Search

The Dental Loop Chatbot was developed as a real-time, evidence-based guidance system for dental practitioners using a fine-tuned large language model (LLM) and Retrieval-Augmented Generation (RAG). This paper outlines the development and preliminary evaluation of the chatbot as a scalable clinical decision-support tool designed for resource-limited settings. The system’s architecture incorporates Quantized Low-Rank Adaptation (QLoRA) for efficient fine-tuning, while dynamic retrieval mechanisms ensure contextually accurate and relevant responses. This prototype lays the groundwork for future triaging and diagnostic support systems tailored specifically to the field of dentistry.

ABSTRACT To create and validate a transformer‐based deep neural network architecture for classifying 3D scans of teeth for computer‐assisted manufacturing and dental prosthetic rehabilitation surpassing previously reported validation accuracies obtained with convolutional neural networks (CNNs). Voxel‐based representation and encoding input data in a high‐dimensional space forms of preprocessing were investigated using 34 3D models of teeth obtained from intraoral scanning. Independent CNNs and vision transformers (ViTs), and their combination (CNN and ViT hybrid model) were implemented to classify the 3D scans directly from standard tessellation language (.stl) files and an Explainable AI (ExAI) model was generated to qualitatively explore the deterministic patterns that influenced the outcomes of the automation process. The results demonstrate that the CNN and ViT hybrid model architecture surpasses conventional supervised CNN, achieving a consistent validation accuracy of 90% through three‐fold cross‐validation. This process validated our initial findings, where each instance had the opportunity to be part of the validation set, ensuring it remained unseen during training. Furthermore, employing high‐dimensional encoding of input data solely with 3DCNN yields a validation accuracy of 80%. When voxel data preprocessing is utilized, ViT outperforms CNN, achieving validation accuracies of 80% and 50%, respectively. The study also highlighted the saliency map's ability to identify areas of tooth cavity preparation of restorative importance, that can theoretically enable more accurate 3D printed prosthetic outputs. The investigation introduced a CNN and ViT hybrid model for classification of 3D tooth models in digital dentistry, and it was the first to employ ExAI in the efforts to automate the process of dental computer‐assisted manufacturing.

Depressive illness, influenced by social, psychological, and biological factors, is a significant public health concern that necessitates accurate and prompt diagnosis for effective treatment. This study explores the multifaceted nature of depression by investigating its correlation with various social factors and employing machine learning, natural language processing, and explainable AI to analyze depression assessment scales. Data from a survey of 520 Bangladeshi university students, encompassing socio-personal and clinical questions, was utilized in this study. Eight machine learning algorithms with optimized hyperparameters were applied to evaluate eight depression assessment scales, identifying the most effective one. Additionally, ten machine learning models, including five BERT-based and two generative large language models, were tested using three prompting approaches and assessed across four categories of social factors: relationship dynamics, parental pressure, academic contentment, and exposure to violence. The results showed that support vector machines achieved a remarkable 99.14% accuracy with the PHQ9 scale. While considering the social factors, the stacking ensemble classifier demonstrated the best results. Among NLP approaches, BioBERT outperformed other BERT-based models with 90.34% accuracy when considering all social aspects. In prompting approaches, the Tree of Thought prompting on Claude Sonnet surpassed other prompting techniques with 75.00% accuracy. However, traditional machine learning models outshined NLP methods in tabular data analysis, with the stacking ensemble model achieving the highest accuracy of 97.88%. The interpretability of the top-performing classifier was ensured using LIME.

