Automatic Program Research Articles

High-Frequency Systolic Array-Based Transformer Accelerator on Field Programmable Gate Arrays

The systolic array is frequently used in accelerators for neural networks, including Transformer models that have recently achieved remarkable progress in natural language processing (NLP) and machine translation. Due to the constraints of FPGA EDA (Field Programmable Gate Array Electronic Design Automation) tools and the limitations of design methodology, existing systolic array accelerators for FPGA deployment often cannot achieve high frequency. In this work, we propose a well-designed high-frequency systolic array for an FPGA-based Transformer accelerator, which is capable of performing the Multi-Head Attention (MHA) block and the position-wise Feed-Forward Network (FFN) block, reaching 588 MHz and 474 MHz for different array size, achieving a frequency improvement of 1.8× and 1.5× on a Xilinx ZCU102 board, while drastically saving resources compared to similar recent works and pushing the utilization of each DSP slice to a higher level. We also propose a semi-automatic design flow with constraint-generating tools as a general solution for FPGA-based high-frequency systolic array deployment.

INTRODUCTION OF GENETIC ALGORITHMS INTO THE INTERACTIVE PLANNING SUPPORT SYSTEM FOR ARRANGEMENT OF TEMPORARY HOUSING UNITS USING BIM AND PROMOTING AUTOMATION OF THE SYSTEM

In this study, we improved the developed automatic arrangement program for the site planning of emergency temporary housing that runs on BIM mainly for the following two points.

Formal Verification of Robot Rotary Kinematics

With the widespread application of robots in aerospace, medicine, automation, and other fields, their motion safety is essential for the well-being of humans and the accomplishment of vital socially beneficial programs. Conventional robot hardware and software designs mainly rely on experiential knowledge and manual testing to ensure safety, but this fails to cover all possible testing paths and adds risks. Alternatively, formal, mathematically rigorous verifications can provide predictable and reliable guarantees of robot motion safety. To demonstrate the feasibility of this approach, we formalize the mathematical coordinate transformation of a robot’s rigid-body kinematics using the Coq Proof Assistant to verify the correctness of its theoretical design. First, based on record-type matrix formalization, we define and verify a robot’s spatial geometry by constructing formal expressions of the matrix’ Frobenius norm, trace, and inner product. Second, we divide rotary motion into revolution and rotation construct and provide their formal definitions. Next, we formally verify the rotational matrices of angle conventions (e.g., roll–pitch–yaw and Euler), and we complete the formal verification of the Rodriguez formula to formally verify the correctness of the motion theory in specific rotating kinematics problems. The formal work of this paper has a variety of essential applications and provides a generalizable kinematics analysis framework for robot control system verification. Moreover, it paves the way for automatic programming capabilities.

The Effect of Offline Medical Resource Distribution on Online Physician-Patient Interaction: Empirical Study With Online and Offline Data

The relationship between online health communities (OHCs) and offline medical care is unclear because both provide physician-patient interaction services and channels. Taking advantage of information and communication technology, patients have been using OHCs widely. However, some physical medical resources (such as hospital beds and medical devices) cannot be replicated by information and communication technologies. Therefore, it is worth studying how offline medical resources affect physician-patient interactions in OHCs and how OHCs help to solve resource scarcity and the uneven distribution of traditional medical treatment. This study aimed to support the notion that physician-patient consultations in OHCs are influenced by the objective distribution of offline health care capital (accessibility and availability) and to provide suggestions for the allocation of medical resources in practice through the judicious use of offline and online channels. The empirical data in this study were collected from both online and offline channels. The offline data include 9 years (2006-2014) of medical resource statistics of 31 provincial administrative regions in mainland China. Moreover, data regarding the geolocation-based physician-patient interaction network in the OHC were also collected. The online data come from one of China's largest OHCs. We obtained 92,492 telephone consultation records of 6006 physicians using an automatic web crawler program. Social network analysis was used to visualize the descriptive statistics of the offline geolocation-based physician-patient interaction network in the OHC. A regression model with a squared variable was applied to analyze online and offline empirical data to further test our hypothesis. Two types of robustness tests were used to increase the reliability of the test results of the initial model. The results of our social network analysis show that there is a uniform geographic distribution of patients who use OHCs, whereas the physician relies more on geographic advantage (eg, a higher medical resource capability). Moreover, the empirical results of the regression model support the notion that physician-patient telephone consultations are positively influenced by physicians' online contributions (βcontribution=.210; P<.001) and capital availability (βbed=.935; P=.07), and, interestingly, spatial accessibility has an inverted U-shaped effect (βdistance=.199; P<.001 and βdistance2=-.00449; P=.008). The results indicate that the use of OHCs, although constrained by offline medical resources, provides a channel for offline resources to flow from areas with high availability to those with low availability. This study explores the relationship between online and offline channels by investigating online physician-patient interactions and offline medical resources. In particular, this study analyzes the impact of offline channels on online channels and verifies the possibility of OHC capital use shifting from a high-availability area to a low-availability area. In addition, it provides a theoretical and practical basis for understanding the interaction of online and offline channels of medical care.

