deviant workplace behavior in a collectivist and developing economy are the contributions of this study to the growing body of literature. However, the use of a single sector was one of the limitations of this study.

The study aims to test the impact of social support from supervisors and self-efficacy on employee performance through office de-clutter (a mediator) in banks. During the COVID-19 pandemic, the supporting factors (social support and self-efficacy) to de-clutter for maintaining employee performance is a novel contribution to the literature and is supported by the social exchange theory—SET. The employee’s performance can be maintained with lower levels of office clutter (de-clutter). The office clutter can be managed through the availability of managerial social support and employee self-efficacy. The impact of supervisor support and self-efficacy on employee performance is examined through the lens of the social exchange theory. A cross-sectional and quantitative study was conducted with 202 primary responses from bank employees. The responses were recorded using closed-ended questionnaires. A response rate of 73.9% was achieved. Reliability and validity were assessed using Cronbach’s alpha scores and AVE, respectively. PLS-SEM was used as a data analysis and hypotheses testing technique. The results revealed that supervisors’ social support and self-efficacy significantly and positively affect employee performance. Moreover, supervisors’ social support and self-efficacy helped in office de-clutter, further ensuring better performance.

Project success is the backbone of competitiveness and sustainability. The study aims to examine the role of cronyism in the relationship between toxic leadership and project success while taking information technology projects as the study context. Cross-sectional data (n = 240) was collected through closed-ended survey questionnaires to record the responses of IT project employees. The structural equation modeling (SEM) technique was used for analyzing the collected data. Results revealed a negative relationship between toxic leadership and project success, while cronyism positively and significantly mediated the relationship and converted the negative relationship between TL and PS to a positive relationship.

During uncertain situations, such as the COVID-19 partial lockdown, maintaining satisfactory levels of employee performance (EP) is an important area of concern for many organizations. The current study examines the relationship of work stress due to COVID-19 (COVID-19 STR) and EP. Using social exchange theory (SET), safety culture (SC) is presented as a moderator for stress and performance relationships. A sample of 213 bank employees was collected using a convenient sampling method. Data were analyzed using stepwise linear regression and PROCESS Macro by Hayes (2013). Results revealed that COVID-19 STR has a negative impact on task and contextual performance (CP) and a positive impact on adaptive performance (AP). Similarly, the prevalence of SC significantly moderates the stress and performance relationships.

Circular ribonucleic acids (circRNAs) are novel non-coding RNAs that emanate from alternative splicing of precursor mRNA in reversed order across exons. Despite the abundant presence of circRNAs in human genes and their involvement in diverse physiological processes, the functionality of most circRNAs remains a mystery. Like other non-coding RNAs, sub-cellular localization knowledge of circRNAs has the aptitude to demystify the influence of circRNAs on protein synthesis, degradation, destination, their association with different diseases, and potential for drug development. To date, wet experimental approaches are being used to detect sub-cellular locations of circular RNAs. These approaches help to elucidate the role of circRNAs as protein scaffolds, RNA-binding protein (RBP) sponges, micro-RNA (miRNA) sponges, parental gene expression modifiers, alternative splicing regulators, and transcription regulators. To complement wet-lab experiments, considering the progress made by machine learning approaches for the determination of sub-cellular localization of other non-coding RNAs, the paper in hand develops a computational framework, Circ-LocNet, to precisely detect circRNA sub-cellular localization. Circ-LocNet performs comprehensive extrinsic evaluation of 7 residue frequency-based, residue order and frequency-based, and physio-chemical property-based sequence descriptors using the five most widely used machine learning classifiers. Further, it explores the performance impact of K-order sequence descriptor fusion where it ensembles similar as well dissimilar genres of statistical representation learning approaches to reap the combined benefits. Considering the diversity of statistical representation learning schemes, it assesses the performance of second-order, third-order, and going all the way up to seventh-order sequence descriptor fusion. A comprehensive empirical evaluation of Circ-LocNet over a newly developed benchmark dataset using different settings reveals that standalone residue frequency-based sequence descriptors and tree-based classifiers are more suitable to predict sub-cellular localization of circular RNAs. Further, K-order heterogeneous sequence descriptors fusion in combination with tree-based classifiers most accurately predict sub-cellular localization of circular RNAs. We anticipate this study will act as a rich baseline and push the development of robust computational methodologies for the accurate sub-cellular localization determination of novel circRNAs.

