Lightweight Transmission Line Fault Detection Method Based on Leaner YOLOv7-Tiny.

Aiming to address the issues of parameter complexity and high computational load in existing fault detection algorithms for transmission lines, which hinder their deployment on devices like drones, this study proposes a novel lightweight model called Leaner YOLOv7-Tiny. The primary goal is to swiftly and accurately detect typical faults in transmission lines from aerial images. This algorithm inherits the ELAN structure from YOLOv7-Tiny network and replaces its backbone with depthwise separable convolutions to reduce model parameters. By integrating the SP attention mechanism, it fuses multi-scale information, capturing features across various scales to enhance small target recognition. Finally, an improved FCIoU Loss function is introduced to balance the contribution of high-quality and low-quality samples to the loss function, expediting model convergence and boosting detection accuracy. Experimental results demonstrate a 20% reduction in model size compared to the original YOLOv7-Tiny algorithm. Detection accuracy for small targets surpasses that of current mainstream lightweight object detection algorithms. This approach holds practical significance for transmission line fault detection.

Detection Method of Stator Coating Quality of Flat Wire Motor Based on Improved YOLOv8s.

The stator of a flat wire motor is the core component of new energy vehicles. However, detecting quality defects in the coating process in real-time is a challenge. Moreover, the number of defects is large, and the pixels of a single defect are very few, which make it difficult to distinguish the defect features and make accurate detection more difficult. To solve this problem, this article proposes the YOLOv8s-DFJA network. The network is based on YOLOv8s, which uses DSFI-HEAD to replace the original detection head, realizing task alignment. It enhances joint features between the classification task and localization task and improves the ability of network detection. The LEFG module replaces the C2f module in the backbone of the YOLOv8s network that reduces the redundant parameters brought by the traditional BottleNeck structure. It also enhances the feature extraction and gradient flow ability to achieve the lightweight of the network. For this research, we produced our own dataset of stator coating quality regarding flat wire motors. Data augmentation technology (Gaussian noise, adjusting brightness, etc.) enriches the dataset, to a certain extent, which improves the robustness and generalization ability of YOLOv8s-DFJA. The experimental results show that in the performance of YOLOv8s-DFJA compared with YOLOv8s, the mAP@.5 index increased by 6.4%, the precision index increased by 1.1%, the recall index increased by 8.1%, the FPS index increased by 9.8FPS/s, and the parameters decreased by 3 Mb. Therefore, YOLOv8s-DFJA can be better realize the fast and accurate detection of the stator coating quality of flat wire motors.

Developing a Portable Fluorescence Imaging Device for Fish Freshness Detection.

Rapid detection of fish freshness is of vital importance to ensuring the safety of aquatic product consumption. Currently, the widely used optical detecting methods of fish freshness are faced with multiple challenges, including low detecting efficiency, high cost, large size and low integration of detecting equipment. This research aims to address these issues by developing a low-cost portable fluorescence imaging device for rapid fish freshness detection. The developed device employs ultraviolet-light-emitting diode (UV-LED) lamp beads (365 nm, 10 W) as excitation light sources, and a low-cost field programmable gate array (FPGA) board (model: ZYNQ XC7Z020) as the master control unit. The fluorescence images captured by a complementary metal oxide semiconductor (CMOS) camera are processed by the YOLOv4-Tiny model embedded in FPGA to obtain the ultimate results of fish freshness. The circuit for the YOLOv4-Tiny model is optimized to make full use of FPGA resources and to increase computing efficiency. The performance of the device is evaluated by using grass carp fillets as the research object. The average accuracy of freshness detection reaches up to 97.10%. Moreover, the detection time of below 1 s per sample and the overall power consumption of 47.1 W (including 42.4 W light source power consumption) indicate that the device has good real-time performance and low power consumption. The research provides a potential tool for fish freshness evaluation in a low-cost and rapid manner.

Research on Coal and Gangue Recognition Based on the Improved YOLOv7-Tiny Target Detection Algorithm.