CAPTCHA RECOGNITION USING DCNN

Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is an important human-machine distinction technology for websites to prevent the automatic malicious program attack. CAPTCHA recognition studies can find security breaches in CAPTCHA technology By using the concept of deep learning and computer vision, the very purpose of the CAPTCHAs can be defeated. This test can be passed automatically with the help of Convolutional Neural networks(CNN). A CNN is an algorithm of deep learning which takes an image as input and then assigns some value to various features in the image which further helps to differentiate one feature from the other. Its main purpose is to transform the images into a form which is much easier to process, without losing features which are essential for getting an optimized prediction. The proposed system for this project is to expand this CAPTCHA recognition system for larger and more noisy CAPTCHA containing all the symbols possible, a method based on the Deep Convolutional Neural Network (DCNN) model to identify CAPTCHA and avoid the traditional image processing technology such as location and segmentation. The adaptive learning rate is introduced to accelerate the convergence rate of the model, and the problem of over fitting and local optimal solution has been solved. The multi task joint training model is used to improve the accuracy and generalization ability of model recognition. The experimental results show that the model has a good recognition effect on CAPTCHA with background noise and character adhesion distortion. The future scope of this project lies in technologies where more noisier images can be processed such as license plates, handwriting recognition etc.

Difference-based firefly programming for symbolic regression problems

Automatic programming is a type of programming that has the ability to analyze and solve problems using the principles of symbolic regression analysis. These methods can solve complex problems regardless of whether they have a specific pattern or not. In this work, we are going to introduce the difference-based firefly programming (DFP) method as an improved version of the standard firefly programming method. We have analyzed the performance of this new improved method, which will be described in detail within the scope of this work. In order to evaluate the performance of the newly presented method, the results have been compared to the results of the standard method and the results of other methods that are used to solve the same type of problems. DFP has been used also in forecasting and modeling a real-world time-series problem, where it showed good performance too. In general, the results demonstrated the improved performance of the newly introduced method and showed its ability to efficiently solve complex problems.

Impact of a Self-Autonomous Evaluation Station and Personalized Training Algorithm on Quality of Life and Physical Capacities in Sedentary Adults: Randomized Controlled Trial.

