Serotype and genomic diversity of dengue virus during the 2023 outbreak in Pakistan reveals the circulation of genotype III of DENV-1 and cosmopolitan genotype of DENV-2.

Dengue, a mosquito-borne viral disease, poses a significant public health challenge in Pakistan, with a significant outbreak in 2023, prompting our investigation into the serotype and genomic diversity of the dengue virus (DENV). NS-1 positive blood samples from 153 patients were referred to the National Institute of Health, Pakistan, between July and October 2023. Among these, 98 (64.1%) tested positive using multiplex real-time PCR, with higher prevalence among males (65.8%) and individuals aged 31-40. Serotyping revealed DENV-1 as the predominant serotype (84.7%), followed by DENV-2 (15.3%). Whole-genome sequencing of 18 samples (DENV-1 = 17, DENV-2 = 01) showed that DENV-1 (genotype III) samples were closely related (>99%) to Pakistan outbreak samples (2022), and approx. > 98% with USA (2022), Singapore and China (2016), Bangladesh (2017), and Pakistan (2019). The DENV-2 sequence (cosmopolitan genotype; clade IVA) shared genetic similarity with Pakistan outbreak sequences (2022), approx. > 99% with China and Singapore (2018-2019) and showed divergence from Pakistan sequences (2008-2013). No coinfection with dengue serotypes or other viruses were observed. Comparisons with previous DENV-1 sequences highlighted genetic variations affecting viral replication efficiency (NS2B:K55R) and infectivity (E:M272T). These findings contribute to dengue epidemiology understanding and underscore the importance of ongoing genomic surveillance for future outbreak responses in Pakistan.

Hydrochemical, hydrogeological, and cancer health risk analysis of groundwater due to anthropogenic activities, Hasilpur, Pakistan.

Drinking water quality deteriorates rapidly due to anthropogenic activities and rapid population growth. These activities, in developing countries, will lead to water scarcity. In Pakistan, 70% of the population has no access to safe water, and people use canal water to drink. This study performed hydrochemical, hydrogeological, and cancer risk analyses on Tahsil Hasilpur, Bahawalpur, Pakistan. Thirteen tube wells were selected for groundwater and borehole log study. Twenty-two drinking water quality parameters were analyzed using standard methods and quality checks. The borehole data (2D and 3D) shows the abundance of sand (fine and coarse) with some uniformities, which changes the groundwater quality. The results of water quality parameters show that the concentration of TDS (2064-11,159 mg/L), Cl-1 (213-4917 mg/L), As+3 (0.048-0.158 mg/L), Pb+2 (1.294-1.673 mg/L), and Cd+2 (0.008-0.053 mg/L) were beyond guideline values. The statistical analysis showed that the parameters have a moderate to strong correlation (Pearson correlation), which may be due to the same origin (ANOVA). The principal component analysis and cluster analysis confirm the multiple sources of pollutants in the groundwater of the study area. The Piper, Durov, Stiff, and Scholler diagrams confirm that the groundwater system has an abundance of Ca+2 and Mg+2 with Cl-1. The Gibbs diagram showed that the groundwater is not saturated and tends to dissolve more minerals. The hazard quotient values are above 1.0, which indicates noncancer risk severity. The HQ trend was As+3 > Pb+2 > Cd+2 > Ni+2 > Cu+2 > Cr+2 > Zn+2 > Fe+2. The cancer risk values showed that 3-5 people/100 population were exposed to cancer risk. The trend of CR was As+3 > Cd+2 > Cr+2 > Pb+2 > Ni+2. The GIP mapping of pollutants showed that the concentration of pollutants near the canals was high compared to the locations away from the canal. The overall groundwater quality is alarming and needs immediate government attention.

5G-Enabled Healthcare in Mobile Scenarios: Challenges and Implementation Considerations.

Wireless connectivity delay, disruption, or failure can significantly affect the performance of wireless-enabled medical devices, which in turn causes potential risks to the patient. Notably, the challenges related to connectivity provisioning are exacerbated in the fifth-generation (5G)-enabled healthcare use cases where mobility is utilized. In this article, we describe relevant 5G-enabled healthcare use cases involving mobility and identify the connectivity challenges that they face. We then illustrate practical implementation considerations, tradeoffs, and future research directions for enabling reliable 5G healthcare transmissions. This is done through simulation of connected ambulances as an example use-case.

