Layer Neural Network Research Articles

Direct Prediction of 48 Month Survival Status in Patients with Uveal Melanoma Using Deep Learning and Digital Cytopathology Images

Background: Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. The median overall survival time for patients who develop metastasis is approximately one year. In this study, we aim to leverage deep learning (DL) techniques to analyze digital cytopathology images and directly predict the 48 month survival status on a patient level. Methods: Fine-needle aspiration biopsy (FNAB) of the tumor was performed in each patient diagnosed with UM. The cell aspirate was smeared on a glass slide and stained with H&E. Each slide then underwent whole-slide scanning. Within each whole-slide image, regions of interest (ROIs) with UM cells were automatically extracted. Each ROI was converted into super pixels, and the super pixels were automatically detected, segmented and annotated as “tumor cell” or “background” using DL. Cell-level features were extracted from the segmented tumor cells. The cell-level features were aggregated into slide-level features which were learned by a fully connected layer in an artificial neural network, and the patient survival status was predicted directly from the slide-level features. The data were partitioned at the patient level (78% training and 22% testing). Our DL model was trained to perform the binary prediction of yes-versus-no survival by Month 48. The ground truth for patient survival was established via a retrospective chart review. Results: A total of 74 patients were included in this study (43% female; mean age at the time of diagnosis: 61.8 ± 11.6 years), and 207,260 unique ROIs were generated for model training and testing. By Month 48 after diagnosis, 18 patients (24%) died from UM metastasis. Our hold-out test set contained 16 patients, where 6 patients had passed away and 10 patients were alive at Month 48. When using a sensitivity threshold of 80% in predicting UM-specific death by Month 48, our model achieved an overall accuracy of 75%. Within the subgroup of patients who died by Month 48, our model achieved a prediction accuracy of 83%. Of note, one patient in our test set was a clinical surprise, namely death by Month 48 despite having a GEP class 1A tumor, which typically portends a good prognosis. Our model correctly predicted this clinical surprise as well. Conclusions: Our DL model was able to predict the Month 48 survival status directly from digital cytopathology images obtained from FNABs of UM tumors with reasonably robust performance. This approach, if validated prospectively, could serve as an alternative survival prediction tool for patients with UM to whom GEP is not available.

TinyHLS: a novel open source high level synthesis tool targeting hardware accelerators for artificial neural network inference.

In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself. This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed
to address these challenges by converting Python-based AI models into platform-independent hardware description language (HDL) code accelerators. Specifically designed for convolutional neural networks (CNNs), tinyHLS seamlessly integrates into the AI developer's workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit (ReLU) is supported as activation. It targets one-dimensional data, with a particular focus on time series data. The generated accelerators are validated in detecting atrial fibrillation (AF) on electrocardiogram (ECG) data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools. Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISCV and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub: https://github.com/Fraunhofer-IMS/tinyHLS.

A spatial code for temporal information is necessary for efficient sensory learning.

The temporal structure of sensory inputs contains essential information for their interpretation. Sensory cortex represents these temporal cues through two codes: the temporal sequences of neuronal activity and the spatial patterns of neuronal firing rate. However, it is unknown which of these coexisting codes causally drives sensory decisions. To separate their contributions, we generated in the mouse auditory cortex optogenetically driven activity patterns differing exclusively along their temporal or spatial dimensions. Mice could rapidly learn to behaviorally discriminate spatial but not temporal patterns. Moreover, large-scale neuronal recordings across the auditory system revealed that the auditory cortex is the first region in which spatial patterns efficiently represent temporal cues on the timescale of several hundred milliseconds. This feature is shared by the deep layers of neural networks categorizing time-varying sounds. Therefore, the emergence of a spatial code for temporal sensory cues is a necessary condition to efficiently associate temporally structured stimuli with decisions.

Developing an EEG-based model to predict awakening after cardiac arrest using partial processing with the BIS Engine.

