Art Models Research Articles

A novel thermo-geometrical model for accurate keyhole porosity prediction in Laser Powder-Bed Fusion

AbstractWhen performing Laser Powder-Bed Fusion, undesired physical phenomena, such as balling, preballing and keyhole, must be avoided in order to achieve high-quality products. To date, keyhole-free process parameters can be identified either using demanding empirical methods or complex numerical simulations, while only a few analytical models can be found in literature for this purpose. In this work, state-of-the-art analytical models for predicting keyhole porosity were summarized and proved to be rather inaccurate because they are only based on thermodynamic principles, whereas they neglect the geometry and both the kinetics and kinematics of the keyhole cavity, which do also influence cavity collapse and porosity formation. Here an innovative physics-based semi-analytical model for predicting the formation of keyhole-related porosities was conceived, in which both thermodynamic and geometrical factors are taken into account. The proposed model was validated by performing single tracks experiments on Ti6Al4V according to a full factorial DoE on laser power and scanning speed. Produced samples were cross-sectioned and analyzed to evaluate keyhole porosity formation. The comparison between experimental data and model predictions confirmed the higher accuracy of the new model with respect to state of the art models. Besides improving the understanding of the keyhole phenomenon, the proposed model may provide a novel, effective and simple tool for fast process parameter optimization in industry.

NAMSTCD: A Novel Augmented Model for Spinal Cord Segmentation and Tumor Classification Using Deep Nets.

Spinal cord segmentation is the process of identifying and delineating the boundaries of the spinal cord in medical images such as magnetic resonance imaging (MRI) or computed tomography (CT) scans. This process is important for many medical applications, including the diagnosis, treatment planning, and monitoring of spinal cord injuries and diseases. The segmentation process involves using image processing techniques to identify the spinal cord in the medical image and differentiate it from other structures, such as the vertebrae, cerebrospinal fluid, and tumors. There are several approaches to spinal cord segmentation, including manual segmentation by a trained expert, semi-automated segmentation using software tools that require some user input, and fully automated segmentation using deep learning algorithms. Researchers have proposed a wide range of system models for segmentation and tumor classification in spinal cord scans, but the majority of these models are designed for a specific segment of the spine. As a result, their performance is limited when applied to the entire lead, limiting their deployment scalability. This paper proposes a novel augmented model for spinal cord segmentation and tumor classification using deep nets to overcome this limitation. The model initially segments all five spinal cord regions and stores them as separate datasets. These datasets are manually tagged with cancer status and stage based on observations from multiple radiologist experts. Multiple Mask Regional Convolutional Neural Networks (MRCNNs) were trained on various datasets for region segmentation. The results of these segmentations were combined using a combination of VGGNet 19, YoLo V2, ResNet 101, and GoogLeNet models. These models were selected via performance validation on each segment. It was observed that VGGNet-19 was capable of classifying the thoracic and cervical regions, while YoLo V2 was able to efficiently classify the lumbar region, ResNet 101 exhibited better accuracy for sacral-region classification, and GoogLeNet was able to classify the coccygeal region with high performance accuracy. Due to use of specialized CNN models for different spinal cord segments, the proposed model was able to achieve a 14.5% better segmentation efficiency, 98.9% tumor classification accuracy, and a 15.6% higher speed performance when averaged over the entire dataset and compared with various state-of-the art models. This performance was observed to be better, due to which it can be used for various clinical deployments. Moreover, this performance was observed to be consistent across multiple tumor types and spinal cord regions, which makes the model highly scalable for a wide variety of spinal cord tumor classification scenarios.

MemU-Net: A new volumetric dose prediction model using deep learning techniques in radiation treatment planning

Objective:Automatic radiation treatment planning systems are gaining significance nowadays. This paper presents a novel deep learning architecture for automatically generating the radiotherapy dose information given to the cancer patients. Methods:A new deep learning architecture MemU-Net is proposed. MemU-Net incorporates the principles of two existing deep learning architectures: Memnet, which was proposed for image restoration, and U-Net, which was proposed for biomedical image segmentation. The proposed model is first trained and tested with the public dataset (OpenKBP). The predicted dose distributions are evaluated based on dosimetric values and Dose volume histogram measures. The results are compared with the predictions made by a standard 3D U-Net, Residual U-Net, Dense U-Net and 3D GAN. The statistical significance of the proposed model is tested by computing the paired t-test P-values. Finally the proposed model is trained and tested on a private dataset collected from MVR Cancer Center and Research Institute. The model performance was evaluated by plotting DVHs and analyzing dosimetric values. Results:The dose distributions of MemU-Net shows superiority in performance compared to other models. MemU-Net had a lower mean absolute error of the predicted and ground truth doses than other models for all targets and OARs except spinal cord. The dosimetric measures of the MemU-Net outperformed the state of the art models except in the case of D0.1cc of OARs. Conclusion:A new variant of U-Net, MemU-Net is proposed, that performs better than the state of the art models, in the dose prediction domain in radiotherapy.