Spatial soil loss prediction impacted by long-term land use/land cover change: a case study of Swat District.

Soil erosion is a destructive consequence of land degradation caused by deforestation, improper farming practices, overgrazing, and urbanization. This irreversible effect negatively impacts the limited renewable soil resource, causing soil truncation, reduced fertility, and unstable slopes. To address the anticipation of erosion modulus resulting from long-term land use and land cover (LULC) changes, a study was conducted in the Swat District of Khyber Pakhtunkhwa (Kpk), Pakistan. The study aimed to predict and evaluate soil erosion concerning these changes using remote sensing (RS), geographic information systems (GIS), and the Revised Universal Soil Loss Equation (RUSLE) model. We also evaluated the impact of the Billion Tree Tsunami Project (BTTP) on soil erosion in the region. Model inputs, such as rainfall erosivity factor, topography factor, land cover and management factor, and erodibility factor, were used to calculate soil erosion. The results revealed that significant soil loss occurred under 2001, 2011, and 2021 LULC conditions, accounting for 67.26%, 61.78%, and 65.32%, falling within the category of low erosion potential. The vulnerable topographical features of the area indicated higher erosion modulus. The maximum soil loss rates observed in 2001, 2011, and 2021 were 80 t/ha-1/year-1, 120 t/ha-1/year-1, and 96 t/ha-1/year-1, respectively. However, the observed reduction in soil loss in 2021 as compared to 2001 and 2011 suggests a positive influence of the BTTP on soil conservation efforts. This study underscores the potential of afforestation initiatives like the BTTP in mitigating soil erosion and highlights the significance of environmental conservation programs in regions with vulnerable topography.

Development and characterization of letrozole-encapsulated polymeric beads for sustained release.

The study aimed to prepare and characterize biodegradable sustained-release beads of letrozole (LTZ) for treating cancerous disease. The ionotropic gelation method was used for the preparation and calcium chloride (CaCl2) was used as a gelating agent, while chitosan (CTS) and sodium alginate (NaAlg) as biodegradable polymeric matrices in the blend hydrogel beads. The beads were characterized for their size, surface morphology, drug entrapment efficiency, drug-polymer interaction and crystallinity using different analytic techniques, including optical microscopy, Scanning Electron Microscopy (SEM), UV-spectroscopy, Fourier-transform Infrared Spectroscopy (FTIR), Thermo gravimetric Analysis (TGA), Differential Scanning Calorimetry (DSC) and X-ray Diffraction Analysis (XRD) respectively. In vitro swelling studies were also applied to observe the response of these polymeric networks against different pH (at 1.2, 6.8 and 7.4 pH). The results from TGA and DSC exhibited that the components in the formulation possess better thermal stability. The XRD of polymeric networks displays a minor crystalline and significant amorphous nature. The SEM micrographs revealed that polymeric networks have uneven surfaces and grooves. Better swelling and in vitro outcomes were achieved at a high pH (6.8,7.4), which endorsed the pH-responsive characteristics of the prepared beads. Hence, beads based on chitosan and sodium alginate were successfully synthesized and can be used for the controlled release of letrozole.

Serum p53 antibodies detection in oral squamous cell carcinoma, oral potentially malignant disorders and healthy individuals: A multicentre study.

OBJECTIVE: To detect antibodies against p53 in serum of patients of oral squamous cell carcinoma and oral potentially malignant disorders compared to healthy individuals. METHODS: The descriptive cross-sectional study was conducted at the departments of Oral and Maxillofacial Surgery, Peshawar Dental College, Peshawar, Khyber College of Dentistry, Peshawar, and the Pakistan Institute of Medical Sciences, Islamabad, Pakistan, from April, 2016 to March, 2017, and comprised serum of oral squamous cell carcinoma patients in group A, oral potentially malignant disorder patients in group B and healthy individuals in group C. Serum concentrations of anti-p53 antibodies were determined by enzyme-linked immunosorbent assay. Data was analysed using SPSS 20. RESULTS: Of the180 subjects, there were 60(33.3%) in each of the three groups. Circulating serum p53 antibodies were detected in 59(98.3%) cases in group A, 58(96.6%) in group B and in 20(33.3%) individuals in group C (p=0.001). CONCLUSIONS: The expression of circulating p53 antibodies in serum samples of squamous cell carcinoma and oral potentially malignant disorders patients indicates the potential to be a probable candidate for being taken as a diagnostic or prognostic biomarker.

