Real-time learning capability of neural networks

Artificial intelligence-assisted dermatology diagnosis: From unimodal to multimodal

Artificial Intelligence (AI) is progressively permeating medicine, notably in the realm of assisted diagnosis. However, the traditional unimodal AI models, reliant on large volumes of accurately labeled data and single data type usage, prove insufficient to assist dermatological diagnosis. Augmenting these models with text data from patient narratives, laboratory reports, and image data from skin lesions, dermoscopy, and pathologies could significantly enhance their diagnostic capacity. Large-scale pre-training multimodal models offer a promising solution, exploiting the burgeoning reservoir of clinical data and amalgamating various data types. This paper delves into unimodal models' methodologies, applications, and shortcomings while exploring how multimodal models can enhance accuracy and reliability. Furthermore, integrating cutting-edge technologies like federated learning and multi-party privacy computing with AI can substantially mitigate patient privacy concerns in dermatological datasets and further fosters a move towards high-precision self-diagnosis. Diagnostic systems underpinned by large-scale pre-training multimodal models can facilitate dermatology physicians in formulating effective diagnostic and treatment strategies and herald a transformative era in healthcare.

Monitoring the soil copper pollution degree based on the reflectance spectrum of an arid desert plant

Visible and near-infrared reflectance spectroscopy offers a rapid, inexpensive, and environmentally friendly method for monitoring copper pollution in the soil. However, the application of this approach in vegetation-covered areas is still a challenge due to interference from plants, making it difficult to acquire soil reflectance spectra. To address this problem, this study assesses whether the reflectance spectrum of a widely distributed arid desert plant (Seriphidium terrae-albae) can be used to rapidly evaluate copper pollution in the soil. A pot experiment was conducted for five months from April to September 2019. The reflectance spectra of the plants were measured in June, July, and August 2019 using an ASD Fieldspec3 spectrometer. Each month, the five vegetation indexes with the highest correlation with the evaluation value of the copper pollution degree were input into an extreme learning machine (ELM) to build a model to monitor the degree of copper pollution in the soil. The results showed that the model could quickly evaluate the degree of copper pollution, but the accuracy varied widely among the calculated vegetation indexes depending on the month when the spectral data were extracted. The model constructed by selecting ten vegetation indexes composed of plant spectra collected in June and July provides high recognition accuracy, reaching 89.02%. Only seven bands were needed due to the model's low complexity, which means that it has great potential to be applied to remote sensing images to establish a real-time monitoring system to detect copper pollution in the soil. This study proposed a simple and rapid method for monitoring copper pollution in soil using plant spectra, and this method could provide extremely valuable for soil protection and management in arid desert areas.

Application of an extreme learning machine network with particle swarm optimization in syndrome classification of primary liver cancer

OBJECTIVE

By optimizing the extreme learning machine network with particle swarm optimization, we established a syndrome classification and prediction model for primary liver cancer (PLC), classified and predicted the syndrome diagnosis of medical record data for PLC and compared and analyzed the prediction results with different algorithms and the clinical diagnosis results. This paper provides modern technical support for clinical diagnosis and treatment, and improves the objectivity, accuracy and rigor of the classification of traditional Chinese medicine (TCM) syndromes.

METHODS

From three top-level TCM hospitals in Nanchang, 10,602 electronic medical records from patients with PLC were collected, dating from January 2009 to May 2020. We removed the electronic medical records of 542 cases of syndromes and adopted the cross-validation method in the remaining 10,060 electronic medical records, which were randomly divided into a training set and a test set. Based on fuzzy mathematics theory, we quantified the syndrome-related factors of TCM symptoms and signs, and information from the TCM four diagnostic methods. Next, using an extreme learning machine network with particle swarm optimization, we constructed a neural network syndrome classification and prediction model that used "TCM symptoms + signs + tongue diagnosis information + pulse diagnosis information" as input, and PLC syndrome as output. This approach was used to mine the nonlinear relationship between clinical data in electronic medical records and different syndrome types. The accuracy rate of classification was used to compare this model to other machine learning classification models.

RESULTS

The classification accuracy rate of the model developed here was 86.26%. The classification accuracy rates of models using support vector machine and Bayesian networks were 82.79% and 85.84%, respectively. The classification accuracy rates of the models for all syndromes in this paper were between 82.15% and 93.82%.