Physical inactivity is a major risk factor for noncommunicable diseases and a leading cause of premature death. The World Health Organization (WHO) recommends at least 150 minutes of moderate intensity physical activity (PA) weekly, regardless of age, gender, or personal habits. However, in both sports performance and clinical settings, personalized training (PT) regimens have shown superior efficacy over general guidelines. We hypothesized that an automatic PT program, informed by initial physical evaluations, would increase overall quality of life, quality of sleep, and physical capabilities and reduce fatigue and depression compared with adherence to WHO recommendations. This 5-month, randomized, single-blinded controlled trial involved 112 sedentary or minimally active participants, divided randomly into PT and free training (FT) groups. Physical capabilities and subjective measures such as quality of life, sleep, depression, and fatigue were evaluated for both groups. After 1 month, both groups were asked to perform 150 minutes of PA per week for 4 months; the PT group could either follow a "virtual coach" on a mobile app to follow some personalized PA or do what they would like, while the FT group was to follow the general PA recommendations of the WHO. We did not find any group×time interaction for PA duration or intensity, physical qualities, and subjective measures. However, considering both groups together, there was a significant pretest and posttest time effect for duration of PA (18.2 vs 24.5 min/d of PA; P<.001), intensity (2.36 vs 3.11; P<.001), and workload (46.8 vs 80.5; P<.001). Almost all physical qualities were increased pretest and posttest (ie, estimated VO2max 26.8 vs 29 mL min-1 kg-1; P<.001; flexibility 25.9 vs 26.9 cm; P=.049; lower limb isometric forces 328 vs 347 Nm; P=.002; reaction time 0.680 vs 0.633 s; P<.001; power output on cyclo-ergometer 7.63 vs 7.82 W; P<.003; and balance for the left and right leg 215 vs 163 mm2; P<.003 and 186 vs 162 mm2; P=.048, respectively). Finally, still considering the PT and FT groups together, there were significant pretest to posttest improvements in the mental component of quality of life using the 12-item Short Form Health Survey (41.9 vs 46.0; P<.006), well-being using the Warwick-Edinburgh Mental Well-Being Scale (48.3 vs 51.7; P<.002), depression using the Center for Epidemiologic Studies Depression Scale (15.5 vs 11.5; P=.02), and fatigue using the Functional Assessment of Chronic Illness Therapy-Fatigue (37.1 vs 39.5; P=.048). The individualized training was not more effective than the general recommendations. A slight increase in PA (from 18 to 24 min/d) in sedentary or poorly active people is enough for a significant increase in physical capabilities and a significant improvement in quality of life, well-being, depression, and fatigue. ClinicalTrials.gov NCT04998266; https://clinicaltrials.gov/study/NCT04998266.

An Improved Text-Based and Image-Based CAPTCHA Based on Solving and燫esponse Time

CAPTCHA is an acronym that stands for Completely Automated Public Turing Test to tell Computers and Humans Apart (CAPTCHA), it is a good example of an authentication system that can be used to determine the true identity of any user. It serves as a security measure to prevent an attack caused by web bots (automatic programs) during an online transaction. It can come as text-based or image-based depending on the project and the programmer. The usability and robustness, as well as level of security, provided each of the varies and call for the development of an improved system. Hence, this paper studied and improved two different CAPTCHA systems (the text-based CAPTCHA and image-based CAPTCHA). The text-based and image-based CAPTCHA were designed using JavaScript. Response time and solving time are the two metrics used to determine the effectiveness and efficiency of the two CAPTCHA systems. The inclusion of response time and solving time improved the shortfall of the usability and robustness of the existing system. The developed system was tested using 200 students from the Federal College of Animal Health and Production Technology. The results of each of the participants, for the two CAPTCHAs, were extracted from the database and subjected to analysis using SPSS. The result shows that text-based CAPTCHA has the lowest average solving time (21.3333 s) with a 47.8% success rate while image-based CAPTCHA has the highest average solving time was 23.5138 s with a 52.8% success rate. The average response time for the image-based CAPTCHA was 2.1855 s with a 37.9% success rate lower than the text-based CAPTCHA response time (3.5561 s) with a 62.1% success rate. This indicates that the text-based CAPTCHA is more effective in terms of usability tests while image-based CAPTCHA is more efficient in terms of system responsiveness and recommended for potential users.

A New Data Processing Method for Magnetic Anomaly Detection and Localization Based on 2-D Orthonormal Basis Functions

