Rice powder template for hausmannite Mn3O4 nanoparticles and its application to aqueous zinc ion battery.

In this study, a simple calcination route was adopted to prepare hausmannite Mn3O4 nanoparticles using rice powder as soft bio-template. Prepared Mn3O4 was characterized by Fourier Transform Infra-Red Spectroscopy (FTIR), Field Emission Scanning Electron Microscopy (FESEM), Energy Dispersive X-ray microanalysis (EDX), Powder X-Ray Diffraction (XRD), Transmission Electron Microscopy (TEM), Brunauer-Emmett-Teller (BET) and Solid state UV-Vis spectroscopic techniques. Mn-O stretching in tetrahedral site was confirmed by FTIR and Raman spectra. % of Mn and O content supported Mn3O4 formation. The crystallinity and grain size was found to be 68.76% and 16.43 nm, respectively; tetragonal crystal system was also cleared by XRD. TEM clarified the planes of crystal formed which supported the XRD results and BET demonstrated mesoporous nature of prepared Mn3O4 having low pore volume. Low optical band gap of 3.24 eV of prepared Mn3O4 nanoparticles indicated semiconductor property and was used as cathode material to fabricate CR-2032 coin cell of Aqueous Rechargeable Zinc Ion Battery (ARZIB). A reversible cyclic voltammogram (CV) showed good zinc ion storage performance. Low cell resistance was confirmed by Electrochemical Impedance Spectroscopy (EIS). The coin cell delivered high specific discharge capacity of 240.75 mAhg-1 at 0.1 Ag-1 current density. The coulombic efficiency was found to be 99.98%. It also delivered excellent capacity retention 94.45% and 64.81% after 300 and 1000 charge-discharge cycles, respectively. This work offers a facile and cost effective approach for preparing cathode material of ARZIBs.

Dual-core silver-coated plasmonic sensor modeling with machine learning.

Plasmonic sensors utilizing surface plasmon resonance (SPR) have emerged as powerful tools for sensitive and label-free detection across a wide range of applications. This study introduces a new dual-core silver-coated plasmonic sensor designed to significantly enhance sensitivity and resolution, making it particularly effective for precise analyte detection in complex environments. A key innovation of this sensor lies in its dual-core architecture, which achieves the highest wavelength sensitivity reported at 30,000 nm/RIU and resolution of 3.33 × 10 - 6 RIU, covering a broad refractive index (RI) range from 1.34 to 1.41. Furthermore, the integration of machine learning (ML) algorithms, including multiple-variable linear regression (MLR), support vector regression (SVR), and random forest regression (RFR), marks a significant advancement in sensor design. These algorithms enable dynamic adaptation and the extraction of data-driven insights, enhancing the sensor's performance in predicting confinement loss and wavelength across various analytes. The innovative combination of a dual-core design and ML integration positions this plasmonic sensor as a highly sensitive and versatile tool well-suited for advanced bio-sensing applications.

Multi-View Soft Attention-Based Model for the Classification of Lung Cancer-Associated Disabilities.

Background: The detection of lung nodules at their early stages may significantly enhance the survival rate and prevent progression to severe disability caused by advanced lung cancer, but it often requires manual and laborious efforts for radiologists, with limited success. To alleviate it, we propose a Multi-View Soft Attention-Based Convolutional Neural Network (MVSA-CNN) model for multi-class lung nodular classifications in three stages (benign, primary, and metastatic). Methods: Initially, patches from each nodule are extracted into three different views, each fed to our model to classify the malignancy. A dataset, namely the Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI), is used for training and testing. The 10-fold cross-validation approach was used on the database to assess the model's performance. Results: The experimental results suggest that MVSA-CNN outperforms other competing methods with 97.10% accuracy, 96.31% sensitivity, and 97.45% specificity. Conclusions: We hope the highly predictive performance of MVSA-CNN in lung nodule classification from lung Computed Tomography (CT) scans may facilitate more reliable diagnosis, thereby improving outcomes for individuals with disabilities who may experience disparities in healthcare access and quality.

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis.

