IntroductionBiological Named Entity Recognition (BioNER) is a crucial preprocessing step for Bio-AI analysis.MethodsOur paper explores the field of Biomedical Named Entity Recognition (BioNER) by closely analysing two advanced models, SciSpaCy and BioBERT. We have made two distinct contributions: Initially, we thoroughly train these models using a wide range of biological datasets, allowing for a methodical assessment of their performance in many areas. We offer detailed evaluations using important parameters like F1 scores and processing speed to provide precise insights into the effectiveness of BioNER activities.ResultsFurthermore, our study provides significant recommendations for choosing tools that are customised to meet unique BioNER needs, thereby enhancing the efficiency of Named Entity Recognition in the field of biomedical research. Our work focuses on tackling the complex challenges involved in BioNER and enhancing our understanding of model performance.ConclusionThe goal of this research is to drive progress in this important field and enable more effective use of advanced data analysis tools for extracting valuable insights from biomedical literature.

Introduction Traditional feed-forward neural networks (FFNN) have been widely used in image processing, but their effectiveness can be limited. To address this, we develop two deep learning models based on FFNN: the deep backpropagation neural network classifier (DBPNN) and the deep radial basis function neural network classifier (DRBFNN), integrating convolutional layers for feature extraction. Methods We apply a training algorithm to the deep, dense layers of both classifiers, optimizing their layer structures for improved classification accuracy across various hyperspectral datasets. Testing is conducted on datasets including Indian Pine, University of Pavia, Kennedy Space Centre, and Salinas, validating the effectiveness of our approach in feature extraction and noise reduction. Results Our experiments demonstrate the superior performance of the DBPNN and DRBFNN classifiers compared to previous methods. We report enhanced classification accuracy, reduced mean square error, shorter training times, and fewer epochs required for convergence across all tested hyperspectral datasets. Conclusion The results underscore the efficacy of deep learning feed-forward classifiers in hyperspectral image processing. By leveraging convolutional layers, the DBPNN and DRBFNN models exhibit promising capabilities in feature extraction and noise reduction, surpassing the performance of conventional classifiers. These findings highlight the potential of our approach to advance hyperspectral image classification tasks.

Introduction Cancer is one of the most prevalent diseases from children to elderly adults. This will be deadly if not detected at an earlier stage of the cancerous cell formation, thereby increasing the mortality rate. One such cancer is colorectal cancer, caused due to abnormal growth in the rectum or colon. Early screening of colorectal cancer helps to identify these abnormal growth and can exterminate them before they turn into cancerous cells. Aim Therefore, this study aims to develop a robust and efficient classification system for colorectal cancer through Convolutional Neural Networks (CNNs) on histological images. Methods Despite challenges in optimizing model architectures, the improved CNN models like ResNet34 and EfficientNet34 could enhance Colorectal Cancer classification accuracy and efficiency, aiding doctors in early detection and diagnosis, ultimately leading to better patient outcomes. Results ResNet34 outperforms the EfficientNet34. Conclusion The results are compared with other models in the literature, and ResNet34 outperforms all the other models.

Background: The process of In Vitro Fertilization (IVF) involves collecting multiple samples of mature eggs that are fertilized with sperms in the IVF laboratory. They are eventually graded, and the most viable embryo out of all the samples is selected for transfer in the mother’s womb for a healthy pregnancy. Currently, the process of grading and selecting the healthiest embryo is performed by visual morphology, and manual records are maintained by embryologists. Objectives: Maintaining manual records makes the process very tedious, time-consuming, and error-prone. The absence of a universal grading leads to high subjectivity and low success rate of pregnancy. To improve the chances of pregnancy, multiple embryos are transferred in the womb elevating the risk of multiple pregnancies. In this paper, we propose a deep learning-based method to perform the automatic grading of the embryos using time series prediction with Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). Methods: CNN extracts the features of the images of embryos, and a sequence of such features is fed to LSTM for time series prediction, which gives the final grade. Results: Our model gave an ideal accuracy of 100% on training and validation. A comparison of obtained results is made with those obtained from a GRU model as well as other pre-trained models. Conclusion: The automated process is robust and eliminates subjectivity. The days-long hard work can now be replaced with our model, which gives the grading within 8 seconds with a GPU.