Accurate prognostication in comatose survivors of cardiac arrest is a challenging and high-stakes endeavor. We sought to determine whether internal EEG subparameters extracted by the Bispectral Index (BIS) monitor, a device commonly used to estimate depth-of-anesthesia intraoperatively, could be repurposed to predict recovery of consciousness after cardiac arrest. In this retrospective cohort study, we trained a 3-layer neural network to predict recovery of consciousness to the point of command following versus not based on 48 hours of continuous EEG recordings in 315 comatose patients admitted to a single US academic medical center after cardiac arrest (Derivation cohort: N=181; Validation cohort: N=134). Continuous EEGs were partially processed into subparameters using virtualized emulation of the BIS Engine (i.e., the internal software of the BIS monitor) applied to signals from the frontotemporal leads of the standard 10-20 EEG montage. Our model was trained on hourly-averaged measurements of these internal subparameters. We compared this model's performance to the modified Westhall qualitative EEG scoring framework. Maximum prognostic accuracy in the Derivation Cohort was achieved using a network trained on only four BIS subparameters (inverse burst suppression ratio, mean spectral power density, gamma power, and theta/delta power). In a held-out sample of 134 patients, our model outperformed current state-of-the-art qualitative EEG assessment techniques at predicting recovery of consciousness (area under the receiver operating characteristic curve: 0.86, accuracy: 0.87, sensitivity: 0.83, specificity: 0.88, positive predictive value: 0.71, negative predictive value: 0.94). Gamma band power has not been previously reported as a correlate of recovery potential after cardiac arrest. In patients comatose after cardiac arrest, four EEG features calculated internally by the BIS Engine were repurposed by a compact neural network to achieve a prognostic accuracy superior to the current clinical qualitative gold-standard, with high sensitivity for recovery. These features hold promise for assessing patients after cardiac arrest.

Effectiveness of Hybrid Quantum-Classical and Quanvolutional Neural Networks for image classification

The article focuses on studying the effectiveness of two different Hybrid Neural Networks (HNNs) architectures for solving real-world image classification problems. The first approach investigated in the research is a hybridization technique that allows creation of HNN based on a classical neural network by replacing a number of hidden layers of the neural network with a variational quantum circuit, which allows to reduce the complexity of the classical part of the neural network and move part of computations to a quantum device. The second approach is a hybridization technique based on utilizing quanvolutional operations for image processing as the first quantum convolutional layer of the hybrid neural network, thus building a Quanvolutional Neural Network (QNN). QNN leverages quantum phenomena to facilitate feature extraction, enabling the model to achieve higher accuracy metrics than its classical counterpart. The effectiveness of both architectures was tested on several image classification problems. The first one is a classical image classification problem of CIFAR10 images classification, widely used as a benchmark for various imagery-related tasks. Another problem used for the effectiveness study is the problem of geospatial data analysis. The second problem represents a real-world use case where quantum computing utilization can be very fruitful in the future. For studying the effectiveness, several models were assembled: HNN with a quantum device that replaces one of the hidden layers of the neural network, QNN based on quanvolutional operation and utilizes VGG-16 architecture as a classical part of the model, and also an unmodified VGG-16 was used as a reference model. Experiments were conducted to measure the models' key efficiency metrics: maximal accuracy, complexity of a quantum part of the model and complexity of a classical part of the model. The results of the research indicated the feasibility of both approaches for solving both proposed image classification problems. Results were analyzed to outline the advantages and disadvantages of every approach in terms of selected key metrics. Experiments showed that QNN architectures proved to be a feasible and effective solution for critical practical tasks requiring higher levels of model prediction accuracy and, simultaneously, can tolerate higher processing time and significantly increased costs due to a high number of quantum operations required. Also, the results of the experiments indicated that HNN architectures proved to be a feasible solution for time-critical practical tasks that require higher processing speed and can tolerate slightly decreased accuracy of model predictions.

Improved CNN architecture for automated classification of skin diseases

ABSTRACT Rosacea, atopic dermatitis and bullous disease are significant skin conditions with distinct characteristics and impacts, which affect millions of people globally. Early and quick diagnosis is crucial for these conditions to prevent complications, alleviate symptoms and improve quality of life for affected individuals. This research article presents an innovative approach to automated classification of common skin diseases using Convolutional Neural Network (CNN) models. The study focuses on diagnosing rosacea, atopic dermatitis and bullous disease, leveraging CNN technology. Four pre-trained CNN models – DarkNet-53, ResNet-18, SqueezeNet and EfficientNet-b0 – were investigated. Additionally, two improvised versions of DarkNet-53 and an improvised version of ResNet-18 were developed, integrating a specific number of fully connected neural network layers and adjusting other CNN layers such as batch normalisation and activation function layers accordingly. The performance of these improvised models surpassed that of the original architectures, demonstrating superior accuracy in identifying the targeted skin diseases. In terms of overall accuracy, improvised versions of DarkNet-53 and ResNet-18 achieved an accuracy of 98% and 98%, respectively, while the original models could achieve an accuracy between 75% and 80%. This research contributes to advancing automated diagnostic systems for dermatological conditions, potentially improving early detection and treatment outcomes.