Alzheimer’s disease, characterized by progressive and irreversible deterioration of cognitive functions, represents a significant health concern, particularly among older adults, as it stands as the foremost cause of dementia. Despite its debilitating nature, early detection of Alzheimer’s disease holds considerable advantages for affected individuals. This study investigates machine-learning methodologies for the early diagnosis of Alzheimer’s disease, utilizing datasets sourced from OASIS and ADNI. The initial classification methods consist of a 5-class ADNI classification and a 3-class OASIS classification. Three unique methodologies encompass binary-class inter-dataset models, which involve training on a single dataset and subsequently testing on another dataset for both ADNI and OASIS datasets. Additionally, a hybrid dataset model is also considered. The proposed methodology entails the concatenation of both datasets, followed by shuffling and subsequently conducting training and testing on the amalgamated dataset. The findings demonstrate impressive levels of accuracy, as Light Gradient Boosting Machine (LGBM) achieved a 99.63% accuracy rate for 5-class ADNI classification and a 95.75% accuracy rate by Multilayer Perceptron (MLP) for 3-class OASIS classification, both when hyperparameter tweaking was implemented. The K-nearest neighbor algorithm demonstrated exceptional performance, achieving an accuracy of 87.50% in ADNI-OASIS (2 Class) when utilizing the Select K Best method. The Gaussian Naive Bayes algorithm demonstrated exceptional performance in the OASIS-ADNI approach, attaining an accuracy of 77.97% using Chi-squared feature selection. The accuracy achieved by the Hybrid method, which utilized LGBM with hyperparameter optimization, was 99.21%. Furthermore, the utilization of Explainable AI approaches, particularly Lime, was implemented in order to augment the interpretability of the model.

This study aimed to evaluate the hematoprotective effects of eugenol against iron overload in male rats. A total of 30 rats were randomly divided into six equal groups as follows: the control negative (C-) group I.P injection distal water. The control positive (C+) group received iron dextran (100 mg/kg-BW) I.P injection. The IE1 and IE2 groups received iron dextran 100 mg/kg-BW I.P and eugenol (50,100 mg/kg-BW) orally, respectively, and the E3 and E4 groups received eugenol (50,100 mg/kg-BW) orally. After 30 days of the experiment, the blood was collected to measure the experimental parameters. The results demonstrated a significant increase in RBCs, Hb percentage, WBCs, PCV, and PTL in the C+ group compared to the C- group. Also, there was a non-significant difference between IE1 and C+ in RBCs and Hb. Meanwhile, PCV decreased significantly in IE1 compared with C+. Conversely, the C+ group showed decreased MCV compared with IE1. Microscopic examination of blood smears indicated normal red blood cell morphology in the C- and iron dextran with eugenol-treated groups, while the C+ group exhibited microcytic hypochromic morphology. In conclusion, the ameliorative effect of eugenol against iron overload-induced hematotoxicity is achieved by restoring the hematological parameters near the normal control.

Abstract This study aimed to estimate human age and gender from panoramic radiographs using various deep learning techniques while using explainability to have a novel hybrid unsupervised model explain the decision-making process. The classification task involved training neural networks and vision transformers on 706 panoramic radiographs using different loss functions and backbone architectures namely ArcFace, a triplet network named TriplePENViT, and the subsequently developed model called PENViT. Pseudo labeling techniques were applied to train the models using unlabeled data. FullGrad Explainable AI was used to gain insights into the decision-making process of the developed PENViT model. The ViT Large 32 model achieved a validation accuracy of 68.21% without ArcFace, demonstrating its effectiveness in the classification task. The PENViT model outperformed other backbones, achieving the same validation accuracy without ArcFace and an improved accuracy of 70.54% with ArcFace. The TriplePENViT model achieved a validation accuracy of 67.44% using hard triplet mining techniques. Pseudo labeling techniques yielded poor performance, with a validation accuracy of 64.34%. Validation accuracy without ArcFace was established at 67.44% for Age and 84.49% for gender. The unsupervised model considered developing tooth buds, tooth proximity and mandibular shape for estimating age within deciduous and mixed dentitions. For ages 20–29, it factored permanent dentition, alveolar bone density, root apices, and third molars. Above 30, it notes occlusal deformity resulting from missing dentition and the temporomandibular joint complex as predictors for age estimation from panoramic radiographs. Graphical abstract

