X-ray detection and imaging via scintillators has been utilized in missions worldwide within areas of scientific research,medical industry,military defense and homeland security.Commercial scintillators are costly wit...X-ray detection and imaging via scintillators has been utilized in missions worldwide within areas of scientific research,medical industry,military defense and homeland security.Commercial scintillators are costly with high energy consumption through the sintering.It is of great significance to seek alternative scintillating materials for sensitive X-ray detection in the next-generation.Herein,eight structure-defined Ln(Ⅲ)-based metal-organic frameworks(Ln-MOFs)were prepared,2D[Ln_(2)(1,4-ndc)_(3)(DMF)_(4)]_(n)·nH_(2)O(Ln=Sm 1,Eu 2,Dy 3,Tb 4)and 3D[Ln_(4)(2,6-ndc)_(6)(μ_(2)H_(2)O)2(H_(2)O)_(4)]n·2nH_(2)O(Ln=Sm 5,Eu 6,Dy 7,Tb 8),where 1,4-H_(2)ndc=1,4-naphthalene dicarboxylate acid,2,6-H_(2)ndc=2,6-napthalene dicarboxylate acid,DMF=N,N-dimethylformamide.Merely compounds 2 and 6 show remarkable X-ray scintillation performance via the characteristic red emissions of Eu(Ⅲ)ions,in which the absorbed energy from the triplet states of the organic moieties can be transferred more efficiently to the resonance emission levels of Eu(Ⅲ)ions than other lanthanide(Ⅲ)ions.The X-ray dosage rate detection limits of 2 and 6 are superior to the standard for the medical X-ray diagnosis dosage rate.As proofs-of-concepts,matrix-mixed membranes fabricated with 2 and 6 have achieved remarkable X-ray imaging with high resolution for practical object shooting.展开更多
In recent years,great progress has been achieved for organicinorganic halide perovskites due to their excellent optoelectronic properties and stability for photovoltaics,light emitting diodes,and high-energy radiation...In recent years,great progress has been achieved for organicinorganic halide perovskites due to their excellent optoelectronic properties and stability for photovoltaics,light emitting diodes,and high-energy radiation detection[1-5].One-dimensional(1D)perovskites,as an important derivative of three-dimensional(3D)perovskites,exhibit low exciton dissociation efficiency,which can produce strong quantum confinement and form self-trapping excited state[6],In addition,the hydrophobic properties and the inhibition of ion migration from large organic cations improve the moisture and thermal stability for optoelectronic devices.展开更多
Scintillation semiconductors play increasingly important medical diagnosis and industrial inspection roles.Recently,two-dimensional(2D)perovskites have been shown to be promising materials for medical X-ray imaging,bu...Scintillation semiconductors play increasingly important medical diagnosis and industrial inspection roles.Recently,two-dimensional(2D)perovskites have been shown to be promising materials for medical X-ray imaging,but they are mostly used in low-energy(≤130 keV)regions.Direct detection of MeV X-rays,which ensure thorough penetration of the thick shell walls of containers,trucks,and aircraft,is also highly desired in practical industrial applications.Unfortunately,scintillation semiconductors for high-energy X-ray detection are currently scarce.Here,This paper reports a 2D(C_(4)H_(9)NH_(3))_(2)PbBr_(4)single crystal with outstanding sensitivity and stability toward X-ray radiation that provides an ultra-wide detectable X-ray range of between 8.20 nGy_(air)s^(-1)(50 keV)and 15.24 mGy_(air)s^(-1)(9 MeV).The(C_(4)H_(9)NH_(3))_(2)PbBr_(4)single-crystal detector with a vertical structure is used for high-performance X-ray imaging,delivering a good spatial resolution of 4.3 Ip mm^(-1)in a plane-scan imaging system.Low ionic migration in the 2D perovskite enables the vertical device to be operated with hundreds of keV to MeV X-ray radiation at high bias voltages,leading to a sensitivity of 46.90μC Gy_(air)-1 cm^(-2)(-1.16 Vμm^(-1))with 9 MeV X-ray radiation,demonstrating that 2D perovskites have enormous potential for high-energy industrial applications.展开更多
Lead-halide perovskites exhibit outstanding performance in X-ray detection due to their intrinsic features such as high charge carrier mobility,large atomic number,and long carrier lifetime,but the toxicity of lead is...Lead-halide perovskites exhibit outstanding performance in X-ray detection due to their intrinsic features such as high charge carrier mobility,large atomic number,and long carrier lifetime,but the toxicity of lead is regarded as the major factor hindering their development.Here,we introduce organic molecule(R)-(-)-2-methylpiperazine(R-MPz)into the bismuth-based structure to synthesize lead-free(R)-(H_(2)MPz)BiI_(5)(R-MBI).The high-quality centimeter-sized single crystals have been obtained,which show a low dark current and superior environmental stability.Particularly,the single-crystal device of R-MBI exhibits a highμτproduct up to 1.88×10^(-4)cm^(2)/V and a low trap density of 1.21×10^(10)cm^(-3).Further,the detector displays excellent detection sensitivity of 263.58μC Gy_(air)^(-1)cm^(-2)and a favorable low detection limit of 4.35μGyair/s,both of which meet the requirement for medical diagnostics.These findings shed light on the exploration of innovative bismuth-based hybrid perovskites for high-performance X-ray detection.展开更多
