Explore the vast range of titles available.

Background Millions of patients around the world are affected by neurological and psychiatric disorders. Deep brain stimulation (DBS) is a device-based therapy that could have fewer side-effects and higher efficiencies in drug-resistant patients compared to other therapeutic options such as pharmacological approaches. Thus far, several efforts have been made to incorporate a feedback loop into DBS devices to make them operate in a closed-loop manner. Methods This paper presents a comprehensive investigation into the existing research-based and commercial closed-loop DBS devices. It describes a brief history of closed-loop DBS techniques, biomarkers and algorithms used for closing the feedback loop, components of the current research-based and commercial closed-loop DBS devices, and advancements and challenges in this field of research. This review also includes a comparison of the closed-loop DBS devices and provides the future directions of this area of research. Results Although we are in the early stages of the closed-loop DBS approach, there have been fruitful efforts in design and development of closed-loop DBS devices. To date, only one commercial closed-loop DBS device has been manufactured. However, this system does not have an intelligent and patient dependent control algorithm. A closed-loop DBS device requires a control algorithm to learn and optimize the stimulation parameters according to the brain clinical state. Conclusions The promising clinical effects of open-loop DBS have been demonstrated, indicating DBS as a pioneer technology and treatment option to serve neurological patients. However, like other commercial devices, DBS needs to be automated and modernized.

Advancements in materials science and fabrication techniques have contributed to the significant growing attention to a wide variety of sensors for digital healthcare. While the progress in this area is tremendously impressive, few wearable sensors with the capability of real-time blood pressure monitoring are approved for clinical use. One of the key obstacles in the further development of wearable sensors for medical applications is the lack of comprehensive technical evaluation of sensor materials against the expected clinical performance. Here, we present an extensive review and critical analysis of various materials applied in the design and fabrication of wearable sensors. In our unique transdisciplinary approach, we studied the fundamentals of blood pressure and examined its measuring modalities while focusing on their clinical use and sensing principles to identify material functionalities. Then, we carefully reviewed various categories of functional materials utilized in sensor building blocks allowing for comparative analysis of the performance of a wide range of materials throughout the sensor operational-life cycle. Not only this provides essential data to enhance the materials’ properties and optimize their performance, but also, it highlights new perspectives and provides suggestions to develop the next generation pressure sensors for clinical use.

In this article, we investigate fifth-order variable coefficient nonlinear Schro-dinger equation, which govern optical pulse in fiber optics and obtain soliton and breather solutions by applying Darboux transformation. Soliton and breather are responsible for data transmission over the long distance without loss of power. In optical fibers, control soliton and breather interactions have important application in signal processing and transmission. In solutions, With different values of coefficients of dispersion we obtain parabolic, cubic and periodical oscillating soliton. By controlling spectral parameter [lambda], we obtain different types of interactions like head on, overtaking and parallel on soliton. The effects of coefficients of dispersion and spectral parameter [lambda] on the pattern of breather also presented. Keywords: Soliton Interactions, Breather Interactions, Optical Soliton, Fiber Optics. AMS Subject Classification: 35C08, 35P30.

The advent of 3D printing has transformed manufacturing. However, extending the library of materials to improve 3D printing quality remains a challenge. Defects can occur when printing parameters like print speed and temperature are chosen incorrectly. These can cause structural or dimensional issues in the final product. This review investigates closed‐loop artificial intelligence‐augmented additive manufacturing (AI2AM) technology that integrates AI‐based monitoring, automation, and optimization of printing parameters and processes. AI2AM uses AI to improve defect detection and prevention, improving additive manufacturing quality and efficiency. This article explores generic 3D printing processes and issues using existing research and developments. Next, it focuses on fused deposition modeling (FDM) printers and reviews their parameters and issues. The current remedies developed for defect detection and monitoring in FDM 3D printers are presented. Then, the article investigates AI‐based 3D printing monitoring, closed‐loop feedback systems, and parameter optimization development. Finally, closed‐loop 3D printing challenges and future directions are discussed. AI‐based systems detect and correct 3D printing failures, enabling current printers to operate within optimal conditions and minimizing the risk of defects or failures, which in turn leads to more sustainable manufacturing with minimum waste and extending the library of materials. This review delves into artificial intelligence (AI)‐augmented additive manufacturing, enhancing defect detection and closed‐loop optimization to boost manufacturing efficiency and quality. It presents AI's role in refining 3D printing parameters, tackling challenges in fused deposition modeling, and discusses prospective advancements for more sustainable and precise additive manufacturing.