Objective:Preservation of patient’s medical information in health care industries under Medical Sensor Networks (MSN).Methods:This paper proposes a novel key management technique known as k- secure with FBKM, which generates a robust key to allow communication between sensors present in the Body Sensor Units (BSU) and Body Central Unit (BCU). This proposed work strengthens the FBKM technique which is placed between BCU and the point accessible to medical experts at a remote place in the overall health care monitoring environment.Results:The FBKM technique has proved its success in authentication and security by improving genuine acceptance rate, false rejection rate, and declining false acceptance rate.Conclusion:The k- secure with FBKM scheme enhances the performance of the existing FBKM scheme in Medical Sensor Networks.

Background: The upsurge of COVID-19 has received significant international contemplation considering its life-threatening ramifications. To ensure that the susceptible patients can be quarantined to control the spread of the disease during the incubation period of the coronavirus, it becomes imperative to automatically and non-invasively mass screen patients. The diagnosis using RT-PCR is arduous and time-consuming. Currently, the non-invasive mass screening of susceptible cases is being performed by utilizing the thermal screening technique. However, with the consumption of paracetamol, the symptoms of fever can be suppressed. Methods: A novel multi-modal approach has been proposed. Throat inflammation-based mass screening and early prediction followed by Chest X-Ray based diagnosis have been proposed. Depth-wise separable convolutions have been utilized by fine-tuning Xception Net and Mobile Net architectures. NADAM optimizer has been leveraged to promote faster convergence. Results: The proposed method achieved 91% accuracy on the throat inflammation identification task and 96% accuracy on chest radiography conducted on the dataset. Conclusion: Evaluation of the proposed method indicates promising results and henceforth validates its clinical reliability. The future direction could be working on a larger dataset in close collaboration with the medical fraternity.

Biomedical signals like ECG, EEG, EMG, EOG, ERG etc. and images such as ultrasound, MRI, CT, PET etc. are very much useful for assessing the wellbeing of a human being. In order to determine the abnormality in a particular organ or part of the body, physicians use these signals and images. Although, today's signal recorders and image scanners are of excellent resolution and quality, sometimes they fail to convey the actual scenario of the body part/ organ [1]. Soft computing and machine learning methods play important role in dealing with biomedical signals/ images and they have numerous applications like noise/ artifact removal from signals/ images, early detection of seizure/ cancer/ tumours, fusion of images for better diagnosis, classification of signals/ images and much more [2,3].

Background: The knowledge of biomechanics helps in predicting stresses in different parts of the knee joint during daily activities. Objective: The objective of this study is to evaluate the biomechanical parameters of the knee joint, such as contact pressure, contact area, and maximum compressive stress, at full extension position during the gait cycle. Methods: The three-dimensional finite element models of human knee joints are developed from magnetic resonance images (MRI) of multiple healthy subjects. The knee joints are subjected to an axial compressive force of 1150 N at full extension position. Results: The maximum compressive stresses on the medial and lateral tibial cartilages were 2.98±0.51 MPa and 2.57±0.53 MPa, respectively. The maximum compressive stresses on the medial and lateral menisci were 2.81±0.92 MPa and 2.52±0.97 MPa, respectively. The contact area estimated on medial and lateral tibial cartilages were 701±89 mm2 and 617±63 mm2, respectively. Conclusion: The results were validated using experimental and numerical results from literature and were found to be in good agreement. The magnitude of maximum compressive stress and the contact pressure was found to be higher at the medial portion of the cartilages as compared to that in the lateral portion of the cartilages. This study shows that the medial meniscus is more prone to tear under severe loading conditions, as the stresses in the medial meniscus are higher than that in the lateral meniscus. The total contact area in the medial tibial cartilage is larger than that in the lateral tibial cartilage.

Objective:Development of surgical instrument robot (MU-LapaRobot) for assisting in conventional laparoscopic surgery.Methods:A robot was designed based on instrument movement for a conventional procedure. The mechanism mimics and constrains manipulation movement through the wire-driven transmission. It is flexible for robot end-effector, which has a lightweight and small size. The usability of the robot is passive and active robot tasks with an interconnected driving system. Three main parts of the robot are robot end-effector, transmission, and a driving system.Results:On a robot platform, a parameter for setup is robot posture. The adjustment of robot position and projection of manipulation area is influenced by the accuracy of movement. To verify movement, command and exact movements are measured. Compensation with the control system is improved in order to improve the accuracy of the system.Conclusion:MU-LapaRobot provides surgical instrument manipulation by using wire-driven transmission with an effective system and requires less interference in the conventional operation.