Lifex-fiber: an open tool for myofibers generation in cardiac computational models

BackgroundModeling the whole cardiac function involves the solution of several complex multi-physics and multi-scale models that are highly computationally demanding, which call for simpler yet accurate, high-performance computational tools. Despite the efforts made by several research groups, no software for whole-heart fully-coupled cardiac simulations in the scientific community has reached full maturity yet.ResultsIn this work we present texttt {life}^{texttt {x}}-fiber, an innovative tool for the generation of myocardial fibers based on Laplace-Dirichlet Rule-Based Methods, which are the essential building blocks for modeling the electrophysiological, mechanical and electromechanical cardiac function, from single-chamber to whole-heart simulations. texttt {life}^{texttt {x}}-fiber is the first publicly released module for cardiac simulations based on texttt {life}^{texttt {x}}, an open-source, high-performance Finite Element solver for multi-physics, multi-scale and multi-domain problems developed in the framework of the iHEART project, which aims at making in silico experiments easily reproducible and accessible to a wide community of users, including those with a background in medicine or bio-engineering.ConclusionsThe tool presented in this document is intended to provide the scientific community with a computational tool that incorporates general state of the art models and solvers for simulating the cardiac function within a high-performance framework that exposes a user- and developer-friendly interface. This report comes with an extensive technical and mathematical documentation to welcome new users to the core structure of texttt {life}^{texttt {x}}-fiber and to provide them with a possible approach to include the generated cardiac fibers into more sophisticated computational pipelines. In the near future, more modules will be successively published either as pre-compiled binaries for x86-64 Linux systems or as open source software.

Computer vision based knowledge distillation model for animal classification and re-identification using Siamese Neural Network

Human-wildlife conflicts in the habitats along the forest fringes are a substantial issue. An automated monitoring system that can find animal breaches and deter them from foraging fields is essential to solve this conflict. However, automatically forefending the intruding animals is a challenging task. In this paper, we propose a deep learning model for elephant identification using YOLO lite with knowledge distillation which could be easily deployed in edge devices. We also propose an elephant re-identification system using Siamese network which is helpful in tracking the number of times the elephant tries to forage the field. This re-encounter information about the same elephant can be used to decide the averting sound for the particular elephant. The proposed system is found to show an accuracy of 89%, which is provides good performance improvement when compared to the state of art models proposed for animal identification. Thus the proposed lite weight knowledge distillation based animal identification model and deep learning based animal re-identification model can be employed in edge devices for real time monitoring and animal deterring to safe guard the farm fields.

Blockchain Based Optimized Energy Trading for E-Mobility Using Quantum Reinforcement Learning

Using microgrids to charge Electric Vehicles (EVs) is a significant step toward achieving Electric mobility. The microgrids generate electricity for self-use and sell surplus energy locally in Peer-to-Peer (P2P) manner, where seller and buyer meet to trade electricity directly on agreed terms without any intermediary. The energy trading decision for the microgrid is a challenging issue due to uncertainty of renewable energy yield, the electric demands of EVs and without knowing the offers of other competitive microgrids together makes it hard to decide the selling price of energy per unit. Further, there is a need to audit and verify the energy trading and store energy transactions securely in distributed manner to avoid collapse of the system in case of single point of failure. In this context, this paper presents a Blockchain and Quantum Reinforcement Learning based optimized Energy Trading (BQL-ET) model for E-mobility. Firstly, a double-auction mechanism is proposed to set optimal market-trading price by observing the selling price of each microgrid and the demand of EV's. Secondly, using smart contracts, consortium blockchain is deployed for the evaluation of overall utility, which includes energy supply, demand, and cost for both microgrids and EVs. Finally, Utility maximization problem is transformed into a Markov Decision Process (MDP), and in order to develop the learning policy and maximize overall utility, a QRL optimization for solving the MDP problem is proposed. Convergence analysis and performance results attest that BQL-ET convergences faster, maximizes the utility of both microgrids an EVs with lower transaction confirmation time and setting of the optimal market-trading price compared to state-of-the art models.