Life satisfaction is a crucial facet of human well-being. Hence, research on life satisfaction is incumbent for understanding how individuals experience their lives and influencing interventions targeted at enhancing mental health and well-being. Life satisfaction has traditionally been measured using analog, complicated, and frequently error-prone methods. These methods raise questions concerning validation and propagation. However, this study demonstrates the potential for machine learning algorithms to predict life satisfaction with a high accuracy of 93.80% and a 73.00% macro F1-score. The dataset comes from a government survey of 19000 people aged 16-64 years in Denmark. Using feature learning techniques, 27 significant questions for assessing contentment were extracted, making the study highly reproducible, simple, and easily interpretable. Furthermore, clinical and biomedical large language models (LLMs) were explored for predicting life satisfaction by converting tabular data into natural language sentences through mapping and adding meaningful counterparts, achieving an accuracy of 93.74% and macro F1-score of 73.21%. It was found that life satisfaction prediction is more closely related to the biomedical domain than the clinical domain. Ablation studies were also conducted to understand the impact of data resampling and feature selection techniques on model performance. Moreover, the correlation between primary determinants with different age brackets was analyzed, and it was found that health condition is the most important determinant across all ages. The best performing Machine Learning model trained in this study is deployed on a public server, ensuring unrestricted usage of the model. We highlight the advantages of machine learning methods for predicting life satisfaction and the significance of XAI for interpreting and validating these predictions. This study demonstrates how machine learning, large language models and XAI can jointly contribute to building trust and understanding in using AI to investigate human behavior, with significant ramifications for academics and professionals working to quantify and comprehend subjective well-being.

The current study aimed to implement and validate an automation system to detect carious lesions from smartphone images using different one-stage deep learning techniques. 233 images of carious lesions were captured using a smartphone camera system at 1432 × 1375 pixels, then classified and screened according to a visual caries classification index. Following data augmentation, the YOLO v5 model for object detection was used. After training the model with 1452 images at 640 × 588 pixel resolution, which included the ones that were created via image augmentation, a discrimination experiment was performed. Diagnostic indicators such as true positive, true negative, false positive, false negative, and mean average precision were used to analyze object detection performance and segmentation of systems. YOLO v5X and YOLO v5M models achieved superior performance over the other models on the same dataset. YOLO v5X’s mAP was 0.727, precision was 0.731, and recall was 0.729, which was higher than other models of YOLO v5, which generated 64% accuracy, with YOLO v5M producing slightly inferior results. Overall mAPs of 0.70, precision of 0.712, and recall of 0.708 were achieved. Object detection through the current YOLO models was able to successfully extract and classify regions of carious lesions from smartphone photographs of in vitro tooth specimens with reasonable accuracy. YOLO v5M was better fit to detect carious microcavitations while YOLO v5X was able to detect carious changes without cavitation. No single model was capable of adequately diagnosing all classifications of carious lesions.

In this research, a novel optimized Proportional-Derivative with Proportional-Integral-Derivative-Acceleration (PD-PIDA) driven static synchronous compensator (STATCOM) is proposed with the goal of improving the frequency performance of power systems through the manipulation of reactive power. When there is a variation in load or when there is a failure of generation, the presented controller is able to maintain the frequency of the system within the allowable limits (±2% as per IEC 60034–1 standard). A recently developed metaheuristic optimization strategy known as the Artificial Rabbits Optimizer, or ARO, is used to do the fine-tuning the PD-PIDA controller’s gain settings. In addition to this, the functionality of the ARO-based PD-PIDA-controlled STATCOM is evaluated in the context of two IEEE standard systems: the two-area four-machine system (Kundur system) and the New England IEEE 39-bus system. According to the outcomes, the ARO-based PD-PIDA controller can give a superior frequency response than the PIDA controller whose parameters are optimized by Marine Predator Algorithm (MPA) that was published in the prior literature. This was determined by comparing the two controllers. In addition, the proposed controller’s resiliency is tested by integrating case studies with wind generation. This helps to ensure that the controller is fit for purpose. In every single one of the examples that were researched, the application of the ARO-based PD-PIDA-controlled STATCOM resulted in a remarkable boost in the frequency performance. Additionally, the outputs are introduced in the form of time domain simulations that were carried out with MATLAB/SIMULINK.