Threshold Computation for Spatially Coupled Turbo-Like Codes on the AWGN Channel.

In this paper, we perform a belief propagation (BP) decoding threshold analysis of spatially coupled (SC) turbo-like codes (TCs) (SC-TCs) on the additive white Gaussian noise (AWGN) channel. We review Monte-Carlo density evolution (MC-DE) and efficient prediction methods, which determine the BP thresholds of SC-TCs over the AWGN channel. We demonstrate that instead of performing time-consuming MC-DE computations, the BP threshold of SC-TCs over the AWGN channel can be predicted very efficiently from their binary erasure channel (BEC) thresholds. From threshold results, we conjecture that the similarity of MC-DE and predicted thresholds is related to the threshold saturation capability as well as capacity-approaching maximum a posteriori (MAP) performance of an SC-TC ensemble.

Exploration of Carica papaya bioactive compounds as potential inhibitors of dengue NS2B, NS3 and NS5 protease.

Current outbreak of dengue has shown serious health concerns in Pakistan. The present study reports the anti-dengue potential of Carica papaya natural compounds. The leaves of C. papaya have previously shown promising results in cure of Dengue fever. The aim of this project is to find specific bioactive compounds by computational screening and biological activities of C. papaya against serine NS2B, NS3 and NS5 proteases of dengue virus. Docking study resulted in the screening of nine bioactive compounds having highest docking scores. However, three compounds namely epigallocatchin, catechin and protocatechuric acid had the strongest binding affinity with the active residues i.e., Ser135, His51 and Asp75 of dengue virus serine proteases. Results also indicated that the extract of C. papaya was a strong antimicrobial and antioxidant agent. It is concluded that the C. papaya compounds can be commercially applied for medical formulations against dengue virus.

A concentric tube-based 4-DOF puncturing needle with a novel miniaturized actuation system for vitrectomy.

BACKGROUND: Vitreoretinal surgeries require precise, dexterous, and steady instruments for operation in delicate parts of the eye. Robotics has presented solutions for many vitreoretinal surgical problems, but, in a few operations, the available tools are still not dexterous enough to carry out procedures with minimum trauma to patients. Vitrectomy is one of those procedures and requires some dexterous instruments to replace straight ones for better navigation to affected sides inside the eyeball. METHOD: In this paper, we propose a new vein puncturing solution with a 4-DOF motion to increase the workspace inside the eye. A two-member concentric tube-based 25G needle is proposed whose shape is optimized. To operate the concentric tube needle, a novel and miniaturized actuation system is proposed that uses hollow shaft motors for the first time. The presented prototype of actuation system has a stroke of 100 mm in a small size of 148 × 25 × 65 mm (L × W × H), suitable for approaching distant positions inside the eyeball. RESULTS: Experimental results validate that the targeting accuracy of the needle is less than one millimeter and the needle tip can apply a force of 23.51 mN which is enough to perform puncturing. Furthermore, the proposed needle covers maximum workspace of around 128.5° inside the eyeball. For the actuation system, experiments show that it can produce repeatable motions with accuracy in submillimeter. CONCLUSION: The proposed needle system can navigate to the sites which are difficult to approach by currently available straight tools requiring reinsertions. Along with the miniaturized actuation system, this work is expected to improve the outcome of vitrectomy with safe and accurate navigation.

Transcutaneous Auricular Vagus Nerve Stimulation with Upper Limb Repetitive Task Practice May Improve Sensory Recovery in Chronic Stroke.