The development of metal nanoparticle-based facile colorimetric assays for drugs and insecticides is an emerging area of current scientific research. In the present work, polypropylene glycol was used for stabilization of gold nanoparticles (AuNPs) in a simple one-pot two-phase process and subsequently employed it for the specific detection of cephradine (CPH). The characterization of the prepared PPG-AuNPs was conducted through various analytical techniques such as UV-visible spectrophotometry, Fourier transform infrared spectroscopy, atomic force microscopy (AFM), zeta potential and zetasizer techniques. As the major target of the study, the stabilized PPG-AuNPs were employed for colorimetric detection of CPH and other drugs. Typical wine-red colour of PPG-AuNPs disappeared immediately and surface plasmon resonance band quenched by addition of CPH in the presence of several other interferents (drugs and salts) and in real samples. PPG-AuNPs permitted efficient, selective, reliable and rapid determination in a concentration range of 0.01–120 mM with a detection limit (LoD) of 11.0 mM. The developed sensor has the potential to be used for fast scanning of pharmaceutical formulations for quantification of CPH at production facilities.

Abstract Background With the advancement of powerful image processing and machine learning techniques, Computer Aided Diagnosis has become ever more prevalent in all fields of medicine including ophthalmology. These methods continue to provide reliable and standardized large scale screening of various image modalities to assist clinicians in identifying diseases. Since optic disc is the most important part of retinal fundus image for glaucoma detection, this paper proposes a two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous. Methods The first stage is based on Regions with Convolutional Neural Network (RCNN) and is responsible for localizing and extracting optic disc from a retinal fundus image while the second stage uses Deep Convolutional Neural Network to classify the extracted disc into healthy or glaucomatous. Unfortunately, none of the publicly available retinal fundus image datasets provides any bounding box ground truth required for disc localization. Therefore, in addition to the proposed solution, we also developed a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization. Results The proposed method is evaluated on seven publicly available datasets for disc localization and on ORIGA dataset, which is the largest publicly available dataset with healthy and glaucoma labels, for glaucoma classification. The results of automatic localization mark new state-of-the-art on six datasets with accuracy reaching 100% on four of them. For glaucoma classification we achieved Area Under the Receiver Operating Characteristic Curve equal to 0.874 which is 2.7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA dataset. Conclusion Once trained on carefully annotated data, Deep Learning based methods for optic disc detection and localization are not only robust, accurate and fully automated but also eliminates the need for dataset-dependent heuristic algorithms. Our empirical evaluation of glaucoma classification on ORIGA reveals that reporting only Area Under the Curve, for datasets with class imbalance and without pre-defined train and test splits, does not portray true picture of the classifier’s performance and calls for additional performance metrics to substantiate the results.

The purpose to conduct this research work is to study the effect of photocatalytic degradation by developing cost-effective and eco-friendly nitrogen and tungsten (metal/non-metal) co-doped titania (TiO2). The inherent characteristics of synthesized nanoparticles (NPs) were analyzed by Fourier transform infra-red spectroscopy (FT-IR), ultra-violet visible (UV-Vis) spectroscopy, Raman spectroscopy, Field emission scanning electron microscopy (FE-SEM), energy dispersive X-ray spectroscopy (EDX), dynamic light scattering (DLS), X-ray diffraction (XRD) spectrometry, and atomic force microscopy (AFM). Co-doping of metal and non-metal has intensified the photocatalysis trait of TiO2 nanoparticles in an aqueous medium. This co-doping of transition metal ions and modification of nitrogen extended the absorption into the visible region subsequently restraining the recombination of electrons/holes pair. The stronger light absorption in the visible region was required for the higher activity of photodegradation of dye under visible light illumination to confine bandgap energy which results in accelerating the rate of photodegradation. After efficient doping, the bandgap of titania reduced to 2.38 eV and caused the photodegradation of malachite green in visible light. The results of photocatalytic degradation were confirmed by using UV/Vis. spectroscopy and high-performance liquid chromatography coupled with a mass spectrophotometer (HPLC-ESI-MS) was used for the analysis of intermediates formed during photocatalytic utility of the work.

