Self-Adaptive Feature Transformation Networks for Object Detection in low luminance Images

Despite the recent improvement of object detection techniques, many of them fail to detect objects in low-luminance images. The blurry and dimmed nature of low-luminance images results in the extraction of vague features and failure to detect objects. In addition, many existing object detection methods are based on models trained on both sufficient- and low-luminance images, which also negatively affect the feature extraction process and detection results. In this article, we propose a framework called Self-adaptive Feature Transformation Network (SFT-Net) to effectively detect objects in low-luminance conditions. The proposed SFT-Net consists of the following three modules: (1) feature transformation module, (2) self-adaptive module, and (3) object detection module. The purpose of the feature transformation module is to enhance the extracted feature through unsupervisely learning a feature domain projection procedure. The self-adaptive module is utilized as a probabilistic module producing appropriate features either from the transformed or the original features to further boost the performance and generalization ability of the proposed framework. Finally, the object detection module is designed to accurately detect objects in both low- and sufficient- luminance images by using the appropriate features produced by the self-adaptive module. The experimental results demonstrate that the proposed SFT-Net framework significantly outperforms the state-of-the-art object detection techniques, achieving an average precision (AP) of up to 6.35 and 11.89 higher on the sufficient- and low- luminance domain, respectively.

Measuring driver cognitive distraction through lips and eyebrows

<span>Cognitive distraction is one of the several contributory factors in road accidents. A number of cognitive distraction detection methods have been developed. One of the most popular methods is based on physiological measurement. Head orientation, gaze rotation, blinking and pupil diameter are among popular physiological parameters that are measured for driver cognitive distraction. In this paper, lips and eyebrows are studied. These new features on human facial expression are obvious and can be easily measured when a person is in cognitive distraction. There are several types of movement on lips and eyebrows that can be captured to indicate cognitive distraction. Correlation and classification techniques are used in this paper for performance measurement and comparison. Real time driving experiment was setup and faceAPI was installed in the car to capture driver’s facial expression. Linear regression, support vector machine (SVM), static Bayesian network (SBN) and logistic regression (LR) are used in this study. Results showed that lips and eyebrows are strongly correlated and have a significant role in improving cognitive distraction detection. Dynamic Bayesian network (DBN) with different confidence of levels was also used in this study to classify whether a driver is distracted or not.</span>

Analysis of Residual Current Flows in Inverter Based Energy Systems Using Machine Learning Approaches

Faults and unintended conditions in grid-connected photovoltaic systems often cause a change of the residual current. This article describes a novel machine learning based approach to detecting anomalies in the residual current of a photovoltaic system. It can be used to detect faults or critical states at an early stage and extends conventional threshold-based detection methods. For this study, a power-hardware-in-the-loop approach was carried out, in which typical faults have been injected under ideal and realistic operating conditions. The investigation shows that faults in a photovoltaic converter system cause a unique behaviour of the residual current and fault patterns can be detected and identified by using pattern recognition and variational autoencoder machine learning algorithms. In this context, it was found that the residual current is not only affected by malfunctions of the system, but also by volatile external influences. One of the main challenges here is to separate the regular residual currents caused by the interferences from those caused by faults. Compared to conventional methods, which respond to absolute changes in residual current, the two machine learning models detect faults that do not affect the absolute value of the residual current.

Quantify pixel-level detection of dam surface crack using deep learning

An increasing number of detection methods based on computer vision are applied to detect cracks in water conservancy infrastructure. However, most studies directly use existing feature extraction networks to extract cracks information, which are proposed for open-source datasets. As the cracks distribution and pixel features are different from these data, the extracted cracks information is incomplete. In this paper, a deep learning-based network for dam surface crack detection is proposed, which mainly addresses the semantic segmentation of cracks on the dam surface. Particularly, we design a shallow encoding network to extract features of crack images based on the statistical analysis of cracks. Further, to enhance the relevance of contextual information, we introduce an attention module into the decoding network. During the training, we use the sum of Cross-Entropy and Dice Loss as the loss function to overcome data imbalance. The quantitative information of cracks is extracted by the imaging principle after using morphological algorithms to extract the morphological features of the predicted result. We built a manual annotation dataset containing 1577 images to verify the effectiveness of the proposed method. This method achieves the state-of-the-art performance on our dataset. Specifically, the precision, recall, IoU, F1_measure, and accuracy achieve 90.81%, 81.54%, 75.23%, 85.93%, 99.76%, respectively. And the quantization error of cracks is less than 4%.