BACKGROUND: Sensory impairment is associated with reduced functional recovery in stroke survivors. Invasive vagus nerve stimulation (VNS) paired with rehabilitative interventions improves motor recovery in chronic stroke. Noninvasive approaches, for example, transcutaneous auricular VNS (taVNS) are safe, well-tolerated and may also improve motor function in those with residual weakness. We report the impact of taVNS paired with a motor intervention, repetitive task practice, on sensory recovery in a cohort of patients with chronic stroke. METHODS: Twelve participants who were more than 3 months postischemic stroke with residual upper limb weakness received 18 × 1 hour sessions over 6 weeks with an average of at least 300 repetitions of functional arm movements per session concurrently with taVNS at maximum tolerated intensity. Light touch and proprioception were scored as part of the Upper Limb Fugl-Meyer (UFM) assessment at baseline and postintervention (score range for sensation 0-12). RESULTS: Eleven participants (92%) had sensory impairment at baseline of whom 7 (64%) regained some sensation (proprioception n = 6 participants, light touch n = 2, both modalities n = 1) postintervention. The maximal increase in UFM sensation score (3 points) was seen in the patient with the greatest improvement in motor function. CONCLUSIONS: taVNS paired with motor rehabilitation may improve sensory recovery in chronic stroke patients. The relative contribution of motor and sensory rehabilitation to overall functional recovery in chronic stroke needs further characterization in a larger, phase 2 study.

Pharmacokinetics profile of serum and cellular Sofosbuvir along with its concentration effect analysis in HCV patients receiving Sofosbuvir and Ribavirin.

Sofosbuvir along with ribavirin is being widely used for treatment of HCV in Pakistan but it may show delayed response and reoccurrence of disease in some cases. The aim of the study was to investigate pharmacokinetics and concentration effect analysis of sofosbuvir. HCV patients (n=100) received 400 mg sofosbuvir along with low dose or weight based ribavirin (400 mg). Nonlinear mixed effects modeling (NONMEM) and unpaired t-test were used for the association of concentrations and treatment outcomes. Average day 10 sofosbuvir metabolite BM 331007 concentration was higher in patients having haemoglobin nadir value <10 g/dl compared to the patients having heamoglobin nadir value >10 g/dl (5.34 versus 4.87 pmol/106 cells; p=0.03). The average concentration trends of GS331007 at day 10 was towards being higher in the patients achieved sustained virologic response (SVR) as compare to the patients relapsed (5.19 versus 4.86 pmol/106 cells; p=0.05). Sofosbuvir (GS331007) thresholds concentration (suggested at day 10 through receiver operating characteristic curve) was 5.4 pmol/106 cells for SVR (p=0.05) and haemoglobin nadir cells was 6.3 pmol/106 with sensitivity and specificity of >60%. Dosing simulations shows that 400 mg sofosbuvir twice daily produce day 10 concentration range of 5.4 to 6.7 pmol/106 cells. The range of therapeutic values was identified for HCV patients receiving sofosbuvir in combination with ribavirin for 24 weeks, suggesting a potential pharmaceutical basis for individualized therapeutic dosing.

Burden of rheumatological disorders in a tertiary care hospital.

OBJECTIVE: T To evaluate the frequency of different rheumatological disorders in patients visiting a tertiary care centre. METHODS: The retrospective analysis was conducted at the Rheumatology Clinic of Jinnah Postgraduate Medical Centre, Karachi, and comprised prospectively collected data of patients with different musculoskeletal disorders from February 2004 to February 2014. Detailed history, examination and laboratory investigations were recorded in a pre-designed structured proforma. The frequency, demographic characteristics and associated co-morbidities were studied. SPSS 17 was used for statistical analysis. RESULTS: Of the 603 patients whose data was analysed, 460(76.3%) were women and 143(23.7%) were men. Overall mean age of the patients was 35.2±12 years. Rheumatoid arthritis was diagnosed in 458(76%) patients, systemic lupus erythematosus in 42(7%) ankylosing spondylitis in 32(5.3%), mixed connective tissue disease in 22(3.6%) and scleroderma in 12(2%) patients. CONCLUSIONS: Rheumatological disorders constitute a major disease burden in a relatively young population of patients. RA was the most common disorder seen in our clinic, as seen elsewhere also, followed by SLE, AS, MCTD, etc.

Application of non-ionic liquids-based modified dielectrics during electric discharge machining (EDM) of Ti6Al4V alloy to enhance machining efficiency and process optimization.