This article presents a unique controller combining fuzzy proportional-integral (PI) and fractional-order proportional-fractional filtered derivative action (FOPDF $^ {\lambda } $ ) with the intention of improving the frequency performance of a hybrid interconnected dual-area power grid incorporating a unified power flow controller (UPFC) and superconducting magnetic energy storage (SMES) devices in the two regions. In the proposed fuzzy PI-FOPDF $^ {\lambda } $ controller, the positive aspects of fuzzy logic control (FLC), PI, and FOPD regulators, as well as the added flexibility afforded by fractional calculus for the derivative filter, have all been incorporated. The authors used a recently developed metaheuristic optimization strategy (i.e., the Zebra Optimization Algorithm, or ZOA) to fine-tune the suggested controller parameters for the two-area hybrid power grids studied in this paper. The system model depicts physical constraints, such as the reheat turbine and the generation rate constraint (GRC). The superiority of ZOA is demonstrated by comparing its results to those of the recently developed optimizations Osprey Optimization Algorithm (OOA) and Jellyfish Search Optimizer (JSO). By comparing the performance of the proposed ZOA-based fuzzy PI-FOPDF $^ {\lambda } $ controller to that of existing ZOA-tuned fuzzy-based controllers (such as fuzzy PIDF and fuzzy PIDD2), it has been demonstrated that the proposed controller is more effective. In order to achieve higher levels of system stability and validate the robustness of the proposed fuzzy PI-FOPDF $^ {\lambda } $ controller, various load patterns were applied to the investigated power system. Step load fluctuation (SLF), pulse load fluctuation (PLF), and sinusoidal wave load fluctuation (SWLF) were among these load patterns. In addition, non-conventional sources such as wind turbines and solar photovoltaic (PV) units have been incorporated into the power system. In addition, a test scenario has been developed to demonstrate how the SMES and UPFC units enhance the overall efficacy of the system. MATLAB simulation results indicate that the proposed fuzzy PI-FOPDF $^ {\lambda } $ controller, which is based on the ZOA, has the potential to enhance system stability despite the aforementioned challenges.

Deep learning techniques have recently demonstrated remarkable success in numerous domains. Typically, the success of these deep learning models is measured in terms of performance metrics such as accuracy and mean average precision (mAP). Generally, a model's high performance is highly valued, but it frequently comes at the expense of substantial energy costs and carbon footprint emissions during the model building step. Massive emission of CO2 has a deleterious impact on life on earth in general and is a serious ethical concern that is largely ignored in deep learning research. In this article, we mainly focus on environmental costs and the means of mitigating carbon footprints in deep learning models, with a particular focus on models created using knowledge distillation (KD). Deep learning models typically contain a large number of parameters, resulting in a 'heavy' model. A heavy model scores high on performance metrics but is incompatible with mobile and edge computing devices. Model compression techniques such as knowledge distillation enable the creation of lightweight, deployable models for these low-resource devices. KD generates lighter models and typically performs with slightly less accuracy than the heavier teacher model (model accuracy by the teacher model on CIFAR 10, CIFAR 100, and TinyImageNet is 95.04%, 76.03%, and 63.39%; model accuracy by KD is 91.78%, 69.7%, and 60.49%). Although the distillation process makes models deployable on low-resource devices, they were found to consume an exorbitant amount of energy and have a substantial carbon footprint (15.8, 17.9, and 13.5 times more carbon compared to the corresponding teacher model). The enormous environmental cost is primarily attributable to the tuning of the hyperparameter, Temperature (τ). In this article, we propose measuring the environmental costs of deep learning work (in terms of GFLOPS in millions, energy consumption in kWh, and CO2 equivalent in grams). In order to create lightweight models with low environmental costs, we propose a straightforward yet effective method for selecting a hyperparameter (τ) using a stochastic approach for each training batch fed into the models. We applied knowledge distillation (including its data-free variant) to problems involving image classification and object detection. To evaluate the robustness of our method, we ran experiments on various datasets (CIFAR 10, CIFAR 100, Tiny ImageNet, and PASCAL VOC) and models (ResNet18, MobileNetV2, Wrn-40-2). Our novel approach reduces the environmental costs by a large margin by eliminating the requirement of expensive hyperparameter tuning without sacrificing performance. Empirical results on the CIFAR 10 dataset show that the stochastic technique achieves an accuracy of 91.67%, whereas tuning achieves an accuracy of 91.78%-however, the stochastic approach reduces the energy consumption and CO2 equivalent each by a factor of 19. Similar results have been obtained with CIFAR 100 and TinyImageNet dataset. This pattern is also observed in object detection classification on the PASCAL VOC dataset, where the tuning technique performs similarly to the stochastic technique, with a difference of 0.03% mAP favoring the stochastic technique while reducing the energy consumptions and CO2 emission each by a factor of 18.5.