The field of automated lung cancer diagnosis using Computed Tomography (CT) scans has been significantly advanced by the precise predictions offered by Convolutional Neural Network (CNN)-based classifiers. Critical areas of study include improving image quality, optimizing learning algorithms, and enhancing diagnostic accuracy. To facilitate a seamless transition from research laboratories to real-world applications, it is crucial to improve the technology's usability-a factor often neglected in current state-of-the-art research. Yet, current state-of-the-art research in this field frequently overlooks the need for expediting this process. This paper introduces Healthcare-As-A-Service (HAAS), an innovative concept inspired by Software-As-A-Service (SAAS) within the cloud computing paradigm. As a comprehensive lung cancer diagnosis service system, HAAS has the potential to reduce lung cancer mortality rates by providing early diagnosis opportunities to everyone. We present HAASNet, a cloud-compatible CNN that boasts an accuracy rate of 96.07%. By integrating HAASNet predictions with physio-symptomatic data from the Internet of Medical Things (IoMT), the proposed HAAS model generates accurate and reliable lung cancer diagnosis reports. Leveraging IoMT and cloud technology, the proposed service is globally accessible via the Internet, transcending geographic boundaries. This groundbreaking lung cancer diagnosis service achieves average precision, recall, and F1-scores of 96.47%, 95.39%, and 94.81%, respectively.

Jute Stick-Derived Cellulose-Based Hydrogel: Synthesis, Characterization, and Methylene Blue Removal from Aqueous Solution.

In this work, microcrystalline cellulose (MCC) was isolated from jute sticks and sodium carboxymethyl cellulose (Na-CMC) was synthesized from the isolated MCC. Na-CMC is an anionic derivative of microcrystalline cellulose. The microcrystalline cellulose-based hydrogel (MCCH) and Na-CMC-based hydrogel (Na-CMCH) were prepared by using epichlorohydrin (ECH) as a crosslinker by a chemical crosslinking method. The isolated MCC, synthesized Na-CMC, and corresponding hydrogels were characterized by Fourier transform infrared (FTIR), X-ray diffraction (XRD), scanning electronic microscopy (SEM), and energy dispersive spectroscopy (EDS) for functional groups, crystallinity, surface morphology, and composite elemental composition, respectively. Pseudo-first-order, pseudo-second-order, and Elovich models were used to investigate the adsorption kinetics. The pseudo-second-order one is favorable for both hydrogels. Freundlich, Langmuir, and Temkin adsorption isotherm models were investigated. MCCH follows the Freundlich model (R2 = 0.9967), and Na-CMCH follows the Langmuir isotherm model (R2 = 0.9974). The methylene blue (MB) dye adsorption capacities of ionic (Na-CMCH) and nonionic (MCCH) hydrogels in different contact times (up to 600 min), initial concentrations (10-50 ppm), and temperatures (298-318 K) were investigated and compared. The maximum adsorption capacity of MCCH and Na-CMCH was 23.73 and 196.46 mg/g, respectively, and the removal efficiency of MB was determined to be 26.93% for MCCH and 58.73% for Na-CMCH. The Na-CMCH efficiently removed the MB from aqueous solutions as well as spiked industrial wastewater. The Na-CMCH also remarkably efficiently reduced priority metal ions from an industrial effluent. An effort has been made to utilize inexpensive, readily available, and environmentally friendly waste materials (jute sticks) to synthesize valuable adsorbent materials.

A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models.

The brain tumor is one of the deadliest cancerous diseases and its severity has turned it to the leading cause of cancer related mortality. The treatment procedure of the brain tumor depends on the type, location and size of the tumor. Relying solely on human inspection for precise categorization can lead to inevitably dangerous situation. This manual diagnosis process can be improved and accelerated through an automated Computer Aided Diagnosis (CADx) system. In this article, a novel approach using two-stage feature ensemble of deep Convolutional Neural Networks (CNN) is proposed for precise and automatic classification of brain tumors. Three unique Magnetic Resonance Imaging (MRI) datasets and a dataset merging all the unique datasets are considered. The datasets contain three types of brain tumor (meningioma, glioma, pituitary) and normal brain images. From five pre-trained models and a proposed CNN model, the best models are chosen and concatenated in two stages for feature extraction. The best classifier is also chosen among five different classifiers based on accuracy. From the extracted features, most substantial features are selected using Principal Component Analysis (PCA) and fed into the classifier. The robustness of the proposed two stage ensemble model is analyzed using several performance metrics and three different experiments. Through the prominent performance, the proposed model is able to outperform other existing models attaining an average accuracy of 99.13% by optimization of the developed algorithms. Here, the individual accuracy for Dataset 1, Dataset 2, Dataset 3, and Merged Dataset is 99.67%, 98.16%, 99.76%, and 98.96% respectively. Finally a User Interface (UI) is created using the proposed model for real time validation.

Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification.

Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image's quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality recognition approach fuses feature from a Fuzzy convolutional neural network (fuzzy CNN) and a handcrafted feature extraction method. We implement the fuzzy layer in between the last max pooling and the fully connected layer of the multiple state-of-the-art CNN models to handle the uncertainty of information. Moreover, the fuzzy CNN uses Particle swarm optimization (PSO) as an optimizer. In addition, a novel Quantitative feature extraction machine (QFEM) extracts hand-crafted features from ultrasound images. Next, the proposed method uses different classifiers to predict the image quality. The classifiers categories ultrasound images into four types (normal, noisy, blurry, and distorted) instead of binary classification into good or poor-quality images. The results of the proposed method exhibit a significant performance in accuracy (99.62%), precision (99.62%), recall (99.61%), and f1-score (99.61%). This method will assist a physician in automatically rating informative ultrasound images with steadfast operation in real-time medical diagnosis.

Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor.

Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes are frequently employed for this purpose, which are now compacted into smart devices, e.g., smartphones. Since the use of smartphones is so widespread now-a-days, activity data acquisition for the HAR systems is a pressing need. In this article, we have conducted the smartphone sensor-based raw data collection, namely H-Activity, using an Android-OS-based application for accelerometer, gyroscope, and linear acceleration. Furthermore, a hybrid deep learning model is proposed, coupling convolutional neural network and long-short term memory network (CNN-LSTM), empowered by the self-attention algorithm to enhance the predictive capabilities of the system. In addition to our collected dataset (H-Activity), the model has been evaluated with some benchmark datasets, e.g., MHEALTH, and UCI-HAR to demonstrate the comparative performance of our model. When compared to other models, the proposed model has an accuracy of 99.93% using our collected H-Activity data, and 98.76% and 93.11% using data from MHEALTH and UCI-HAR databases respectively, indicating its efficacy in recognizing human activity recognition. We hope that our developed model could be applicable in the clinical settings and collected data could be useful for further research.

Localization and targeting of an unusual pyridine nucleotide transhydrogenase in Entamoeba histolytica.

Pyridine nucleotide transhydrogenase (PNT) catalyzes the direct transfer of a hydride-ion equivalent between NAD(H) and NADP(H) in bacteria and the mitochondria of eukaryotes. PNT was previously postulated to be localized to the highly divergent mitochondrion-related organelle, the mitosome, in the anaerobic/microaerophilic protozoan parasite Entamoeba histolytica based on the potential mitochondrion-targeting signal. However, our previous proteomic study of isolated phagosomes suggested that PNT is localized to organelles other than mitosomes. An immunofluorescence assay using anti-E. histolytica PNT (EhPNT) antibody raised against the NADH-binding domain showed a distribution to the membrane of numerous vesicles/vacuoles, including lysosomes and phagosomes. The domain(s) required for the trafficking of PNT to vesicles/vacuoles was examined by using amoeba transformants expressing a series of carboxyl-terminally truncated PNTs fused with green fluorescent protein or a hemagglutinin tag. All truncated PNTs failed to reach vesicles/vacuoles and were retained in the endoplasmic reticulum. These data indicate that the putative targeting signal is not sufficient for the trafficking of PNT to the vesicular/vacuolar compartments and that full-length PNT is necessary for correct transport. PNT displayed a smear of >120 kDa on SDS-PAGE gels. PNGase F and tunicamycin treatment, chemical degradation of carbohydrates, and heat treatment of PNT suggested that the apparent aberrant mobility of PNT is likely attributable to its hydrophobic nature. PNT that is compartmentalized to the acidic compartments is unprecedented in eukaryotes and may possess a unique physiological role in E. histolytica.

LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data.

Lung cancer, also known as pulmonary cancer, is one of the deadliest cancers, but yet curable if detected at the early stage. At present, the ambiguous features of the lung cancer nodule make the computer-aided automatic diagnosis a challenging task. To alleviate this, we present LungNet, a novel hybrid deep-convolutional neural network-based model, trained with CT scan and wearable sensor-based medical IoT (MIoT) data. LungNet consists of a unique 22-layers Convolutional Neural Network (CNN), which combines latent features that are learned from CT scan images and MIoT data to enhance the diagnostic accuracy of the system. Operated from a centralized server, the network has been trained with a balanced dataset having 525,000 images that can classify lung cancer into five classes with high accuracy (96.81%) and low false positive rate (3.35%), outperforming similar CNN-based classifiers. Moreover, it classifies the stage-1 and stage-2 lung cancers into 1A, 1B, 2A and 2B sub-classes with 91.6% accuracy and false positive rate of 7.25%. High predictive capability accompanied with sub-stage classification renders LungNet as a promising prospect in developing CNN-based automatic lung cancer diagnosis systems.

A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray images.

Coronavirus disease-19 (COVID-19) is a severe respiratory viral disease first reported in late 2019 that has spread worldwide. Although some wealthy countries have made significant progress in detecting and containing this disease, most underdeveloped countries are still struggling to identify COVID-19 cases in large populations. With the rising number of COVID-19 cases, there are often insufficient COVID-19 diagnostic kits and related resources in such countries. However, other basic diagnostic resources often do exist, which motivated us to develop Deep Learning models to assist clinicians and radiologists to provide prompt diagnostic support to the patients. In this study, we have developed a deep learning-based COVID-19 case detection model trained with a dataset consisting of chest CT scans and X-ray images. A modified ResNet50V2 architecture was employed as deep learning architecture in the proposed model. The dataset utilized to train the model was collected from various publicly available sources and included four class labels: confirmed COVID-19, normal controls and confirmed viral and bacterial pneumonia cases. The aggregated dataset was preprocessed through a sharpening filter before feeding the dataset into the proposed model. This model attained an accuracy of 96.452% for four-class cases (COVID-19/Normal/Bacterial pneumonia/Viral pneumonia), 97.242% for three-class cases (COVID-19/Normal/Bacterial pneumonia) and 98.954% for two-class cases (COVID-19/Viral pneumonia) using chest X-ray images. The model acquired a comprehensive accuracy of 99.012% for three-class cases (COVID-19/Normal/Community-acquired pneumonia) and 99.99% for two-class cases (Normal/COVID-19) using CT-scan images of the chest. This high accuracy presents a new and potentially important resource to enable radiologists to identify and rapidly diagnose COVID-19 cases with only basic but widely available equipment.

Analysis the significant risk factors on type 2 diabetes perspective of Bangladesh.

Millions of people in Bangladesh and the world have a metabolic disease named diabetes. It is also responsible for occurring different kinds of diseases such as heart attack, kidney disease, blindness and renal failure. Diabetes is a deadly, disabling disease whose risk is increasing at an alarming rate day by day perspective to Bangladesh. The detection process of diabetes is a tedious and multilayered task from some important risk factors. Like other diseases, Type2 diabetes also depends on some factors that are known as risk factors of Type2 diabetes. Risk factors are divided into four categories like Scio-economic condition, Habits, Family History and Hard Diseases etc. in proposed system. Initially 731 diabetes and non-diabetes patient's data have been collected from different diagnostic centers, pre-processed and clustered for identifying relevant and non-relevant data. Significant factors are discovered according to four categories. Next correlation is assessment among significant factors. Finally highly significant factors are discovered whose are directly or indirectly associated with type2 diabetes. Results indicate that Age, Area of Residence, Education Level, Social Status, Family Income, Expense, Tobacco, BMI, Family History, Physical Exercise and Hard Diseases have worst impact on Quality of Life (QoL) among all factors of type2 diabetes respectively.