The non-conventional manufacturing technologies are notorious when it comes to productivity and processing time in production-related industries. However, the aerospace and other high-end sectors enjoy another quality matrix of these processes and compromise on the processing time. For instance, the machinability of hard-to-cut materials such as Ti6Al4V aerospace alloy for micro-impressions is challenging and commonly carried out through non-conventional processes. Among these processes, the electric discharge machining (EDM) is famous for machining Ti6Al4V. In the current study, the EDM process is enhanced through modified dielectrics such as kerosene with non-ionic liquids (span 20, 60, and 80) and cryogenically treated tool electrodes (aluminum and graphite), and is compared to the conventional kerosene-based process. A three-phase experimental campaign is deployed to explore parametric effects including modified dielectric conditions (non-ionic liquid type and concentration), tool material, and machine parameter pulse ON:OFF time. A total of 60 experiments (54 modified dielectrics and 6 as baseline) were performed to explore process physics. The statistical analyses show that the unmodified process (kerosene dielectric-based) results in the least favorable results 0.58 mm3/min against cryo-graphite and 1.2 mm3/min against cryo-aluminum electrodes. However, the modified dielectrics outperform and improve process dynamics by altering dielectric conditions through hydrophilic-lipophilic balance. Surface morphological analysis shows significantly shallow craters on the machined surface showing evidence of effective flushing through a modified dielectric (S-20) as compared to a kerosene-based dielectric. A thorough microscopical, statistical, and scanning electron-based analysis is carried out to explain the process and correlate significant improvements.

Insights into the Engineered Gold Nanoparticle-Based Remedy for Supplementation Therapy of Ovarian Carcinoma.

Chronic diseases, notably cancer, pose a significant global threat to human life. Oncologists and medical professionals addressing malignancies confront challenges such as toxicity and multidrug resistance. To tackle these issues, the focus has shifted toward the employment of multifunctional colloidal gold nanoparticles. This study aims to design pH-sensitive doxorubicin-loaded gold nanoparticles using polyvinylpyrrolidone. The cytotoxic efficacy of the designed gold nanoarchitecture and its doxorubicin counterpart was assessed in an in vitro model using the HeLa cell. In comparison to the free drug, experimental evaluations showed that the gold nanoarchitecture outperformed significantly lower unspecific drug leaching and efficiently delivered the payload in a controlled manner, boosting the chemotherapy outcomes. This work opens a streamlined approach for engineering gold nanoarchitecture that could be further expanded to incorporate other therapeutics and/or functional moieties that require optimized controlled delivery, offering a one-size-fits-all solution and paving the revolutionary adjustments to healthcare procedures.

Turning trash into treasure: Torrefaction of mixed waste for improved fuel properties. A case study of metropolitan city.

Solid waste management is one of the biggest challenges of the current era. The combustible fractions in the waste stream turn out to be a good energy source if converted into refuse-derived fuel. Researchers worldwide are successfully converting it into fuel. However, certain challenges are associated with its application in gasifiers, boilers, etc. to co-fire it with coal. These include high moisture content, low calorific value, and difficulty to transport and store. The present study proposed torrefaction as a pretreatment of the waste by heating it in the range of 200 °C-300 °C in the absence of oxygen at atmospheric pressure. The combustible fraction from the waste stream consisting of wood, textile, paper, carton, and plastics termed as mixed waste was collected and torrefied at 225 °C, 250 °C, 275 °C, and 300 °C for 15 and 30 min each. It was observed that the mass yield and energy yield decreased to 45% and 62.96% respectively, but the energy yield tended to increase by the ratio of 1.39. Proximate analysis showed that the moisture content and volatile matter decreased for torrefied samples, whereas the ash content and fixed carbon content increased. Similarly, the elemental analysis revealed that the carbon content increased around 23% compared to raw samples with torrefaction contrary to hydrogen and oxygen, which decreased. Moreover, the higher heating value (HHV) of the torrefied samples increased around 1.3 times as compared to the raw sample. This pretreatment can serve as an effective solution to the current challenges and enhance refuse-derived fuel's fuel properties.

Platelet Count to Prothrombin Time: A Noninvasive Predictor of Esophageal Varices in Patients With Chronic Liver Disease.

