Header Recognition Research Articles

Scalable photonic reservoir computing based on pulse propagation in parallel passive dispersive links

We propose and demonstrate a scalable photonic reservoir computing system based on pulse propagation in parallel passive dispersive links. The approach features a simple structure and is composed of passive components, such as dispersive elements and ring resonators. The system utilizes a pulsed laser and employs a multi-channel architecture with dispersive elements for pulse broadening and ring resonators for delay stacking. It is verified for its capability to handle both digital tasks (2-bit Boolean logic operations, header recognition) and analog tasks (Mackey-Glass time-series prediction, Lorenz 63 time-series prediction). A major advantage of the approach lies in its scalability. It has been confirmed that more complex tasks can be processed by using a system with more channels, along with dispersive elements and ring resonators with larger dispersion amounts and delays, respectively.

Recognition Method of Cabbage Heads at Harvest Stage under Complex Background Based on Improved YOLOv8n

To address the problems of low recognition accuracy and slow processing speed when identifying harvest-stage cabbage heads in complex environments, this study proposes a lightweight harvesting period cabbage head recognition algorithm that improves upon YOLOv8n. We propose a YOLOv8n-Cabbage model, integrating an enhanced backbone network, the DyHead (Dynamic Head) module insertion, loss function optimization, and model light-weighting. To assess the proposed method, a comparison with extant mainstream object detection models is conducted. The experimental results indicate that the improved cabbage head recognition model proposed in this study can adapt cabbage head recognition under different lighting conditions and complex backgrounds. With a compact size of 4.8 MB, this model achieves 91% precision, 87.2% recall, and a mAP@50 of 94.5%—the model volume has been reduced while the evaluation metrics have all been improved over the baseline model. The results demonstrate that this model can be applied to the real-time recognition of harvest-stage cabbage heads under complex field environments.

A Comparative Dataset of Annotated Broccoli Heads Recorded with Depth Cameras from a Moving Vehicle

An extensive, publicly available dataset is presented—the LAR Broccoli dataset—which contains 20,000 manually annotated images of broccoli heads captured from a moving tractor at an organic farm in the UK. The dataset contains images of the same row of broccoli heads recorded at 30 frames per second (fps) with three different cameras. Two off-the-shelf, relatively low-cost depth-sensing cameras were used, with the tractor moving at a speed of around 1 km/h, in addition to a webcam, with the tractor moving twice as fast. The utility of the dataset is demonstrated in four ways. First, three different state-of-the-art detector models were trained on the dataset, achieving an overall mean Average Precision (mAP) score of over 95% for the best-performing detector. The results validate the utility of the dataset for the standard task of in-field broccoli head recognition. Second, experiments with transfer learning were conducted, initialised with a smaller pre-trained broccoli detection model, and refined with the LAR Broccoli dataset. Third, we assessed the advantages of transfer learning not only using mAP but also according to time and space requirements for training models, which provides a proxy metric for energy efficiency, a practical consideration for real-world model training. Fourth, the cross-camera generalisation among the three camera systems was compared. The results highlight that testing and training detector models using different camera systems can lead to reduced performance, unless the training set also includes some images captured in the same manner as those in the test set.

Experimental reservoir computing with diffractively coupled VCSELs.

We present experiments on reservoir computing (RC) using a network of vertical-cavity surface-emitting lasers (VCSELs) that we diffractively couple via an external cavity. Our optical reservoir computer consists of 24 physical VCSEL nodes. We evaluate the system's memory and solve the 2-bit XOR task and the 3-bit header recognition (HR) task with bit error ratios (BERs) below 1% and the 2-bit digital-to-analog conversion (DAC) task with a root mean square error (RMSE) of 0.067.