Mechanically robust ferrogels with high self-healing ability might change the design of soft materials used in strain sensing. Herein, a robust, stretchable, magneto-responsive, notch insensitive, ionic conductive nanochitin ferrogel was fabricated with both autonomous self-healing and needed resilience for strain sensing application without the need for additional irreversible static chemical crosslinks. For this purpose, ferric (III) chloride hexahydrate and ferrous (II) chloride as the iron source were initially co-precipitated to create magnetic nanochitin and the co-precipitation was confirmed by FTIR and microscopic images. After that, the ferrogels were fabricated by graft copolymerisation of acrylic acid-g-starch with a monomer/starch weight ratio of 1.5. Ammonium persulfate and magnetic nanochitin were employed as the initiator and crosslinking/nano-reinforcing agents, respectively. The ensuing magnetic nanochitin ferrogel provided not only the ability to measure strain in real-time under external magnetic actuation but also the ability to heal itself without any external stimulus. The ferrogel may also be used as a stylus for a touch-screen device. Based on our findings, our research has promising implications for the rational design of multifunctional hydrogels, which might be used in applications such as flexible and soft strain sensors, health monitoring, and soft robotics.

In this paper, a highly sensitive graphene-based multiple-layer (BK7/Au/PtSe2/Graphene) coated surface plasmon resonance (SPR) biosensor is proposed for the rapid detection of the novel Coronavirus (COVID-19). The proposed sensor was modeled on the basis of the total internal reflection (TIR) technique for real-time detection of ligand-analyte immobilization in the sensing region. The refractive index (RI) of the sensing region is changed due to the interaction of different concentrations of the ligand-analyte, thus impacting surface plasmon polaritons (SPPs) excitation of the multi-layer sensor interface. The performance of the proposed sensor was numerically investigated by using the transfer matrix method (TMM) and the finite-difference time-domain (FDTD) method. The proposed SPR biosensor provides fast and accurate early-stage diagnosis of the COVID-19 virus, which is crucial in limiting the spread of the pandemic. In addition, the performance of the proposed sensor was investigated numerically with different ligand-analytes: (i) the monoclonal antibodies (mAbs) as ligand and the COVID-19 virus spike receptor-binding domain (RBD) as analyte, (ii) the virus spike RBD as ligand and the virus anti-spike protein (IgM, IgG) as analyte and (iii) the specific probe as ligand and the COVID-19 virus single-standard ribonucleic acid (RNA) as analyte. After the investigation, the sensitivity of the proposed sensor was found to provide 183.33°/refractive index unit (RIU) in SPR angle (θSPR) and 833.33THz/RIU in SPR frequency (SPRF) for detection of the COVID-19 virus spike RBD; the sensitivity obtained 153.85°/RIU in SPR angle and 726.50THz/RIU in SPRF for detection of the anti-spike protein, and finally, the sensitivity obtained 140.35°/RIU in SPR angle and 500THz/RIU in SPRF for detection of viral RNA. It was observed that whole virus spike RBD detection sensitivity is higher than that of the other two detection processes. Highly sensitive two-dimensional (2D) materials were used to achieve significant enhancement in the Goos-Hänchen (GH) shift detection sensitivity and plasmonic properties of the conventional SPR sensor. The proposed sensor successfully senses the COVID-19 virus and offers additional (1 + 0.55) × L times sensitivity owing to the added graphene layers. Besides, the performance of the proposed sensor was analyzed based on detection accuracy (DA), the figure of merit (FOM), signal-noise ratio (SNR), and quality factor (QF). Based on its performance analysis, it is expected that the proposed sensor may reduce lengthy procedures, false positive results, and clinical costs, compared to traditional sensors. The performance of the proposed sensor model was checked using the TMM algorithm and validated by the FDTD technique.