Cyber attack detection in IOT-WSN devices with threat intelligence using hidden and connected layer based architectures

In this paper, cyber-attacks in IOT-WSN are detected through proposed optimized-Neural Network algorithms such as (i) Equilibrium Optimizer Neural Network (EO-NN), (ii) Particle Swarm Optimization (PSO-NN), (iii) Single Candidate Optimizer Neural Network (SCO-NN) and (iv) Single Candidate Optimizer Long Short-Term Memory (SCO-LSTM) with different connecting, hidden neural network layers and threat intelligence data. The proposed algorithms detect the attacker node, which frequently changes the behaviour such as attacker node/ normal node. Existing IDS system detects the attacks in WSN and unable to detect the changing behavior attacker nodes in IOT-WSN. The behaviour of attacker node changes from normal behaviour to attacker behaviour due to nodes connected to internet continuously. The classification accuracy rates of proposed SCO-LSTM algorithm without and with threat intelligence are about 99.7% and 99.89%, respectively.

Low-power scalable multilayer optoelectronic neural networks enabled with incoherent light

Optical approaches have made great strides towards the goal of high-speed, energy-efficient computing necessary for modern deep learning and AI applications. Read-in and read-out of data, however, limit the overall performance of existing approaches. This study introduces a multilayer optoelectronic computing framework that alternates between optical and optoelectronic layers to implement matrix-vector multiplications and rectified linear functions, respectively. Our framework is designed for real-time, parallelized operations, leveraging 2D arrays of LEDs and photodetectors connected via independent analog electronics. We experimentally demonstrate this approach using a system with a three-layer network with two hidden layers and operate it to recognize images from the MNIST database with a recognition accuracy of 92% and classify classes from a nonlinear spiral data with 86% accuracy. By implementing multiple layers of a deep neural network simultaneously, our approach significantly reduces the number of read-ins and read-outs required and paves the way for scalable optical accelerators requiring ultra low energy.

An Ensemble Deep Learning Approach for EEG-Based Emotion Recognition Using Multi-Class CSP.

In recent years, significant advancements have been made in the field of brain-computer interfaces (BCIs), particularly in the area of emotion recognition using EEG signals. The majority of earlier research in this field has missed the spatial-temporal characteristics of EEG signals, which are critical for accurate emotion recognition. In this study, a novel approach is presented for classifying emotions into three categories, positive, negative, and neutral, using a custom-collected dataset. The dataset used in this study was specifically collected for this purpose from 16 participants, comprising EEG recordings corresponding to the three emotional states induced by musical stimuli. A multi-class Common Spatial Pattern (MCCSP) technique was employed for the processing stage of the EEG signals. These processed signals were then fed into an ensemble model comprising three autoencoders with Convolutional Neural Network (CNN) layers. A classification accuracy of 99.44 ± 0.39% for the three emotional classes was achieved by the proposed method. This performance surpasses previous studies, demonstrating the effectiveness of the approach. The high accuracy indicates that the method could be a promising candidate for future BCI applications, providing a reliable means of emotion detection.

Data-driven approach for the classification of gas turbine faults

Gas turbines (GTs) play a crucial role in the production of electricity. Extreme working conditions can lead to deterioration in GTs' performance, resulting in the occurrence of various issues. This study proposes an approach to deal with this issue by combining a layered recurrent neural network (LRNN) with principal component analysis (PCA). This approach aims to reduce the dimensionality of data and computational complexity effectively while enhancing the accuracy of gas turbine fault classification. The methodology outlined consists of two steps. The first step is to apply PCA to the dataset that was collected from the gas turbine. By transforming the data into a lower-dimensional space, PCA helps to eliminate redundant information and improve computational efficiency. Next, LRNN is employed to detect and classify faults in the gas turbine. The LRNN’s structure enables it to capture complex patterns and relationships in the data, which enhances the accuracy of fault classification. This study is based on historical data collected from a gas turbine power station, consisting of 8200 samples of 34 measured variables. The operating parameters contain data such as temperature and pressure. Each data point's relationship to a specific turbine scenario reveals if it is healthy or one of the four faulty scenarios. The results showed that by combining the LRNN with PCA, the gas turbine fault classification achieved good performance in terms of accuracy, precision and neural network model performances, while also showcasing the faster convergence speed of the LRNN when trained on PCA instead of the original dataset.

