Search

The 19th International Symposium on Laboratory Automation and Robotics provided presentations on state-of-the-art developments in laboratory automation and robotics. The symposium programme included papers and posters on all aspects of the technology. These comprised: managing laboratory automation (drug discovery); bioanalytical analysis; managing laboratory automation in drug discovery development and QC laboratory; functional genomics strategies and high throughput screening; advanced integration strategies; method development and global methods transfer; compound handling and logistics; combinatorial chemistry and automated synthesis; high throughput LC-MS-MS; increasing efficiency in dissolution testing; lead optimization; strategies for UHTS; increasing throughput for ADME toxicology; data management/data handling and bioinformatics; using contract laboratories to increase productivity; assay miniaturization; process optimization; compliance and automation-the regulatory perspective; novel high throughput screening technologies; compliance and automation-the industry perspective. Several discussion sessions were included and activated, and provided interactive communication on a wider range of subjects. Although the programme was very comprehensive, the Symposium was designed to provide time for both formal and informal exchange of information. The technical presentations were organized into concurrent sessions with grouped papers on related topics. Abstracts for each paper and each poster are included here. Full presentations of several of these papers will appear in later editions of this journal. [ABSTRACT FROM AUTHOR]

Under the background of the rapid development of digital economy, this paper empirically analyzes the impact of digital transformation on enterprise innovation and selects the panel data of China's Shanghai and Shenzhen A-share listed companies from 2013 to 2021 as the research objective is to study the impact of digital transformation on enterprise innovation from theoretical and empirical perspectives. First, we find that digital transformation accelerates enterprise innovation, a conclusion that has been validated through robustness testing. Second, digital transformation impacts enterprise innovation by enhancing productivity and information transparency. Third, financing constraints and financial redundancy play distinct regulatory roles in the process. Fourth, heterogeneity analysis finds that the role of digital transformation in promoting enterprise innovation has different effects in state-owned and non-state-owned enterprises, high-tech and non-high-tech enterprises, and enterprises with different life cycles. Finally, the functional analysis suggests that further investigation is needed to determine whether digital transformation can significantly promote the sustainable development of enterprises through innovation while also recognizing that this function may have a lag effect. Overall, this study contributes to a deeper understanding of digital transformation and innovation-driven practices and encourages more significant integration of the real and digital economies. [ABSTRACT FROM AUTHOR]

Presents abstracts of papers on automation and robotics presented at the 18th International Symposium on Laboratory Automation and Robotics. 'Genomics and the new era of drug discovery: A Wall Street perspective,' by E. James Streator; 'Productivity and drug discovery: The Genzyme small molecule experience,' by Frederick Vinick; 'Modern HTS: Infrastructure and workflow versus technology and science,' by Melvin Reichman.

In order to solve the problems of poor stability and low operation efficiency of the traditional power marketing metering production automatic scheduling system, this paper proposes a power metering automation system based on the Internet of Things. In this paper, the hardware and software of the system are designed under the environment of the Internet of Things. The hardware part is mainly divided into three platforms: basic resource layer, platform business layer, and interface presentation layer. The normal operation is realized through the network topology, and the load balancing server and business subsystem are emphatically designed. The software is completed in four steps: coding, scheduling, backup, and display. The experimental results show that the integrity rate of the electric quantity data collected by this system in the experiment with the traditional system is as high as 99%. Compared with the traditional dispatching system, the power information dispatching system designed under the Internet of Things has better stability and higher operation efficiency. [ABSTRACT FROM AUTHOR]

This paper extends our previous method for COVID-19 diagnosis, proposing an enhanced solution for detecting COVID-19 from computed tomography (CT) images using a lean transfer learning-based model. To decrease model misclassifications, two key steps of image processing were employed. Firstly, the uppermost and lowermost slices were removed, preserving sixty percent of each patient's slices. Secondly, all slices underwent manual cropping to emphasize the lung areas. Subsequently, resized CT scans (224 × 224) were input into an Xception transfer learning model with a modified output. Both Xception's architecture and pretrained weights were leveraged in the method. A big and rigorously annotated database of CT images was used to verify the method. The number of patients/subjects in the dataset is more than 5000, and the number and shape of the slices in each CT scan varies greatly. Verification was made both on the validation partition and on the test partition of unseen images. Results on the COV19-CT database showcased not only improvement from our previous solution and the baseline but also comparable performance to the highest-achieving methods on the same dataset. Further validation studies could explore the scalability and adaptability of the developed methodologies across diverse healthcare settings and patient populations. Additionally, investigating the integration of advanced image processing techniques, such as automated region of interest detection and segmentation algorithms, could enhance the efficiency and accuracy of COVID-19 diagnosis. [ABSTRACT FROM AUTHOR]

Undercarriage device is one of the essential parts of an aeroplane, and accurate detection of whether the aeroplane undercarriage is operating normally can effectively avoid aeroplane accidents. To address the problems of low automation and low accuracy of small target detection in existing aeroplane undercarriage detection methods, an improved algorithm for aeroplane undercarriage detection YOLO V4 is proposed. Firstly, the convolutional network structure of Inception-ResNet is integrated into the CSPDarkNet53 framework to improve the algorithm's ability to extract semantic information of target features; then an attention mechanism is added to the path aggregation network algorithm structure to improve the importance and relevance of different features after conceptual operations. In addition, aeroplane and undercarriage datasets were constructed, and finally, the generated partitioned test sets were tested to evaluate the test performance of Faster R-CNN, YOLO V3, and YOLO V4 target detection algorithms. The experimental results show that the improved algorithm has significantly improved the recall rate and the mean accuracy of detection for small targets in our dataset compared with the YOLO V4 algorithm. The reasonableness and advancedness of the improved algorithm in this paper are effectively verified. [ABSTRACT FROM AUTHOR]

Purpose. Single-period segmentation is one of the important steps in time-domain analysis of pulse signals, which is the basis of time-domain feature extraction. The existing single-period segmentation methods have the disadvantages of generalization, reliability, and robustness. Method. This paper proposed a period segmentation method of pulse signals based on long short-term memory (LSTM) network. The preprocessing was performed to remove noises and baseline drift of pulse signals. Thus, LabelMe was used to label each period of the pulse signals into two parts according to the location of the starting point of main wave and the dicrotic notch, and the dataset of the pulse signal period segmentation was established. Consequently, the labeled dataset was input into the LSTM for training and testing, and the results were compared with sum slope function method. Result. The remarkable result with the whole period segmentation accuracy of 92.8% was achieved for the segmentation of seven types of pulse signals. And the segmentation accuracies of the systolic phase, diastolic phase, and whole period using this method were higher than those of the sum slope function method. Conclusion. LSTM-based pulse signal segmentation method can achieve outstanding, robust, and reliable segmentation effects of the systolic phase, diastolic phase, and whole period of pulse signals. The research provides a new idea and method for the segmentation of pulse signals. [ABSTRACT FROM AUTHOR]

