Autonomous Detection Research Articles

Mechanism of TMB Discoloration Catalyzed by Layered CoNi@CN Nanozymes: Application Based on Smart Phone for Resorcinol Detection

Comprehensive SummaryReal‐time on‐site monitoring of resorcinol (RS) concentrations is crucial for detecting hazardous levels, enabling prompt response measures to mitigate potential environmental and health risks. In this study, we developed an innovative method using CoNi@CN‐2 nanozymes to activate peroxymonosulfate (PMS) for oxidizing 3,3',5,5'‐tetramethylbenzidine (TMB). Our results show that the formation of Ni2+ through the oxidation of Ni0 on the CoNi@CN‐2 surface significantly enhances the electron‐donating capacity of Co0. The catalytic reaction of TMB is mediated by redox active species (SO4•−, •O2−, •OH and 1O2). RS drives colorimetry by transferring electrons to the benzene ring and specific nitrogen atoms in ox‐TMB, reducing ox‐TMB to TMB. Furthermore, the colorimetric assay shows a robust linear correlation between RS concentration and absorbance (Abs), described by Abs = –0.44[RS] + 0.886 (0—200 μmol/L, R2 = 0.983). Also, we introduce a novel smartphone‐integrated autonomous detection software that can analyze RS concentration and grayscale values (GSV), yielding GSV = 0.327[RS] + 63.601 (0—200 μmol/L, R2 = 0.990) with a detection limit of 5.29 μmol/L. Additionally, excess PMS leads to ROS attacking specific sites in ox‐TMB, forming secondary oxidation products. This study has enabled rapid and accurate detection of RS, making a significant contribution to environmental safety and protection.

A solution for the automatic detection of expansion joints in dam stilling pools using underwater robots

This research addresses the critical challenges of detecting and measuring underwater concrete structure expansion joints (CSEJ), with a particular focus on dam stilling basin environments. A full set of algorithms for detecting expansion joints with underwater robots is presented by the research, enabling real-time and offline analysis along with visualization. These algorithms introduce the use of Convolutional Neural Networks (CNNs) for image feature extraction and segmentation in CSEJ detection, significantly improving accuracy and adaptability over traditional methods. An automated approach known as the Underwater Dam Crack Detection Network (UDCD Network) was introduced by this research. And advanced attention gates and hybrid dilated convolutions to enhance its detection capabilities are incorporated in this system. Additionally, a three-phase deep transfer learning strategy during training was utilized in this research, which significantly improves the model's performance. The research suggests an underwater image restoration algorithm that uses a dark channel prior and dynamic white balance correction to improve image clarity. Furthermore, unique underwater environmental challenges were tackled by this research, such as non-contact measurement of expansion joint widths using a view-geometry-based algorithm and comprehensive detection of dam wall surfaces. Experimental validation demonstrates that the advanced imaging technologies of the proposed underwater robots hold significant potential for autonomous detection of expansion joints in dam stilling basins.

Application of Artificial Intelligence in Ophthalmology: An Updated Comprehensive Review.

Artificial intelligence (AI) holds immense promise for transforming ophthalmic care through automated screening, precision diagnostics, and optimized treatment planning. This paper reviews recent advances and challenges in applying AI techniques such as machine learning and deep learning to major eye diseases. In diabetic retinopathy, AI algorithms analyze retinal images to accurately identify lesions, which helps clinicians in ophthalmology practice. Systems like IDx-DR (IDx Technologies Inc, USA) are FDA-approved for autonomous detection of referable diabetic retinopathy. For glaucoma, deep learning models assess optic nerve head morphology in fundus photographs to detect damage. In age-related macular degeneration, AI can quantify drusen and diagnose disease severity from both color fundus and optical coherence tomography images. AI has also been used in screening for retinopathy of prematurity, keratoconus, and dry eye disease. Beyond screening, AI can aid treatment decisions by forecasting disease progression and anti-VEGF response. However, potential limitations such as the quality and diversity of training data, lack of rigorous clinical validation, and challenges in regulatory approval and clinician trust must be addressed for the widespread adoption of AI. Two other significant hurdles include the integration of AI into existing clinical workflows and ensuring transparency in AI decision-making processes. With continued research to address these limitations, AI promises to enable earlier diagnosis, optimized resource allocation, personalized treatment, and improved patient outcomes. Besides, synergistic human-AI systems could set a new standard for evidence-based, precise ophthalmic care.