Research on the Application of Intelligent Recognition Technology in the Prediction of Violation Behaviour at Electricity Work Sites

Abstract To realize the safe operation of electric power site, this paper proposes an intelligent recognition technology to automatically identify violations. This study successfully constructs a face detection model for power operation sites by combining deep convolutional neural networks and target detection algorithms. A three-way connected feature pyramid structure containing a neuron self-processing module is adopted, and an accuracy test is completed using a Tri-FPN-based target detection network, significantly improving recognition accuracy. In this paper, we also utilized the on-site images collected by video surveillance equipment, combined with CNN algorithm and HOG feature extraction technology to effectively identify the violations and provide early warning of the breaches of the personnel at the power operation site. MAP curves evaluated the detection performance, and the results showed that the head recognition rate was up to 0.9913, and the accuracy rate of all violations exceeded 0.9350.The high accuracy of CNN-based feature fusion extraction algorithm in the recognition of violations of personnel at the site of electric power operation provides effective technical support to ensure personnel safety.

Design and analysis of all optical header recognition system employing combination of carrier reservoir SOA and conventional SOA

Design and analysis of all optical header recognition system employing combination of carrier reservoir SOA and conventional SOA

Validation of an instrumented mouthguard in rugby union-a pilot study comparing impact sensor technology to video analysis.

To better understand the biomechanical profile of direct head impacts and the game scenarios in which they occur in Rugby Union, there is a need for an on-field validation of a new instrumented mouthguard (IMG) against the reference standard. This study considers the potential of a combined biomechanical (IMG) and video analysis approach to direct head impact recognition, both of which in isolation have limitations. The aim of this study is to assess the relationship between an instrumented mouthguard and video analysis in detection of direct head impacts in rugby union. Pilot Study - Observational Cohort design. The instrumented mouthguard was worn by ten (3 backs, 7 forwards) professional Rugby Union players during the 2020-21 Gallagher Premiership (UK) season. Game-day video was synchronized with timestamped head acceleration events captured from the instrumented mouthguard. Direct Head Impacts were recorded in a 2 × 2 contingency table to determine sensitivity. Impact characteristics were also collected for all verified head impacts to further the understanding of head biomechanics during the game. There were 2018 contact events that were reviewed using video analysis. Of those 655 were categorized as direct head impacts which also correlated with a head acceleration event captured by the IMG. Sensitivity analysis showed an overall sensitivity of 93.6% and a positive predictive value (PPV of 92.4%). When false positives were excluded due to ball out of play, mouthguard removal or handling after a scoring situation or stoppage, PPV was improved (98.3%). Most verified head impacts occurred in and around the ruck contest (31.2%) followed by impacts to the primary tackler (28.4%). This pilot validation study demonstrates that this IMG provides a highly accurate measurement device that could be used to complement video verification in the recognition of on-field direct head impacts. The frequency and magnitude of direct head impacts derived from specific game scenarios has been described and allows for greater recognition of high-risk situations. Further studies with larger sample sizes and in different populations of Rugby Union players are required to develop our understanding of head impact and enable strategies for injury mitigation.

Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning- Optimized Double-Ring Resonators

Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning- Optimized Double-Ring Resonators

WheatLFANet: in-field detection and counting of wheat heads with high-real-time global regression network

BackgroundDetection and counting of wheat heads are of crucial importance in the field of plant science, as they can be used for crop field management, yield prediction, and phenotype analysis. With the widespread application of computer vision technology in plant science, monitoring of automated high-throughput plant phenotyping platforms has become possible. Currently, many innovative methods and new technologies have been proposed that have made significant progress in the accuracy and robustness of wheat head recognition. Nevertheless, these methods are often built on high-performance computing devices and lack practicality. In resource-limited situations, these methods may not be effectively applied and deployed, thereby failing to meet the needs of practical applications.ResultsIn our recent research on maize tassels, we proposed TasselLFANet, the most advanced neural network for detecting and counting maize tassels. Building on this work, we have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection. WheatLFANet features a more compact encoder-decoder structure and an effective multi-dimensional information mapping fusion strategy, allowing it to run efficiently on low-end devices while maintaining high accuracy and practicality. According to the evaluation report on the global wheat head detection dataset, WheatLFANet outperforms other state-of-the-art methods with an average precision AP of 0.900 and an R2 value of 0.949 between predicted values and ground truth values. Moreover, it runs significantly faster than all other methods by an order of magnitude (TasselLFANet: FPS: 61).ConclusionsExtensive experiments have shown that WheatLFANet exhibits better generalization ability than other state-of-the-art methods, and achieved a speed increase of an order of magnitude while maintaining accuracy. The success of this study demonstrates the feasibility of achieving real-time, lightweight detection of wheat heads on low-end devices, and also indicates the usefulness of simple yet powerful neural network designs.