In order to solve the problem of low production efficiency of the mechanical electromechanical automatic control system, this paper proposes a manufacturing mechanical automatic detection system based on Internet of things technology. Automatic detection of manufacturing machinery is realized by setting data module monitoring, which includes the data monitoring module and signal detection module. The experimental results show that compared with the traditional computer vision system, the detection system designed in this paper has a higher level of basic data and better detection accuracy. The detection accuracy can be improved by about 10% in different detection times. Conclusion. The mechanical and electrical automation control system based on the Internet of things can effectively improve the production efficiency and control accuracy of the mechanical and electrical automation control system. [ABSTRACT FROM AUTHOR]

At present, there are frequent occurrences in the industry of manufacturers only having products, but they have no product data, resulting in manufacturers unable to open molds to produce the products themselves and can only buy them at high prices. This article takes the rear case of an automobile generator produced by a company as an example, which aims to show the design of automobile injection molds through automation technology. This paper studies the use of automation technology to achieve the automatic model reconstruction of products, and uses the CAD technology to design injection molds based on the obtained digital models of products. This paper also uses the CAE technology to verify the feasibility and rationality of the designed mold, exploring the optimization method of the injection molding process of the mold. In this paper, a special product pouring system and demolding mechanism are designed according to the product process requirements. The design greatly simplifies the mold structure while fulfilling the product process requirements, which avoids the use of expensive hot runners and complex flip-chip mold structures, reducing the mold manufacturing cost. Secondly, the overall design of the injection mold is carried out, and the external dimensions and other main parameters of the mold are determined. Then, Moldflow software is used to simulate the injection molding process, verifying the feasibility and rationality of the designed mold. The optimization method of the injection molding process is also proposed, and the optimal injection process parameters are determined to ensure that the mold can produce qualified products and ensure high production efficiency. It can be seen from the analysis results that the maximum warpage deformation of the plastic part under all effects is 0.65 mm, which meets the product process requirements. [ABSTRACT FROM AUTHOR]

In today's society, the rapid development of information technology has had a profound impact on human work and life as well as on education. In recent years, the rapid development of the Internet and information technology has laid a solid foundation for the digital transmission of information, which has changed the mode of information transmission and improved the efficiency of information dissemination. As an important part of network information dissemination, blended teaching is rapidly developing from an on-demand learning platform to an interactive learning platform and has now become a blended teaching platform in China. The main problem of the current blended teaching model is that the effect of improving performance is not good. In order to solve this problem, this paper introduces automation technology, which can significantly improve the extraction accuracy of information extraction methods in specific fields by using rich domain knowledge and features and complete the extraction tasks at multiple levels. The automation method based on automation technology has great advantages in this regard and effectively improves the English performance. Two groups of voluntary college students were randomly selected to conduct a one-semester blended teaching model designed in this paper to investigate the 'students' English scores. The average grades of students were 95.2, 96.7, 96.8, and 97.2, respectively, which is a big improvement over the existing system. [ABSTRACT FROM AUTHOR]

With the continuous updating and advancement of artificial intelligence technology, it gradually begins to shine in various industries, especially playing an increasingly important role in incremental music teaching and assisted therapy systems. This study designs artificial intelligence models from the perspectives of attention mechanism, contextual information guidance, and distant dependencies combined with incremental music teaching for the segmentation of MS (multiple sclerosis) lesions and achieves the automatic and accurate segmentation of MS lesions through the multidimensional analysis of multimodal magnetic resonance imaging data, which provides a basis for physicians to quantitatively analyze MS lesions, thus assisting them in the diagnosis and treatment of MS. To address the highly variable characteristics of MS lesion location, size, number, and shape, this paper firstly designs a 3D context-guided module based on Kronecker convolution to integrate lesion information from different fields of view, starting from lesion contextual information capture. Then, a 3D spatial attention module is introduced to enhance the representation of lesion features in MRI images. The experiments in this paper confirm that the context-guided module, cross-dimensional cross-attention module, and multidimensional feature similarity module designed for the characteristics of MS lesions are effective, and the proposed attentional context U-Net and multidimensional cross-attention U-Net have greater advantages in the objective evaluation index of lesion segmentation, while being combined with the incremental music teaching approach to assist treatment, which provides a new idea for the intelligent assisted treatment approach. In this paper, from algorithm design to experimental validation, both in terms of accuracy, the operational difficulty of the experiment, consumption of arithmetic power, and time cost, the unique superiority of the artificial intelligence attention-based combined with incremental music teaching adjunctive therapy system proposed in this paper can be seen in the MS lesion segmentation task. [ABSTRACT FROM AUTHOR]

Substation automation systems (SAS) are critical infrastructures whose design and maintenance must be optimised to guarantee a suitable performance. In order to provide a collection of solutions that balance availability and cost, this paper explores the optimisation of the design and maintenance of a section of SAS. Multiobjective evolutionary algorithms are combined with discrete event simulation while the performance of two state-of-the-art multiobjective evolutionary algorithms is studied. On the one hand, the nondominated sorting genetic algorithm II (NSGA-II), and on the other hand, the S-metric selection evolutionary multiobjective optimisation algorithm (SMS-EMOA). Such a problem is solved from 2 and 3-objective approaches by attending to the multiobjectivisation concept. The robustness of the methodology is brought to light, and benefits were observed from the multiobjectivisation approach. Decision-makers can employ this knowledge to make informed decisions based on economic and reliability criteria. [ABSTRACT FROM AUTHOR]

With the rapid development of science and technology, modeling technology involves more and more fields and the data objects studied are more and more abstract. Based on the Internet plus complex discrete dynamic modeling technology, this paper studies the auditing and control of computerized accounting computerization. In order to maintain the steady state of the discrete dynamic system, the lifting method boosting, least square method, gradient boost, and LS-Ensem algorithm are added in the modeling process. Then, in order to improve the data recognition ability of the system, the recognition algorithm is added. The results show that the complex discrete dynamic system composed of the above algorithms is different from the ordinary system and can be better suitable for small-scale data. It also improves the stability of the whole system and then improves the accuracy of the model. Compared with ordinary discrete systems, the complex discrete dynamic systems studied in this paper can better overcome external factors and avoid errors. The system can quickly analyze and process the data that need statistics and has good application value. [ABSTRACT FROM AUTHOR]