Comprehensive Review on Wearable Sweat-Glucose Sensors for Continuous Glucose Monitoring

The incidence of diabetes is increasing at an alarming rate, and regular glucose monitoring is critical in order to manage diabetes. Currently, glucose in the body is measured by an invasive method of blood sugar testing. Blood glucose (BG) monitoring devices measure the amount of sugar in a small sample of blood, usually drawn from pricking the fingertip, and placed on a disposable test strip. Therefore, there is a need for non-invasive continuous glucose monitoring, which is possible using a sweat sensor-based approach. As sweat sensors have garnered much interest in recent years, this study attempts to summarize recent developments in non-invasive continuous glucose monitoring using sweat sensors based on different approaches with an emphasis on the devices that can potentially be integrated into a wearable platform. Numerous research entities have been developing wearable sensors for continuous blood glucose monitoring, however, there are no commercially viable, non-invasive glucose monitors on the market at the moment. This review article provides the state-of-the-art in sweat glucose monitoring, particularly keeping in sight the prospect of its commercialization. The challenges relating to sweat collection, sweat sample degradation, person to person sweat amount variation, various detection methods, and their glucose detection sensitivity, and also the commercial viability are thoroughly covered.

Development of a europium nanoparticles lateral flow immunoassay for NGAL detection in urine and diagnosis of acute kidney injury

Background AKI is related to severe adverse outcomes and mortality with Coronavirus Disease 2019 (COVID-19) patients, that early diagnosed and intervened is imperative. Neutrophil gelatinase-associated lipocalin (NGAL) is one of the most promising biomarkers for detection of acute kidney injury (AKI), but current detection methods are inadequacy, so more rapid, convenient and accuracy methods are needed to detect NGAL for early diagnosis of AKI. Herein, we established a rapid, reliable and accuracy lateral flow immunoassay (LFIA) based on europium nanoparticles (EU-NPS) for the detection of NGAL in human urine specimens. Methods A double-antibody sandwich immunofluorescent assay using europium doped nanoparticles was employed and the NGAL monoclonal antibodies (MAbs) conjugate as labels were generated by optimizing electric fusion parameters. Eighty-three urine samples were used to evaluate the clinical application efficiency of this method. Results The quantitative detection range of NGAL in AKI was 1-3000 ng/mL, and the detection sensitization was 0.36 ng/mL. The coefficient of variation (CV) of intra-assay and inter-assay were 2.57-4.98 % and 4.11-7.83 %, respectively. Meanwhile, the correlation coefficient between europium nanoparticles-based lateral fluorescence immunoassays (EU-NPS-LFIA) and ARCHITECT analyzer was significant (R2 = 0.9829, n = 83, p < 0.01). Conclusions Thus, a faster and easier operation quantitative assay of NGAL for AKI has been established, which is very important and meaningful to diagnose the early AKI, suggesting that the assay can provide an early warning of final outcome of disease.

YOLOv4-Lite–Based Urban Plantation Tree Detection and Positioning With High-Resolution Remote Sensing Imagery

Automatic tree identification and position using high-resolution remote sensing images are critical for ecological garden planning, management, and large-scale environmental quality detection. However, existing single-tree detection methods have a high rate of misdetection in forests not only due to the similarity of background and crown colors but also because light and shadow caused abnormal crown shapes, resulting in a high rate of misdetections and missed detection. This article uses urban plantations as the primary research sample. In conjunction with the most recent deep learning method for object detection, a single-tree detection method based on the lite fourth edition of you only look once (YOLOv4-Lite) was proposed. YOLOv4’s object detection framework has been simplified, and the MobileNetv3 convolutional neural network is used as the primary feature extractor to reduce the number of parameters. Data enhancement is performed for categories with fewer single-tree samples, and the loss function is optimized using focal loss. The YOLOv4-Lite method is used to detect single trees on campus, in an orchard, and an economic plantation. Not only is the YOLOv4-Lite method compared to traditional methods such as the local maximum value method and the watershed method, where it outperforms them by nearly 46.1%, but also to novel methods such as the Chan-Vese model and the template matching method, where it outperforms them by nearly 26.4%. The experimental results for single-tree detection demonstrate that the YOLOv4-Lite method improves accuracy and robustness by nearly 36.2%. Our work establishes a reference for the application of YOLOv4-Lite in additional agricultural and plantation products.