Image Description Generator using Residual Neural Network and Long Short-Term Memory

Human beings can describe scenarios and objects in a picture through vision easily whereas performing the same task with a computer is a complicated one. Generating captions for the objects of an image helps everyone to understand the scenario of the image in a better way. Instinctively describing the content of an image requires the apprehension of computer vision as well as natural language processing. This task has gained huge popularity in the field of technology and there is a lot of research work being carried out. Recent works have been successful in identifying objects in the image but are facing many challenges in generating captions to the given image accurately by understanding the scenario. To address this challenge, we propose a model to generate the caption for an image. Residual Neural Network (ResNet) is used to extract the features from an image. These features are converted into a vector of size 2048. The caption generation for the image is obtained with Long Short-Term Memory (LSTM). The proposed model is experimented on the Flickr8K dataset and obtained an accuracy of 88.4\%. The experimental results indicate that our model produces appropriate captions compared to the state of art models.

A learning approach towards metre-based classification of similar Hindi poems using proposed two-level data transformation

Abstract With the advancement in technology and digitalization of resources, computation of humanities problems is no exception to remain untouched. Automatic poetry classification is now a well-defined problem which can be solved using various approaches. Mood-based poetry classification is one of the popular ones. We propose a learning approach towards metre-based classification of Hindi metrical poetry. The state of art model for the metre-based poetry classification uses the rule-based approach whereas the proposed system uses learning models to perform classification. Feature extraction and classification are the two main components of text classification in natural language processing. Text is transformed into machine-readable numbers through the process of feature extraction, which is subsequently submitted to classification models. Poems, in their most natural formulation, are unfit to any learning-based algorithms. However, transforming the data into certain form and selecting a fixed number of features out of it (feature extraction) made the classification possible using machine learning approach which was yet untouched and can act as benchmark for the concerned area of research. The article deals with six popular and similar types of Hindi poems. The dataset is collected and processed to form an early dataset that undergoes two levels of data transformation and feature engineering, resulting in the pre-processed dataset. The pre-processed dataset is then fed as input to selected machine learning models (Bernoulli Naïve Bayes, k-nearest neighbour, random forest, and support vector machine) producing classification result with best accuracy of 99%, that further undergoes a post-processing step based on observed misclassifications.

The Economic Potential of Wood Carving Art and Its Marketing Strategy in Sumenep

This study aims to reveal three main issues that are the focus of this research, namely (1) how is the potential of wood carving art in Karduluk village as an artistic and cultural heritage of the Sumenep Madura community, (2) how is the promotion strategy of wood carving by craftsmen, and (3) what is the role of the government area in promoting the wood carving art of Karduluk village as the center of the craft industry in Madura. This study uses qualitative research to explore the promotion strategy of Karduluk village carving as a cultural heritage of the Madurese community. Data collection techniques in the field use three techniques, namely observation, interviews, and documentation. Meanwhile, the analytical method used is deep analysis to process empirical data in the field. In conducting data analysis, the researcher carried out several stages: data reduction, presenting empirical material, and verifying. There are three main findings in this research. First, is the potential of the wood carving art in Karduluk village, namely the economic potential, the potential for carving tourism development, and the potential interest of foreign consumers. Second, promotion strategies for wood carving art are done by participating in art exhibitions, personal selling, online promotion, increasing the variety of wood carving art models, maintaining product quality standards, and mentally competing. Third, the role of the government in promoting the wood carving art of Karduluk village, namely holding an exhibition of wood carving art products, establishing Karduluk village as a carving village, providing marketing capital assistance, assisting in partnership, and facilitating business licensing.

A Data Transfer and Relevant Metrics Matching Based Approach for Heterogeneous Defect Prediction

Heterogeneous defect prediction (HDP) is a promising research area in the software defect prediction domain to handle the unavailability of the past homogeneous data. In HDP, the prediction is performed using source dataset in which the independent features (metrics) are entirely different than the independent features of target dataset. One important assumption in machine learning is that independent features of the source and target datasets should be relevant to each other for better prediction accuracy. However, these assumptions do not generally hold in HDP. Further in HDP, the selected source dataset for a given target dataset may be of small size causing insufficient training. To resolve these issues, we have proposed a novel heterogeneous data preprocessing method, namely, Transfer of Data from Target dataset to Source dataset selected using Relevance score (TDTSR), for heterogeneous defect prediction. In the proposed approach, we have used chi-square test to select the relevant metrics between source and target datasets and have performed experiments using proposed approach with various machine learning algorithms. Our proposed method shows an improvement of at least 14% in terms of AUC score in the HDP scenario compared to the existing state of the art models.