Ensuring safety is the key to sustainability especially, in the oil and gas sector. The study aims to examine the effects of five dimensions of toxic leadership on the safety performance of engineers working in Oil and Gas Companies. Through social learning theory and conservation of resource theory, an overarching framework of the research model has been proposed. Cross-sectional data from a sample of 219 site engineers, male and female, working in oil and gas companies operating in Pakistan, were collected and analyzed. Results revealed that out of five dimensions of toxic leadership, only abusive supervision and narcissism had a significant negative impact on safety performance. Similarly, organizational commitment appeared as an essential stress moderator and has successfully dampened the negative impact of abusive supervision and narcissism on safety performance.

The antibacterial activity of silver nanoparticles (AgNPs) stabilized with a four-armed star-shaped poly(ε-caprolactone)-block-poly(ethylene oxide) copolymer [St-P(CL-b-EO)] and its application as a drug delivery vehicle for cephalexin (Cp) was evaluated against pathogenic Staphylococcus aureus. The prepared AgNPs were characterized by ultraviolet-visible spectroscopy, Fourier transform infrared spectroscopy, zeta sizer and atomic force microscopy (AFM). The antibacterial efficiency of Cp is enhanced several-fold by its delivery through complexation with St-P(CL-b-EO)-AgNPs, monitored by microplate assay and biofilm destruction studies. Finally, the visual destruction of bacterial cells and its biofilms by employing Cp and its conjugates at their minimum inhibitory concentration (MIC50) and minimum biofilm inhibitory concentration (MBIC50), respectively, is observed by topographic imaging by AFM. Enhanced antibacterial activity of St-P(CL-b-EO)-AgNPs loaded Cp is attributed to penetrative nature of the drug cargo St-P(CL-b-EO)-AgNPs towards the bacterial cell wall.

Leadership styles have direct impact on employee commitment and may influence organizational sustainability. Previously the positive aspects of leadership are highlighted, and negative aspects still need to bring to light. This study aims to examine the relationship of abusive leadership and organizational commitment of bank employees where in employee’s emotional intelligence acts as a mediator. A sample of 255 bank employees was selected and their responses were gathered through closed-ended questionnaires. PLS—SEM was used for analysis by using SmartPLS Ver. 3.0. The results show that the abusive behaviors disrupt organizational commitment of bank employees. Despite the fact that emotional intelligence mediates the relationship but could not turn organizational commitment to positive due to strong negative intensity of abusive leadership. This study therefore recommends that employee commitment is likely to be achieved when the negative effects of abusive leadership can be weakened through using emotional intelligence by the bank employees. The paper selected a sample from banking sector from a developing country and tested a model empirically. The findings are novel to highlight the presence of abusive/toxic leadership in the banks.

The world is on the verge of a technological evolution that will revolutionize Internet access across the globe using direct device-to-satellite links. Such direct global connectivity brings with it an opportunity for the medical community to have a new framework for the secure transmission of confidential personal medical information and clinical systems data. Such a framework has the potential to connect developed-country expertise with less-advanced health services in developing countries, remote communities, patients' homes, or in disaster zones. This paper explores this emerging concept along with potential communication advancements in medical equipment and presents a conceptual view of implementing ever-demanding health-care services that can benefit the global population. Further, the paper elaborates upon cyber security challenges to digital health-care services. We provide evidence on the need to improve or develop encryption and hashing algorithms and how it can help to meet the cyber security challenges faced by key stakeholders for e-Health. This will ensure fast, reliable, and effective health-care services for both developing economies and remote locations in developed countries.

This paper presents a novel approach for the detection of tables present in documents, leveraging the potential of deep neural networks. Conventional approaches for table detection rely on heuristics that are error prone and specific to a dataset. In contrast, the presented approach harvests the potential of data to recognize tables of arbitrary layout. Most of the prior approaches for table detection are only applicable to PDFs, whereas, the presented approach directly works on images making it generally applicable to any format. The presented approach is based on a novel combination of deformable CNN with faster R-CNN/FPN. Conventional CNN has a fixed receptive field which is problematic for table detection since tables can be present at arbitrary scales along with arbitrary transformations (orientation). Deformable convolution conditions its receptive field on the input itself allowing it to mold its receptive field according to its input. This adaptation of the receptive field enables the network to cater for tables of arbitrary layout. We evaluated the proposed approach on two major publicly available table detection datasets: ICDAR-2013 and ICDAR-2017 POD. The presented approach was able to surpass the state-of-the-art performance on both ICDAR-2013 and ICDAR-2017 POD datasets with a F-measure of 0.994 and 0.968, respectively, indicating its effectiveness and superiority for the task of table detection.