This work proposes a new processing method based on orthonormal basis functions (OBFs) for two-dimensional (2D) magnetic anomaly data, which is an innovative extension of one-dimensional (1D) OBFs. In most surveys, ferromagnetic targets are usually regarded as magnetic dipoles. The magnetic anomaly field of a dipole in a horizontal plane is essentially a linear combination of linearly independent basis functions, which are then transformed into a set of 2D orthonormal basis functions (2D-OBFs) using the Gram–Schmidt algorithm. On the basis of the 2D-OBFs, a processing procedure for 2D magnetic anomaly data is established and named the 2D-OBF method. This method converts magnetic anomaly maps to energy maps, in which there is only one positive peak corresponding to the horizontal location of a magnetic dipole. As a consequence, the detection and localization are significantly simplified. To verify this new method, a total of 3000 Monte Carlo simulations were carried out, and the synthetic data were also processed using the traditional 1D-OBF method. The statistics of the 2D-OBF results showed that the localization accuracy and false alarm rate are 0.34 m and 1.9 %, respectively, at a data noise level of 10 nT, which was much better than the 1D-OBF method. Another synthetic data experiment verified the reliability of the 2D method for handling multiple targets simultaneously, even when the magnetic anomalies of adjacent targets are severely superimposed. For the measured aeromagnetic data, the 2D-OBF method also works well. Additionally, this method exhibits outstanding noise immunity in all tests. The signal-to-noise ratios (SNR) of the energy data are improved by approximately 14 dB compared to that of the magnetic anomaly data within the signal bandwidth. Developed from rigorous mathematical physics definitions, the 2D-OBF method is more conducive to the implementation of automatic data processing programs and has considerable practical promise.

The representation of the science media image (exemplified by mediatexts of the regional online news publication 1obl.ru)

The article is devoted to identifying a science media image speech representation’ features in the official online news publication of the Chelyabinsk region, covering the events of the industrial Russian region. The news media texts of the regional news portal 1obl.ru served as the object of the study, selected by systematic sampling, relevant to the keyword “science”. The specific formation of science media image is analyzed by frequency and infrequent content analysis. The analysis’ unit is the frequent lexemes of the text corpus relevant to the topic of science. To implement frequency content analysis, automatic semantic processing is used, which allows to identify discursive features, nuclear and peripheral semantic constructions of the concept, transmitting frequent patterns of behavior and cultural and value orientations. The Miratext automatic semantic analysis program is used as a toolkit. Infrequent content analysis provides for the definition of linguistic and cognitive mechanisms by which the media image of science is presented, emotional and value characteristics, as a result of which significant semantic components included in the structure of the concept “science” are determined and, moreover, checks the accuracy of entering into the semantic structures of the concept, eliminates statistical errors of automatic semantic analysis. The analysis of the material suggests that the media coverage of the region’s scientific potential, the emotional background and the connotations should be taken into account. This stimulates the involvement, interest and increases the literacy of the regional reader in the development of regional science, as well as raises the prestige of the region. The explanatory function of media publications contributes to the adoption of state priorities in the field of science and the consolidation of value orientations in the linguistic consciousness of the reader. The conclusions present the identified features of the South Ural’ science media image.

Automatic SDG budget tagging: Building public financial management capacity through natural language processing

Abstract The “budgeting for SDGs”–B4SDGs–paradigm seeks to coordinate the budgeting process of the fiscal cycle with the sustainable development goals (SDGs) set by the United Nations. Integrating the goals into public financial management systems is crucial for an effective alignment of national development priorities with the objectives set in the 2030 Agenda. Within the dynamic process defined in the B4SDGs framework, the step of SDG budget tagging represents a precondition for subsequent budget diagnostics. However, developing a national SDG taxonomy requires substantial investment in terms of time, human, and administrative resources. Such costs are exacerbated in least-developed countries, which are often characterized by a constrained institutional capacity. The automation of SDG budget tagging could represent a cost-effective solution. We use well-established text analysis and machine learning techniques to explore the scope and scalability of automatic labeling budget programs within the B4SDGs framework. The results show that, while our classifiers can achieve great accuracy, they face limitations when trained with data that is not representative of the institutional setting considered. These findings imply that a national government trying to integrate SDGs into its planning and budgeting practices cannot just rely solely on artificial intelligence (AI) tools and off-the-shelf coding schemes. Our results are relevant to academics and the broader policymaker community, contributing to the debate around the strengths and weaknesses of adopting computer algorithms to assist decision-making processes.