Direct X-ray detectors,which directly convert X-rays into electrical signals through semiconductors,have higher space solution than scintillator-mediated indirect X-ray ones and are high desirable for early cancer det...Direct X-ray detectors,which directly convert X-rays into electrical signals through semiconductors,have higher space solution than scintillator-mediated indirect X-ray ones and are high desirable for early cancer detection and other applications,but the mainstream commercialα-Se detector is still largely limited by high production costs,large leakage current and low stability.This article reports an easily prepared,stable radiochromic semiconductive metal–organic framework(MOF),(MV)[Cd_(3)(tdc)_(4)]·2H_(2)O(RCS-1,H_(2)tdc=2,5-thiophenedicarboxylic acid;MV^(2+)=methyl viologen cation)with direct X-ray detecting ability.With a large bulk resistivity of 8.40×10^(9)Ωcm,this material ensures minimal dark current and low noise for X-ray detection.Additionally,it exhibits higher sensitivity to W KαX-rays(98.58μC Gy^(-1)cm^(-2))thanα-Se(~20μC Gy^(-1)cm^(-2)).Meanwhile,unlike most reported direct X-ray detecting semiconductors,compound RCS-1 shows remarkable color change upon X-ray irradiation owing to the presence of photochromism-active viologen cations.This feature offers an appealing visual detecting ability to direct X-ray detectors that provide only the electrical signals.展开更多
X-ray detection plays a crucial role across various aspects of our daily lives,encompassing medical diagnoses,security screenings,and non-destructive examinations in industrial settings.Given the wide array of applica...X-ray detection plays a crucial role across various aspects of our daily lives,encompassing medical diagnoses,security screenings,and non-destructive examinations in industrial settings.Given the wide array of application contexts,a wealth of opportunities is entailed with the practical utilization of both organic and inorganic X-ray detection materials.A novel and promising contender in this realm is the emergence of metal-free organic halide perovskites(O-PVSKs),offering great opportunities and tremendous potential in X-ray detection.This potential can be attributed to the distinct crystalline configuration of O-PVSKs,where organic constituents are structured into an ABX3perovskite arrangement.Consequently,O-PVSKs exhibit captivating characteristics reminiscent of organic materials,such as lightweight nature and modifiability,all while retaining the distinctive traits associated with halide perovskites ranging from diverse structures to tunable optoelectronic properties.This review article delves into the intrinsic attributes of O-PVSKs and critically examines the viability of O-PVSKs in X-ray detection,through which key features that distinguish O-PVSKs from traditional organic semiconductors and perovskites are outlined.This is followed by a perspective given on their future avenues for exploration.展开更多
Halide perovskites have emerged as the next generation of optoelectronic materials and their remarkable performances have been attractive in the fields of solar cells,light-emitting diodes,photodetectors,etc.In additi...Halide perovskites have emerged as the next generation of optoelectronic materials and their remarkable performances have been attractive in the fields of solar cells,light-emitting diodes,photodetectors,etc.In addition,halide perovskites have been reported as an attractive new class of X-ray direct detecting materials recently,owning to the strong X-ray stopping capacity,excellent carrier transport,high sensitivity,and cost-effective manufacturing.Meanwhile,perovskite based direct Xray imagers have been successfully demonstrated as well.In this review article,we firstly introduced some fundamental principles of direct X-ray detection and imaging,and summarized the advances of perovskite materials for these purposes and finally put forward some needful and feasible directions.展开更多
Sensitive and reliable X-ray detectors are essential for medical radiography,industrial inspection and security screening.Lowering the radiation dose allows reduced health risks and increased frequency and fidelity of...Sensitive and reliable X-ray detectors are essential for medical radiography,industrial inspection and security screening.Lowering the radiation dose allows reduced health risks and increased frequency and fidelity of diagnostic technologies for earlier detection of disease and its recurrence.Three-dimensional(3 D)organic-inorganic hybrid lead halide perovskites are promising for direct X-ray detection-they show improved sensitivity compared to conventional X-ray detectors.However,their high and unstable dark current,caused by ion migration and high dark carrier concentration in the 3 D hybrid perovskites,limits their performance and long-term operation stability.Here we report ultrasensitive,stable X-ray detectors made using zero-dimensional(0 D)methylammonium bismuth iodide perovskite(MA3Bi2I9)single crystals.The 0 D crystal structure leads to a high activation energy(Ea)for ion migration(0.46 e V)and is also accompanied by a low dark carrier concentration(~10^6 cm^-3).The X-ray detectors exhibit sensitivity of 10,620μC Gy-1 air cm-2,a limit of detection(Lo D)of 0.62 nG yairs-1,and stable operation even under high applied biases;no deterioration in detection performance was observed following sensing of an integrated X-ray irradiation dose of^23,800 m Gyair,equivalent to>200,000 times the dose required for a single commercial X-ray chest radiograph.Regulating the ion migration channels and decreasing the dark carrier concentration in perovskites provide routes for stable and ultrasensitive X-ray detectors.展开更多