Space has become a driver not only for knowledge, inspiration, cooperation, and policymaking, but also for high-end technology integration into the manufacturing domain. As the high-density city quarters, the Macau Peninsula carries multiple functions via its public outdoor spaces, and they are of vital significance. Closely intertwined with Industry 4.0 is therefore the next industrial revolution that is already showcasing the benefits of increased connectivity, intelligence, and flexible automation. The rapid urbanization of Macao was not guided by sound land use planning, induced the scattering of many negative spaces on narrow streets. Because of their irregular shapes and utilization difficulties, these spaces gradually become leftover spaces. A number of measurement-based street leftover spaces models have been developed over the years by researchers as well as standards bodies to model path in typical wireless environments. In this paper, the streets of Macao are analyzed based on the city characteristics. The pedestrians and spatial relationships are investigated via space syntax and SPSS regression fitting. Finally, activation design of street leftover spaces is conducted, for making better use of leftover spaces, compensate for the functional deficiencies of streets, and endow them with more vigor and vitality. [ABSTRACT FROM AUTHOR]

In order to solve the problems of large demand for power business and small number of customer service, an intelligent customer service questioning and answering a system for power business scenario based on AI technology is designed. The approach first uses the particle swarm optimization algorithm to automatically classify the question attributes and then uses the fuzzy c-means clustering algorithm to match the answers with the highest similarity to the questions and return to the customers. The system collects the questions raised by customers through the acquisition module, uploads the question work order to the knowledge base through the information assistance module, and stores the preprocessed questions to the knowledge base. After completing the problem attribute classification through the particle swarm clustering algorithm classification model in the batch analysis and calculation module, the question answers are matched through fuzzy c-means clustering. At the same time, the similarity of different keywords is calculated to find a series of related questions. After the obtained data are analyzed in real time through the self-service customer service module, the answer is extracted and fed back to the customer, and the question answer is presented to the customer in the system interface. The experimental results show that the designed system has low worst-case time complexity, which is up to 0.35 only. The reason is that the system in this paper can use priority information to deal with the problems raised by customers, which is different from the past work where dealing with customers request via priority information is not used. The system can give the corresponding answers according to the customer's options. It has convenient operation, high integrated control ability, and good information management performance. Compared with the traditional approach which could waste a lot of resource and data, the proposed approach can reduce the differences between problem data, eliminate invalid data, and simplify the data classification process. The application of the system can effectively accelerate the information transmission efficiency of the power company and can be used for power exchange platform automation in the future. [ABSTRACT FROM AUTHOR]

Automatic production system scheduling problem under a just-in-time environment is researched in this paper. The automatic production system is composed of many tanks and one robotic, the tank of the researched problem is responsible for processing the job, and the robotic moves the job from one tank to the other tank. The difference between the researched problem and the classic shop scheduling problem is that the former must consider job scheduling and the robotic move sequence, but the latter considers only job scheduling. For optimizing simultaneously job scheduling and robotic move sequence in the proposed problem and minimizing total earliness/tardiness, an improved NEH (Nawaz-Enscore-Ham) and variable search (INEH-VNS) algorithm are developed. In the proposed method, firstly, to obtain initial solution, an improved NEH is shown. Secondly, for computing value of the objective function, the double procedure method is constructed. Thirdly, according to the properties of the proposed problem, three neighborhood structures, adjacent exchange, random insertion, and job exchange, are investigated. To test the performance of the INEH-VNS, 100 instances are randomly generated. When the run time is the same, compared with CPLEX 12.5, the INEH-VNS algorithm can find high-quality approximate optimal solution, a special big scale. Compared with the G-VNS algorithm, the average improvement rate of the approximate optimal solution is 45.9%, and the average stability rate of the INEH-VNS algorithm enhances 75.04%. That is to say, the INEH-VNS algorithm is outstanding and more effective. [ABSTRACT FROM AUTHOR]

In order to improve the forecasting effect of the gray prediction model, this paper combines the fuzzy theory to construct the gray prediction model and explores its forecasting accuracy. Moreover, this paper uses the entropy weight method to obtain the objective weight to correct the subjective weight, which makes the weight calculation more reasonable. In view of the uncertainty of the control signal of the research object, this paper introduces the gray system theory to conduct cluster analysis on the fire control computer and mainly introduces the general whitening weight function. Furthermore, this paper adopts the center point mixed with a triangular whitening weight function to carry out gray clustering according to the difficulty of defining the gray class boundary and gives the solution steps to obtain the intelligent gray prediction model. Finally, this paper verifies that the intelligent gray prediction model based on fuzzy theory has a good effect through experiments, which can effectively improve the prediction effect of the intelligent prediction model. [ABSTRACT FROM AUTHOR]

In order to further improve the automation setting of distribution system, this paper proposes an optimization research of distribution automation system based on artificial intelligence wireless network technology. This method uses artificial intelligence wireless network technology to optimize the automation of distribution system and improve the automation ability of distribution system. The experimental results show that when the number of iterations in the training process reaches 338, the mean square error is 0.001. Conclusion. The optimization research method of distribution automation system based on artificial intelligence wireless network technology can more effectively improve the automation level of distribution system. [ABSTRACT FROM AUTHOR]

In order to improve the effect of electrical automation control, this paper combines the intelligent computer technology to construct the electrical automation control system, explores the principle of the active disturbance rejection controller, and applies it to the induction motor vector control system. The active disturbance rejection controller estimates the state variables of the system and their changing trends in real time through the extended state observer, compensates them by nonlinear feedback method, and provides appropriate control signals. In addition, this paper builds the induction motor active disturbance rejection control system based on ant colony algorithm and conducts a lot of simulation analysis. The research shows that the electrical automatic control system based on the intelligent computer algorithm proposed in this paper has a good electrical automatic control effect. [ABSTRACT FROM AUTHOR]

Presents abstracts presented at the 1999 Pittsburgh Conference on automated methods and management in chemistry in Pennsylvania. 'Microfabrication as a Route to Nanovolume Separation Systems,' by Fred Regnier, Brian Burke and Bing He; 'Fast FTIR Imaging of Multicomponent Polymer Systems,' by J.L. Koenig and C.M. Snively; 'The Emergence of PC-based Measurement and Automation at Pittcon,' by Dudley Baker.