A novel pipeline employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy

Metastasis driven by cancer cell migration is the leading cause of cancer-related deaths. It involves significant changes in the organization of the cytoskeleton, which includes the actin microfilaments and the vimentin intermediate filaments. Understanding how these filament change cells from normal to invasive offers insights that can be used to improve cancer diagnosis and therapy. We have developed a computational, transparent, large-scale and imaging-based pipeline, that can distinguish between normal human cells and their isogenically matched, oncogenically transformed, invasive and metastasizing counterparts, based on the spatial organization of actin and vimentin filaments in the cell cytoplasm. Due to the intricacy of these subcellular structures, manual annotation is not trivial to automate. We used established deep learning methods and our new multi-attention channel architecture. To ensure a high level of interpretability of the network, which is crucial for the application area, we developed an interpretable global explainable approach correlating the weighted geometric mean of the total cell images and their local GradCam scores. The methods offer detailed, objective and measurable understanding of how different components of the cytoskeleton contribute to metastasis, insights that can be used for future development of novel diagnostic tools, such as a nanometer level, vimentin filament-based biomarker for digital pathology, and for new treatments that significantly can increase patient survival.

Asymmetric flexible graphene oxide papers for moisture-driven actuators and water level indicators

Smart actuators have shown great potential for a range of industries, including artificial muscles, sensors, and smart devices. However, traditional actuators often suffer from small deformation and complex materials and manufacturing processes. Graphene oxide (GO) has emerged as an ideal candidate for moisture-responsive actuators due to its excellent moisture sensitivity. In this study, we present the development of a moisture-responsive actuator using a simple and straightforward approach based on a monolayer graphene oxide (GO) paper. By utilizing the different affinity of its two sides for water, the graphene oxide actuator demonstrates excellent performance in response to humidity gradients, achieving a large bending amplitude with a curvature of 3 cm−1. Furthermore, the graphene oxide actuator was used as a humidity-sensitive switch to perform on and off switch movements, demonstrating its capability for autonomous detection for real-time humidity monitoring. This work provides a new avenue for the development of moisture-responsive materials and their potential applications in the design of intelligent control systems, actuators, soft robots, artificial muscles, and switches.

Exploring the potential of water channels for developing genetically encoded reporters and biosensors for diffusion-weighted MRI

Genetically encoded reporters for magnetic resonance imaging (MRI) offer a valuable technology for making molecular-scale measurements of biological processes within living organisms with high anatomical resolution and whole-organ coverage without relying on ionizing radiation. However, most MRI reporters rely on synthetic contrast agents, typically paramagnetic metals and metal complexes, which often need to be supplemented exogenously to create optimal contrast. To eliminate the need for synthetic contrast agents, we previously introduced aquaporin-1, a mammalian water channel, as a new reporter gene for the fully autonomous detection of genetically labeled cells using diffusion-weighted MRI. In this study, we aimed to expand the toolbox of diffusion-based genetic reporters by modulating aquaporin membrane trafficking and harnessing the evolutionary diversity of water channels across species. We identified a number of new water channels that functioned as diffusion-weighted reporter genes. In addition, we show that loss-of-function variants of yeast and human aquaporins can be leveraged to design first-in-class diffusion-based sensors for detecting the activity of a model protease within living cells.