Introduction Esophageal variceal bleeding is a potentially deadly consequence of portal hypertension in patients with cirrhosis. Although upper gastrointestinal endoscopy is still the preferred method for identifying esophageal varices (EV), the present study measured the platelet count to prothrombin time (PLT/PT) ratio for the assessment of portal hypertension and subsequent diagnosis of EVs in patients with chronic liver disease (CLD). Methods This was an observational comparative study conducted in the outpatient department of Patel Hospital, Karachi, Pakistan, using a non-probability consecutive sampling technique. Ethical approval was obtained from the Patel Hospital ethical review committee (PH/IRB/2022/028). An independent sample t-test was used for parametric data, whereas the Mann-Whitney U test was used for non-parametric data. The chi-square test was used to compare the categorical data of patients with and without EV. Receiver operating characteristic (ROC) analysis was performed to evaluate the cutoff values for the PLT/PT ratio, sensitivity, specificity, and area under the curve (AUC). Results The study involved 105 patients with and without EV. Among them, 38 (63.3%) males and 22 (36.7%) females had EV, whereas 30 (66.7%) males and 15 (33.3%) females did not. The platelet (PLT) count was also significantly lower in patients with EV (87.6 ± 59.8) than in those without (176.6 ± 87.7) (p < 0.001). The PLT/PT ratio was significantly lower in patients with EV (median: 5.04, IQR: 3.12-9.21) compared to those without (median: 14.57, IQR: 8.08-20.58) (p < 0.001). The sensitivity and specificity of the PLT/PT ratio for identifying EVs were 97.80% and 83.30%, respectively. Conclusion We found a significantly lower PLT/PT ratio in cases with EV than those without EV. After defining an optimal cutoff, PLT/PT had a high sensitivity in identifying cases with EVs in CLD. Therefore, we conclude that in patients with CLD, the PLT/PT ratio is a noninvasive predictor for the presence of EV.

Clinical spectrum and various forms of thyrotoxcosis in endocrine clinic of Jinnah Postgraduate Medical Centre.

OBJECTIVE: To evaluate clinical symptoms, signs and various forms of thyrotoxicosis, and to assess the thyroid function status at the first 6-week follow-up. METHODS: The retrospective chart review involved thyrotoxic patients presenting at the Endocrine Clinic of Jinnah Postgraduate Medical Centre, Karachi, between April 2007 and January 2011. All hyperthyroid patients were included with the exception of those with suspected or proven malignancy. The records were maintained on a structured proforma and analysed statistically to work out frequencies and percentages. RESULTS: A total of 507 patients were included. Most common form of thyrotoxicosis was Graves' disease, with diffuse toxic goiter affecting 269 (53%) patients; followed by toxic multinodular goiter in 102 (20.1%); solitary toxic nodule in 56 (11%); thyrotoxicosis without goiter in 44 (8.7%); subclinical hyperthyroidism in 22 (4.3.%); thyroiditis in 9 (1.8%); and thyrotoxicosis with solitary cold nodule in 4 (0.9%). The common presenting symptoms and signs were goiter (n=415; 85.7%), with eye signs present in 137 (27.7%) patients and heart failure in 20 (4.8%) patients. Of the 321 patients who attended the first six-week follow-up, 309 (94.4%) had their FT4 levels checked. Out of them, 130(42.1%) had euthyroid levels; 113 (36.6%) had lower but still toxic level; 36 (11.7%) had no change; and 30 (9.7%) became hypothyroid. TSH levels at first follow-up remained suppressed in 211 (73%) patients; normal in 47 (16.3%); and increased in 31 (10.7%). CONCLUSIONS: Graves' disease was found to be the most common cause of hyperthyroidism. At first follow-up 10.4% of patients had become hypothyroid. Therefore the starting dose of antithyroid drugs was reduced in the clinic. Thyroid stimulating hormone assay was of little help in adjusting treatment at the 6-week follow-up, as almost all cases of hypothyroidism could have been picked up on FT4 assay alone.

DC-AAE: Dual channel adversarial autoencoder with multitask learning for KL-grade classification in knee radiographs.