Blockchain (BC) maintains a continuously growing database in a "decentralized" way, and its impact on the financial auditing industry is becoming increasingly significant. This paper aims to study the research on financial automation auditing methods supported by blockchain technology and proposes the related concepts of blockchain technology, hash function, financial auditing analysis, and the impact of BP Neural Network (BPNN) and its algorithms on financial automation auditing methods. Simultaneously, this paper likewise disperses the poll overview to definite individuals, for example, endeavor, monetary work force, focus and ranking directors, university researchers, and specialists, who have pragmatic support in the execution and use of monetary review. The experimental results of this paper show that speculation based on the interconnected environment is the most basic natural factor for understanding this idea, and its score is also the largest at 4.36 points. [ABSTRACT FROM AUTHOR]

Objective. Artificial intelligence-powered screening systems of coronavirus disease 2019 (COVID-19) are urgently demanding since the ongoing outbreak of SARS-CoV-2 worldwide. Chest CT or X-ray is not sufficient to support the large-scale screening of COVID-19 because mildly-infected patients do not have imaging features on these images. Therefore, it is imperative to exploit supplementary medical imaging strategies. Traditional Chinese medicine has played an essential role in the fight against COVID-19. Methods. In this paper, we conduct two kinds of verification experiments based on a newly-collected multi-modality dataset, which consists of three types of modalities: tongue images, chest CT scans, and X-ray images. First, we study a binary classification experiment on tongue images to verify the discriminative ability between COVID-19 and non-COVID-19. Second, we design extensive multimodality experiments to validate whether introducing tongue image can improve the screening accuracy of COVID-19 based on chest CT or X-ray images. Results. Tongue image screening of COVID-19 showed that the accuracy (ACC), sensitivity (SEN), specificity (SPEC), and Matthew correlation coefficient (MCC) of the improved AlexNet and Googlenet both reached 98.39%, 98.97%, 96.67%, and 99.11%. The fusion of chest CT and tongue images used a tandem multimodal classifier fusion strategy to achieve optimal classification, and the results and screening accuracy of COVID-19 reached 98.98%, resulting in a significant improvement of 4.75% the highest accuracy in 375 years compared with the single-modality model. The fusion of chest x-rays and tongue images also had good classification accuracy. Conclusions. Both experimental results demonstrate that tongue image not only has an excellent discriminative ability for screening COVID-19 but also can improve the screening accuracy based on chest CT or X-rays. To the best of our knowledge, it is the first work that verifies the effectiveness of tongue image on screening COVID-19. This paper provides a new perspective and a novel solution that contributes to large-scale screening toward fast stopping the pandemic of COVID-19. [ABSTRACT FROM AUTHOR]

The key problem of operation optimization for automated container terminal is the coordinated scheduling of automated quay crane (QC), automated guided vehicle (AGV), and automated stacking crane (ASC). In order to solve this problem, this paper proposed a new method to optimize the scheduling of ASC and AGV. In the automated container terminal, each container block is equipped with twin ASCs. At the same time, buffer zones are set at both ends of the container block to achieve the decoupling operation among ASC, AGV, and container truck. Considering the buffer capacity constraint and twin ASC operation interference, and introducing the design of handshake area, this paper developed a collaborative scheduling model of AGV and ASC in automatic terminal relay operation mode. This model is designed based on the genetic algorithm. The model aims to minimize the AGV waiting time and the ASC running time. The results indicated that the introduction of handshake area can effectively reduce the ASC operation interference by 10.56% on average. Also, it can be found that increasing buffer capacity can reduce the waiting time of AGV by about 4.25% on average, and the effect of relay operation is more obvious in large-scale operation. It was proved that buffer zone and handshake area can reduce task delay time and improve coordination between AGV and ASC. [ABSTRACT FROM AUTHOR]

Cloud model and sensor network are the research hotspots in recent years. This paper proposes a congestion and rate control strategy for wireless sensor networks based on cloud model. It adjusts the input rate of nodes based on cloud model through node congestion detection. Aiming at the problem of network congestion control, two congestion adjustment algorithms based on red are improved. Congestion threshold and congestion degree are used as the basis of packet transmission rate adjustment to realize network support plug control. In this paper, the congestion control strategy NP starts to alleviate congestion at about 40 s and controls the packet loss rate at about 116 packets/s, which is 45.3% lower than the multipath congestion control strategy and is more stable. However, when β = 0 , the packet loss rate of the double congestion threshold algorithm is 20% lower than that of the single congestion threshold algorithm. The reason is that the double congestion threshold algorithm allows a stronger source rate control mechanism earlier than the single congestion threshold algorithm a large number of packets are lost in a point, but this also makes the network performance relatively low. [ABSTRACT FROM AUTHOR]

Summary: Around the world, automation is transforming work, business, and the economy as one of the Pillars of a smart grid. The vital role behind utilizing the automation system into distribution networks is to achieve grid self‐healing and improve the reliability level. Distributed Automation (DA) can be achieved via Smart secondary substations at each load point with installed automatic sectionalize switches that need a large investment. Therefore, this paper provides a long‐term plan based on a cost/benefit study to define the optimal automation level of Distribution networks constrained with system reliability indices limits. DA planning is categorized as a non‐linear Mixed Integer optimization problem with multi‐dimensions. Hence, it is not possible to apply numerical algorithms to directly search for all possible automation scenarios. To solve that problem; Hybrid Particle Swarm Optimization and Gravitational Search Algorithm (HPSO‐GSA) technique provides a binary‐coded procedure to handle all the controlled variables to provide the best solution within the permissible limits. The effectiveness of the proposed methodology is demonstrated by applying it to RBTS‐Bus 4 standard reliability test system considering uncertainty in Cost Damage Function (CDF), Investment Cost (IC), and Failure Rate (FR). Also, this paper study the effect of change in Depreciation ratio (DR), Load Growth (LG) rate besides; peak Load Change (LC). Finally, a reliability assessment using NEPLAN software is done for the optimal decision to enhance the technical analysis. Moreover, Distributed Generations (DG) has a significant impact on the reliability of distribution networks. Simulation results indicate that the system reliability cost is significantly reduced with adequate system reliability level, with comparative results to those in literary studies. [ABSTRACT FROM AUTHOR]