X-ray andγ-ray detectors are widely used in medical,military,security,material analysis,and industrial inspection.In recent years,perovskite materials have become promising materials for radiation detection owing to ...X-ray andγ-ray detectors are widely used in medical,military,security,material analysis,and industrial inspection.In recent years,perovskite materials have become promising materials for radiation detection owing to their strong stopping power,considerable carrier transportation ability,and simple synthesis process.Previous studies have demonstrated both direct and indirect radiation detectors using perovskite materials.In this review,we aim to elucidate the mechanism by which X-rays andγ-rays interact with matter,explain the principles of the energy integrating mode and photon counting mode for direct detection,and discuss the key factors determining device performance.Furthermore,we summarize recent advances in perovskite-based radiation detectors for both modes.Additionally,we identify challenges that need to be overcome to enable perovskite materials to be successfully commercialized.展开更多
A diamond film with a size of 6×6×0.5 mm^3 is fabricated by electron-assisted chemical vapor deposition. Raman spectrum analysis, x-ray diffraction and scanning electron microscope images confirm the high pu...A diamond film with a size of 6×6×0.5 mm^3 is fabricated by electron-assisted chemical vapor deposition. Raman spectrum analysis, x-ray diffraction and scanning electron microscope images confirm the high purity and large grain size, which is larger than 300 μm. Its resistivity is higher than 10^12 W· cm. Interlaced-finger electrodes are imprinted onto the diamond film to develop an x-ray detector. Ohmic contact is confirmed by checking the linearity of its current–voltage curve. The dark current is lower than 0.1 n A under an electric field of 30 k V cm^-1. The time response is 220 ps. The sensitivity is about 125 m A W^-1 under a biasing voltage of 100 V.A good linear radiation dose rate is also confirmed. This diamond detector is used to measure x-ray on a Z-pinch, which has a double-layer 'nested tungsten wire array'. The pronounced peaks in the measured waveform clearly characterize the x-ray bursts, which proves the performance of this diamond detector.展开更多
Complementary metal-oxide-semiconductor(CMOS) sensors can convert X-rays into detectable signals; therefore, they are powerful tools in X-ray detection applications. Herein, we explore the physics behind X-ray detecti...Complementary metal-oxide-semiconductor(CMOS) sensors can convert X-rays into detectable signals; therefore, they are powerful tools in X-ray detection applications. Herein, we explore the physics behind X-ray detection performed using CMOS sensors. X-ray measurements were obtained using a simulated positioner based on a CMOS sensor, while the X-ray energy was modified by changing the voltage, current, and radiation time. A monitoring control unit collected video data of the detected X-rays. The video images were framed and filtered to detect the effective pixel points(radiation spots).The histograms of the images prove there is a linear relationship between the pixel points and X-ray energy. The relationships between the image pixel points, voltage, and current were quantified, and the resultant correlations were observed to obey some physical laws.展开更多
A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defec...A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.展开更多
AIM: To determine the utility of X-ray in identifying non-metallic foreign body(FB) and assess inter-radiologist agreement in identifying non-metal FB. METHODS: Focus groups of nurses, fellows, and attending physician...AIM: To determine the utility of X-ray in identifying non-metallic foreign body(FB) and assess inter-radiologist agreement in identifying non-metal FB. METHODS: Focus groups of nurses, fellows, and attending physicians were conducted to determine commonly ingested objects suitable for inclusion. Twelve potentially ingested objects(clay, plastic bead, crayon, plastic ring, plastic army figure, glass bead, paperclip, drywall anchor, eraser, Lego?, plastic triangle toy, and barrette) were embedded in a gelatin slab placed on top of a water-equivalent phantom to simulate density of a child's abdomen. The items were selected due to wide availability and appropriate size for accidental pediatric ingestion. Plain radiography of the embedded FBs was obtained. Five experienced radiologists blinded to number and types of objects were asked to identify the FBs. The radiologist was first asked to count thenumber of items that were visible then to identify the shape of each item and describe it to a study investigator who recorded all responses. Overall inter-rater reliability was analyzed using percent agreement and κ coefficient. We calculated P value to assess the probability of error involved in accepting the κ value.RESULTS: Fourteen objects were radiographed including 12 original objects and 2 duplicates. The model's validity was supported by