The recognition technology of coal and gangue is one of the key technologies of intelligent mine construction. Aiming at the problems of the low accuracy of coal and gangue recognition models and the difficult recognition of small-target coal and gangue caused by low-illumination and high-dust environments in the coal mine working face, a coal and gangue recognition model based on the improved YOLOv7-tiny target detection algorithm is proposed. This paper proposes three model improvement methods. The coordinate attention mechanism is introduced to improve the feature expression ability of the model. The contextual transformer module is added after the spatial pyramid pooling structure to improve the feature extraction ability of the model. Based on the idea of the weighted bidirectional feature pyramid, the four branch modules in the high-efficiency layer aggregation network are weighted and cascaded to improve the recognition ability of the model for useful features. The experimental results show that the average precision mean of the improved YOLOv7-tiny model is 97.54%, and the FPS is 24.73 f·s-1. Compared with the Faster-RCNN, YOLOv3, YOLOv4, YOLOv4-VGG, YOLOv5s, YOLOv7, and YOLOv7-tiny models, the improved YOLOv7-tiny model has the highest recognition rate and the fastest recognition speed. Finally, the improved YOLOv7-tiny model is verified by field tests in coal mines, which provides an effective technical means for the accurate identification of coal and gangue.

Tiny-Machine-Learning-Based Supply Canal Surface Condition Monitoring.

The South-to-North Water Diversion Project in China is an extensive inter-basin water transfer project, for which ensuring the safe operation and maintenance of infrastructure poses a fundamental challenge. In this context, structural health monitoring is crucial for the safe and efficient operation of hydraulic infrastructure. Currently, most health monitoring systems for hydraulic infrastructure rely on commercial software or algorithms that only run on desktop computers. This study developed for the first time a lightweight convolutional neural network (CNN) model specifically for early detection of structural damage in water supply canals and deployed it as a tiny machine learning (TinyML) application on a low-power microcontroller unit (MCU). The model uses damage images of the supply canals that we collected as input and the damage types as output. With data augmentation techniques to enhance the training dataset, the deployed model is only 7.57 KB in size and demonstrates an accuracy of 94.17 ± 1.67% and a precision of 94.47 ± 1.46%, outperforming other commonly used CNN models in terms of performance and energy efficiency. Moreover, each inference consumes only 5610.18 µJ of energy, allowing a standard 225 mAh button cell to run continuously for nearly 11 years and perform approximately 4,945,055 inferences. This research not only confirms the feasibility of deploying real-time supply canal surface condition monitoring on low-power, resource-constrained devices but also provides practical technical solutions for improving infrastructure security.

PDT-YOLO: A Roadside Object-Detection Algorithm for Multiscale and Occluded Targets.

To tackle the challenges of weak sensing capacity for multi-scale objects, high missed detection rates for occluded targets, and difficulties for model deployment in detection tasks of intelligent roadside perception systems, the PDT-YOLO algorithm based on YOLOv7-tiny is proposed. Firstly, we introduce the intra-scale feature interaction module (AIFI) and reconstruct the feature pyramid structure to enhance the detection accuracy of multi-scale targets. Secondly, a lightweight convolution module (GSConv) is introduced to construct a multi-scale efficient layer aggregation network module (ETG), enhancing the network feature extraction ability while maintaining weight. Thirdly, multi-attention mechanisms are integrated to optimize the feature expression ability of occluded targets in complex scenarios, Finally, Wise-IoU with a dynamic non-monotonic focusing mechanism improves the accuracy and generalization ability of model sensing. Compared with YOLOv7-tiny, PDT-YOLO on the DAIR-V2X-C dataset improves mAP50 and mAP50:95 by 4.6% and 12.8%, with a parameter count of 6.1 million; on the IVODC dataset by 15.7% and 11.1%. We deployed the PDT-YOLO in an actual traffic environment based on a robot operating system (ROS), with a detection frame rate of 90 FPS, which can meet the needs of roadside object detection and edge deployment in complex traffic scenes.

Computer vision model for the detection of canine pododermatitis and neoplasia of the paw.