Aiming at the problems of the radial basis network model, this paper proposes a multimedia vocal singing automation evaluation network model, combined with the characteristics of multimedia modeling innovation design, and proposes a two-level comprehensive model. First of all, the theory and algorithm of analytic hierarchy process and radial basis function network are researched and analyzed, and the RBF is predicted for the mature area of multimedia development based on the three indicators of the total amount of classified vocals. The prediction scheme evaluation system is then used to fit the prediction data and influencing factors using the RBF network, and then the classified vocals are adjusted and synthesized hierarchically, and a multimedia vocal classification prediction model is established. Finally, this paper uses an example to verify the feasibility performance and prediction accuracy. Based on the above theory, the experiment uses VC++ 6.0 and Matlab 6.5 combined with database technology to initially realize the evaluation system and achieves a good evaluation effect. The simulation results show that three different algorithms are used to establish RBFO content prediction models. The correlation coefficient limit, root mean square error prediction, and relative analysis error (RED) reached 0.9937, 15.5095, and 8.216, respectively. At the same time, the evaluation results have high accuracy and credibility, which not only provide designers with ideas and improvement basis for innovative designs but also ensure design quality, improve design efficiency, and show that RBF networks have good generalization capabilities. [ABSTRACT FROM AUTHOR]

Smart network management automation (SNMA) is a technology that enables the automation of network management tasks. It provides a platform for automating network management, allowing administrators to manage their networks more reliably and efficiently. It provides the tools to monitor and manage network performance, identify and troubleshoot problems, and automate the deployment of new services and applications. SNMA also allows for scalability to meet the needs of any organization, regardless of size or complexity. With SNMA, network administrators can quickly and accurately identify problems, increase network uptime, and reduce time spent on manual tasks. The SNMA provides the ability to adjust configurations quickly and respond to changes in the network environment. It can help reduce costs and improve the efficiency of network operations. This paper proposed an intelligent network management automation algorithm for network administration and management in 5G communication networks. The proposed algorithm achieved 91.82% of remote network administration, 95.25% of global network administration, 96.59% of urban network administration, and 95.07% of local network administration. It creates a single submission to the network to make configuration changes, register network resources, manage users' IP addresses, and filter packets to ensure information security and other tasks. [ABSTRACT FROM AUTHOR]

The California Department of Motor Vehicles (DMV) reports, including disengagement and collision reports, provide information on each accident or disengagement activity for on-road testing of autonomous driving systems (ADSs) and autonomous vehicles (AVs). Unfortunately, current DMV reports have been misleading in relation to many key details, making it challenging for readers of those reports to discern the events' root causes and interrelationships. Therefore, appropriate systematic classification methods and principles need to be adopted. We follow an identification method similar to fault tree analysis (FTA) with the help of the driving reliability and error analysis method (DREAM 3.0) and the Haddon matrix to find the potential key accident factors from all disengagement data. We also conduct ADS risk assessments of potential disengagements and genuine accidents classified by traditional accident types. In addition, the automated driving system is composed of various software modules, and a classification method that is suitable from the standpoint of ADS software developers is developed in this paper. Next, we sort out the characteristics of the most frequent accidents based on the risk assessment results. Finally, we propose a workable risk reduction solution according to the characteristics of accidents. [ABSTRACT FROM AUTHOR]

Development and deployment technologies for data-intensive web applications have considerably evolved in the last years. Domain-specific frameworks or model-driven web engineering approaches are examples of these technologies. They have made possible to face implicit problems of these systems such as quick evolving business rules or severe time-to-market requirements. Both approaches propose the automation of redundant development tasks as the key factor for their success. The implementation of CRUD operations is a clear example of repetitive and recurrent task that may be automated. However, although web application frameworks have provided mechanisms to automate the implementation of CRUD operations, model-driven web engineering approaches have generally ignored them, so automation has not been properly faced yet. This paper presents a pattern-based development approach for the Interaction Flow Modeling Language as a way to finally automate repetitive specification tasks. Our approach is illustrated by defining and applying IFML patterns for CRUD operations. Additionally, a supporting tool, which enables automation, is shown. The suitability of our approach and the utility of its tool have been evaluated by its application into several real projects developed by a software company specialized in model-driven web application development. The results obtained present evidence of a significant productivity improvement obtained by the automation of the IFML specification of CRUD operations. [ABSTRACT FROM AUTHOR]

Connecting joints are significant components in mechanical systems as well as the Cartesian flexible robotic manipulator (FRM) which consists of a flexible arm and a moving base through connecting joints. Uncertain factors, such as unqualified assembly, accidental collision, and longtime service, will reduce the restraint stiffness of the connecting joints and enhance the dynamic nonlinearity of the system subsequently. In this case, the traditional perfectly fixed restrained model cannot reflect the real property of the connecting joints. This paper focuses on the elasticity property of the connecting joints with uncertain restraint stiffness, which is defined as the elastically restrained connecting joints (ERCJ), and investigates the dynamic characteristics and restraint mechanism of the ERCJ. An elastic restrained model is proposed to describe the elasticity property of the connecting joints and determine the elastic restrained region of the ERCJ, and the frequency relationship equation in the elastic restrained region is simultaneously determined and verified. Based on the proposed elastic restrained model and Hamilton’s variational principle, the dynamic model and vibration displacement equation of the FRM with elastically restrained connecting joints (FRMERCJ) are established. The virtual prototype experiment of the FRMERCJ is conducted to verify the dynamic model and reveal the restraint mechanism of the ERCJ. The proposed elastic restrained model in this paper can accurately describe the elasticity property of the connecting joints, and the ERCJ is sensitive to motion velocities especially under higher velocities for higher-order vibrations in the initial stage. The results are meaningful for the dynamic analysis and vibration control of robotic manipulators. [ABSTRACT FROM AUTHOR]

The localization technology is the essential requirement of constructing a smart building and smart city. It is one of the most important technologies for wireless sensor networks (WSNs). However, when WSNs are deployed in harsh indoor environments, obstacles can result in non-line-of-sight (NLOS) propagation. In addition, NLOS propagation can seriously reduce localization accuracy. In this paper, we propose a NLOS localization method based on residual analysis to reduce the influence of NLOS error. The time of arrival (TOA) measurement model is used to estimate the distance. Then, the NLOS measurement is identified through the residual analysis method. Finally, this paper uses the LOS measurements to establish the localization objective function and proposes the particle swarm optimization with a constriction factor (PSO-C) method to compute the position of an unknown node. Simulation results show that the proposed method not only effectively identifies the LOS/NLOS propagation condition but also reduces the influence of NLOS error. [ABSTRACT FROM AUTHOR]