clear identification of a radiolucent paperclip as a positive control, and lack of identification of plastic beads(negative control) despite repeated inclusion. Each radiologist identified 7-9 of the 14 objects(mean 8, 67%). Six unique objects(50%) were identified by all radiologists and four unique objects(33%) were not identified by any radiologist(plastic bead, LegoTM, plastic triangle toy, and barrette). Identification of objects that were not present, false-positives, occurred 1-2 times per radiologist(mean 1.4). An additional 17% of unique objects were identified by less than half of the radiologists. Agreement between radiologists was considered almost perfect(kappa 0.86 ± 0.08, P < 0.0001).CONCLUSION: We demonstrate potential non-identification of commonly ingested non-metal FBs in children. A registry for radiographic visibility of ingested objects should be created to improve clinical decision-making.展开更多
This study explores the application of X-ray-induced photochromism and photoluminescence in optical storage,anti-counterfeiting,non-destructive testing,and high-resolution X-ray detection and imaging.Ba_(2)LaNbO_(6):B...This study explores the application of X-ray-induced photochromism and photoluminescence in optical storage,anti-counterfeiting,non-destructive testing,and high-resolution X-ray detection and imaging.Ba_(2)LaNbO_(6):Bi,Eu phosphors were synthesized,with Bi enhancing X-ray-induced photochromic prop-erties.Under X-ray irradiation,the phosphors transfer from white to red in bright field conditions and emit red photoluminescence in dark field conditions.Exposure to 470 nm ultraviolet light induces rapid bleaching.The mechanisms of photochromism and photoluminescence,particularly Bi's role as a colorant,were systematically investigated.The Ba_(2)LaNbO_(6):Bi,Eu phosphors film achieves high resolution,high-lighting its potential for X-ray imaging and non-destructive testing.Furthermore,the flexible Ba_(2)LaNbO_(6):Bi,Eu film supports dual-mode imaging and detection,addressing the limitations of traditional flat dis-plays in 3D imaging.展开更多
Two-dimensional(2D)multilayered perovskites are poised to revitalize the field of efficient X-ray detection due to their strong X-ray absorption ability and excellent carrier transport.However,2D alternating cations i...Two-dimensional(2D)multilayered perovskites are poised to revitalize the field of efficient X-ray detection due to their strong X-ray absorption ability and excellent carrier transport.However,2D alternating cations intercalation(ACI)type multilayered perovskites,which hold promise as potential X-ray detection materials,still remain largely unexplored in X-ray detection capabilities.Herein,through methylammonium intercalation reorienting aromatic amine cations,an ACI multilayered perovskite(NMA)_(3)(MA)_(3)Pb_(4)I_(14)(NMPI,NMA=N-methylbenzylaminium,MA=methylammonium)is successfully constructed for efficient self-driven X-ray detection.Specifically,the reconstructed NMPI has a smoother multilayered inorganic framework with an enhanced mobility-lifetime product compared with the prototype(NMA)_(4)Pb_(3)I_(10).Notably,based on polar structure-induced radiation photovoltage(1.2 V),NMPI exhibits a high sensitivity of 113.78μC Gy^(-1)cm^(-2)and a low detection limit of 162 nGy s^(-1)under zero bias.This work first explores sensitive self-driven X-ray detection in ACI-type multilayered perovskite,shedding light on future exploration for high-performance X-ray detection.展开更多
Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakt...Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.展开更多
In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds...In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propo...Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.展开更多
基金supported by the National Natural Science Foundation of China(Nos.21971240 and 21827813)the National Key R&D Program of China(No.2017YFA0206802)the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDB20000000).
文摘X-ray detection and imaging via scintillators has been utilized in missions worldwide within areas of scientific research,medical industry,military defense and homeland security.Commercial scintillators are costly with high energy consumption through the sintering.It is of great significance to seek alternative scintillating materials for sensitive X-ray detection in the next-generation.Herein,eight structure-defined Ln(Ⅲ)-based metal-organic frameworks(Ln-MOFs)were prepared,2D[Ln_(2)(1,4-ndc)_(3)(DMF)_(4)]_(n)·nH_(2)O(Ln=Sm 1,Eu 2,Dy 3,Tb 4)and 3D[Ln_(4)(2,6-ndc)_(6)(μ_(2)H_(2)O)2(H_(2)O)_(4)]n·2nH_(2)O(Ln=Sm 5,Eu 6,Dy 7,Tb 8),where 1,4-H_(2)ndc=1,4-naphthalene dicarboxylate acid,2,6-H_(2)ndc=2,6-napthalene dicarboxylate acid,DMF=N,N-dimethylformamide.Merely compounds 2 and 6 show remarkable X-ray scintillation performance via the characteristic red emissions of Eu(Ⅲ)ions,in which the absorbed energy from the triplet states of the organic moieties can be transferred more efficiently to the resonance emission levels of Eu(Ⅲ)ions than other lanthanide(Ⅲ)ions.The X-ray dosage rate detection limits of 2 and 6 are superior to the standard for the medical X-ray diagnosis dosage rate.As proofs-of-concepts,matrix-mixed membranes fabricated with 2 and 6 have achieved remarkable X-ray imaging with high resolution for practical object shooting.