A Multi-Architecture Approach for Offensive Language Identification Combining Classical Natural Language Processing and BERT-Variant Models

Offensive content is a complex and multifaceted form of harmful material that targets individuals or groups. In recent years, offensive language (OL) has become increasingly harmful, as it incites violence and intolerance. The automatic identification of OL on social networks is essential to curtail the spread of harmful content. We address this problem by developing an architecture to effectively respond to and mitigate the impact of offensive content on society. In this paper, we use the Davidson dataset containing 24,783 samples of tweets and proposed three different architectures for detecting OL on social media platforms. Our proposed approach involves concatenation of features (TF-IDF, Word2Vec, sentiments, and FKRA/FRE) and a baseline machine learning model for the classification. We explore the effectiveness of different dimensions of GloVe embeddings in conjunction with deep learning models for classifying OL. We also propose an architecture that utilizes advanced transformer models such as BERT, ALBERT, and ELECTRA for pre-processing and encoding, with 1D CNN and neural network layers serving as the classification components. We achieve the highest precision, recall, and F1 score, i.e., 0.89, 0.90, and 0.90, respectively, for both the “bert encased preprocess/1 + small bert/L4H512A8/1 + neural network layers” model and the “bert encased preprocess/1 + electra small/2 + cnn” architecture.

A Multiple Controlled Toffoli Driven Adaptive Quantum Neural Network Model for Dynamic Workload Prediction in Cloud Environments.

The key challenges in cloud computing encompass dynamic resource scaling, load balancing, and power consumption. Accurate workload prediction is identified as a crucial strategy to address these challenges. Despite numerous methods proposed to tackle this issue, existing approaches fall short of capturing the high-variance nature of volatile and dynamic cloud workloads. Consequently, this paper introduces a novel model aimed at addressing this limitation. This paper presents a novel Multiple Controlled Toffoli-driven Adaptive Quantum Neural Network (MCT-AQNN) model to establish an empirical solution to complex, elastic as well as challenging workload prediction problems by optimizing the exploration, adaption, and exploitation proficiencies through quantum learning. The computational adaptability of quantum computing is ingrained with machine learning algorithms to derive more precise correlations from dynamic and complex workloads. The furnished input data point and hatched neural weights are refitted in the form of qubits while the controlling effects of Multiple Controlled Toffoli (MCT) gates are operated at the hidden and output layers of Quantum Neural Network (QNN) for enhancing learning capabilities. Complimentarily, a Uniformly Adaptive Quantum Machine Learning (UAQL) algorithm has evolved to functionally and effectually train the QNN. The extensive experiments are conducted and the comparisons are performed with state-of-the-art methods using four real-world benchmark datasets. Experimental results evince that MCT-AQNN has up to 32%-96% higher accuracy than the existing approaches.

A novel surface deformation prediction method based on AWC-LSTM model

Severe surface deformation can damage the ecological environment, trigger geological disasters, and threaten human life and property. Reliable surface deformation prediction is conducive to reducing potential risks and mitigating disaster losses. Currently, machine learning-based surface deformation prediction models have shown significant improvements in prediction performance. However, most prediction models do not sufficiently consider the characteristics of surface deformation, exhibit subjectivity in parameter settings, and inadequately capture local features in time series data. We introduce the AWC-LSTM model to predict surface deformation. Initially, leveraging the strengths of the autoregressive integrated moving average (ARIMA) model in handling linear signals, the obtained surface deformation information is decomposed to linear and nonlinear parts, and the linear part is predicted. Secondly, by incorporating convolutional neural network (CNN) layers into the long short term memory (LSTM) model, the ability to learn local features is enhanced and the whale optimization algorithm (WOA) is introduced to determine the optimal hyperparameters of the model, thereby predicting nonlinear deformation. The proposed AWC-LSTM model was validated using the Shilawusu coal mine and Beijing as case studies. The outcomes indicate that the deformation predictions for the Shilawusu coal mine and Beijing exhibit a high degree of consistency with the monitored data, with root mean square errors (RMSE) not exceeding 3 mm. This underscores the model’s reliability and applicability across different areas. Comparisons with existing prediction models indicate that the AWC-LSTM model achieves higher predictive accuracy, with an average improvement in accuracy ranging from 28.38 % to 80.59 % over other models.