The impact of team heterogeneity on team effectiveness has received extensive attention. The paper aims to explore the mechanism of the effect of cognitive heterogeneity on behavioral integration in R&D teams. Based on the IPO theory, this study proposed six hypotheses about how cognitive heterogeneity directly and indirectly (via team conflict and conflict management) affect behavioral integration in R&D teams. Using data collected from 383 R&D teams in 326 high-tech enterprises in China, we investigated whether the dimensions of team conflict mediate the relationship between cognitive heterogeneity and behavioral integration and whether the dimensions of conflict management regulate the impact of cognitive heterogeneity on behavioral integration. The results show the following: (1) cognitive heterogeneity has a significant negative impact on the behavioral integration of R&D teams. Task conflict and relationship conflict fully mediate the relationship between cognitive heterogeneity and behavioral integration. (2) Cooperative conflict management positively moderates the impact of cognitive heterogeneity on task conflict and the impact of task conflict on team behavioral integration. (3) Avoidance conflict management reversely adjusts the positive impact of cognitive heterogeneity on task conflict and relationship conflict and the negative impact of relationship conflict on team behavioral integration. The research results can provide theoretical guidance to improve the process management of cognitive heterogeneity R&D teams. [ABSTRACT FROM AUTHOR]

This article is aimed at studying the features of the control systems development for a small-sized Computer Numerical Control (CNC) portative laser engraver. The CNC is implemented in mobile maintenance and repair platforms for remote sensing of the environment where the wild environment may not allow us to access the animals and places. The proposed work in this paper is based on recent research, which shows that applying the automated CNC speeds up the processes of repair, modernizes the equipment size, and significantly reduces the economic costs; accordingly, the authors developed a block diagram of a portable CNC laser engraver. The choice of the hardware was also made, taking into account the possibility of quick replacement in the field, which reduces the repair time and the cost of the developed layout. A control system based on the selected modules was synthesized, and a stability check was carried out using MatLab tools. To check the correctness of the developed control system, the authors developed and assembled an experimental layout to illustrate the results of engraving on such a layout. Finally, the stability and sensitivity of the proposed system have been obtained and proved that the system works in a comfortable zone of stability. The obtained results show that the proposed CNC laser engraver has achieved the expected improvements (high speed, small size, short production and repairing time, minimum human influence factor, and achieving a better outcome). [ABSTRACT FROM AUTHOR]

In recent years, people are committed to developing new technologies and technologies for energy storage and conversion, environmental detection, high-performance sensors and energy security, and other aspects of the increasingly prominent problems in the field of environmental and biosafety. The purpose of this paper is to explore the manufacturing system and automatic synthesis equipment of carbon nanomaterials, understand the control device and control method, and analyze the structure and morphology characteristics of three kinds of carbon nanomaterials produced by carbon nanomaterial manufacturing system by X-ray diffraction and infrared spectroscopy. The results show that the carbon nanomaterial manufacturing system and automatic synthesis system in this paper solve the problems of high cost, low efficiency, and small scale of the existing carbon nanomaterials manufacturing and achieve the precision control of automatic production, so that the productivity is increased by 20%–35%, and the cost is reduced by 15%–30%. Therefore, they are widely used in the fields of science and technology, environmental protection, and intelligent manufacturing broad prospects. Carbon nanotube manufacturing equipment and automatic synthesis equipment have great production advantages, which can greatly improve the quality and efficiency of carbon nanomaterials. UPY, GO, and UGO carbon nanomaterials produced by carbon nanotube manufacturing equipment are not easy to fall off from the materials. When the wavelength is 500 nm, the absorption frequency of the three materials is the largest. With the extension of the spectral wavelength, the absorption frequency of the three materials is reduced by 52%, 33%, and 34.7%, respectively. [ABSTRACT FROM AUTHOR]

Applying machine learning technology to automatic image analysis and auxiliary diagnosis of whole slide image (WSI) may help to improve the efficiency, objectivity, and consistency of pathological diagnosis. Due to its extremely high resolution, it is still a great challenge to directly process WSI through deep neural networks. In this paper, we propose a novel model for the task of classification of WSIs. The model is composed of two parts. The first part is a self-supervised encoding network with a UNet-like architecture. Each patch from a WSI is encoded as a compressed latent representation. These features are placed according to their corresponding patch's original location in WSI, forming a feature cube. The second part is a classification network fused by 4 famous network blocks with heterogeneous architectures, with feature cube as input. Our model effectively expresses the feature and preserves location information of each patch. The fused network integrates heterogeneous features generated by different networks which yields robust classification results. The model is evaluated on two public datasets with comparison to baseline models. The evaluation results show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Objective. Internet of Things (IoT) integrates several technologies where devices learn from the experience of each other thereby reducing human-intervened likely errors. Modern technologies like IoT and machine learning enable the conventional to patient-specific approach transition in healthcare. In conventional approach, the biggest challenge faced by healthcare professionals is to predict a disease by observing the symptoms, monitoring the remote area patient, and also attending to the patient all the time after being hospitalised. IoT provides real-time data, makes decision-making smarter, and provides far superior analytics, and all these to help improve the quality of healthcare. The main objective of the work was to create an IoT-based automated system using machine learning models for symptom-based COVID-19 prognosis. Methods. Comparative analysis of predictive microbiology of COVID-19 from case symptoms using various machine learning classifiers like logistics regression, k-nearest neighbor, support vector machine, random forest, decision trees, Naïve Bayes, and gradient booster is reported here. For the sake of the validation and verification of the models, performance of each model based on the retrieved cloud-stored data was measured for accuracy. Results. From the accuracy plot, it was concluded that k-NN was more accurate (97.97%) followed by decision tree (97.79), support vector machine (97.42), logistics regression (96.50), random forest (90.66), gradient boosting classifier (87.77), and Naïve Bayes (73.50) in COVID-19 prognosis. Conclusion. The paper presents a health monitoring IoT framework having high clinical significance in real-time and remote healthcare monitoring. The findings reported here and the lessons learnt shall enable the healthcare system worldwide to counter not only this ongoing COVID but many other such global pandemics the humanity may suffer from time to come. [ABSTRACT FROM AUTHOR]

With the vigorous development of China's market economy, a new generation of artificial intelligence technology has also developed rapidly, which has strongly promoted the optimization and improvement of China's electrical automation control system. The use of artificial intelligence technology in power automation systems mainly has the following two advantages: it can reduce the manufacturing time of power products, thereby increasing the number of workers manufacturing power products and promoting enterprises to conduct larger-scale machine manufacturing, thereby improving the comprehensive economic benefits of enterprise machine manufacturing, but also improve the quality of manufactured products of electric power products. Since the machine control of artificial intelligence is more efficient than manual manufacturing, it reduces the manufacturing problems caused by the subjective factors of manufacturing workers to a certain extent and thus improves the qualification rate of machine production. Electrical engineering plays an important role in China's urban development, and automatic control is an important part of electrical engineering, which can have a direct impact on the quality of electrical engineering. Therefore, in order to promote the healthy development of cities in China, this paper studies the application of artificial intelligence technology in electrical engineering automation by analyzing relevant data, in order to provide a reliable basis for relevant personnel to carry out their work. [ABSTRACT FROM AUTHOR]