基金supported by the National Key Research and Development Program of China (2016YFA0202403, 2017YFA0204800)the National Natural Science Foundation of China (61974085)+2 种基金the 111 Project (Grant No. B21005)National 1000-talent-plan program (1110010341)the National University Research Fund (Grant No. GK202103104).
文摘In recent years,great progress has been achieved for organicinorganic halide perovskites due to their excellent optoelectronic properties and stability for photovoltaics,light emitting diodes,and high-energy radiation detection[1-5].One-dimensional(1D)perovskites,as an important derivative of three-dimensional(3D)perovskites,exhibit low exciton dissociation efficiency,which can produce strong quantum confinement and form self-trapping excited state[6],In addition,the hydrophobic properties and the inhibition of ion migration from large organic cations improve the moisture and thermal stability for optoelectronic devices.
基金financial support from the National Natural Science Foundation of China(Nos.22075284,51872287,and U2030118)the Youth Innovation Promotion Association CAS(No.2019304)+1 种基金the Fund of Mindu Innovation Laboratory(No.2021ZR201)the Scientific Instrument Developing Project of the Chinese Academy of Sciences(No.YJKYYQ20210039)
文摘Scintillation semiconductors play increasingly important medical diagnosis and industrial inspection roles.Recently,two-dimensional(2D)perovskites have been shown to be promising materials for medical X-ray imaging,but they are mostly used in low-energy(≤130 keV)regions.Direct detection of MeV X-rays,which ensure thorough penetration of the thick shell walls of containers,trucks,and aircraft,is also highly desired in practical industrial applications.Unfortunately,scintillation semiconductors for high-energy X-ray detection are currently scarce.Here,This paper reports a 2D(C_(4)H_(9)NH_(3))_(2)PbBr_(4)single crystal with outstanding sensitivity and stability toward X-ray radiation that provides an ultra-wide detectable X-ray range of between 8.20 nGy_(air)s^(-1)(50 keV)and 15.24 mGy_(air)s^(-1)(9 MeV).The(C_(4)H_(9)NH_(3))_(2)PbBr_(4)single-crystal detector with a vertical structure is used for high-performance X-ray imaging,delivering a good spatial resolution of 4.3 Ip mm^(-1)in a plane-scan imaging system.Low ionic migration in the 2D perovskite enables the vertical device to be operated with hundreds of keV to MeV X-ray radiation at high bias voltages,leading to a sensitivity of 46.90μC Gy_(air)-1 cm^(-2)(-1.16 Vμm^(-1))with 9 MeV X-ray radiation,demonstrating that 2D perovskites have enormous potential for high-energy industrial applications.
基金financially supported by the National Natural Science Foundation of China(Nos.22175177,21971238,22193042,21833010,22125110,22122507,21921001,and U21A2069)the Key Research Program of Frontier Sciences of the Chinese Academy of Sciences(No.ZDBS-LY-SLH024)+1 种基金The National Postdoctoral Program for Innovative Talents(No.BX2021315)the National Key Research and Development Program of China(No.2019YFA0210402)。
文摘Lead-halide perovskites exhibit outstanding performance in X-ray detection due to their intrinsic features such as high charge carrier mobility,large atomic number,and long carrier lifetime,but the toxicity of lead is regarded as the major factor hindering their development.Here,we introduce organic molecule(R)-(-)-2-methylpiperazine(R-MPz)into the bismuth-based structure to synthesize lead-free(R)-(H_(2)MPz)BiI_(5)(R-MBI).The high-quality centimeter-sized single crystals have been obtained,which show a low dark current and superior environmental stability.Particularly,the single-crystal device of R-MBI exhibits a highμτproduct up to 1.88×10^(-4)cm^(2)/V and a low trap density of 1.21×10^(10)cm^(-3).Further,the detector displays excellent detection sensitivity of 263.58μC Gy_(air)^(-1)cm^(-2)and a favorable low detection limit of 4.35μGyair/s,both of which meet the requirement for medical diagnostics.These findings shed light on the exploration of innovative bismuth-based hybrid perovskites for high-performance X-ray detection.
基金financial support by the National Key Research and Development Program of Ministry of Science and Technology(No.2021YFB3801604)the National Natural Science Foundation(Nos.22073102,21827813,21921001)of China。
文摘Direct X-ray detectors,which directly convert X-rays into electrical signals through semiconductors,have higher space solution than scintillator-mediated indirect X-ray ones and are high desirable for early cancer detection and other applications,but the mainstream commercialα-Se detector is still largely limited by high production costs,large leakage current and low stability.This article reports an easily prepared,stable radiochromic semiconductive metal–organic framework(MOF),(MV)[Cd_(3)(tdc)_(4)]·2H_(2)O(RCS-1,H_(2)tdc=2,5-thiophenedicarboxylic acid;MV^(2+)=methyl viologen cation)with direct X-ray detecting ability.With a large bulk resistivity of 8.40×10^(9)Ωcm,this material ensures minimal dark current and low noise for X-ray detection.Additionally,it exhibits higher sensitivity to W KαX-rays(98.58μC Gy^(-1)cm^(-2))thanα-Se(~20μC Gy^(-1)cm^(-2)).Meanwhile,unlike most reported direct X-ray detecting semiconductors,compound RCS-1 shows remarkable color change upon X-ray irradiation owing to the presence of photochromism-active viologen cations.This feature offers an appealing visual detecting ability to direct X-ray detectors that provide only the electrical signals.
