Underwater Image Processing and Object Detection Based on Deep CNN MethodRead the full article
Journal of Sensors publishes research focused on all aspects of sensors, from their theory and design, to the applications of complete sensing devices.
Chief Editor, Professor Harith Ahmad, is currently the director of the Photonics Research Center, University of Malaya, Malaysia. His current research is in the exploration of various 2D and 3D nanomaterials for optoelectronics applications.
Latest ArticlesMore articles
Debonding Performance of CFRP-Strengthened Nanomaterial Concrete Beam Using Wavelet Packet Analysis
The carbon fiber reinforced polymer- (CFRP-) strengthened nanomaterial concrete beam (SNCB) has been increasingly attracting a widespread attention because of the advantages of using the excellent properties of nanomaterials to improve structural properties. An active sensing approach based on a piezoceramic transducer is developed to detect the interfacial debonding performance of CFRP-SNCB. A CFRP-SNCB specimen was fabricated and subjected to periodic loading test to initiate the debonding damage. Three piezoceramic smart aggregates (SAs) and three piezoceramic smart nanomaterial aggregates (SNAs) are embedded in the specimen and used as an actuator and sensor. Experiments show that the nanomaterial concrete becomes a good conduit for wave propagation due to the nucleation and filling effect of nanomaterial. The stress wave signal caused by the embedded SNAs is more sensitive to the debonding performance between CFRP and concrete than SA. The attenuation of stress wave caused by the increase of the severity of debonding damage can be clearly observed from the signals received from SAs and SNAs in the frequency domain analysis. The debonding cracking of the tension end region is earlier than the bond end region, which proves the starting point of structural debonding damage. Furthermore, the debonding state can be evaluated by wavelet packet analysis. The research results demonstrate that the proposed method has potentials to detect the interfacial debonding performance of CFRP-SNCB.
Schiff-Based Fluorescent-ON Sensor L Synthesis and Its Application for Selective Determination of Cerium in Aqueous Media
In the present study, a fluorescent sensor L for sensing of Ce3+ ion was designed and characterized by XRD, 1HNMR, and FTIR. Its fluorescence behavior towards metal ion was examined by fluorescence spectroscopy. Chelation-enhanced fluorescence was shown by the sensor L upon interaction with Ce3+ ion. This fluorescent sensor exhibits high sensitivity and selectivity towards Ce3+ ion in acetonitrile solution, forming 2 : 1 (L : M) complex as determined by Job’s plot. Association constant was found to be estimated from the Benesi-Hildebrand plot. No significant interference was observed in the presence of other studied alkali, alkaline, and transition metal ions. A rapid response was observed when employed for the determination of Ce3+ ion in spiked water samples with a limit of detection equal to .
Support Vector Regression-Based Recursive Ensemble Methodology for Confidence Interval Estimation in Blood Pressure Measurements
The monitors of oscillometry blood pressure measurements are generally utilized to measure blood pressure for many subjects at hospitals, homes, and office, and they are actively studied. These monitors usually provide a single blood pressure point, and they are not able to indicate the confidence interval of the measured quantity. In this paper, we propose a new technique using a recursive ensemble based on a support vector machine to estimate a confidence interval for oscillometry blood pressure measurements. The recursive ensemble is based on a support vector machine that is used to effectively estimate blood pressure and then measure the confidence interval for the systolic blood pressure and diastolic blood pressure. The recursive ensemble methodology provides a lower standard deviation of error, mean error, and mean absolute error for the blood pressure as compared to those of the conventional techniques.
ctDNA Detection in Microfluidic Platform: A Promising Biomarker for Personalized Cancer Chemotherapy
Early detection and characterization of circulating tumor DNA (ctDNA) can reveal mint of comprehensive biological insights from indicating the presence of tumor, identifying mutational changes of malignant cells, and allowing precision or targeted therapy together with monitoring disease progression, treatment resistance, and relapse of the disease. Apart from these, one of the greatest axiomatic implications of ctDNA detection is that it provides a new shed of light as noninvasive liquid biopsy as a replaceable procedure of surgical tumor biopsy. Despite the tremendous potential of ctDNA in cancer research, there remains a paucity of quantitative study on ctDNA detection and analysis. The majority of previously published microfluidic-based studies have focused on circulating tumor cell (CTC) detection and have failed to address the potential of ctDNA. The studies on microfluidic ctDNA detection are not consistent might be due to the complexity of ctDNA isolation as they present in low concentration in blood plasma. Researchers need to leverage the ability of microfluidic system for ctDNA analysis so that the significant enigma about cancer can be resolved effectively. This study, therefore, highlights the importance of ctDNA as cancer biomarker for liquid biopsy and provides an overview of the current laboratory as well as microfluidic techniques for ctDNA detection. This paper also attempts to show the emergence of new strands of microfluidic ctDNA detection and analysis for personalized cancer chemotherapy.
Vehicle Detection and Ranging Using Two Different Focal Length Cameras
Vehicle detection is a crucial task for autonomous driving and demands high accuracy and real-time speed. Considering that the current deep learning object detection model size is too large to be deployed on the vehicle, this paper introduces the lightweight network to modify the feature extraction layer of YOLOv3 and improve the remaining convolution structure, and the improved Lightweight YOLO network reduces the number of network parameters to a quarter. Then, the license plate is detected to calculate the actual vehicle width and the distance between the vehicles is estimated by the width. This paper proposes a detection and ranging fusion method based on two different focal length cameras to solve the problem of difficult detection and low accuracy caused by a small license plate when the distance is far away. The experimental results show that the average precision and recall of the Lightweight YOLO trained on the self-built dataset is 4.43% and 3.54% lower than YOLOv3, respectively, but the computing speed of the network decreases 49 ms per frame. The road experiments in different scenes also show that the long and short focal length camera fusion ranging method dramatically improves the accuracy and stability of ranging. The mean error of ranging results is less than 4%, and the range of stable ranging can reach 100 m. The proposed method can realize real-time vehicle detection and ranging on the on-board embedded platform Jetson Xavier, which satisfies the requirements of automatic driving environment perception.
Quantitative Nondestructive Testing of Broken Wires for Wire Rope Based on Magnetic and Infrared Information
The lifetime of wire rope is crucial in industry manufacturing, mining, and so on. The damage can be detected by using appropriate nondestructive testing techniques or destructive tests by cutting the part. For broken wires classification problems, this work is aimed at improving the recognition accuracy. Facing the defects at the exterior of the rope, a novel method for recognition of broken wires is firstly developed based on magnetic and infrared information fusion. A denoising method, which is adopted for magnetic signal, is proposed for eliminating baseline signal and wave strand. An image segmentation method is employed for parting the defects of infrared images. Characteristic vectors are extracted from magnetic images and infrared images, then kernel extreme learning machine network is applied to implement recognition of broken wires. Experimental results show that the denoising method and image segmentation are effective and the information fusion can improve the classification accuracy, which can provide useful information for estimating the residual lifetime of wire rope.