Underwater Side-Scan Sonar Target Detection: YOLOv7 Model Combined with Attention Mechanism and Scaling Factor

Side-scan sonar plays a crucial role in underwater exploration, and the autonomous detection of side-scan sonar images is vital for detecting unknown underwater environments. However, due to the complexity of the underwater environment, the presence of a few highlighted areas on the targets, blurred feature details, and difficulty in collecting data from side-scan sonar, achieving high-precision autonomous target recognition in side-scan sonar images is challenging. This article addresses this problem by improving the You Only Look Once v7 (YOLOv7) model to achieve high-precision object detection in side-scan sonar images. Firstly, given that side-scan sonar images contain large areas of irrelevant information, this paper introduces the Swin-Transformer for dynamic attention and global modeling, which enhances the model’s focus on the target regions. Secondly, the Convolutional Block Attention Module (CBAM) is utilized to further improve feature representation and enhance the neural network model’s accuracy. Lastly, to address the uncertainty of geometric features in side-scan sonar target features, this paper innovatively incorporates a feature scaling factor into the YOLOv7 model. The experiment initially verified the necessity of attention mechanisms in the public dataset. Subsequently, experiments on our side-scan sonar (SSS) image dataset show that the improved YOLOv7 model has 87.9% and 49.23% in its average accuracy (mAP0.5) and (mAP0.5:0.95), respectively. These results are 9.28% and 8.41% higher than the YOLOv7 model. The improved YOLOv7 algorithm proposed in this paper has great potential for object detection and the recognition of side-scan sonar images.

Automatic damping estimation via bootstrap technique and Bayesian analysis for mechanical system condition monitoring

Monitoring mechanical systems that are exposed to dynamic loads during operation requires a technical indicator that provides reliable information on degradation. In this paper, the damping ratio is used as an indicator and can be obtained from monitoring data such as acceleration. Its change from the initial value highly correlates with the system change that can lead to failure. The damping ratio can be relatively easily estimated from the free response data. Such events occur frequently for systems that are subjected to environmental loads such as wind gusts on structures, or sudden stops and changes in the operational cycle.The problem addressed by this research is the fully autonomous detection of these free-response events and the subsequent estimation of the damping ratio, including uncertainty. Therefore, a novel monitoring approach is proposed, utilising the Bootstrap technique and Bayesian analysis. Bootstrap provides automatic free response detection without monitoring the excitation force. Once the event is detected as a valid free response, Bayesian analysis in the form of a gamma-exponential conjugate prior is applied to estimate the damping ratio. As damping estimation is in the form of distribution, uncertainty is also quantified, which is a required feature when monitoring the degradation process and remaining useful life prediction.The monitoring approach is demonstrated and verified numerically and experimentally on a single degree of freedom air-bearing testbed as well as on multiple degrees of freedom beam system. As shown, the combination of the Bootstrap technique and Bayesian analysis provided satisfactory results, demonstrating that the degradation process can be reliably monitored by the proposed approach.

Deep learning improved YOLOv8 algorithm: Real-time precise instance segmentation of crown region orchard canopies in natural environment

Autonomous detection and segmentation of tree canopies, trunks, and nontarget areas is crucial for optimizing pesticide use and minimizing off-target spray deposition in orchards for precision spraying. To improve the precision of pesticide application in orchards, a real-time orchard tree segmentation method using an improved YOLOv8 deep learning algorithm was proposed. First, to enhance precision, a dilated convolution approach was introduced into the backbone of the YOLO algorithm, and then, to better converge and regularize the model GELU activation function was added into the dilated convolution network. Finally, a total of 600 images of manually labeled orchard canopies were used, and the adaptive gradient algorithm (AdaGrad) was employed to adjust the weights and minimize the loss function. Additionally, the ReduceLROnPlateau scheduler was utilized to fine-tune the model during training. The performance of the proposed method was assessed through a comparative analysis. The results of the improved algorithm showed a mean average precision (mAP) of 93.3 % with an improvement of 1.3 %, precision (P) of 93.6 % with an improvement of 3.8 %, and inference time of 28 ms. To verify the effectiveness of the proposed method, the results were compared with those of YOLO family algorithms and Mask RCNN. An outdoor experiment was conducted to assess the algorithm’s performance to evaluate the deposition outcomes of the spray for variable-rate spraying, which proved to be reduced by 40 % compared to uncontrolled spraying. The deposit coverage was more than 20 % on trees of different sizes, which were positioned 1.7 m away from each side of the spraying robot. The obtained results confirm the satisfactory performance of the improved YOLOv8 algorithm and aim to offer valuable technical assistance for improving the efficiency and precision of an orchard spraying machine.