BACKGROUND: Artificial intelligence (AI) has been used successfully in human dermatology. AI utilises convolutional neural networks (CNN) to accomplish tasks such as image classification, object detection and segmentation, facilitating early diagnosis. Computer vision (CV), a field of AI, has shown great results in detecting signs of human skin diseases. Canine paw skin diseases are a common problem in general veterinary practice, and computer vision tools could facilitate the detection and monitoring of disease processes. Currently, no such tool is available in veterinary dermatology. ANIMALS: Digital images of paws from healthy dogs and paws with pododermatitis or neoplasia were used. OBJECTIVES: We tested the novel object detection model Pawgnosis, a Tiny YOLOv4 image analysis model deployed on a microcomputer with a camera for the rapid detection of canine pododermatitis and neoplasia. MATERIALS AND METHODS: The prediction performance metrics used to evaluate the models included mean average precision (mAP), precision, recall, average precision (AP) for accuracy and frames per second (FPS) for speed. RESULTS: A large dataset labelled by a single individual (Dataset A) used to train a Tiny YOLOv4 model provided the best results with a mean mAP of 0.95, precision of 0.86, recall of 0.93 and 20 FPS. CONCLUSIONS AND CLINICAL RELEVANCE: This novel object detection model has the potential for application in the field of veterinary dermatology.

A 1-min double embedding method for small tissue specimens preserves comedone histology and eliminates the need for punch biopsies.

BACKGROUND: It is difficult to preserve the structure and microbial distribution inside comedonal plugs during routine processing. OBJECTIVE: The objective of this study is to determine the optimal method to preserve the comedonal corneum plug structure and inherent microorganisms thereby eliminating the need to perform punch biopsies in relevant studies. METHODS: Corneum plugs were extracted from comedones of acne vulgaris patients. Primary embedding using either a 2% agarose, 2% agar, 25% gelatin, or 2% agar + 2.5% gelatin solution was subsequently performed and the results compared. The specimens were then fixed, waxed, sectioned, and examined by light, fluorescence, and scanning electron microscopies to observe the structures and microorganisms within the plugs. RESULTS: Both the 25% gelatin and 2% agarose solutions successfully preserved the structural integrity of corneum plugs and the inherent microorganisms. When considering other factors such as thermostability, reusability, and convenience, the 25% gelatin solution was the superior choice among the four materials. CONCLUSION: We report a simple and effective method for double embedding comedonal plugs and other small tissue specimens. The technique preserves the structure and microbial distribution in situ within comedonal corneum plugs, eliminates the need for punch biopsies. This method may also be applied to other tiny and fragile tissue specimens, thereby enabling a potentially wide array of future large-scale investigations and alleviated patients' pain.

MiCrowd: Vision-Based Deep Crowd Counting on MCU.

Microcontrollers (MCUs) have been deployed on numerous IoT devices due to their compact sizes and low costs. MCUs are capable of capturing sensor data and processing them. However, due to their low computational power, applications processing sensor data with deep neural networks (DNNs) have been limited. In this paper, we propose MiCrowd, a floating population measurement system with a tiny DNNs running on MCUs since the data have essential value in urban planning and business. Moreover, MiCrowd addresses the following important challenges: (1) privacy issues, (2) communication costs, and (3) extreme resource constraints on MCUs. To tackle those challenges, we designed a lightweight crowd-counting deep neural network, named MiCrowdNet, which enables on-MCU inferences. In addition, our dataset is carefully chosen and completely re-labeled to train MiCrowdNet for counting people from an mobility view. Experiments show the effectiveness of MiCrowdNet and our relabeled dataset for accurate on-device crowd counting.

Fire Detection in Ship Engine Rooms Based on Deep Learning.

Ship fires are one of the main factors that endanger the safety of ships; because the ship is far away from land, the fire can be difficult to extinguish and could often cause huge losses. The engine room has many pieces of equipment and is the principal place of fire; however, due to its complex internal environment, it can bring many difficulties to the task of fire detection. The traditional detection methods have their own limitations, but fire detection using deep learning technology has the characteristics of high detection speed and accuracy. In this paper, we improve the YOLOv7-tiny model to enhance its detection performance. Firstly, partial convolution (PConv) and coordinate attention (CA) mechanisms are introduced into the model to improve its detection speed and feature extraction ability. Then, SIoU is used as a loss function to accelerate the model's convergence and improve accuracy. Finally, the experimental results on the dataset of the ship engine room fire made by us shows that the mAP@0.5 of the improved model is increased by 2.6%, and the speed is increased by 10 fps, which can meet the needs of engine room fire detection.

TSR-YOLO: A Chinese Traffic Sign Recognition Algorithm for Intelligent Vehicles in Complex Scenes.