Knee osteoarthritis (OA) is a frequent musculoskeletal disorder that leads to physical disability in older adults. Manual OA assessment is performed via visual inspection, which is highly subjective as it suffers from moderate to high inter-observer variability. Many deep learning-based techniques have been proposed to address this issue. However, owing to the limited amount of labelled data, all existing solutions have limitations in terms of performance or the number of classes. This paper proposes a novel fully automatic Kellgren and Lawrence (KL) grade classification scheme in knee radiographs. We developed a semi-supervised multi-task learning-based approach that enables the exploitation of additional unlabelled data in an unsupervised as well as supervised manner. Specifically, we propose a dual-channel adversarial autoencoder, which is first trained in an unsupervised manner for reconstruction tasks only. To exploit the additional data in a supervised way, we propose a multi-task learning framework by introducing an auxiliary task. In particular, we use leg side identification as an auxiliary task, which allows the use of more datasets, e.g., CHECK dataset. The work demonstrates that the utilization of additional data can improve the primary task of KL-grade classification for which only limited labelled data is available. This semi-supervised learning essentially helps to improve the feature learning ability of our framework, which leads to improved performance for KL-grade classification. We rigorously evaluated our proposed model on the two largest publicly available datasets for various aspects, i.e., overall performance, the effect of additional unlabelled samples and auxiliary tasks, robustness analysis, and ablation study. The proposed model achieved the accuracy, precision, recall, and F1 score of 75.53%, 74.1%, 78.51%, and 75.34%, respectively. Furthermore, the experimental results show that the suggested model not only achieves state-of-the-art performance on two publicly available datasets but also exhibits remarkable robustness.

Predictive modelling framework on the basis of artificial neural network: A case of nano-powder mixed electric discharge machining.

In this modern era where Industry 4.0, plays a crucial role in enhancing productivity, quality, and resource utilization by digitalizing and providing smart operation to industrial systems. Therefore, there is a need to establish a framework that enhances productivity and quality of work to achieve the net-zero from industry. In this study, a comprehensive and generic analytical framework has been established to mitigate or lessen the research and technological gap in the manufacturing sector. In addition to that, the key stages involved in artificial intelligence (AI) based modelling and optimization analysis for manufacturing systems have also been incorporated. To assess the proposed AI framework, electric discharge machining (EDM) as a case study has been selected. The focus enlightens the emergence of optimizing the material removal rate (MRR) and surface roughness (SR) for Inconel 617 (IN617) material. A full factorial design of the experiment was carried out for experimentation. After that, an artificial neural network (ANN) as a modelling framework is selected, and fine-tuning of hyperparameters during training has been carried out. To validate the predictive performance of the trained models, an external validation (Valext) test has been conducted. Through sensitivity analysis (SA) on the developed AI framework, the most influential factors affecting MRR and SR in EDM have been identified. Specifically, powder concentration (Cp) contributes the most to the percentage significance, accounting for 79.00 % towards MRR, followed by treatment (16.35 %) and 4.67 % surfactant concentration (Sc). However, the highest % significance in SR is given by Sc (36.86 %), followed by Cp (33.23 %), and then treatment (29.90 %), respectively. Furthermore, a parametric optimization has been performed using the framework and found that MRR and SR are 93.75 % and 58.90 % better than experimental data. This successful performance optimization proposed by the framework has the potential for application to other manufacturing systems.

Residual attention based uncertainty-guided mean teacher model for semi-supervised breast masses segmentation in 2D ultrasonography.

Breast tumor is the second deadliest disease among women around the world. Earlier tumor diagnosis is extremely important for improving the survival rate. Recent deep-learning techniques proved helpful in the timely diagnosis of various tumors. However, in the case of breast tumors, the characteristics of the tumors, i.e., low visual contrast, unclear boundary, and diversity in shape and size of breast lesions, make it more challenging to design a highly efficient detection system. Additionally, the scarcity of publicly available labeled data is also a major hurdle in the development of highly accurate and robust deep-learning models for breast tumor detection. To overcome these issues, we propose residual-attention-based uncertainty-guided mean teacher framework which incorporates the residual and attention blocks. The residual for optimizing the deep network by enabling the flow of high-level features and attention modules improves the focus of the model by optimizing its weights during the learning process. We further explore the potential of utilizing unlabeled data during the training process by employing the semi-supervised learning (SSL) method. Particularly, the uncertainty-guided mean-teacher student architecture is exploited to demonstrate the potential of incorporating the unlabeled samples during the training of residual attention U-Net model. The proposed SSL framework has been rigorously evaluated on two publicly available labeled datasets, i.e., BUSI and UDIAT datasets. The quantitative as well as qualitative results demonstrate that the proposed framework achieved competitive performance with respect to the previous state-of-the-art techniques and outperform the existing breast ultrasound masses segmentation techniques. Most importantly, the study demonstrates the potential of incorporating the additional unlabeled data for improving the performance of breast tumor segmentation.