基金support from the National Natural Science Foundation of China(Nos.62205154 and 62205155)the Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications(Nos.NY221112 and NY222104)。
文摘X-ray detection plays a crucial role across various aspects of our daily lives,encompassing medical diagnoses,security screenings,and non-destructive examinations in industrial settings.Given the wide array of application contexts,a wealth of opportunities is entailed with the practical utilization of both organic and inorganic X-ray detection materials.A novel and promising contender in this realm is the emergence of metal-free organic halide perovskites(O-PVSKs),offering great opportunities and tremendous potential in X-ray detection.This potential can be attributed to the distinct crystalline configuration of O-PVSKs,where organic constituents are structured into an ABX3perovskite arrangement.Consequently,O-PVSKs exhibit captivating characteristics reminiscent of organic materials,such as lightweight nature and modifiability,all while retaining the distinctive traits associated with halide perovskites ranging from diverse structures to tunable optoelectronic properties.This review article delves into the intrinsic attributes of O-PVSKs and critically examines the viability of O-PVSKs in X-ray detection,through which key features that distinguish O-PVSKs from traditional organic semiconductors and perovskites are outlined.This is followed by a perspective given on their future avenues for exploration.
文摘Halide perovskites have emerged as the next generation of optoelectronic materials and their remarkable performances have been attractive in the fields of solar cells,light-emitting diodes,photodetectors,etc.In addition,halide perovskites have been reported as an attractive new class of X-ray direct detecting materials recently,owning to the strong X-ray stopping capacity,excellent carrier transport,high sensitivity,and cost-effective manufacturing.Meanwhile,perovskite based direct Xray imagers have been successfully demonstrated as well.In this review article,we firstly introduced some fundamental principles of direct X-ray detection and imaging,and summarized the advances of perovskite materials for these purposes and finally put forward some needful and feasible directions.
基金supported by the National Natural Science Foundation of China(Grant nos.21773218,61974063)the Sichuan Province(Grant no.2018JY0206)the China Academy of Engineering Physics(Grant no.YZJJLX2018007)。
文摘Sensitive and reliable X-ray detectors are essential for medical radiography,industrial inspection and security screening.Lowering the radiation dose allows reduced health risks and increased frequency and fidelity of diagnostic technologies for earlier detection of disease and its recurrence.Three-dimensional(3 D)organic-inorganic hybrid lead halide perovskites are promising for direct X-ray detection-they show improved sensitivity compared to conventional X-ray detectors.However,their high and unstable dark current,caused by ion migration and high dark carrier concentration in the 3 D hybrid perovskites,limits their performance and long-term operation stability.Here we report ultrasensitive,stable X-ray detectors made using zero-dimensional(0 D)methylammonium bismuth iodide perovskite(MA3Bi2I9)single crystals.The 0 D crystal structure leads to a high activation energy(Ea)for ion migration(0.46 e V)and is also accompanied by a low dark carrier concentration(~10^6 cm^-3).The X-ray detectors exhibit sensitivity of 10,620μC Gy-1 air cm-2,a limit of detection(Lo D)of 0.62 nG yairs-1,and stable operation even under high applied biases;no deterioration in detection performance was observed following sensing of an integrated X-ray irradiation dose of^23,800 m Gyair,equivalent to>200,000 times the dose required for a single commercial X-ray chest radiograph.Regulating the ion migration channels and decreasing the dark carrier concentration in perovskites provide routes for stable and ultrasensitive X-ray detectors.
基金supported by the Outstanding Youth Fund of the National Natural Science Foundation of China(No.T2325020)the National Natural Science Foundation of China(Nos.62074136 and 52273307)the Natural Science Foundation of Zhejiang Province,China(No.LZ23F050005).
文摘X-ray andγ-ray detectors are widely used in medical,military,security,material analysis,and industrial inspection.In recent years,perovskite materials have become promising materials for radiation detection owing to their strong stopping power,considerable carrier transportation ability,and simple synthesis process.Previous studies have demonstrated both direct and indirect radiation detectors using perovskite materials.In this review,we aim to elucidate the mechanism by which X-rays andγ-rays interact with matter,explain the principles of the energy integrating mode and photon counting mode for direct detection,and discuss the key factors determining device performance.Furthermore,we summarize recent advances in perovskite-based radiation detectors for both modes.Additionally,we identify challenges that need to be overcome to enable perovskite materials to be successfully commercialized.