Recognizing traffic signs is an essential component of intelligent driving systems' environment perception technology. In real-world applications, traffic sign recognition is easily influenced by variables such as light intensity, extreme weather, and distance, which increase the safety risks associated with intelligent vehicles. A Chinese traffic sign detection algorithm based on YOLOv4-tiny is proposed to overcome these challenges. An improved lightweight BECA attention mechanism module was added to the backbone feature extraction network, and an improved dense SPP network was added to the enhanced feature extraction network. A yolo detection layer was added to the detection layer, and k-means++ clustering was used to obtain prior boxes that were better suited for traffic sign detection. The improved algorithm, TSR-YOLO, was tested and assessed with the CCTSDB2021 dataset and showed a detection accuracy of 96.62%, a recall rate of 79.73%, an F-1 Score of 87.37%, and a mAP value of 92.77%, which outperformed the original YOLOv4-tiny network, and its FPS value remained around 81 f/s. Therefore, the proposed method can improve the accuracy of recognizing traffic signs in complex scenarios and can meet the real-time requirements of intelligent vehicles for traffic sign recognition tasks.

An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments.

Industrial assets often feature multiple sensing devices to keep track of their status by monitoring certain physical parameters. These readings can be analyzed with machine learning (ML) tools to identify potential failures through anomaly detection, allowing operators to take appropriate corrective actions. Typically, these analyses are conducted on servers located in data centers or the cloud. However, this approach increases system complexity and is susceptible to failure in cases where connectivity is unavailable. Furthermore, this communication restriction limits the approach's applicability in extreme industrial environments where operating conditions affect communication and access to the system. This paper proposes and evaluates an end-to-end adaptable and configurable anomaly detection system that uses the Internet of Things (IoT), edge computing, and Tiny-MLOps methodologies in an extreme industrial environment such as submersible pumps. The system runs on an IoT sensing Kit, based on an ESP32 microcontroller and MicroPython firmware, located near the data source. The processing pipeline on the sensing device collects data, trains an anomaly detection model, and alerts an external gateway in the event of an anomaly. The anomaly detection model uses the isolation forest algorithm, which can be trained on the microcontroller in just 1.2 to 6.4 s and detect an anomaly in less than 16 milliseconds with an ensemble of 50 trees and 80 KB of RAM. Additionally, the system employs blockchain technology to provide a transparent and irrefutable repository of anomalies.

Scalable Lightweight IoT-Based Smart Weather Measurement System.

The Internet of Things (IoT) plays a critical role in remotely monitoring a wide variety of different application sectors, including agriculture, building, and energy. The wind turbine energy generator (WTEG) is a real-world application that can take advantage of IoT technologies, such as a low-cost weather station, where human activities can be significantly affected by enhancing the production of clean energy based on the known direction of the wind. Meanwhile, common weather stations are neither affordable nor customizable for specific applications. Moreover, due to weather forecast changes over time and location within the same city, it is not efficient to rely on a limited number of weather stations that may be located far away from a recipient's location. Therefore, in this paper, we focus on presenting a low-cost weather station that relies on an artificial intelligence (AI) algorithm that can be distributed across a WTEG area with minimal cost. The proposed study measures multiple weather parameters, such as wind direction, wind velocity (WV), temperature, pressure, mean sea level, and relative humidity to provide current measurements to recipients and AI-based forecasts. In addition, the proposed study consists of several heterogeneous nodes and a controller for each station in a target area. The collected data can be transmitted through Bluetooth low energy (BLE). The experimental results reveal that the proposed study matches the standard of the National Meteorological Center (NMC), with a nowcast measurement of 95% accuracy for WV and 92% for wind direction (WD).

Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices.

Tiny machine learning (TinyML) has become an emerging field according to the rapid growth in the area of the internet of things (IoT). However, most deep learning algorithms are too complex, require a lot of memory to store data, and consume an enormous amount of energy for calculation/data movement; therefore, the algorithms are not suitable for IoT devices such as various sensors and imaging systems. Furthermore, typical hardware accelerators cannot be embedded in these resource-constrained edge devices, and they are difficult to drive real-time inference processing as well. To perform the real-time processing on these battery-operated devices, deep learning models should be compact and hardware-optimized, and hardware accelerator designs also have to be lightweight and consume extremely low energy. Therefore, we present an optimized network model through model simplification and compression for the hardware to be implemented, and propose a hardware architecture for a lightweight and energy-efficient deep learning accelerator. The experimental results demonstrate that our optimized model successfully performs object detection, and the proposed hardware design achieves 1.25× and 4.27× smaller logic and BRAM size, respectively, and its energy consumption is approximately 10.37× lower than previous similar works with 43.95 fps as a real-time process under an operating frequency of 100 MHz on a Xilinx ZC702 FPGA.