Integrated photonic reservoir computing with an all-optical readout.

Integrated photonic reservoir computing has been demonstrated to be able to tackle different problems because of its neural network nature. A key advantage of photonic reservoir computing over other neuromorphic paradigms is its straightforward readout system, which facilitates both rapid training and robust, fabrication variation-insensitive photonic integrated hardware implementation for real-time processing. We present our recent development of a fully-optical, coherent photonic reservoir chip integrated with an optical readout system, capitalizing on these benefits. Alongside the integrated system, we also demonstrate a weight update strategy that is suitable for the integrated optical readout hardware. Using this online training scheme, we successfully solved 3-bit header recognition and delayed XOR tasks at 20 Gbps in real-time, all within the optical domain without excess delays.

Experimental demonstration of 84 Gbps QPSK signal’s 4-symbol all-optical pattern recognition

In the F5G era, a promising all-optical processing technology named all-optical pattern recognition has attracted more and more attention. Its applications include not only all-optical header recognition or address recognition in OCDMA but also optoelectronic firewalls. The higher the recognition rate of pattern recognition, the higher the processing rate of both applications can reach. To meet the development features of eFFB in F5G, high-speed all-optical pattern recognition should be achieved. In this paper, a QPSK all-optical pattern recognition system with a data rate of up to 84Gbps is proposed, analyzed, and experimentally demonstrated by employing commercial independent optical components. The system first converts the I branch of the input QPSK signal to a positive and a negative IM signal by adding the coherent carrier from the orthogonal polarization. Then the converted IM signals are coupled into time delay lines and optical AND logic gates implemented by HNLFs to achieve the optical correlation operation. In the end, a high-level optical pulse indicating the pattern recognized result is output. Numerical simulation results reveal that the proposed system can recognize the target sequence from the I branch of the input sequence and the position of the output high-level pulse in the time window of the I branch of the input sequence is the position of the last symbol of the target sequence. The results of the experiment demonstrate that the proposed system can recognize a 4-symbol target sequence from the I branch of an 8-symbol 84Gbps QPSK input sequence, which proves the all-optical pattern recognition of QPSK signals.

Two-terminal fault combination location method on MMC-HVDC transmission lines based on ensemble empirical mode decomposition

In the HVDC transmission system, the main factors that affect the accuracy of traditional two-terminal fault traveling wave distance measurement are the selection of appropriate wave velocity and whether the wave head can be identified. The line dispersion and transition resistance of the DC transmission will make it more difficult to determine the time when the wavehead reaches the two ends of the two sides, and the boundary elements of both terminal of the line will cause distortion of the wave head. Based on fault traveling waves characteristics of the time–frequency domain, we propose a method of Two-Terminal Fault Combination Location (TTFCL) on High Voltage Direct Current based on MMC (MMC-HVDC) transmission line. The method combines the natural frequency fault location method and the traveling wave fault location method. The first step of the walking wave natural frequency method is used for rough ranging, so that the approximate time range of the initial traveling wave of fault to reach the busbar can be obtained, and then can be calculated the rough position range of the fault point. Then the second step of accurate ranging is carried out, using the Ensemble Empirical Mode Decomposition (EEMD) algorithm to decompose the processed signal, extract the traveling wave component of the high-frequency, identify the traveling wave of initial head recognition and calibration, obtain the time parameters required for fault ranging, and calculate the more accurate fault point location by the two-ended fault ranging formula. In PSCAD/EMTDC, we built a simulation model of MMC-HVDC system line fault, and the simulation experiments are compared with different fault types and locations, and the results show that the combined fault ranging method eliminate the wave speed influence on accurate positioning and effectively identifies the wave head, which further improves the ranging accuracy.