Prediction of ground water quality in western regions of Tamil Nadu using deep auto encoders

The main objective of this research is the prediction of ground water quality in western regions of Tamil Nadu. Groundwater pollution by nitrates is a worldwide issue that must be addressed with technological and regulatory solutions. Many regions of the world have discovered that their groundwater contains dangerously high levels of nitrates. The development of ecologically friendly nitrate treatment and removal methodologies, as well as an increased knowledge of the processes of nitrate formation and pollution in groundwater, have been the focus of current research efforts. However, the impacts of nitrate and chloride contaminant are not well analyzed in the previous works with proper evaluations. In this paper, the research analyses the presence of nitrate and chloride contaminant in ground water. The presence of nitrate and chloride contaminant is collected from western regions of Tamil Nadu and the quality is determined initially using Water quality indicator (WQI). The deep auto encoder is proposed in this research to estimate if the quality obtained is influenced by the presence of various contaminant in that region. The performance of the proposed approach is evaluated and compared with the existing state of art models using various parameters like accuracy, recall, precision, and F1-score.

MCC-Net: A class attention-enhanced multi-scale model for internal structure segmentation of rice seedling stem

Internal structural parameters of rice seedling stems are of great significance for rice growth detection, rice selection, breeding, and damage examination. Aiming at the problems of non-repeatability and low detection accuracy in the existing plant internal structure phenotypic traits detection methods, this paper presents a non-destructive segmentation method for examining the internal structure of rice seedling stems based on deep learning. We use a standard X-ray CT imaging technology to obtain non-destructive tomographic images of rice seedling stems and then design a class attention-enhanced multi-scale segmentation model (MCC-Net), where UNet is used as the backbone network. Specifically, the proposed MCC-Net mainly consists of three core components: multi-scale convolutional block (MCB), coordinate spatial attention (CSA) module, and class attention enhancement (CAE) module. MCB is the main component of the encoder to improve the feature extraction ability of the model for regions of different sizes in the internal structure. CSA is embedded into the UNet skip connections to enhance the expression of effective features and automatically locate the regions with different structures of rice seedling stems. CAE is designed to calculate the dependencies between image pixels and categories, which can enhance the feature expression from the perspective of categories and correct the category errors in the segmentation results. The experimental results show that MIOU, average dice coefficient and average precision of our proposed MCC-Net model on the self-built rice seedling stem CT image dataset are 92.56%, 96.33% and 96.59% respectively. Compared with several state of the art models, the proposed model achieves better segmentation performance on the rice seedling stem CT image dataset.

Early- and late-winter ENSO teleconnections to the Euro-Atlantic region in state-of-the-art seasonal forecasting systems

A number of recent studies have highlighted the differences in the northern extratropical response to the El Niño-Southern Oscillation (ENSO) during the early and late part of the boreal cold season, particularly over the North Atlantic/European (NAE) region. Diagnostic analyses of multi-decadal GCM simulations performed as a part of CMIP5 and CMIP6 projects have shown that early winter tropical teleconnections are usually simulated with lower fidelity than their late-winter equivalents. Although some results from individual seasonal forecasting systems have been published on this topic, it is still unclear to what extent the problems detected in multi-decadal simulations also affect initialised seasonal forecasts from state-of-the art models. In this study, we diagnose ENSO teleconnections from the re-forecast ensembles of nine models contributing (during winter 2021/22) to the multi-model seasonal forecasting system of the Copernicus Climate Change Service (C3S). The re-forecasts cover winters from 1993/94 to 2016/17, and are archived in the C3S Climate Data Store. Regression and composite patterns of 500-hPa height are computed separately for El Niño and La Niña winters, based on 2-month averages in November–December (ND) and January–February (JF). Model results are compared with the corresponding patterns derived from the ERA5 re-analysis. Signal-to-noise ratios are computed from time series of projections of individual winter anomalies onto the ENSO regression patterns. The results of this study indicate that initialised seasonal forecasts exhibit similar deficiencies to those already diagnosed in multi-decadal simulations, with a significant underestimation of the amplitude of early-winter teleconnections between ENSO and the NAE circulation, and of the signal-to-noise ratio in the early-winter response to El Niño. Further diagnostics highlight the impact of mis-representing the constructive interference of teleconnections from the Indian and Pacific Oceans in the early-winter ENSO response over the North Atlantic.

