Error compensation in machine tools: a neural network approach

For a non-idealized machine tool, each point in the workspace is associated with a tool point positioning error vector. If this error map can be determined, then it is possible to substantially improve the positioning performance of the machine by introducing suitable compensation into the control loop. This paper explores the possibility of using an artifical neural network (ANN) to compute this mapping. The training set for the ANN is obtained by mounting a physical artifact whose dimensions are precisely known in the machine's workspace. The machine, equipped with a touch trigger probe, measures the positions of features on the artifact. The difference between the machine reading and the known dimension is the machine error at that point in the workspace. Using standard modeling techniques, the kinematic error model for a CNC turning center was developed. This model was parameterized by measurement of the parametric error functions using a laser interferometer, electronic levels and a precision square. The kinematic model was then used to simulate the artifact-measuring process and develop the ANN training set. The effect of changing artifact geometry was explored and a machining operation was simulated using the ANN output to provide compensation. The results show that the ANN is capable of learning the error map of a real machine, and that ANN-based compensation can significantly reduce part-dimensional errors.     

Collaborative writing in multiple discourse contexts

Research in computer-supported writing has traditionally compared electronic communication with oral, face-to-face communication to identify the benefits and weaknesses of each, as if they entailed dichotomous choices. In this article, we challenge that view and argue instead that any form of communication and its educational usefulness is shaped by the situation in which it is used, the backgrounds and goals of the participants, the institutional and technological setup, and the intended purpose of the medium. Three modes of communication in one graduate course are examined — oral discussion, synchronous written discussion on a local area network, and asynchronous written postings on an email list set up for the class. It was found that patterns of participation, topic introduction, and topic development differed across the three communication modes, but that the three were interwoven with each other and embedded within the larger classroom context and forms of knowledge creation in the class. Thus, rather than examining different communication media separately, researchers interested in understanding computer-supported collaborative writing need to look at how different media are used to create a meta-medium, which is established by the discourse community involved.     

The learning convergence of CMAC in cyclic learning

In this paper we discuss the learning convergence of the cerebellar model articulation controller (CMAC) in cyclic learning.We prove the following results.First,if the training samples are noiseless,the training algorithm converges if and only if the learning rate is chosen from (0,2).Second,when the training samples have noises,the learning algorithm will converge with a probability of one if the learning rate is dynamically decreased.Third,in the case with noises,with a small but fixed learning rate ε the mean square error of the weight sequences generated by the CMAC learning algorithm will be bounded by O(ε).Some simulation experiments are carried out to test these results.     

The influence of user cognition on consumption decision-making from the perspective of bounded rationality

Consumer decision-making is related to the success or failure of enterprises, and products that cater to the cognitive preferences of users have become a focus of current research. Based on the theory of bounded rationality, this paper explores the cognitive process of consumer decision-making. Then, how product shape affects consumption decision-making is analyzed with eye-tracking technology. Finally, the design principle of the product form is further explored. The results demonstrate the following: (1) the perceptual cognition of users has a driving effect on consumption behavior; (2) as a key factor affecting the perceptual cognition of users, product form affects consumer decision-making by influencing the degree of approach motivation; (3) by establishing the mapping relationship between product form elements and user images, the principles of product form design can be more consistent with user image preferences. This study provides useful suggestions for how to increase the purchase behavior of users from the perspective of bounded rationality.     

Ship detection based on multi-scale weighted fusion

Ship surveillance plays an important role in ensuring the safety of maritime transportation and navigation. Due to the influence of factors such as waves and special weather, the existing detection methods still cannot balance the accuracy, speed and the parameters of the model in the changeable and complex marine environment. To solve this problem, this paper proposes an improved real-time method based on YOLOv5, which has few parameters and achieves high detection accuracy with little memory and computation cost. Collaborative Attention (CA) mechanism is added to the network structure, which enables the model to more accurately locate and identify target regions. We also design a Spatial Pyramid Pooling module (SPP) and a weighted pyramid network called Bidirectional Feature Pyramid Network (BiFPN) based on the characteristics of the ships to better fuse feature information. Transformer encoder is introduced to capture long-distance dependencies and preserve global and local features to the greatest extent. Furthermore, the ability of our proposed structure to localize objects at each stage is improved through integrating the output of multiple modules. The experimental results show that, the comprehensive performance of this method is better than the existing technology in ship detection on different evaluation criteria.     

Improving robustness of industrial object detection by automatic generation of synthetic images from CAD models

Object detection (OD) is used for visual quality control in factories. Images that compose training datasets are often collected directly from the production line and labeled with bounding boxes manually. Such data represent well the inference context but might lack diversity, implying a risk of overfitting. To address this issue, we propose a dataset construction method based on an automated pipeline, which receives a CAD model of an object and returns a set of realistic synthetic labeled images (code publicly available). Our approach can be easily used by non-expert users and is relevant for industrial applications, where CAD models are widely available. We performed experiments to compare the use of datasets obtained by the two different ways—collecting and labeling real images or applying the proposed automated pipeline—in the classification of five different industrial parts. To ensure that both approaches can be used without deep learning expertise, all training parameters were kept fixed during these experiments. In our results, both methods were successful for some objects but failed for others. However, we have shown that the combined use of real and synthetic images led to better results. This finding has the potential to make industrial OD models more robust to poor data collection and labeling errors, without increasing the difficulty of the training process.     