Autonomous firefighting using a quadruped robot

This paper presents the development of a proof-of-concept autonomous firefighting robot based on the Spot quadruped robot. Both the payload and software package for the autonomous detection, localization, and extinguishing of a small fire are discussed. A thermal camera is mounted to the front of Spot and a standard ABC fire extinguisher is mounted to the back. The thermal camera is used to autonomously detect fires and the fire extinguisher is used to put out a detected fire. The system was successfully tested at a local fire station in a controlled setting with actual fires. The results of this project have direct application in the area of autonomous first response in complex industrial environments and fire watch applications.

EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection

PurposeThe purpose of this work is to present an approach for autonomous detection of eye disease in fundus images. Furthermore, this work presents an improved variant of the Tiny YOLOv7 model developed specifically for eye disease detection. The model proposed in this work is a highly useful tool for the development of applications for autonomous detection of eye diseases in fundus images that can help and assist ophthalmologists.Design/methodology/approachThe approach adopted to carry out this work is twofold. Firstly, a richly annotated dataset consisting of eye disease classes, namely, cataract, glaucoma, retinal disease and normal eye, was created. Secondly, an improved variant of the Tiny YOLOv7 model was developed and proposed as EYE-YOLO. The proposed EYE-YOLO model has been developed by integrating multi-spatial pyramid pooling in the feature extraction network and Focal-EIOU loss in the detection network of the Tiny YOLOv7 model. Moreover, at run time, the mosaic augmentation strategy has been utilized with the proposed model to achieve benchmark results. Further, evaluations have been carried out for performance metrics, namely, precision, recall, F1 Score, average precision (AP) and mean average precision (mAP).FindingsThe proposed EYE-YOLO achieved 28% higher precision, 18% higher recall, 24% higher F1 Score and 30.81% higher mAP than the Tiny YOLOv7 model. Moreover, in terms of AP for each class of the employed dataset, it achieved 9.74% higher AP for cataract, 27.73% higher AP for glaucoma, 72.50% higher AP for retina disease and 13.26% higher AP for normal eye. In comparison to the state-of-the-art Tiny YOLOv5, Tiny YOLOv6 and Tiny YOLOv8 models, the proposed EYE-YOLO achieved 6–23.32% higher mAP.Originality/valueThis work addresses the problem of eye disease recognition as a bounding box regression and detection problem. Whereas, the work in the related research is largely based on eye disease classification. The other highlight of this work is to propose a richly annotated dataset for different eye diseases useful for training deep learning-based object detectors. The major highlight of this work lies in the proposal of an improved variant of the Tiny YOLOv7 model focusing on eye disease detection. The proposed modifications in the Tiny YOLOv7 aided the proposed model in achieving better results as compared to the state-of-the-art Tiny YOLOv8 and YOLOv8 Nano.

Near-Miss Detection Metrics: An Approach to Enable Sensing Technologies for Proactive Construction Safety Management

One in every five occupational deaths occurs in the construction sector. A proactive approach for improving on-site safety is identifying and analyzing accident precursors, such as near-misses, that provide early warnings of accidents. Despite the importance of near-misses, they are frequently left unreported and unrecorded in the construction sector. The adoption of modern technologies can prevent accidents by automated data collection and analysis. This study aims to develop near-miss detection metrics to facilitate the automated detection of near-misses through sensors. The study adopted a mixed method approach including both qualitative and quantitative approaches. First, a quantifiable definition of near-misses was developed from the literature. Hazards, accidents, and the causes of accidents were identified. Through empirical and statistical analyses of accidents from the OSHA repository, combinations of unsafe acts and conditions responsible for a near-miss were identified. The identified factors were analyzed using a frequency analysis, correlation, and a lambda analysis. The results revealed twelve significant near-misses, such as A1—approach to restricted areas and C2—unguarded floor/roof openings, A5—equipment and tool inspection was incomplete and C8—unsafely positioned ladders and scaffolds, A2—no or improper use of PPE and C2—unguarded floor or roof openings, etc. Lastly, measurable data required by sensors for autonomous detection of near-misses were determined. The developed metric set the basis for automating near-miss reporting and documentation using modern sensing technology to improve construction safety. This study contributes to improving construction safety by addressing the underreporting of near-miss events. Overall, the developed metrics lay the groundwork for enhancing construction safety through automated near-miss reporting and documentation. Furthermore, it helps for the establishment of safety management schemes in the construction industry, specifically in identifying near-misses. This research offers valuable insight into developing guidelines for safety managers to improve near-miss reporting and detection on construction sites. In sum, the findings can be valuable for other industries also looking to establish or assess their own safety management systems.