A lightweight attention deep learning method for human-vehicle recognition based on wireless sensing technology.

Wireless sensing-based human-vehicle recognition (WiHVR) methods have become a hot spot for research due to its non-invasiveness and cost-effective advantages. However, existing WiHVR methods shows limited performance and slow execution time on human-vehicle classification task. To address this issue, a lightweight wireless sensing attention-based deep learning model (LW-WADL) is proposed, which consists of a CBAM module and several depthwise separable convolution blocks in series. LW-WADL takes raw channel state information (CSI) as input, and extracts the advanced features of CSI by jointly using depthwise separable convolution and convolutional block attention mechanism (CBAM). Experimental results show that the proposed model achieves 96.26% accuracy on the constructed CSI-based dataset, and the model size is only 5.89% of the state of the art (SOTA) model. The results demonstrate that the proposed model achieves better performance on WiHVR tasks while reducing the model size compared to SOTA model.

A comparison of manual and automated neural architecture search for white matter tract segmentation

Segmentation of white matter tracts in diffusion magnetic resonance images is an important first step in many imaging studies of the brain in health and disease. Similar to medical image segmentation in general, a popular approach to white matter tract segmentation is to use U-Net based artificial neural network architectures. Despite many suggested improvements to the U-Net architecture in recent years, there is a lack of systematic comparison of architectural variants for white matter tract segmentation. In this paper, we evaluate multiple U-Net based architectures specifically for this purpose. We compare the results of these networks to those achieved by our own various architecture changes, as well as to new U-Net architectures designed automatically via neural architecture search (NAS). To the best of our knowledge, this is the first study to systematically compare multiple U-Net based architectures for white matter tract segmentation, and the first to use NAS. We find that the recently proposed medical imaging segmentation network UNet3+ slightly outperforms the current state of the art for white matter tract segmentation, and achieves a notably better mean Dice score for segmentation of the fornix (+ 0.01 and + 0.006 mean Dice increase for left and right fornix respectively), a tract that the current state of the art model struggles to segment. UNet3+ also outperforms the current state of the art when little training data is available. Additionally, manual architecture search found that a minor segmentation improvement is observed when an additional, deeper layer is added to the U-shape of UNet3+. However, all networks, including those designed via NAS, achieve similar results, suggesting that there may be benefit in exploring networks that deviate from the general U-Net paradigm.

Deep hyper optimization approach for disease classification using artificial intelligence

Disease classification using Artificial Intelligence (AI) is one of the emerging areas for medical professionals to diagnose the disease. There are common diseases like breast cancer, hepatitis, thyroid and heart attack are faced by most of the people that produce severe health problems. An Artificial Neural Network (ANN) is a part of AI used to identify the nonlinear relationship among the features for better prediction. However, there are some common problems like under fitting, overfitting, increased elapsed time and vanishing gradient that occur during the analysis and prediction which reduces the performance of the model. So, there is a need for complex structure recognition without overfitting and under fitting. The present study suggests the Deep Hyper Optimization (DHO) technique to reduce the elapsed time of execution. It is used to fine tune the weight, bias and identify the optimal number of hyper parameters in the hidden layer. As a second opinion to medical professionals, various state of art classification models are used such as Logistic Regression, Decision Tree, Random Forest, K Nearest Neighbor and Gradient Boosting algorithms. The performance of state of art models are observed and compared with Deep Hyper Optimization (DHO) technique. It chooses the best hyper parameter for classification based on the highest probability based on the divide and conquer approach. The proposed model is tested for four different datasets and the performance of model is observed based on the accuracy, elapsed time, precision, recall, and F1 score, FPR, FNR, TNR and Area under Curve (AUC).