Sign Language provides the means of conveying messages for hearing impaired people. Effective communication with the masses is a great challenge for the hearing impaired community, as Sign Language is not commonly understood. Many researchers have done numerous works in foreign language datasets like English, French, Japanese, etc. However, for Bangla, one of the most widely spoken languages, much significant work has not been done yet. Most of the works on Bangla Sign Language are executed on small datasets and report satisfactory performance. However, when small datasets are evaluated from the perspective of generalizability, particularly when using deep learning based solutions, these models fail to reproduce to the same performance. Therefore, this paper poses inter-dataset evaluation as the main evaluation criteria and evaluates several deep learning based models. This evaluation is done for Bangla by leveraging two popular datasets of Bangla Sign Language. Unsurprisingly, the inter-dataset performance is inferior, and several approaches to improve are explored and documented, including the use of angular margin based loss functions. The results demonstrate the importance of such an evaluation and also show that one of the proposed approaches shows promising performance, albeit with significant room for improvement. This raises the need for a standardized dataset to overcome this issue of generalization for real-life applications, as well as the need to encourage future works to concentrate on challenging evaluations instead of pursuing deceptively good intra-dataset performance.

Abstract Background Changes in Doppler flow patterns of hepatic veins (HV), portal vein (PV) and intra-renal veins (RV) reflect right atrial pressure and venous congestion; the feasibility of obtaining these assessments and the clinical relevance of the findings is unknown in a general ICU population. This study compares the morphology of HV, PV and RV waveform abnormalities in prediction of major adverse kidney events at 30 days (MAKE30) in critically ill patients. Study design and methods We conducted a prospective observational study enrolling adult patients within 24 h of admission to the ICU. Patients underwent an ultrasound evaluation of the HV, PV and RV. We compared the rate of MAKE-30 events in patients with and without venous flow abnormalities in the hepatic, portal and intra-renal veins. The HV was considered abnormal if S to D wave reversal was present. The PV was considered abnormal if the portal pulsatility index (PPI) was greater than 30%. We also examined PPI as a continuous variable to assess whether small changes in portal vein flow was a clinically important marker of venous congestion. Results From January 2019 to June 2019, we enrolled 114 patients. HV abnormalities demonstrate an odds ratio of 4.0 (95% CI 1.4–11.2). PV as a dichotomous outcome is associated with an increased odds ratio of MAKE-30 but fails to reach statistical significance (OR 2.3 95% CI 0.87–5.96), but when examined as a continuous variable it demonstrates an odds ratio of 1.03 (95% CI 1.00–1.06). RV Doppler flow abnormalities are not associated with an increase in the rate of MAKE-30 Interpretation Obtaining hepatic, portal and renal venous Doppler assessments in critically ill ICU patients are feasible. Abnormalities in hepatic and portal venous Doppler are associated with an increase in MAKE-30. Further research is needed to determine if venous Doppler assessments can be useful measures in assessing right-sided venous congestion in critically ill patients.

Named Entity Recognition (NER) is a task in Natural Language Processing (NLP) that aims to classify words into a predetermined list of Named Entities (NE). Many architectures have produced good results on high resourced languages like English and Chinese. However, the NER task has not yet achieved much progress for Bangla, a low resource Language. In this paper, we perform the NER task on Bangla Language using Word2Vec and contextual Bidirectional Encoder Representations from Transformers (BERT) embeddings. We propose multiple BERT-based deep learning models that use the contextualized embedding from BERT as inputs and a simple statistical approach for class weight cost sensitive learning. The modified cost-sensitive loss function was used to address the class imbalance of the data. In our modified cost-sensitive loss function, we penalize the dominant classes by taking the ratio concerning the maximum sample in a class instead of the whole dataset. This penalty is made so that the learner learns slowly for the dominant class. In addition, we experiment by adding a Conditional Random Field (CRF) layer and incorporating Focal Loss to the training process. We found the best F1 Macro score to be 65.96%, F1 Micro score of 90.64%, and F1 Message Understanding Coreference (MUC) score of 72.04%, which were calculated at Named Entity level. Our experimental results demonstrate that one of the proposed models, which jointly optimizes for the CRF loss and class weighted cost-sensitive loss according to our proposed statistical approach, achieve an improvement of over 8% F1 MUC score on a recently introduced Bangla NER dataset when compared to previously published work.