Arrhythmias are anomalies in the heartbeat rhythm that occur occasionally in people's lives. These arrhythmias can lead to potentially deadly consequences, putting your life in jeopardy. As a result, arrhythmia identification and classification are an important aspect of cardiac diagnostics. An electrocardiogram (ECG), a recording collecting the heart's pumping activity, is regarded the guideline for catching these abnormal episodes. Nevertheless, because the ECG contains so much data, extracting the crucial data from imagery evaluation becomes extremely difficult. As a result, it is vital to create an effective system for analyzing ECG's massive amount of data. The ECG image from ECG signal is processed by some image processing techniques. To optimize the identification and categorization process, this research presents a hybrid deep learning-based technique. This paper contributes in two ways. Automating noise reduction and extraction of features, 1D ECG data are first converted into 2D pictures. Then, based on experimental evidence, a hybrid model called CNNLSTM is presented, which combines CNN and LSTM models. We conducted a comprehensive research using the broadly used MIT_BIH arrhythmia dataset to assess the efficacy of the proposed CNN-LSTM technique. The results reveal that the proposed method has a 99.10 percent accuracy rate. Furthermore, the proposed model has an average sensitivity of 98.35 percent and a specificity of 98.38 percent. These outcomes are superior to those produced using other procedures, and they will significantly reduce the amount of involvement necessary by physicians. [ABSTRACT FROM AUTHOR]

With the rapid development of computer control and vehicle intelligence technology, speed and safety of vehicles have been greatly improved, and the requirements for vehicle control performance are getting higher and higher. For the direct braking force control, in the process of deceleration, a fast braking response can be obtained, which improves the braking performance and vehicle safety. This paper concentrates on direct braking force estimation and control strategy using a tire inverse model based on the antilock braking system, and to solve the problem of the existing ABS system is mainly antilock braking function, no direct braking force control function. Taking magic formula model for reference inverse model, the critical parameters under different road surfaces are obtained according to experience data. Then, the desired slip ratio corresponding to braking force can be obtained via fast tire inverse model look-up table method. The tyre friction self-adjustment decision making is obtained using the tire inverse model method. A direct braking force antilock braking system (DBF-ABS) controller is built using the nonsingular fast terminal sliding mode method. The simulation results indicated that the control strategy has adaptability and stability to the change of road conditions. [ABSTRACT FROM AUTHOR]

Machinery is the most important basic tool for modern times, and it is also an indispensable sharp weapon for creating big country projects. The production line management of general machinery is particularly important. Traditional production line management causes a lot of labor waste, time waste, and low production efficiency, so the efficiency of production line management also determines the quality and output of general machinery. Therefore, it has become an industry consensus to realize intelligent management in the manufacturing process of general machinery. General machinery is not only a complex industrial structure but also has a series of preconditions that are not conducive to production, such as the diversity of parts and the low precision of preparation in the early stage. Therefore, to realize automation in the field of construction machinery manufacturing, it usually faces more challenges. Whether it is traditional production process or automatic production process, the realization of intelligent production line is the primary problem, because both production efficiency and product quality are determined by the efficient production line management efficiency and exquisite process. The workload of production line management is heavy, which is time-consuming, labor-consuming, and expensive. Adhere to the goal of quality first, and how to improve the efficiency of the production line has become the biggest problem at present. Based on the above problems, this paper adopts intelligent computing model to improve the efficiency of production line management and optimize the process. A series of tedious processes from product adoption to final shipment of production lines need intelligent technology to simplify the process, which can effectively improve the production efficiency of general machinery, reduce production costs, and improve the production quality of machinery. Supply chain management theory is used to manage suppliers' production behavior, so as to reduce costs and improve quality and service, thus improving the competitiveness of batch production lines and enterprises. Advanced manufacturing technology is used to realize automation and flexible production of batch production lines, thus improving the rapid response ability of production lines to market demand. [ABSTRACT FROM AUTHOR]

Machine intelligence is what has been generated by programming computers with certain aspects of human intellect, like training, solving problems, and priority setting. A machine can solve a number of complicated issues using these capabilities. In major industries, such as customer support and manufacturing, machine intelligence is now being employed. The growth and quick development of digital technology and artificial intelligence (AI) technologies are becoming more and more difficult. At now, sophisticated manufacturing, the world of invention, and broad acceptance are undergoing a fast transition. Robotics is much more vital as it may now be related to the human brain by the connection between machine and brain, as AI develops. The world's economy faces substantial difficulties by increasing productivity in the manufacturing industry. This study examines the present progress of robotic communication styles of artificial intelligence (AI). In many specific applications, communication between members of a robotic group or even people becomes vital. The paper solves the problem of implementation of an independent industry mobile robot in all fields in the major business, live interactive, planning, mobile robot technologies, and intending. In order to identify the best solution to this issue, a mixed integer robotic model has been developed. [ABSTRACT FROM AUTHOR]

Prefabricated construction has been well recognized for its benefits, including accelerated construction cycle time and improved sustainability. However, low efficiency in the production of precast concrete components due to component and production complexity has not been sufficiently addressed in previous research. This paper explores the complexity of precast concrete components by establishing complexity indices and evaluating their influence on production efficiency. First, referring to research on product complexity in the machinery manufacturing industry, we define the complexity of precast concrete components in the construction industry. Then, based on a literature review, field studies, and expert interviews, we systematically construct the complexity indices of precast concrete components using the three-stage coding method, Grounded Theory. The overall complexity index system for precast concrete components constructed comprises 16 constituent complexity indices in three dimensions (i.e., structural complexity of the component, production complexity, and management complexity). The relationship between complexity indices and production efficiency is then explored using structural equation model analysis based on the data collected through a questionnaire survey. The results reveal that complexity indices have a significant impact on the production efficiency for precast concrete components, where the number of embedded parts, waiting time in production, operating proficiency of workers, and degree of automation of the production line are found to be the most influential complexity indices. This study provides a foundation upon which production managers improve production efficiency for precast concrete components based on an analysis of their product complexity. [ABSTRACT FROM AUTHOR]