基金supported by the National Key R&D Program of China(Grant No.2017YFE0301300)the Hunan Provincial Innovation Foundation for Postgraduate(Grant No.CX2018B588)。
文摘A diamond film with a size of 6×6×0.5 mm^3 is fabricated by electron-assisted chemical vapor deposition. Raman spectrum analysis, x-ray diffraction and scanning electron microscope images confirm the high purity and large grain size, which is larger than 300 μm. Its resistivity is higher than 10^12 W· cm. Interlaced-finger electrodes are imprinted onto the diamond film to develop an x-ray detector. Ohmic contact is confirmed by checking the linearity of its current–voltage curve. The dark current is lower than 0.1 n A under an electric field of 30 k V cm^-1. The time response is 220 ps. The sensitivity is about 125 m A W^-1 under a biasing voltage of 100 V.A good linear radiation dose rate is also confirmed. This diamond detector is used to measure x-ray on a Z-pinch, which has a double-layer 'nested tungsten wire array'. The pronounced peaks in the measured waveform clearly characterize the x-ray bursts, which proves the performance of this diamond detector.
基金supported by the Plan for Science Innovation Talent of Henan Province(No.154100510007)the Natural and Science Foundation in Henan Province(No.162300410179)the Cultivation Foundation of Henan Normal University National Project(No.2017PL04)
文摘Complementary metal-oxide-semiconductor(CMOS) sensors can convert X-rays into detectable signals; therefore, they are powerful tools in X-ray detection applications. Herein, we explore the physics behind X-ray detection performed using CMOS sensors. X-ray measurements were obtained using a simulated positioner based on a CMOS sensor, while the X-ray energy was modified by changing the voltage, current, and radiation time. A monitoring control unit collected video data of the detected X-rays. The video images were framed and filtered to detect the effective pixel points(radiation spots).The histograms of the images prove there is a linear relationship between the pixel points and X-ray energy. The relationships between the image pixel points, voltage, and current were quantified, and the resultant correlations were observed to obey some physical laws.
文摘A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.
文摘AIM: To determine the utility of X-ray in identifying non-metallic foreign body(FB) and assess inter-radiologist agreement in identifying non-metal FB. METHODS: Focus groups of nurses, fellows, and attending physicians were conducted to determine commonly ingested objects suitable for inclusion. Twelve potentially ingested objects(clay, plastic bead, crayon, plastic ring, plastic army figure, glass bead, paperclip, drywall anchor, eraser, Lego?, plastic triangle toy, and barrette) were embedded in a gelatin slab placed on top of a water-equivalent phantom to simulate density of a child's abdomen. The items were selected due to wide availability and appropriate size for accidental pediatric ingestion. Plain radiography of the embedded FBs was obtained. Five experienced radiologists blinded to number and types of objects were asked to identify the FBs. The radiologist was first asked to count thenumber of items that were visible then to identify the shape of each item and describe it to a study investigator who recorded all responses. Overall inter-rater reliability was analyzed using percent agreement and κ coefficient. We calculated P value to assess the probability of error involved in accepting the κ value.RESULTS: Fourteen objects were radiographed including 12 original objects and 2 duplicates. The model's validity was supported by clear identification of a radiolucent paperclip as a positive control, and lack of identification of plastic beads(negative control) despite repeated inclusion. Each radiologist identified 7-9 of the 14 objects(mean 8, 67%). Six unique objects(50%) were identified by all radiologists and four unique objects(33%) were not identified by any radiologist(plastic bead, LegoTM, plastic triangle toy, and barrette). Identification of objects that were not present, false-positives, occurred 1-2 times per radiologist(mean 1.4). An additional 17% of unique objects were identified by less than half of the radiologists. Agreement between radiologists was considered almost perfect(kappa 0.86 ± 0.08, P < 0.0001).CONCLUSION: We demonstrate potential non-identification of commonly ingested non-metal FBs in children. A registry for radiographic visibility of ingested objects should be created to improve clinical decision-making.
基金supported by the Key Project of the National Natural Science Foundation of China-Yunnan Joint Fund(No.U2102215)National Natural Science Foundation(No.52472002)+5 种基金Science and Technology Project of Southwest Joint Graduate School of Yunnan Province(No.202302A0370008)2024 Industrial Innovation Talent Support Project(Preparation of luminous materials,performance control and application in plateau agriculture,No.YFGRC202407)National Natural Science Foundation of High-End Foreign Expert Introduction Plan(No.G2022039008L)Academician Workstation of Cherkasova Tatiana in Yunnan Province(No.202305AF150099)Yunnan Province Major Science and Technology Special Plan(No.202302AB080005)and UTS Chancellor’s Research Fellowship Program(No.J.L.,PRO22-15457)the National Health and Medical Research Council(No.J.L.,2025442).