The goal of this study is to determine the elements that contribute to the profitability of commercial banks in Saudi Arabia. The study is important due to the fact that Saudi vision 2030 foresees Saudi Arabia as a global investment powerhouse and fulfilling this objective requires a profitable banking sector. The method chosen for the study is multiple regression analysis. The sample data is taken for the period ranging 2009 and 2015 for the 12 local banks. The research concludes that bank’s internal factors specifically, bank size, liquidity, credit risk and operational efficiency are significantly determining the profitability in the banks as compared to the economy’s macro-economic variables.

Purpose: During fracture fixation, the size of tibial nail is a vital factor affecting the outcomes and thus preoperative estimation of tibial nail length is very important. This study aims to find out whether “olecranon to 5th metacarpal head” (O-MH) measurement can be used to reliably predict the tibial nail length. Methods: This was a cross sectional study involving 100 volunteers. Measurements were done and recorded by two observers on two separate occasions. Tibial nail length estimation measurement was done from highest point of tibial tuberosity to the tip of the medial malleolus (TT-MM). O-MH measurement was taken from tip of olecranon to the tip of 5th metacarpal head with wrist in neutral position and hand clenched. Statistical analysis was done to find out correlation between two measurements and influence of age, gender and body mass index on them. Results: Paired t-test showed no systematic error between the readings. Intraclass correlation coefficient showed strong agreement in inter and intra observer settings. Strong correlation was found between the TT-MM & O-MH measurements using Pearson's correlation coefficient test (r = 0.966). Hierarchical regression analysis showed age, gender and BMI have no statistically significant bearings on these measurements and their correlations. Conclusion: O-MH measurement is a useful and accurate means of estimating tibial nail length preoperatively. Keywords: Tibial nail length, Olecranon, 5th metacarpal head, Correlation, Accurate estimation

BanglaLekha-Isolated, a Bangla handwritten isolated character dataset is presented in this article. This dataset contains 84 different characters comprising of 50 Bangla basic characters, 10 Bangla numerals and 24 selected compound characters. 2000 handwriting samples for each of the 84 characters were collected, digitized and pre-processed. After discarding mistakes and scribbles, 1,66,105 handwritten character images were included in the final dataset. The dataset also includes labels indicating the age and the gender of the subjects from whom the samples were collected. This dataset could be used not only for optical handwriting recognition research but also to explore the influence of gender and age on handwriting. The dataset is publicly available at https://data.mendeley.com/datasets/hf6sf8zrkc/2.

The emergence of biometric-based authentication using modern sensors on electronic devices has led to an escalated use of face recognition technologies. While these technologies may seem intriguing, they are accompanied by numerous implicit drawbacks. In this paper, we look into the problem of face anti-spoofing (FAS) on a frame level in an attempt to ameliorate the risks of face-spoofed attacks in biometric authentication processes. We employed a bi-directional feature pyramid network (BiFPN) that is used for convolutional multi-scaled feature extraction on the EfficientDet detection architecture, which is novel to the task of FAS. We further use these convolutional multi-scaled features in order to perform deep pixel-wise supervision. For all of our experiments, we performed evaluations across all major datasets and attained competitive results for the majority of the cases. Additionally, we showed that introducing an auxiliary self-supervision branch tasked with reconstructing the inputs in the frequency domain demonstrates an average classification error rate (ACER) of 2.92% on Protocol IV of the OULU-NPU dataset, which is significantly better than the currently available published works on pixel-wise face anti-spoofing. Moreover, following the procedures of prior works, we performed inter-dataset testing, which further consolidated the generalizability of the proposed models, as they showed optimum results across various sensors without any fine-tuning procedures.