Data news does not appear out of nowhere. It is the result of the press's ongoing exploration and innovation as part of the ongoing development of information technology. It is based on early computer-assisted news reporting, statistical news and precise news. In terms of theory and technology, it is a game-changer. The media industry is most sensitive to new technologies and is most willing to apply new technologies in the entire process of news reporting, such as information acquisition, content production and management, and content release, in an era of great changes in the popularity of the Internet and the in-depth application of data processing technology in all walks of life. The data news intelligent production platform investigated and designed in this paper, when combined with current emerging technologies, such as big data, cloud computing, and machine learning algorithms, realizes intelligent and automatic news production, ushering traditional news into an era of intelligence, knowledge, and digitization. Machine learning has made significant progress in the automatic production of data news technology and will continue to do so in the future information society. [ABSTRACT FROM AUTHOR]

Brain tumor is a fatal disease, caused by the growth of abnormal cells in the brain tissues. Therefore, early and accurate detection of this disease can save patient's life. This paper proposes a novel framework for the detection of brain tumor using magnetic resonance (MR) images. The framework is based on the fully convolutional neural network (FCNN) and transfer learning techniques. The proposed framework has five stages which are preprocessing, skull stripping, CNN-based tumor segmentation, postprocessing, and transfer learning-based brain tumor binary classification. In preprocessing, the MR images are filtered to eliminate the noise and are improve the contrast. For segmentation of brain tumor images, the proposed CNN architecture is used, and for postprocessing, the global threshold technique is utilized to eliminate small nontumor regions that enhanced segmentation results. In classification, GoogleNet model is employed on three publicly available datasets. The experimental results depict that the proposed method is achieved average accuracies of 96.50%, 97.50%, and 98% for segmentation and 96.49%, 97.31%, and 98.79% for classification of brain tumor on BRATS2018, BRATS2019, and BRATS2020 datasets, respectively. The outcomes demonstrate that the proposed framework is effective and efficient that attained high performance on BRATS2020 dataset than the other two datasets. According to the experimentation results, the proposed framework outperforms other recent studies in the literature. In addition, this research will uphold doctors and clinicians for automatic diagnosis of brain tumor disease. [ABSTRACT FROM AUTHOR]

The upper computer communication operation state automatic monitoring system is mainly used to remotely monitor the equipment, obtain various parameter indexes in the operation process of remote equipment, realize remote monitoring and fault diagnosis, and improve the management efficiency of decentralized equipment. This paper completes the design of communication, data storage, query, and other subsystems of upper and lower computers. The lower computer establishes a data channel with the OPC server through the MPI protocol and uploads the collected data to the OPC server in real time. The upper computer reads the data through the OPC server and displays the changes of monitored parameters in real time through the monitoring interface, so as to give an alarm under abnormal conditions. In addition, since the default database of Kingview is access, considering that the Microsoft Access database can store up to 2G of content, in order to upgrade and expand the subsequent system, SQL Server database is selected for data query, backup, and saving. The parameter setting method of communication control system is analyzed, the simulation model of industrial boiler control system is established by using Matlab/Simulink, and the interface between host computer software (IBCCS-e) and the model is provided. This paper analyzes the results of communication parameter adjustment. The simulation results show that the industrial boiler computer control system (IBCCS) has stable performance, low cost, convenient operation, and good maintainability. After further improvement, it has certain application value in the operation transformation of new small- and medium-sized boilers and original boilers. [ABSTRACT FROM AUTHOR]

This paper describes the end-to-end automation framework developed as part of the TRIANGLE project. The TRIANGLE project is devoted to the benchmarking of apps and devices in mobile networks. For that purpose, it is needed to ensure the repeatability in the behaviour of all the components of the mobile network during the execution of the same test. This is why one of the main objectives of the project was to develop an end-to-end automation framework to provide repeatable testing. This paper describes in detail the design and the implementation of the framework. [ABSTRACT FROM AUTHOR]

Pavement cracking is a significant symptom of pavement deterioration and deficiency. Conventional manual inspections of road condition are gradually replaced by novel automated inspection systems. As a result, a great amount of pavement surface information is digitized by these systems with a high resolution. With pavement surface data, pavement cracks can be detected using crack detection algorithms. In this paper, a fully automated algorithm for segmenting and enhancing pavement crack is proposed, which consists of four major procedures. First, a preprocessing procedure is employed to remove spurious noise and rectify the original 3D pavement data. Second, crack saliency maps are segmented from 3D pavement data using steerable matched filter bank. Third, 2D tensor voting is applied to crack saliency maps to achieve better curve continuity of crack structure and higher accuracy. Finally, postprocessing procedures are used to remove redundant noises. The proposed procedures were evaluated over 200 asphalt pavement images with diverse cracks. The experimental results demonstrated that the proposed method showed a high performance and could achieve average precision of 88.38%, recall of 93.15%, and F-measure of 90.68%, respectively. Accordingly, the proposed approach can be helpful in automated pavement condition assessment. [ABSTRACT FROM AUTHOR]

Mobile Robot Indoor Positioning System has wide application in the industry and home automation field. Unfortunately, existing mobile robot indoor positioning methods often suffer from poor positioning accuracy, system instability, and need for extra installation efforts. In this paper, we propose a novel positioning system which applies the centralized positioning method into the mobile robot, in which real-time positioning is achieved via interactions between ARM and computer. We apply the Kernel extreme learning machine (K-ELM) algorithm as our positioning algorithm after comparing four different algorithms in simulation experiments. Real-world indoor localization experiments are conducted, and the results demonstrate that the proposed system can not only improve positioning accuracy but also greatly reduce the installation efforts since our system solely relies on Wi-Fi devices. [ABSTRACT FROM AUTHOR]

Because of the lack of discriminative face representations and scarcity of labeled training data, facial beauty prediction (FBP), which aims at assessing facial attractiveness automatically, has become a challenging pattern recognition problem. Inspired by recent promising work on fine-grained image classification using the multiscale architecture to extend the diversity of deep features, BeautyNet for unconstrained facial beauty prediction is proposed in this paper. Firstly, a multiscale network is adopted to improve the discriminative of face features. Secondly, to alleviate the computational burden of the multiscale architecture, MFM (max-feature-map) is utilized as an activation function which can not only lighten the network and speed network convergence but also benefit the performance. Finally, transfer learning strategy is introduced here to mitigate the overfitting phenomenon which is caused by the scarcity of labeled facial beauty samples and improves the proposed BeautyNet's performance. Extensive experiments performed on LSFBD demonstrate that the proposed scheme outperforms the state-of-the-art methods, which can achieve 67.48% classification accuracy. [ABSTRACT FROM AUTHOR]