CONCLUSION

Compared with the case of data processed using traditional binary inputs, the experiment shows that the medical record data processed by fuzzy mathematics was more accurate, and closer to clinical findings. In addition, the model developed here was more refined, more accurate, and quicker than other classification models. This model provides reliable diagnosis for clinical treatment of PLC and a method to study of the rules of syndrome differentiation and treatment in TCM.

Classification of Microscopic Laser Engraving Surface Defect Images Based on Transfer Learning Method

Microscopic laser engraving surface defect classification plays an important role in the industrial quality inspection field. The key challenges of accurate surface defect classification are the complete description of the defect and the correct distinction into categories in the feature space. Traditional classification methods focus on the terms of feature extraction and independent classification; therefore, feed handcrafted features may result in useful feature loss. In recent years, convolutional neural networks (CNNs) have achieved excellent results in image classification tasks with the development of deep learning. Deep convolutional networks integrate feature extraction and classification into self-learning, but require large datasets. The training datasets for microscopic laser engraving image classification are small; therefore, we used pre-trained CNN models and applied two fine-tuning strategies. Transfer learning proved to perform well even on small future datasets. The proposed method was evaluated on the datasets consisting of 1986 laser engraving images captured by a metallographic microscope and annotated by experienced staff. Because handcrafted features were not used, our method is more robust and achieves better results than traditional classification methods. Under five-fold-validation, the average accuracy of the best model based on DenseNet121 is 96.72%.

Brain abnormality detection using template matching

Magnetic resonance imaging (MRI) is a widely used imaging modality to evaluate brain disorders. MRI generates huge volumes of data, which consist of a sequence of scans taken at different instances of time. As the presence of brain disorders has to be evaluated on all magnetic resonance (MR) sequences, manual brain disorder detection becomes a tedious process and is prone to inter- and intra-rater errors. A technique for detecting abnormalities in brain MRI using template matching is proposed. Bias filed correction is performed on volumetric scans using N4ITK filter, followed by volumetric registration. Normalized cross-correlation template matching is used for image registration taking into account, the rotation and scaling operations. A template of abnormality is selected which is then matched in the volumetric scans, if found, the corresponding image is retrieved. Post-processing of the retrieved images is performed by the thresholding operation; the coordinates and area of the abnormality are reported. The experiments are carried out on the glioma dataset obtained from Brain Tumor Segmentation Challenge 2013 database (BRATS 2013). Glioma dataset consisted of MR scans of 30 real glioma patients and 50 simulated glioma patients. NVIDIA Compute Unified Device Architecture framework is employed in this paper, and it is found that the detection speed using graphics processing unit is almost four times faster than using only central processing unit. The average Dice and Jaccard coefficients for a wide range of trials are found to be 0.91 and 0.83, respectively.

Robust Regression Estimation Based on Low-Dimensional Recurrent Neural Networks

The robust Huber's M-estimator is widely used in signal and image processing, classification, and regression. From an optimization point of view, Huber's M-estimation problem is often formulated as a large-sized quadratic programming (QP) problem in view of its nonsmooth cost function. This paper presents a generalized regression estimator which minimizes a reduced-sized QP problem. The generalized regression estimator may be viewed as a significant generalization of several robust regression estimators including Huber's M-estimator. The performance of the generalized regression estimator is analyzed in terms of robustness and approximation accuracy. Furthermore, two low-dimensional recurrent neural networks (RNNs) are introduced for robust estimation. The two RNNs have low model complexity and enhanced computational efficiency. Finally, the experimental results of two examples and an application to image restoration are presented to substantiate superior performance of the proposed method over conventional algorithms for robust regression estimation in terms of approximation accuracy and convergence rate.

The Head Turning Modulation System: An Active Multimodal Paradigm for Intrinsically Motivated Exploration of Unknown Environments