Analyzing Chinese text with clause relevance structure

Discourse structure is generally represented as hierarchical structure, the two most well known representations are rhetorical structure theory (RST) and Penn discourse treebank (PDTB). The main problem of the hierarchical structure is that it can not describe the direct semantic relevance between the elementary discourse units (EDU), especially the non-adjacent and cross-level EDUs. Discourse dependency structure (DDS) has been put forward in recent years to describe the head-dependent relation between the EDUs. However, the judgment process of the head can not be answered theoretically. This problem is particularly serious in Chinese discourse analysis, because Chinese lacks the form differences between the main clauses and the subordinate clauses. In this paper, we propose clause relevance structure to represent the discourse structure. Compared with the hierarchical discourse structure and DDS, the clause relevance structure can effectively describe the direct semantic association between discontinuous and cross-level clauses in a text, and the construction of structure is not presupposed by the head recognition. We propose the judgment criteria and formal constraints of the clause relevance structure, and built a human-annotated corpus on Chinese text. Based on the Chinese corpus, we explore the automatic recognition of clause relevance structure. The clause relevance recognition task is formalized as a classification problem and performed by the BERT-based model. A bidirectional LSTM layer is added on the top of the BERT to improve the performance, and the recognition accuracy (90.77%) is achieved by the BERT-LSTM model. Experimental results show that the long distance clause pairs are the main difficulties in the clause relevance recognition, and these difficulties mainly focus on the positive examples, while the clause pairs with short distance are especially difficult to be correctly recognized as negative relevance.

Helmet Wearing Recognition of Construction Workers Using Convolutional Neural Network

One of the most effective ways to prevent construction workers from suffering a head injury is to wear a safety helmet. The use of a computer vision method to detect whether or not construction workers are wearing helmets can improve external construction worker supervision, reducing the number of head injury accidents. A helmet-wearing recognition method based on head recognition is proposed using CNN (convolutional neural network). The area of the head of constructors can be accurately located using crossvalidation of facial feature recognition and head recognition, which solves the problem of determining constructor head position under complex posture. The I-YOLOv3 target detection network is used to detect helmet wear, and the relative position relationship between the helmet and the human body is determined. The findings show that the helmet wearing identification system can be successfully applied to helmet wearing identification work in a complex environment construction site, and it offers a new research perspective and technical method for construction industry information-based safety monitoring.

Optical dendrites for spatio-temporal computing with few-mode fibers [Invited

Multimode fibers have been extensively used in short-range communication systems and optical imaging. More recently, they have been considered for optical computing by exploiting the complex spatial and spatio-temporal transformation at the fiber end. Mimicking the dendrites of real neurons, we consider here the spatial modes that propagate with different group velocities along the fiber as different dendritic branches. The multimode fiber plays the role of an optical dendritic unit and the signals obtained from the different dendritic branches are temporally mixed and used for spatio-temporal information processing. We numerically demonstrate the use of a few-mode, step-index fiber as a linear computing element in an ultra-fast spatio-temporal coincidence detector that operates at 40 Gb/s data encoding rate. We evaluate this detector as a linear classifier in header recognition and bit counting tasks.

Putin on Trial: The Reality of Heads of State Immunity before International Criminal Courts

The prosecution of serving heads of state before international criminal courts is still very challenging even though most of these courts do not recognise immunities for international crimes. While the recognition of head of state immunity before national and foreign domestic courts for international crimes is supported by customary international law, the recognition of immunities before international criminal courts is determined by the statute creating the court.. Consequently, while the Rome Statute creating the International Criminal Court (the ICC) does not recognise any form of immunity, the Malabo Protocol creating the African Criminal Court (the ACC) recognised the immunity of senior serving state officials for international crimes. Currently, the ICC is investigating the situation in Ukraine which may lead to the possible arrest of President Putin of Russia and his senior officials for crimes against humanity and war crimes committed when Russia invaded Ukraine. The article argues that prosecuting a serving president like Putin by the ICC may be similar to the Al Bashir case because it will be difficult to arrest and surrender him to the Court and also the fact that Russia is not state party to the Rome Statute. Consequently, the waiving of immunity before an international court is not enough; cooperation by the home state of the offender and other states is needed in matters arrest and surrender to the prosecuting court.