Accuracy degradation aware bit rate allocation for layer-wise uniform quantization of weights in neural network

Abstract Motivated by the fact that optimizing quantization error fails to minimize the accuracy degradation caused by the quantization of Neural Network (NN) weights, in this paper, we highlight the need for a comprehensive analysis of post-training quantization, covering average bit rate, accuracy degradation and SQNR. One such analysis, for the layer-wise uniform quantization and its application is NN weight compression is presented in this paper. We introduce an additional aspect of Uniform Quantizer (UQ) choice, and we allow the selection of one of two UQs (2-bit or 3-bit UQs) for each layer of NN. However, choosing a particular bit rate allocation to minimize average bit rate and accuracy degradation requires finding a trade-off solution. To solve the issue underpinning our motivation, for a post-training layer-wise uniform quantization framework with two UQs, we propose an algorithm for generating bit rate allocation patterns and corresponding pairs of average bit rate and accuracy degradation. We analyze the output of this algorithm and determine a solution of the elaborated two-objective optimization problem. To confirm the validity of the results we also apply the Pareto dominance method. This work can be considered a solid foundation for further analyses of more complex and deeper NNs.

HyperKAN: Kolmogorov-Arnold Networks Make Hyperspectral Image Classifiers Smarter.

In traditional neural network designs, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov-Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we studied KAN-based networks for pixel-wise classification of hyperspectral images. Initially, we compared baseline MLP and KAN networks with varying numbers of neurons in their hidden layers. Subsequently, we replaced the linear, convolutional, and attention layers of traditional neural networks with their KAN-based counterparts. Specifically, six cutting-edge neural networks were modified, including 1D (1DCNN), 2D (2DCNN), and 3D convolutional networks (two different 3DCNNs, NM3DCNN), as well as transformer (SSFTT). Experiments conducted using seven publicly available hyperspectral datasets demonstrated a substantial improvement in classification accuracy across all the networks. The best classification quality was achieved using a KAN-based transformer architecture.

Feature Coding and Graph via Transformer: Different Granularities Classification for Aircraft

Against the background of the sky, imaging and perception of aircraft are crucial for various vision applications. Thanks to the ever-evolving nature of the convolutional neural network (CNN), it has become easier to distinguish and recognize different types of aircraft. Nevertheless, accurate classification for sub-categories of aircraft still poses great challenges. On one hand, fine-grained recognition focuses on exploring and studying such problems. On the other hand, aircraft under different sub-categories and granularities put forward higher requirements for feature representation to classify, which led us to rethink the in-depth application of features. We noticed that information in the swin-transformer effectively represents the features in neural network layers, fully showcasing encoding and indexing for information. Through further research based on this, we proposed a better understanding of encoding and reuse for features, and innovatively performed feature coding graphically for classification. In this paper, our approach shows the effects on aircraft feature representation and classification, manifested from the flexible recognition effect at different aircraft category granularities, and outperforms other famous fine-grained classification models on this vision task. Not only did the approach we proposed demonstrate adaptability to aircraft at different classification granularities, but it also revealed the mechanisms and characteristics of feature encoding under different sample space partitions for classification. The relationship between the oriented representation of aircraft features and various classification granularities, which is manifested through different classification criteria, shows that feature coding and graph construction via the transformer opens a new door for specific defined classification tasks where objects are divided under various partition criteria, and provides another perspective on calculation and feature extraction in fine-grained classification.