Building a reliable and precise model for disease classification and identifying abnormal sites can provide physicians assistance in their decision-making process. Deep learning based image analysis is a promising technique for enriching the decision making process, and accordingly strengthening patient care. This work presents a convolutional attention mapping deep learning model, Cardio-XAttentionNet, to classify and localize cardiomegaly effectively. We revisit the global average pooling (GAP) system and add a weighting term to develop a light and effective Attention Mapping Mechanism (AMM). The model enables the classification of cardiomegaly from chest X-rays through image-level classification and pixel-level localization only from image-level labels. We leverage some of the advanced ConvNet architectures as a backbone-model of the proposed attention mapping network to build Cardio-XAttentionNet. The proposed model is trained on ChestX-Ray14, which is a publicly accessible chest X-ray dataset. The best single model achieves an overall precision, recall, F-1 measure and area under curve (AUC) scores of 0.87, 0.85, 0.86 and 0.89, respectively, for the classification of the cardiomegaly. The results also demonstrate that the Cardio-XAttentionNet model well captures the cardiomegaly class information at image-level as well as localization at pixel-level on chest x-rays. A comparative analysis between the proposed AMM and existing GAP based models shows that the proposed model achieves a state-of-the-art performance on this dataset for cardiomegaly detection using a single model.

Defective PV panels reduce the efficiency of the whole PV string, causing loss of investment by decreasing its efficiency and lifetime. In this study, firstly, an isolated convolution neural model (ICNM) was prepared from scratch to classify the infrared images of PV panels based on their health, i.e., healthy, hotspot, and faulty. The ICNM occupies the least memory, and it also has the simplest architecture, lowest execution time, and an accuracy of 96% compared to transfer learned pre-trained ShuffleNet, GoogleNet, and SqueezeNet models. Afterward, ICNM, based on its advantages, is reused through transfer learning to classify the defects of PV panels into five classes, i.e., bird drop, single, patchwork, horizontally aligned string, and block with 97.62% testing accuracy. This proposed approach can identify and classify the PV panels based on their health and defects faster with high accuracy and occupies the least amount of the system’s memory, resulting in savings in the PV investment.

Pneumonia is a virulent disease that causes the death of millions of people around the world. Every year it kills more children than malaria, AIDS, and measles combined and it accounts for approximately one in five child-deaths worldwide. The invention of antibiotics and vaccines in the past century has notably increased the survival rate of Pneumonia patients. Currently, the primary challenge is to detect the disease at an early stage and determine its type to initiate the appropriate treatment. Usually, a trained physician or a radiologist undertakes the task of diagnosing Pneumonia by examining the patient’s chest X-ray. However, the number of such trained individuals is nominal when compared to the 450 million people who get affected by Pneumonia every year. Fortunately, this challenge can be met by introducing modern computers and improved Machine Learning techniques in Pneumonia diagnosis. Researchers have been trying to develop a method to automatically detect Pneumonia using machines by analyzing and the symptoms of the disease and chest radiographic images of the patients for the past two decades. However, with the development of cogent Deep Learning algorithms, the formation of such an automatic system is very much within the realms of possibility. In this paper, a novel diagnostic method has been proposed while using Image Processing and Deep Learning techniques that are based on chest X-ray images to detect Pneumonia. The method has been tested on a widely used chest radiography dataset, and the obtained results indicate that the model is very much potent to be employed in an automatic Pneumonia diagnosis scheme.

Object detection is a vital step in satellite imagery-based computer vision applications such as precision agriculture, urban planning and defense applications. In satellite imagery, object detection is a very complicated task due to various reasons including low pixel resolution of objects and detection of small objects in the large scale (a single satellite image taken by Digital Globe comprises over 240 million pixels) satellite images. Object detection in satellite images has many challenges such as class variations, multiple objects pose, high variance in object size, illumination and a dense background. This study aims to compare the performance of existing deep learning algorithms for object detection in satellite imagery. We created the dataset of satellite imagery to perform object detection using convolutional neural network-based frameworks such as faster RCNN (faster region-based convolutional neural network), YOLO (you only look once), SSD (single-shot detector) and SIMRDWN (satellite imagery multiscale rapid detection with windowed networks). In addition to that, we also performed an analysis of these approaches in terms of accuracy and speed using the developed dataset of satellite imagery. The results showed that SIMRDWN has an accuracy of 97% on high-resolution images, while Faster RCNN has an accuracy of 95.31% on the standard resolution (1000 × 600). YOLOv3 has an accuracy of 94.20% on standard resolution (416 × 416) while on the other hand SSD has an accuracy of 84.61% on standard resolution (300 × 300). When it comes to speed and efficiency, YOLO is the obvious leader. In real-time surveillance, SIMRDWN fails. When YOLO takes 170 to 190 milliseconds to perform a task, SIMRDWN takes 5 to 103 milliseconds.