Speaker identification is gaining popularity, with notable applications in security, automation, and authentication. For speaker identification, deep-convolutional-network-based approaches, such as SincNet, are used as an alternative to i-vectors. Convolution performed by parameterized sinc functions in SincNet demonstrated superior results in this area. This system optimizes softmax loss, which is integrated in the classification layer that is responsible for making predictions. Since the nature of this loss is only to increase interclass distance, it is not always an optimal design choice for biometric-authentication tasks such as face and speaker recognition. To overcome the aforementioned issues, this study proposes a family of models that improve upon the state-of-the-art SincNet model. Proposed models AF-SincNet, Ensemble-SincNet, and ALL-SincNet serve as a potential successor to the successful SincNet model. The proposed models are compared on a number of speaker-recognition datasets, such as TIMIT and LibriSpeech, with their own unique challenges. Performance improvements are demonstrated compared to competitive baselines. In interdataset evaluation, the best reported model not only consistently outperformed the baselines and current prior models, but also generalized well on unseen and diverse tasks such as Bengali speaker recognition.

Malaria is a life-threatening disease that is spread by the Plasmodium parasites. It is detected by trained microscopists who analyze microscopic blood smear images. Modern deep learning techniques may be used to do this analysis automatically. The need for the trained personnel can be greatly reduced with the development of an automatic accurate and efficient model. In this article, we propose an entirely automated Convolutional Neural Network (CNN) based model for the diagnosis of malaria from the microscopic blood smear images. A variety of techniques including knowledge distillation, data augmentation, Autoencoder, feature extraction by a CNN model and classified by Support Vector Machine (SVM) or K-Nearest Neighbors (KNN) are performed under three training procedures named general training, distillation training and autoencoder training to optimize and improve the model accuracy and inference performance. Our deep learning-based model can detect malarial parasites from microscopic images with an accuracy of 99.23% while requiring just over 4600 floating point operations. For practical validation of model efficiency, we have deployed the miniaturized model in different mobile phones and a server-backed web application. Data gathered from these environments show that the model can be used to perform inference under 1 s per sample in both offline (mobile only) and online (web application) mode, thus engendering confidence that such models may be deployed for efficient practical inferential systems.

Introduction: Rotational malalignment after intramedullary fixation of fractures of the shaft of femur and tibia has been assessed by many studies but less frequently after intramedullary fixation of intertrochanteric fractures. Intertrochanteric fractures are managed by closed reduction in a traction table and fixation either by dynamic hip screw or proximal femoral nail under image intensifier. Reduction is checked intraoperatively by antero-posterior and lateral views with image intensifier in which rotational alignment cannot be assessed. Aim: To study the rotational malalignment in the operated limb compared to normal limb by computed tomography (CT). Materials and Methods: A prospective study was conducted on 70 patients at Kasturba Medical College and allied hospitals with intertrochanteric fractures with intramedullary fixation and with normal anatomy on opposite side. Postoperative CT with pelvis and knee was done and compared for rotational alignment. Results: The mean anteversion on the normal side was 13.20. The mean anteversion on the operated side was 15.70. The mean rotational malalignment was 9.70; there was internal rotational deformity in 41 cases (58.6%) and external rotational deformity in 29 cases (41.4%) with Grade III malrotation in 17 (24.3%) cases. Conclusion: Rotational malalignment postoperatively is frequently present and needs to be corrected intraoperatively by improving assessment methods.