WDN: A One-Stage Detection Network for Wheat Heads with High Performance

The counting of wheat heads is labor-intensive work in agricultural production. At present, it is mainly done by humans. Manual identification and statistics are time-consuming and error-prone. With the development of machine vision-related technologies, it has become possible to complete wheat head identification and counting with the help of computer vision detection algorithms. Based on the one-stage network framework, the Wheat Detection Net (WDN) model was proposed for wheat head detection and counting. Due to the characteristics of wheat head recognition, an attention module and feature fusion module were added to the one-stage backbone network, and the formula for the loss function was optimized as well. The model was tested on a test set and compared with mainstream object detection network algorithms. The results indicate that the mAP and FPS indicators of the WDN model are better than those of other models. The mAP of WDN reached 0.903. Furthermore, an intelligent wheat head counting system was developed for iOS, which can present the number of wheat heads within a photo of a crop within 1 s.

Photonic neuromorphic technologies in optical communications

Abstract Machine learning (ML) and neuromorphic computing have been enforcing problem-solving in many applications. Such approaches found fertile ground in optical communications, a technological field that is very demanding in terms of computational speed and complexity. The latest breakthroughs are strongly supported by advanced signal processing, implemented in the digital domain. Algorithms of different levels of complexity aim at improving data recovery, expanding the reach of transmission, validating the integrity of the optical network operation, and monitoring data transfer faults. Lately, the concept of reservoir computing (RC) inspired hardware implementations in photonics that may offer revolutionary solutions in this field. In a brief introduction, I discuss some of the established digital signal processing (DSP) techniques and some new approaches based on ML and neural network (NN) architectures. In the main part, I review the latest neuromorphic computing proposals that specifically apply to photonic hardware and give new perspectives on addressing signal processing in optical communications. I discuss the fundamental topologies in photonic feed-forward and recurrent network implementations. Finally, I review the photonic topologies that were initially tested for channel equalization benchmark tasks, and then in fiber transmission systems, for optical header recognition, data recovery, and modulation format identification.

Fault location of hybrid three-terminal HVDC transmission line based on improved LMD

To reduce the impact of traveling wave velocity, wave head recognition, and LMD (Local Mean Decomposition) end effect and mode mixing on location accuracy, this paper presents a fault location method based on improved LMD for hybrid three-terminal HVDC transmission lines, which is not affected by wave velocity. Firstly, the improved LMD is used to get the time when the fault traveling wave first arrives at the four measuring terminals. Then the fault branch is identified according to the ratio of the time of the fault traveling wave arriving at the measuring terminal. Finally, the equation is listed according to the principle of traveling wave location and the measurement equation which is not affected by the wave velocity is deduced. A hybrid three-terminal HVDC transmission system model is built by PSCAD to simulate various faults and output fault data under various fault conditions. MATLAB is used to process the fault data and verify the location algorithm. The simulation results show that the location method proposed in this paper is not affected by fault distances, fault types, infeed levels and transition resistances. In addition, it has higher accuracy than LMD based on CSI (Cubic Spline Interpolation) algorithm, wavelet packet location algorithm and double-ended location method of using wave velocity calculation.

Winners and losers: Recognition of spontaneous emotional expressions increases across childhood

Research using posed emotional expressions is problematic because they lack ecological validity. Adults’ recognition of spontaneous real-world expressions may require the inclusion of postural information. Whether posture improves children’s recognition of real-world expressions was unknown. Younger children (n = 30; 5- to 7-year-olds), older children (n = 30; 8- to 10-year-olds), and adults (n = 30) judged whether tennis players had won or lost a point. Images showed one of three cue types: Head-only, Body-only, or Head–Body expressions. Recognition of expressions improved with age; older children and adults performed better than younger children. In addition, recognition of Body-only and Head–Body cues was better than Head-only cues for all ages. Spontaneous expression recognition improved throughout childhood and with the inclusion of postural information.