A performance evaluation framework of public health distribution network for essential medicines: lessons from the select Indian states

The present work has been carried out to develop a performance evaluation framework of distribution network design in public health with specific reference to essential medicines based on six different types of public health distribution networks (PHDNs) prevalent across six Indian states. We evaluated the performance of PHDNs on the criteria of cost and service and also on the sub-criteria of cost and service by following the analytic hierarchy process. We utilized the pairwise comparison method in determining the relative importance of criteria and sub-criteria by seeking responses from several experts and subsequently evaluated the PHDNs on all sub-criteria in a 7-point Likert scale by seeking views from the same experts. Finally, we developed the “cost–service matrix,” in which cost and service have been depicted in the horizontal and vertical axes, respectively. We demonstrated the performance of six PHDNs in this matrix in terms of cost and service by plotting scores obtained by them on cost and service, respectively. The findings of the study provide rich insights to the policy planners of public health.     

Optimal Deep Learning Based Intruder Identification in Industrial Internet of Things Environment

With the increased advancements of smart industries, cybersecurity has become a vital growth factor in the success of industrial transformation. The Industrial Internet of Things (IIoT) or Industry 4.0 has revolutionized the concepts of manufacturing and production altogether. In industry 4.0, powerful Intrusion Detection Systems (IDS) play a significant role in ensuring network security. Though various intrusion detection techniques have been developed so far, it is challenging to protect the intricate data of networks. This is because conventional Machine Learning (ML) approaches are inadequate and insufficient to address the demands of dynamic IIoT networks. Further, the existing Deep Learning (DL) can be employed to identify anonymous intrusions. Therefore, the current study proposes a Hunger Games Search Optimization with Deep Learning-Driven Intrusion Detection (HGSODL-ID) model for the IIoT environment. The presented HGSODL-ID model exploits the linear normalization approach to transform the input data into a useful format. The HGSO algorithm is employed for Feature Selection (HGSO-FS) to reduce the curse of dimensionality. Moreover, Sparrow Search Optimization (SSO) is utilized with a Graph Convolutional Network (GCN) to classify and identify intrusions in the network. Finally, the SSO technique is exploited to fine-tune the hyper-parameters involved in the GCN model. The proposed HGSODL-ID model was experimentally validated using a benchmark dataset, and the results confirmed the superiority of the proposed HGSODL-ID method over recent approaches.     

An Ophthalmic Evaluation of Central Serous Chorioretinopathy

Nowadays in the medical field, imaging techniques such as Optical Coherence Tomography (OCT) are mainly used to identify retinal diseases. In this paper, the Central Serous Chorio Retinopathy (CSCR) image is analyzed for various stages and then compares the difference between CSCR before as well as after treatment using different application methods. The first approach, which was focused on image quality, improves medical image accuracy. An enhancement algorithm was implemented to improve the OCT image contrast and denoise purpose called Boosted Anisotropic Diffusion with an Unsharp Masking Filter (BADWUMF). The classifier used here is to figure out whether the OCT image is a CSCR case or not. 150 images are checked for this research work (75 abnormal from Optical Coherence Tomography Image Retinal Database, in-house clinical database, and 75 normal images). This article explicitly decides that the approaches suggested aid the ophthalmologist with the precise retinal analysis and hence the risk factors to be minimized. The total precision is 90 percent obtained from the Two Class Support Vector Machine (TCSVM) classifier and 93.3 percent is obtained from Shallow Neural Network with the Powell-Beale (SNNWPB) classifier using the MATLAB 2019a program.     

Evaluation of Grid-Connected Photovoltaic Plants Based on Clustering Methods

Photovoltaic (PV) systems are electric power systems designed to supply usable solar power by means of photovoltaics, which is the conversion of light into electricity using semiconducting materials. PV systems have gained much attention and are a very attractive energy resource nowadays. The substantial advantage of PV systems is the usage of the most abundant and free energy from the sun. PV systems play an important role in reducing feeder losses, improving voltage profiles and providing ancillary services to local loads. However, large PV grid-connected systems may have a destructive impact on the stability of the electric grid. This is due to the fluctuations of the output AC power generated from the PV systems according to the variations in the solar energy levels. Thus, the electrical distribution system with high penetration of PV systems is subject to performance degradation and instabilities. For that, this project attempts to enhance the integration process of PV systems into electrical grids by analyzing the impact of installing grid-connected PV plants. To accomplish this, an indicative representation of solar irradiation datasets is used for planning and power flow studies of the electric network prior to PV systems installation. Those datasets contain lengthy historical observations of solar energy data, that requires extensive analysis and simulations. To overcome that the lengthy historical datasets are reduced and clustered while preserving the original data characteristics. The resultant clusters can be utilized in the planning stage and simulation studies. Accordingly, studies related to PV systems integration into the electric grid are conducted in an efficient manner, avoiding computing resources and processing times with easier and practical implementation.