Real-Time Detection of Drill Pipe Joints Using Improved YOLOv5x Model Applied to Drilling Operation Images

It is widely known that pipe assembly and disassembly still lacks automation. To enhance drilling efficiency, we propose an autonomous detection and positioning model based on improved YOLOv5x for drill pipe joints. Firstly, we use Activate or Not (ACON) activation function and Convolution Block Attention Module (CBAM) to enhance feature extraction and representation ability. Then, the loss function is changed from Complete IoU (CIOU) loss to Scale-Invariant IoU (SIOU) loss, which increases the accuracy of the bounding box regression. Finally, the predict heads are tailored to be more effective in detecting tiny targets. Following network training, the final drill pipe joint detection model, based on the improved YOLOv5x, achieved an average accuracy of 99.10%, a 3.5% improvement over the base YOLOv5x algorithm. The proposed method effectively promotes the intelligence of oil drilling equipment by quickly and accurately detecting drill pipe joints, consequently enhancing drilling operation efficiency.

Brain Tumor Classification using Probabilistic Neural Network

Brain tumour classification is proposed in this work using probabilistic neural networks to handle images and data processing techniques for autonomous detection. Conventionally, the classification and detection of brain tumours are done by human inspection with a medical resonance image (MRI) of the brain. The manually operated methods could be more practical for massive datasets and non-reproducible. During MRI screening, noise is generated, and it leads to serious accuracy issues in classifying the disease. The real-time difficulties should be overcome with the help of artificial intelligence, which is a better solution for this field. Hence, this paper applied the probabilistic neural network. The proposed work was split into two stages: decision-making, performed in two phases; feature extraction using the principal component analysis; and classification using probabilistic neural network (PNN). The performance evaluation of the PNN classifier was based on the network's training performance and classification results. Probabilistic Neural Network provides better classification and is a promising tool for classifying tumours.

Dementia detection using parameter optimization for multimodal datasets

Dementia, a neurodegenerative disorder, is more prominent among elderly people. This disease is one of the primary contributors amongst other diseases having a high social impact in continents of Europe and America. Treatment of the neurological disorders of dementia patients have become possible due to the Advances in medical diagnosis as in the use of Magnetic Resonance Imaging (MRI). Artificial Intelligence (AI) and Machine Learning (ML) techniques have provided solutions that enable fast, accurate and autonomous detection of diseases at their early stage. This in turn has improvised the entire health care system. This study proposes a diagnostic method, based on ML, for detecting dementia disease. The Open Access Series of Imaging Studies (OASIS) database and Alzheimer’s dataset (4 class of images) have been used for testing and training of various ML models. This involves the classification of the dependent variable into demented and non-demented patient. ML models as in Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, k-nearest neighbor (KNN), Random Forest, Adaptive Boosting (ADA boost), Gradient Boosting, XG Boost, were trained and tested using OASIS dataset. Models were trained with 70% of data and tested on 30% of data. Hyper tuning of parameters of these models was also carried out to check for improvement in the results. Analysis showed that Naïve Bayes was the best amongst all giving 95% accuracy, 98% precision, 93% recall and 95% F1-score.