Apart from protein-coding Ribonucleic acids (RNAs), there exists a variety of non-coding RNAs (ncRNAs) which regulate complex cellular and molecular processes. High-throughput sequencing technologies and bioinformatics approaches have largely promoted the exploration of ncRNAs which revealed their crucial roles in gene regulation, miRNA binding, protein interactions, and splicing. Furthermore, ncRNAs are involved in the development of complicated diseases like cancer. Categorization of ncRNAs is essential to understand the mechanisms of diseases and to develop effective treatments. Sub-cellular localization information of ncRNAs demystifies diverse functionalities of ncRNAs. To date, several computational methodologies have been proposed to precisely identify the class as well as sub-cellular localization patterns of RNAs). This paper discusses different types of ncRNAs, reviews computational approaches proposed in the last 10 years to distinguish coding-RNA from ncRNA, to identify sub-types of ncRNAs such as piwi-associated RNA, micro RNA, long ncRNA, and circular RNA, and to determine sub-cellular localization of distinct ncRNAs and RNAs. Furthermore, it summarizes diverse ncRNA classification and sub-cellular localization determination datasets along with benchmark performance to aid the development and evaluation of novel computational methodologies. It identifies research gaps, heterogeneity, and challenges in the development of computational approaches for RNA sequence analysis. We consider that our expert analysis will assist Artificial Intelligence researchers with knowing state-of-the-art performance, model selection for various tasks on one platform, dominantly used sequence descriptors, neural architectures, and interpreting inter-species and intra-species performance deviation.

MicroRNAs (miRNA) are small noncoding RNA sequences consisting of about 22 nucleotides that are involved in the regulation of almost 60% of mammalian genes. Presently, there are very limited approaches for the visualization of miRNA locations present inside cells to support the elucidation of pathways and mechanisms behind miRNA function, transport, and biogenesis. MIRLocator, a state-of-the-art tool for the prediction of subcellular localization of miRNAs makes use of a sequence-to-sequence model along with pretrained k-mer embeddings. Existing pretrained k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. However, in RNA sequences, positional information of nucleotides is more important because distinct positions of the four nucleotides define the function of an RNA molecule. Considering the importance of the nucleotide position, we propose a novel approach (kmerPR2vec) which is a fusion of positional information of k-mers with randomly initialized neural k-mer embeddings. In contrast to existing k-mer-based representation, the proposed kmerPR2vec representation is much more rich in terms of semantic information and has more discriminative power. Using novel kmerPR2vec representation, we further present an end-to-end system (MirLocPredictor) which couples the discriminative power of kmerPR2vec with Convolutional Neural Networks (CNNs) for miRNA subcellular location prediction. The effectiveness of the proposed kmerPR2vec approach is evaluated with deep learning-based topologies (i.e., Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN)) and by using 9 different evaluation measures. Analysis of the results reveals that MirLocPredictor outperform state-of-the-art methods with a significant margin of 18% and 19% in terms of precision and recall.

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922, respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features.

Propensity of skin diseases to manifest in a variety of forms, lack and maldistribution of qualified dermatologists, and exigency of timely and accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD for dermatology by exploring the potential of Deep Learning to classify hundreds of skin diseases, improving classification performance, and utilizing disease taxonomy. We trained state-of-the-art Deep Neural Networks on two of the largest publicly available skin image datasets, namely DermNet and ISIC Archive, and also leveraged disease taxonomy, where available, to improve classification performance of these models. On DermNet we establish new state-of-the-art with 80% accuracy and 98% Area Under the Curve (AUC) for classification of 23 diseases. We also set precedence for classifying all 622 unique sub-classes in this dataset and achieved 67% accuracy and 98% AUC. On ISIC Archive we classified all 7 diseases with 93% average accuracy and 99% AUC. This study shows that Deep Learning has great potential to classify a vast array of skin diseases with near-human accuracy and far better reproducibility. It can have a promising role in practical real-time skin disease diagnosis by assisting physicians in large-scale screening using clinical or dermoscopic images.