Over the last 20 years, a significant part of the research in exploratory robotics partially switches from looking for the most efficient way of exploring an unknown environment to finding what could motivate a robot to autonomously explore it. Moreover, a growing literature focuses not only on the topological description of a space (dimensions, obstacles, usable paths, etc.) but rather on more semantic components, such as multimodal objects present in it. In the search of designing robots that behave autonomously by embedding life-long learning abilities, the inclusion of mechanisms of attention is of importance. Indeed, be it endogenous or exogenous, attention constitutes a form of intrinsic motivation for it can trigger motor command toward specific stimuli, thus leading to an exploration of the space. The Head Turning Modulation model presented in this paper is composed of two modules providing a robot with two different forms of intrinsic motivations leading to triggering head movements toward audiovisual sources appearing in unknown environments. First, the Dynamic Weighting module implements a motivation by the concept of Congruence, a concept defined as an adaptive form of semantic saliency specific for each explored environment. Then, the Multimodal Fusion and Inference module implements a motivation by the reduction of Uncertainty through a self-supervised online learning algorithm that can autonomously determine local consistencies. One of the novelty of the proposed model is to solely rely on semantic inputs (namely audio and visual labels the sources belong to), in opposition to the traditional analysis of the low-level characteristics of the perceived data. Another contribution is found in the way the exploration is exploited to actively learn the relationship between the visual and auditory modalities. Importantly, the robot-endowed with binocular vision, binaural audition and a rotating head-does not have access to prior information about the different environments it will explore. Consequently, it will have to learn in real-time what audiovisual objects are of "importance" in order to rotate its head toward them. Results presented in this paper have been obtained in simulated environments as well as with a real robot in realistic experimental conditions.

Multi-Agent System Based on the Extreme Learning Machine and Fuzzy Control for Intelligent Energy Management in Microgrid

Renewable energies constitute an alternative to fossil energies for several reasons. The microgrid can be assumed as the ideal way to integrate a renewable energy source in the production of electricity and give the consumer the opportunity to participate in the electricity market not just like a consumer but also like a producer. In this paper, we present a multi-agent system based on wind and photovoltaic power prediction using the extreme learning machine algorithm. This algorithm was tested on real weather data taken from the region of Tetouan City in Morocco. The process aimed to implement a microgrid located in Tetouan City and composed of different generation units (solar and wind energies were combined together to increase the efficiency of the system) and storage units (batteries were used to ensure the availability of power on demand as much as possible). In the proposed architecture, the microgrid can exchange electricity with the main grid; therefore, it can buy or sell electricity. Thus, the goal of our multi-agent system is to control the amount of power delivered or taken from the main grid in order to reduce the cost and maximize the benefit. To address uncertainties in the system, we use fuzzy logic control to manage the flow of energy, to ensure the availability of power on demand, and to make a reasonable decision about storing or selling electricity.

Efficient Implementation of the Backpropagation Algorithm in FPGAs and Microcontrollers

The well-known backpropagation learning algorithm is implemented in a field-programmable gate array (FPGA) board and a microcontroller, focusing in obtaining efficient implementations in terms of a resource usage and computational speed. The algorithm was implemented in both cases using a training/validation/testing scheme in order to avoid overfitting problems. For the case of the FPGA implementation, a new neuron representation that reduces drastically the resource usage was introduced by combining the input and first hidden layer units in a single module. Further, a time-division multiplexing scheme was implemented for carrying out product computations taking advantage of the built-in digital signal processor cores. In both implementations, the floating-point data type representation normally used in a personal computer (PC) has been changed to a more efficient one based on a fixed-point scheme, reducing system memory variable usage and leading to an increase in computation speed. The results show that the modifications proposed produced a clear increase in computation speed in comparison with the standard PC-based implementation, demonstrating the usefulness of the intrinsic parallelism of FPGAs in neurocomputational tasks and the suitability of both implementations of the algorithm for its application to the real world problems.

Neural Net Gains Estimation Based on an Equivalent Model

A model of an Equivalent Artificial Neural Net (EANN) describes the gains set, viewed as parameters in a layer, and this consideration is a reproducible process, applicable to a neuron in a neural net (NN). The EANN helps to estimate the NN gains or parameters, so we propose two methods to determine them. The first considers a fuzzy inference combined with the traditional Kalman filter, obtaining the equivalent model and estimating in a fuzzy sense the gains matrix A and the proper gain K into the traditional filter identification. The second develops a direct estimation in state space, describing an EANN using the expected value and the recursive description of the gains estimation. Finally, a comparison of both descriptions is performed; highlighting the analytical method describes the neural net coefficients in a direct form, whereas the other technique requires selecting into the Knowledge Base (KB) the factors based on the functional error and the reference signal built with the past information of the system.