Adversarial patch-based false positive creation attacks against aerial imagery object detectors

Although adversarial attacks have revealed weaknesses in Deep Neural Networks (DNNs)-based aerial detectors, they present a new paradigm for concealing vulnerable assets from autonomous detection systems onboard satellites. Among them, adversarial patches were widely applied due to their physical realizability. Nonetheless, most existing adversarial patch-based attack methods are developed to hide objects from detectors to achieve a vanishing attack. This paper proposes a novel Adversarial Patch False Positive Creation Attack (APFP-CA) framework that enables aerial detectors to recognize non-existent objects, thereby realizing a creation attack. Concretely, the APFP-CA models the creation attack as a two-stage optimization problem. The first stage uses a well-designed efficient loss function to increase the objectness score of patches placed anywhere in the scene to achieve untargeted attacks. The second stage involves elaborating two category-dependent loss functions for fulfilling targeted attacks. Experiments conducted on diverse datasets and detectors demonstrate the effectiveness and universality of our method. Transfer attacks across different datasets and models validate the generalizability of the optimized adversarial patches. Finally, we perform several proportionally scaled experiments physically to illustrate that the optimized adversarial patches can successfully deceive aerial detectors in the physical world. The proposed approach offers a novel contribution to adversarial attacks against aerial imagery objectors and holds potential for practical applications in high-security systems.

Autonomous Detection of Humans in Off-Limits Mountain Areas.

This paper is on the autonomous detection of humans in off-limits mountains. In off-limits mountains, a human rarely exists, thus human detection is an extremely rare event. Due to the advances in artificial intelligence, object detection-classification algorithms based on a Convolution Neural Network (CNN) can be used for this application. However, considering off-limits mountains, there should be no person in general. Thus, it is not desirable to run object detection-classification algorithms continuously, since they are computationally heavy. This paper addresses a time-efficient human detector system, based on both motion detection and object classification. The proposed scheme is to run a motion detection algorithm from time to time. In the camera image, we define a feasible human space where a human can appear. Once motion is detected inside the feasible human space, one enables the object classification, only inside the bounding box where motion is detected. Since motion detection inside the feasible human space runs much faster than an object detection-classification method, the proposed approach is suitable for real-time human detection with low computational loads. As far as we know, no paper in the literature used the feasible human space, as in our paper. The outperformance of our human detector system is verified by comparing it with other state-of-the-art object detection-classification algorithms (HOG detector, YOLOv7 and YOLOv7-tiny) under experiments. This paper demonstrates that the accuracy of the proposed human detector system is comparable to other state-of-the-art algorithms, while outperforming in computational speed. Our experiments show that in environments with no humans, the proposed human detector runs 62 times faster than YOLOv7 method, while showing comparable accuracy.

Evaluation of deep learning techniques for plant disease detection

In recent years, several proposals have been based on Artificial Intelligence techniques for automatically detecting the presence of pests and diseases in crops from images usually taken with a camera. By training with pictures of affected crops and healthy crops, artificial intelligence techniques learn to distinguish one from the other. Furthermore, in the long term, it is intended that the tools developed from such approaches will allow the automation and increased frequency of plant analysis, thus increasing the possibility of determining and predicting crop health and potential biotic risks. However, the great diversity of proposed solutions leads us to the need to study them, present possible situations for their improvement, such as image preprocessing, and analyse the robustness of the proposals examined against more realistic pictures than those existing in the datasets typically used. Taking all this into account, this paper embarks on a comprehensive exploration of various AI techniques leveraging leaf images for the autonomous detection of plant diseases. By fostering a deeper understanding of the strengths and limitations of these methodologies, this research contributes to the vanguard of agricultural disease detection, propelling innovation, and fostering the maturation of AI-driven solutions in this critical domain.

RRT Autonomous Detection Algorithm Based on Multiple Pilot Point Bias Strategy and Karto SLAM Algorithm

RRT Autonomous Detection Algorithm Based on Multiple Pilot Point Bias Strategy and Karto SLAM Algorithm

A Ground-to-Air Infrared Small and Small Target Autonomous Detection Equipment

A Ground-to-Air Infrared Small and Small Target Autonomous Detection Equipment