Introduction: Correct length of the femoral tunnel is required for adequate length of graft inside the femoral canal. Length of femoral tunnel depends on mass, height, dimensions of lateral femoral condyle and amount of flexion of knee intraoperatively. Increasing weight and BMI affects the length of femoral canal since they affect positioning of limb in maximal knee flexion. Aim: To measure tunnel length in independent femoral tunnel drilling using the medial portal and to correlate the tunnel length with anthropometric data (height, weight, BMI of patient) and with width and depth of Lateral Femoral Condyle (LFC) based on MRI. Materials and Methods: The present prospective study including 40 patients were conducted. Participants were selected by a non-random convenience sampling methodology. Complete details of patients were collected by verbal communication with the patients and their attendees, clinical examination, baseline investigations, radiological investigations and surgical findings. Radiological investigations included preoperative assessment of LFC in MRI. Surgical findings were determined by measuring the femoral tunnel length after initial drilling through the medial portal using a depth gauge placed through the medial portal. SPSS version 17.0 was used for data analysis. Results: A total of 40 patients, 30 males and 10 females were included. Mean BMI was 24.22 kg/m2 with the range of 18 to 30. Mean width of LFC was 32.9 mm with range of 26.2 mm to 37.3 mm and depth of LFC was 58.79 with range of 50.7 mm to 66.2 mm. Mean femoral tunnel length was 38.4 mm with range from 32 mm to 44 mm. Conclusion: Average femoral tunnel length in Anterior Cruciate Ligament (ACL) reconstruction was 38.4 mm for assessed 40 patients. This correlated positively with height and weight of the patient. It also correlated positively with the width (p=0.027) and depth (p=0.029) of lateral femoral condyle.

A numerical study of the two-dimensional steady free convection flow in an inclined annulus between two concentric square cavities filled with a porous medium is presented in this paper for the case when the side outer walls are kept with differentially heated temperature while the horizontal outer walls and the inner walls are insulated. The heated wall is assumed to have spatial sinusoidal temperature variation about a constant mean value. The Darcy model is used and the fluid is assumed to be a standard Boussinesq fluid. For the Cartesian coordinate system, the governing equations which were used in stream function form are discretized by using the finite difference method with successive under relaxation method (SUR) and are solved by Gauss-Siedel iterative method. The upwind scheme was used for the transport terms in the energy conservation equation. The results are presented to demonstrate the streamlines, the isotherms, and the Nusselt number depending on the Rayleigh number ranging from (Ra =10 to 1000), dimension ratio from (Dr = 0.15 to 0.45), and the inclination angle from ( = 0o to 45o). Also the effects of the amplitude ( =0 to 1) and the wave number (f =0 to 5) of the heated side wall temperature variation on the free convection are investigated. The results show the effect of previous parameters (Ra, Dr, , , and f) on the flow fields and temperature profiles. It also show that the average Nusselt number is a strong function of the Rayleigh number, inclination angle, dimension ratio, and temperature variation. The peak value of the average Nusselt number based on the hot wall temperature is observed to occur at dimension ratio of (0.15), inclination angle of (40.1°), amplitude and wave number (1 & 0.75) for Rayleigh number of (1000).

In this investigation, steady two – dimensional natural convection heattransfer of Newtonian and non-Newtonian fluids inside square enclosure has beenanalyzed numerically for a wide range of the modified Rayleigh number of (103 ≤Ra ≤ 105), with non-dimensional parameter(NE) of Prandtl – Eyring model rangingfrom (0 to 10), and modified Prandtl number in the range (Pr* =1,10, and 100).Two types of boundary conditions have been considered. The first,is when the sidewalls are heated at different uniform temperatures and the horizontal walls areinsulated. The second, when the bottom wall is heated by applying a uniform heatflux while the other walls are at the constant cold temperature. Also, the non-Newtonian fluids under consideration were assumed to obey the Prandtl – Eyringmodel. The numerical results of the values of average Nusselt number have beenconfirmed by comparing them to similar known yeslts of previous works using thesame boundary conditions. Good agreement was obtained. The results arepresented in terms of isotherms and streamlines to show the behavior of the fluidflow and temperature fields. In addition, some graphics represent the relationbetween average Nusselt number and the parameters that are mentionedpreviously. The results show the effect of non – dimensional parameter (NE) on thevelocity and temperature profiles. It also shows that the average Nusselt number isa strong function of modified Rayleigh number, modified Prandtl number, nondimensionalparameter, and the boundary conditions. Four different correlationshave been made to show the dependence of the average Nusselt number on thenon-dimensional parameter, the modified Rayleigh and Prandtl numbers.