Digital ethics challengers in Russian and English media texts: Migrant discourse case study

With digital technologies penetrating all spheres of life, the problem of digital ethics has become one of the most perspective and widely researched tasks of modern science and linguistics in particular. Digitalization influences the processes of media communication, which requires development of certain ethical standards in virtual environment. The given study aims at analysing and comparing digital ethics in Russian and English media texts. Within the framework of this study, digital etiquette is seen as a continuation of speech etiquette aimed at neutralizing aggression towards vulnerable members of society in the online environment. Using a combination of methods, namely sentiment analysis and analysis of lexical associations, messages about migrants in social networks, forums, blogs, instant messengers and microblogs were analyzed. The sentiment orientation of the text was determined using an automatic text analysis program and subsequent linguistic expertise. For this study we collected social media data of 8,478,629 characters (VKontakte, Odnoklassniki, YouTube, etc.). For the analysis of English-language media texts, iWeb data on the input word migrant was collected. The total volume of the analyzed English-language Internet messages is 1,185,200 characters. Migrant discourse in Russian and English social media texts is polythematic. The results show that negative and neutral tone prevail in English media texts while in Russian there are neutral, positive and negative texts. In English media texts, there are messages expressing solidarity with migrants. At the same time, the problems of ethnic intolerance and religious stereotyping still require consideration and further development of regulatory tools.

Let’s Talk With Developers, Not About Developers: A Review of Automatic Program Repair Research

Automatic program repair (APR) offers significant potential for automating some coding tasks. Using APR could reduce the high costs historically associated with fixing code faults and deliver significant benefits to software engineering. Adopting APR could also have profound implications for software developers’ daily activities, transforming their work practices. To realise the benefits of APR it is vital that we consider how developers feel about APR and the impact APR may have on developers’ work. Developing APR tools without consideration of the developer is likely to undermine the success of APR deployment. In this paper, we critically review how developers are considered in APR research by analysing how human factors are treated in 260 studies from Monperrus’s Living Review of APR. Over half of the 260 studies in our review were motivated by a problem faced by developers (e.g., the difficulty associated with fixing faults). Despite these human-oriented motivations, fewer than 7% of the 260 studies included a human study. We looked in detail at these human studies and found their quality mixed (for example, one human study was based on input from only one developer). Our results suggest that software developers are often talked <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">about</i> in APR studies, but are rarely talked <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">with</i> . A more comprehensive and reliable understanding of developer human factors in relation to APR is needed. Without this understanding, it will be difficult to develop APR tools and techniques which integrate effectively into developers’ workflows. We recommend a future research agenda to advance the study of human factors in APR.

Physiological Challenges of Space Travel and Ground-Based Simulation Possibilities for Monitoring Brain Circulatory Changes: A Rheoencephalography Study

The functional integrity of brain perfusion and oxygen transport profoundly determines mental performance during military flight missions and spaceflight. Presently, at the selection phase of pilot candidates, there are no screening methods to evaluate cerebral circulation and its autonomous regulation (AR), meanwhile the pilot information processing capacity could be insufficient in dangerous flight situations with high mental workload or during high “head-to-foot” G loads. On-board ISS (International Space Station) and during deep-space missions circulatory changes can be evolved in the opposite direction due to the microgravity: blood shift toward the head-neck region can increase ICP (Intracranial Pressure) and tenfold increase of carbon-dioxide concentration can provoke complaints and disturbances in eye and brain blood circulation (Space Associated Neuro-Ocular Syndrome – SANS). The alteration of brain perfusion dynamics and oxygen utilisation was investigated on the head-down tilting table (HDT) test and in the hypobaric (low-pressure) chamber. We registered the brain regional pulse wave changes by the bioimpedance (Rheoencephalography – REG) on 19 volunteers in rest and after the breath-holding manoeuvre. We found that during the head-down tilt (HDT) position, the amplitude of the second peak of the REG pulse wave increased, like the ICP pulse wave, being an unfavourable sign for intracranial pressure increase in clinical cases. Manual readings resulted in significant differences during HDT between the female (P = 0.0007) and male (P &lt; 0.0001) groups. With automated analysis, the increase in REG P2 wave was significant, and the ratio was 4/5 (80%) for women and 10/14 (71%) for men. The newly written automatic program script was able to detect this in 92% of the cases. The calculated values detected the state of cerebral circulatory autoregulation and the identity between the male and female groups. Based on this result and previous REG correlation studies, it can be concluded that REG could be used to monitor fighter pilots, astronauts, and neurocritical care patients in real-time as emergency alert in the transitory cessation of brain perfusion.