An Automated System for Skeletal Maturity Assessment by Extreme Learning Machines

Assessing skeletal age is a subjective and tedious examination process. Hence, automated assessment methods have been developed to replace manual evaluation in medical applications. In this study, a new fully automated method based on content-based image retrieval and using extreme learning machines (ELM) is designed and adapted to assess skeletal maturity. The main novelty of this approach is it overcomes the segmentation problem as suffered by existing systems. The estimation results of ELM models are compared with those of genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results signify improvement in assessment accuracy over GP and ANN, while generalization capability is possible with the ELM approach. Moreover, the results are indicated that the ELM model developed can be used confidently in further work on formulating novel models of skeletal age assessment strategies. According to the experimental results, the new presented method has the capacity to learn many hundreds of times faster than traditional learning methods and it has sufficient overall performance in many aspects. It has conclusively been found that applying ELM is particularly promising as an alternative method for evaluating skeletal age.

A novel single neuron perceptron with universal approximation and XOR computation properties

We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous system. The resulting architecture of SNP can be trained by supervised excitatory and inhibitory online learning rules. The main features of proposed single layer perceptron are universal approximation property and low computational complexity. The method is tested on 6 UCI (University of California, Irvine) pattern recognition and classification datasets. Various comparisons with multilayer perceptron (MLP) with gradient decent backpropagation (GDBP) learning algorithm indicate the superiority of the approach in terms of higher accuracy, lower time, and spatial complexity, as well as faster training. Hence, we believe the proposed approach can be generally applicable to various problems such as in pattern recognition and classification.

Color face recognition based on steerable pyramid transform and extreme learning machines

This paper presents a novel color face recognition algorithm by means of fusing color and local information. The proposed algorithm fuses the multiple features derived from different color spaces. Multiorientation and multiscale information relating to the color face features are extracted by applying Steerable Pyramid Transform (SPT) to the local face regions. In this paper, the new three hybrid color spaces, YSCr, ZⁿSCr, and BⁿSCr, are firstly constructed using the Cb and Cr component images of the YCbCr color space, the S color component of the HSV color spaces, and the Zⁿ and Bⁿ color components of the normalized XYZ color space. Secondly, the color component face images are partitioned into the local patches. Thirdly, SPT is applied to local face regions and some statistical features are extracted. Fourthly, all features are fused according to decision fusion frame and the combinations of Extreme Learning Machines classifiers are applied to achieve color face recognition with fast and high correctness. The experiments show that the proposed Local Color Steerable Pyramid Transform (LCSPT) face recognition algorithm improves seriously face recognition performance by using the new color spaces compared to the conventional and some hybrid ones. Furthermore, it achieves faster recognition compared with state-of-the-art studies.

Dynamic extreme learning machine and its approximation capability

Extreme learning machines (ELMs) have been proposed for generalized single-hidden-layer feedforward networks which need not be neuron alike and perform well in both regression and classification applications. The problem of determining the suitable network architectures is recognized to be crucial in the successful application of ELMs. This paper first proposes a dynamic ELM (D-ELM) where the hidden nodes can be recruited or deleted dynamically according to their significance to network performance, so that not only the parameters can be adjusted but also the architecture can be self-adapted simultaneously. Then, this paper proves in theory that such D-ELM using Lebesgue p-integrable hidden activation functions can approximate any Lebesgue p-integrable function on a compact input set. Simulation results obtained over various test problems demonstrate and verify that the proposed D-ELM does a good job reducing the network size while preserving good generalization performance.

Comments on the "No-Prop" algorithm

This letter points out that the main ideas and conclusions of the "The No-Prop algorithm" paper which has recently appeared in this journal were proposed earlier by G.-B. Huang et al. 10 years ago and intensively discussed and applied by other authors in the past 10 years.

Applications of machine learning techniques to a sensor-network-based prosthesis training system

In the past, the utilization of the limb prosthesis has improved the daily life of amputees or patients with movement disorders. However, a leg-amputee has to take a series of training after wearing a limb prosthesis, and the training results determine whether a patient can use the limb prosthesis correctly in her/his daily life. Limb prosthesis vendors thus desire to offer the leg-amputee a complete and well-organized training process, but they often fail to do so owing to the factors such as the limited support of human resource and financial condition of the amputee. This work proposes a prosthesis training system that the amputees can borrow or buy from the limb prosthesis vendors and train themselves at home. Instant feedback messages provided by the prosthesis training system are used to correct their walking postures during the self-training process. An embedded chip is used as a core to establish a body area sensor network for the prosthesis training system. RFID readers and tags are employed to acquire the 3D positioning information of the amputee's limbs in this work to assist in diagnosing the amputee's walking problem. A series of simulations were conducted and the simulation results exhibit the effectiveness and practicability of the proposed prosthesis training system.