Development of Automatic Portable Pathology Scanner and Its Evaluation for Clinical Practice.

Digital pathological scanners transform traditional glass slides into whole slide images (WSIs), which significantly improve the efficiency of pathological diagnosis and promote the development of digital pathology. However, the huge economic burden limits the spread and application of general WSI scanners in relatively remote and backward regions. In this paper, we develop an automatic portable cytopathology scanner based on mobile internet, Landing-Smart, to avert the above problems. Landing-Smart is a tiny device with a size of 208 mm × 107 mm × 104 mm and a weight of 1.8 kg, which integrates four main components including a smartphone, a glass slide carrier, an electric controller, and an optical imaging unit. By leveraging a simple optical imaging unit to substitute the sophisticated but complex conventional light microscope, the cost of Landing-Smart is less than $3000, much cheaper than general WSI scanners. On the one hand, Landing-Smart utilizes the built-in camera of the smartphone to acquire field of views (FoVs) in the section one by one. On the other hand, it uploads the images to the cloud server in real time via mobile internet, where the image processing and stitching method is implemented to generate the WSI of the cytological sample. The practical assessment of 209 cervical cytological specimens has demonstrated that Landing-Smart is comparable to general digital scanners in cytopathology diagnosis. Landing-Smart provides an effective tool for preliminary cytological screening in underdeveloped areas.

Exploring the role of nature-based typologies and stewardship schemes in enhancing urban green spaces: Citizen perceptions of landscape design scenarios and ecosystem services.

This research investigates the UK citizens' perceptions of the ecosystem services (ES) created using a range of Nature-Based Solutions (NBS) in urban green spaces (UGS). The longevity of the ES derived from UGS is dependent on the effective on-going maintenance of urban landscapes, therefore this paper also gathers data on direct UGS participation specifically through the lens of civic stewardship to assess the impact of such schemes upon ES. NBS typologies were created and used, in the mixed methods study, to gauge perceptions of and preferences for alternative urban landscape design. The UGS survey collected data from 345 respondents on ES and the NBS typologies. Twelve semi-structured interviews provide qualitative data on NBS typology preferences, perceptions, and understanding of ES as well as motivations behind civic engagement in UGS in the UK. Stewardship programmes were found to increase community resilience by providing additional ES. The results showed a preference for integrating complex, multifunctional UGS into the fabric of urban centres to ensure accessibility and to maximise engagement. More complex NBS typologies were perceived to provide additional ES when compared with traditional monoculture mown grass and shrub amenity planting. Mixed native planting and Tiny Forest NBS typologies were perceived as providing more provisioning, cultural, regulating, and supporting ES. Considering both UK citizens' perceptions of the ES gained from alternative NBS and stewardship schemes in UGS represents a holistic approach that can improve the design and management of NBS in cities. This study is the first to explore both concepts in the UK and suggests a holistic UGS approach to address urban challenges, including those related to Climate Change.

Designing "Tiny Forests" as a lesson for transdisciplinary urban ecology learning.

The sustainability and livability of urban areas call for the next generation of scientists, practitioners and policy makers to understand the benefits, implementation and management of urban greenspaces. We harnessed the concept of "Tiny Forests©" - a restoration strategy for small wooded areas (~100-400 m2) - to create a transdisciplinary and experiential project for university forestry students that follows an ecology-with-cities framework. We worked with 16 students and a local municipality in the Munich, Germany metropolitan region to survey a community about its needs and desires and then used this information alongside urban environmental features and data collected by students (e.g., about soil conditions) to design a Tiny Forest. In this article, we describe the teaching concept, learning outcomes and activities, methodological approach, and instructor preparation and materials needed to adapt this project. Designing Tiny Forests provides benefits to students by having them approach authentic tasks in urban greening while experiencing the challenges and benefits of transdisciplinary communication and engagement with community members. Supplementary Information: The online version contains supplementary material available at 10.1007/s11252-023-01371-7.