Design Automation of a Two Scissors Lift

In this study, the design of a two scissors greenhouse lift trolley is considered. The maximum height of the platform from the ground is 3500 mm. A program developed in Visual BASIC to automate the design is introduced. The lift is modeled in SolidWorks (SW) and the finite element (FE) modal and static analyses are performed as an initial design first by using graphical user interface (GUI). The lift contains revolute joints and slider joints. A simply supported beam which has two revolute joints and a slider joint is studied to verify how to model the joints. Pim connectors are defined for revolute joints in SW-FE analysis. Spring connectors with very large values are defined between sliding faces in the normal direction for translational joints. The results obtained with solid finite elements in SW are compared with analytical results for the natural frequency and static analyses and it was observed that the results are in good agreement for the simply supported beam. &#x0D; An Excel file where a main sheet contains the list of the bodies and all the geometric values is created after the initial design. The Excel file also contains sheets for each body. Body sheets have all the dimensions in the sketches and features. The dimension values in the cells of the body sheets are defined by formulas related to the geometric values given in the main sheet. Kinematic, kinetic, and revision of the SW model are performed by the design automation program. The FE analyses are done by GUI and the results are evaluated. If the results are not satisfactory, the geometric values are changed in Excel file and the analyses are repeated. The final design is obtained by the iteration easily. The automation program and the procedure developed in this work can be extended other scissors lifts.

작업 자세 부하 평가를 위한 모션 데이터 기반 자동 인간공학적 평가 프로그램 개발 및 검증

Objective: This study aims to develop a simultaneous automatic evaluation program for three evaluation tools using motion data of wearable IMU sensors that can be used in the field, and to present various measures for the results of each evaluation tool of the entire work.BRBRBackground: Work-related musculoskeletal diseases have been on the rise over the past four years, and improvement based on the results of work posture evaluation is needed to prevent such musculoskeletal diseases. Recently, various automation evaluation methods have been proposed in consideration of the limitations of the existing observation method, but the image processing technology is difficult to apply on-site, and the motion data-based has a limitation using a small number of evaluation tools mainly focused on the upper and lower limbs.BRBRMethod: In the research procedure, after designing algorithms for each of the three ergonomic assessment tools, algorithm reliability was verified through analysis of the agreement between the manual evaluation results and automatic evaluation results, and simultaneous automatic evaluation programs were developed. Finally, the results of each assessment tool and evaluation scale were derived and compared by applying motion data of two types of work to the developed program.BRBRResults: Measurement items and criteria of motion data for 3 angles of 5 upper limbs and 3 lower limb postures were derived and based on algorithms for each of the 3 ergonomic assessment tools were designed. As a result of analyzing the degree of agreement between manual evaluation and automatic evaluation, the Kappa coefficient corresponded to a very high degree of agreement in all ergonomic assessment tools. The developed program presented the angles of major body parts according to time for each frame of the entire data, risk levels according to all assessment tools and individual assessment tools, and various evaluation scales such as Max, Min, Mode, Mean, Most posture, and Worst postures for each analyzed data.BRBRConclusion: As a result of Cohen

Deep Learning with a Dataset Created Using Kanno Saitama Macro, a Self-Made Automatic Foveal Avascular Zone Extraction Program.