文摘This study explores the application of X-ray-induced photochromism and photoluminescence in optical storage,anti-counterfeiting,non-destructive testing,and high-resolution X-ray detection and imaging.Ba_(2)LaNbO_(6):Bi,Eu phosphors were synthesized,with Bi enhancing X-ray-induced photochromic prop-erties.Under X-ray irradiation,the phosphors transfer from white to red in bright field conditions and emit red photoluminescence in dark field conditions.Exposure to 470 nm ultraviolet light induces rapid bleaching.The mechanisms of photochromism and photoluminescence,particularly Bi's role as a colorant,were systematically investigated.The Ba_(2)LaNbO_(6):Bi,Eu phosphors film achieves high resolution,high-lighting its potential for X-ray imaging and non-destructive testing.Furthermore,the flexible Ba_(2)LaNbO_(6):Bi,Eu film supports dual-mode imaging and detection,addressing the limitations of traditional flat dis-plays in 3D imaging.
基金supported by the National Natural Science Foundation of China(22435005,22193042,21921001,22125110,22122507,U21A2069)the Key Research Program of Frontier Sciences of the Chinese Academy of Sciences(ZDBSLY-SLH024)。
文摘Two-dimensional(2D)multilayered perovskites are poised to revitalize the field of efficient X-ray detection due to their strong X-ray absorption ability and excellent carrier transport.However,2D alternating cations intercalation(ACI)type multilayered perovskites,which hold promise as potential X-ray detection materials,still remain largely unexplored in X-ray detection capabilities.Herein,through methylammonium intercalation reorienting aromatic amine cations,an ACI multilayered perovskite(NMA)_(3)(MA)_(3)Pb_(4)I_(14)(NMPI,NMA=N-methylbenzylaminium,MA=methylammonium)is successfully constructed for efficient self-driven X-ray detection.Specifically,the reconstructed NMPI has a smoother multilayered inorganic framework with an enhanced mobility-lifetime product compared with the prototype(NMA)_(4)Pb_(3)I_(10).Notably,based on polar structure-induced radiation photovoltage(1.2 V),NMPI exhibits a high sensitivity of 113.78μC Gy^(-1)cm^(-2)and a low detection limit of 162 nGy s^(-1)under zero bias.This work first explores sensitive self-driven X-ray detection in ACI-type multilayered perovskite,shedding light on future exploration for high-performance X-ray detection.
基金funded by Key research and development Program of Henan Province(No.251111211200)National Natural Science Foundation of China(Grant No.U2004163).
文摘Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.
基金funded by the Joint Funds of the National Natural Science Foundation of China(U2341223)the Beijing Municipal Natural Science Foundation(No.4232067).
文摘In printed circuit board(PCB)manufacturing,surface defects can significantly affect product quality.To address the performance degradation,high false detection rates,and missed detections caused by complex backgrounds in current intelligent inspection algorithms,this paper proposes CG-YOLOv8,a lightweight and improved model based on YOLOv8n for PCB surface defect detection.The proposed method optimizes the network architecture and compresses parameters to reduce model complexity while maintaining high detection accuracy,thereby enhancing the capability of identifying diverse defects under complex conditions.Specifically,a cascaded multi-receptive field(CMRF)module is adopted to replace the SPPF module in the backbone to improve feature perception,and an inverted residual mobile block(IRMB)is integrated into the C2f module to further enhance performance.Additionally,conventional convolution layers are replaced with GSConv to reduce computational cost,and a lightweight Convolutional Block Attention Module based Convolution(CBAMConv)module is introduced after Grouped Spatial Convolution(GSConv)to preserve accuracy through attention mechanisms.The detection head is also optimized by removing medium and large-scale detection layers,thereby enhancing the model’s ability to detect small-scale defects and further reducing complexity.Experimental results show that,compared to the original YOLOv8n,the proposed CG-YOLOv8 reduces parameter count by 53.9%,improves mAP@0.5 by 2.2%,and increases precision and recall by 2.0%and 1.8%,respectively.These improvements demonstrate that CG-YOLOv8 offers an efficient and lightweight solution for PCB surface defect detection.
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金supported by project ZR2022MF330 supported by Shandong Provincial Natural Science Foundationthe National Natural Science Foundation of China under Grant No.61701286.
文摘Synthetic speech detection is an essential task in the field of voice security,aimed at identifying deceptive voice attacks generated by text-to-speech(TTS)systems or voice conversion(VC)systems.In this paper,we propose a synthetic speech detection model called TFTransformer,which integrates both local and global features to enhance detection capabilities by effectively modeling local and global dependencies.Structurally,the model is divided into two main components:a front-end and a back-end.The front-end of the model uses a combination of SincLayer and two-dimensional(2D)convolution to extract high-level feature maps(HFM)containing local dependency of the input speech signals.The back-end uses time-frequency Transformer module to process these feature maps and further capture global dependency.Furthermore,we propose TFTransformer-SE,which incorporates a channel attention mechanism within the 2D convolutional blocks.This enhancement aims to more effectively capture local dependencies,thereby improving the model’s performance.The experiments were conducted on the ASVspoof 2021 LA dataset,and the results showed that the model achieved an equal error rate(EER)of 3.37%without data augmentation.Additionally,we evaluated the model using the ASVspoof 2019 LA dataset,achieving an EER of 0.84%,also without data augmentation.This demonstrates that combining local and global dependencies in the time-frequency domain can significantly improve detection accuracy.