Towards Deploying DNN Models on Edge for Predictive Maintenance Applications

Almost all rotating machinery in the industry has bearings as their key building block and most of these machines run 24 × 7. This makes bearing health prediction an active research area for predictive maintenance solutions. Many state of the art Deep Neural Network (DNN) models have been proposed to solve this. However, most of these high performance models are computationally expensive and have high memory requirements. This limits their use to very specific industrial applications with powerful hardwares deployed close the the machinery. In order to bring DNN-based solutions to a potential use in the industry, we need to deploy these models on Microcontroller Units (MCUs) which are cost effective and energy efficient. However, this step is typically neglected in literature as it poses new challenges. The primary concern when inferencing the DNN models on MCUs is the on chip memory of the MCU that has to fit the model, the data and additional code to run the system. Almost all the state of the art models fail this litmus test since they feature too many parameters. In this paper, we show the challenges related to the deployment, review possible solutions and evaluate one of them showing how the deployment can be realized and what steps are needed. The focus is on the steps required for the actual deployment rather than finding the optimal solution. This paper is among the first to show the deployment on MCUs for a predictive maintenance use case. We first analyze the gap between State Of The Art benchmark DNN models for bearing defect classification and the memory constraint of two MCU variants. Additionally, we review options to reduce the model size such as pruning and quantization. Afterwards, we evaluate a solution to deploy the DNN models by pruning them in order to fit them into microcontrollers. Our results show that most models under test can be reduced to fit MCU memory for a maximum loss of 3% in average accuracy of the pruned models in comparison to the original models. Based on the results, we also discuss which methods are promising and which combination of model and feature work best for the given classification problem.

Hybrid bayesian convolutional neural network object detection architectures for tracking small markers in automotive crashtest videos

Automotive crash tests are an important aspect of everyday safety, where accurate measurements and evaluations play a crucial role. In order to automate this process, we implement a bayesian hybrid computer vision model to detect two different kinds of target markers. These are commonly used in crash tests, by e.g. automotive manufacturers, to aid the localisation of the car’s positional data by attaching these markers at different positions to the vehicle. A tracking algorithm is subsequently used to add contextual time information to the marker objects. The extracted information can then be used in downstream tasks to calculate important metrics for the crash test evaluation, e.g. the speed, momentum, acceleration and trajectory at particular parts of the car during different stages of the crash test. The model consists of a pre-trained Faster-RCNN for the region proposals with the addition of a bayesian convolutional neural network to estimate a statistical uncertainty on the model’s classifications. This uncertainty estimation can be used as a tool to improve safety in uncertain edge cases in videos where lighting conditions and light reflections are not optimal. Our pipeline achieves an average recall and precision of 0.89 and 0.99, respectively, when applied to test data. This outperforms the recall of state of the art models like the Faster-RCNN Resnet-152 by more than 28\% while delivering slightly better precision, increasing robustness in most of the tested use-cases.

Underwater Object Classification in SAS Images Based on a Deformable Residual Network and Transfer Learning

To solve the problem of low classification accuracy caused by differences in object types, shapes, and scales in SAS images, an object classification method based on a deformable residual network and transfer learning is proposed. First, a lightweight deformable convolution module DSDCN was designed by adding offsets to a traditional convolution, to adapt to objects with different shapes in SAS images, and the depthwise separable convolution was used to optimize the module. Second, a deformable residual network was designed with the DSDCN, which combined the traditional depth features with deformable features for object representation and improved the robustness of the model. Furthermore, the network was trained by the transfer learning method to save training time and prevent model overfitting. The model was trained and validated on the acquired SAS images. Compared with other existing state-of-the art models, the classification accuracy in this study improved by an average of 6.83% and had an advantage in the amount of computation, which is 108 M. On the deformation dataset, this method improved the accuracy, recall, and F1 scores by an average of 5.3%, 5.6%, and 5.8%, respectively. In the ablation experiments of the DSDCN module, the classification accuracy of the model with the addition of the DSDCN module improved by 5.18%. In addition, the training method of transfer learning also led to an improvement in model classification performance, reflected in the classification accuracy, which increased by 7.4%.

Research on rapid generation of 3D models based on art and design cognitive models

Human-computer interaction interfaces based on hand-drawing are currently being used more and more widely. Hand-drawing is a natural and easy way for designers to do this. Most interfaces currently provide designers with only one smoothly drawn stroke, rather than the multiple strokes they are more accustomed to using. This paper is based on an algorithm for hand-drawn interfaces, which analyses multiple strokes and replaces them with a single stroke in order to rationalise the designer’s creative intent. The space is subdivided recursively until only one stroke remains or a suitable order is achieved using principal component analysis, then the subdivided space is reconnected and a large list of points is produced; finally, because the curve is very noisy, the algorithm uses reverse subdivision to find control points to fit a smooth B spline curve.