The extraction of the foveal avascular zone (FAZ) from optical coherence tomography angiography (OCTA) images has been used in many studies in recent years due to its association with various ophthalmic diseases. In this study, we investigated the utility of a dataset for deep learning created using Kanno Saitama Macro (KSM), a program that automatically extracts the FAZ using swept-source OCTA. The test data included 40 eyes of 20 healthy volunteers. For training and validation, we used 257 eyes from 257 patients. The FAZ of the retinal surface image was extracted using KSM, and a dataset for FAZ extraction was created. Based on that dataset, we conducted a training test using a typical U-Net. Two examiners manually extracted the FAZ of the test data, and the results were used as gold standards to compare the Jaccard coefficients between examiners, and between each examiner and the U-Net. The Jaccard coefficient was 0.931 between examiner 1 and examiner 2, 0.951 between examiner 1 and the U-Net, and 0.933 between examiner 2 and the U-Net. The Jaccard coefficients were significantly better between examiner 1 and the U-Net than between examiner 1 and examiner 2 (p < 0.001). These data indicated that the dataset generated by KSM was as good as, if not better than, the agreement between examiners using the manual method. KSM may contribute to reducing the burden of annotation in deep learning.

Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision

Whether the wheelset of a high-speed train has defects such as cracks is very important to the safety of high-speed trains. Hence, the wheelset must be regularly inspected for flaws. For flaw detection of a wheelset, it is necessary to record the axle end information of the wheelset to correlate with the flaw detection results. To quickly and accurately identify the axle end mark of the wheelset, an automatic identification method based on machine vision is proposed. Our method identifies seven types of marks on the axle end, including the smelting number, steel grade number, unit number, sequence number, year and month, axle type mark, and the azimuth mark. Using the established automatic identification method of axle end marks, based on Retinex theory, an improved dual-core Laplacian combined with Gaussian filtering operation is proposed to solve the problem of the low contrast of the wheelset axle end image. An improved image tilt correction algorithm based on the combination of Hough circle detection and bilinear interpolation is proposed, which solves the angle tilt problem of the target character area of the axis end image. To handle the various types of axis end markers and the small amount of data, a retraining method to improve recognition accuracy is proposed. This method first uses Chi_Sim as the basic font for training and then retrains based on the trained font. Finally, Tesseract-OCR is used to improve the accuracy of the recognition results. Experiments are carried out by developing an automatic recognition program for axle end marks. The results show that the proposed method can effectively identify and classify seven-character types, and the recognition accuracy reaches 96.88% while the recognition time of each image is 5.88 s.

Smart Karyotyping Image Selection Based on Commonsense Knowledge Reasoning

Karyotyping requires chromosome instances to be segmented and classified from the metaphase images. One of the difficulties in chromosome segmentation is that the chromosomes are randomly positioned in the image, and there is a great chance for chromosomes to be touched or overlap with others. It is always much easier for operators and automatic programs to tackle images without overlapping chromosomes than ones with largely overlapped chromosomes. In order to reduce the processing difficulty, adding a smart image selection procedure ahead of segmentation is practical and necessary. In this paper, we introduce the Smart Karyotyping Image Selection (SKIS) based on Commonsense Knowledge Reasoning. The initial experiment demonstrates that the proposed approach can select the expected images based on reasoning and benefit following karyotyping processes.

STUDY OF THE BEHAVIOUR FOR THE WORK EQUIPMENT OF A FORKLIFT DURING THE WORKING PROCESS USING FINITE ELEMENT ANALYSIS

Industrial manipulators and robots play a very important role in the current process of advanced industrialization. The use of industrial robots has led to increased labor productivity, human replacement in hazardous work situations, increased product quality, rapid recovery of investment. Supple automation, the highest level of programmable automation, is organized into computer-driven production cells and serviced by one or more industrial robots. The transformation of production systems from the human-machine system to the human-robot-machine system has replaced the human in the process of performing dangerous or uncomfortable works. The diversity of definitions given to industrial robots and the lack of consensus on the notion of "industrial robot" is a premise for opening new horizons in trying to bring the machine closer to human perfection. The present paper aims to conduct a study of the behavior for the work equipment of a forklift during the work process. The tool used to conduct the study was finite element analysis using specialized Solid Edge software. A 3D model of the forklift's work equipment was introduced in Solid Edge and a dynamic analysis was performed, which led to the equipment's eigenmodes and eigenfrequencies. The displacement of the nodes of the structure in the first 10 eigenmodes of vibration and the potential deformation energy accumulated by the system were chosen for visualization, suggestive results and especially important for the specialists in the domain of construction equipments.