TINY BRANCHED HAIR functions in multicellular trichome development through an ethylene pathway in Cucumis sativus L.

The fruit trichomes of Cucurbitaceae are widely desired in many Asian countries and have been a key determinant of cucumber (Cucumis sativus L.) cultivar selection for commercial production and breeding. However, our understanding of the initiation and development of cucumber trichomes is still limited. Here, we found that the cucumber TINY BRANCHED HAIR (TBH) gene is preferentially expressed in multicellular trichomes. Overexpression of CsTBH in tbh mutants restored the trichome phenotype and increased the percentage of female flowers, whereas silencing of CsTBH in wild-type plants resulted in stunted trichomes with a lower rate of female flowers. Furthermore, we provide evidence that CsTBH can directly bind to the promoters of cucumber 1-Aminocyclopropane-1-Carboxylate Synthase (CsACS) genes and regulate their expression, which affects multicellular trichome development, ethylene accumulation, and sex expression. Two cucumber acs mutants with different trichome morphology and sex morphs compared with their near-isogenic line further support our findings. Collectively, our study provides new information on the molecular mechanism of CsTBH in regulating multicellular trichome development and sex expression through an ethylene pathway.

Single coil endovascular embolization of very tiny (≤2 mm) intracranial aneurysms: one center's experience.

Background: To investigate the safety and efficacy of endovascular embolization of very tiny (≤2 mm) intracranial aneurysms with single coil and summarize experience. Methods: A retrospective analysis was performed for 15 consecutive patients with very tiny aneurysms treated by coil embolization alone or stent-assisted coil embolization between January 2017 and January 2020. 15 patients with six unruptured aneurysms and nine ruptured aneurysms were included in this study. There were eight males and seven females with a mean age of 50.0 ± 5.2 years (range 41 to 57 years old). Intraoperative complications, imaging outcomes, clinical outcomes and follow-up data were analyzed. Results: All aneurysms were embolized with a single coil. Lvis stents were used in all coil assisted embolizations. The embolization success rate was 100%. The average volume embolization ratio (VER) of aneurysm embolization was 53.7 ± 25.5%. An intraoperative aneurysm re-rupture complication occurred in one patient (6.7%). 11 patients (73.3%) had immediate complete occlusion after embolization. After a mean follow-up period of 6.7 ± 1.4 months, 13 patients (86.7%) had complete occlusion. No patients had aneurysm re-rupture, an ischemic event or recurrence during follow-up. All patients achieved favorable clinical outcomes with a modified rankin scale (MRS) of 0-2. Conclusions: This study demonstrates that endovascular embolization of very tiny intracranial aneurysms with a single coil is safe and effective. However, the follow-up period was not long enough and studies with larger numbers of patients are required. The summary of experience reported here is expected to provide significant patient benefits.

Towards High Accuracy Pedestrian Detection on Edge GPUs.

Despite the rapid development of pedestrian detection algorithms, the balance between detection accuracy and efficiency is still far from being achieved due to edge GPUs (low computing power) limiting the parameters of the model. To address this issue, we propose the YOLOv4-TP-Tiny based on the YOLOv4 model, which mainly includes two modules, two-dimensional attention (TA) and pedestrian-based feature extraction (PFM). First, we integrate the TA mechanism into the backbone network, which increases the attention of the network to the visible area of pedestrians and improves the accuracy of pedestrian detection. Then, the PFM is used to replace the original spatial pyramid pooling (SPP) structure in the YOLOv4 to obtain the YOLOv4-TP algorithm, which can adapt to different sizes of people to obtain higher detection accuracy. To maintain detection speed, we replaced the normal convolution with a ghost network with a TA mechanism, resulting in more feature maps with fewer parameters. We constructed a one-way multi-scale feature fusion structure to replace the down-sampling process, thereby reducing network parameters to obtain the YOLOv4-TP-Tiny model. The experimental results show that the YOLOv4-TP-tiny has 58.3% AP and 31 FPS in the winder person pedestrian dataset. With the same hardware conditions and dataset, the AP of the YOLOv4-tiny is 55.9%, and the FPS is 29.