Outlier Detection in Bayesian Neural Networks

Describing uncertainty is one of the major issues in modern deep learning. Artificial Intelligence models could be used with greater confidence by having solid methods for identifying and quantifying uncertainty. This article proposes two alternative methods for outlier detection in Bayesian Neural Networks used for classification tasks. This is done by looking for unusual pre-activation neuron values in the last layer of a Bayesian Neural Network. The proposed methods are compared to a baseline method for outlier detection, Predictive Entropy, on three datasets: a simulated dataset, the MNIST dataset, and the Breast Cancer Wisconsin dataset. In addition, we introduce a method for separating In-Between and Out-Of-Distribution outliers. The results indicate that the proposed methods' performance depends on the dataset type. In the case of a simple simulated dataset, we see that the proposed methods outperform the baseline method. The proposed method also outperforms the baseline method on the Breast Cancer Wisconsin dataset. However, when tested on the MNIST image dataset, we observed that the baseline is better than the proposed method. As expected, for all three datasets, an OR-combination of the two methods gives slightly better POWER score than the two methods separately, but this comes at the price of also obtaining a higher FDR score.

Physical Reservoir Computing with Electrochemical Reactions

Machine learning based on neural networks (NN) has been used for information processing.1 However, some disadvantages of NN are the high cost of computational resources and long training process. To overcome these limitations, physical reservoir computing (PRC) was proposed.2 In PRC, signals are fed to PR devices that produce non-linear responses and short-term memory for input history. The outputs of the PR devices will be used as the input of the NN or a simpler network for the machine learning process.PR devices are also expected to be used as so-called edge computing devices because they can convert input signals into signals more suitable for machine learning in real time. For this purpose, time responses of PR devices should match those of the signals to be processed. The time response of PR by electrochemistry can be tuned by various parameters such as choice of reactions, concentration, temperature and hydrodynamics of solution in electrochemical cell. This wide capability would make electrochemistry as attractive and useful resource for PR devices.PRC is expected to cost less than conventional NN systems because fewer layers of NNs are required. To date, PR devices have been proposed using optical circuits,3 dielectric relaxation in ferroelectrics,4 spin relaxation,5 and solid-state redox reactions.6,7 To produce the characteristics required for PR devices, redox reactions in the liquid phase, that is, electrochemistry in solutions, are useful because many non-linear phenomena appear in simple electrochemical setups.8,9 Several studies have reported the use of charging of electrical double layers,10 redox reactions in solutions,11,12 and formation of complex network structures.13,14 However, the relationship between electrochemical reactions and PR properties has not been fully understood, even though it is essential for the rational design of electrochemical PR devices.In this study, we demonstrate PRC using the electrochemical formation and reduction of gold-oxide (herein referred to as Au oxidation-reduction for the simplicity while the reaction consists of several steps and multiple products) in aqueous solutions 15,16 with a standard three-electrode electrochemical setup. Au oxidation-reduction is easily reproducible because the gold-oxide remains on the surface of electrodes and characteristics of reactions are relatively insensitive to the structure of electrochemical cell and configuration of electrodes. These characteristics makes Au oxidation-reduction a good model system. Short-term memory is realized and tuned by adjusting the oxidation and reduction processes involved during the pulse signal transduction. An image classification task is demonstrated as an application example (Figure 1) 17. PRC using other electrochemical reactions will be also demonstrated1 S. Samarasinghe, Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition, CRC Press, 2016.2 G. Tanaka, et al., Neural Netw., 2019, 115, 100–123.3 D. Brunner, et al., J. Appl. Phys., 2018, 124, 152004.4 E. Nako, et al., in 2020 IEEE Symposium on VLSI Technology, 2020, pp. 1–2.5 J. Torrejon, et al., Nature, 2017, 547, 428–431.6 M. Nakajima, et al., Nanoscale, 2022, 14, 7634–7640.7 Y. Usami, et al., Adv. Mater., 2021, 33, e2102688.8 M. T. M. Koper, J. Chem. Soc. Faraday Trans., 1998, 94, 1369–1378.9 D. Kim and J.-S. Lee, ACS Appl. Electron. Mater., 2023, 5, 664–673.10 S.-G. Koh, et al., Sci. Rep., 2022, 12, 6958.11 S. Kan, , et al., Adv. Sci., 2022, 9, e2104076.12 T. Matsuo, et al., ACS Appl. Mater. Interfaces, 2022, 14, 36890–36901.13 M. Cucchi, et al., Sci Adv, , DOI:10.1126/sciadv.abh0693.14 G. Milano, , et al., Nat. Mater., 2022, 21, 195–202.15 L. D. Burke and P. F. Nugent, Gold Bull., 1997, 30, 43–53.16 S. Cherevko, et al. RSC Adv., 2013, 3, 16516–16527.17 R. Yamada et al., RSC Adv., 2023, 13, 24801. Figure 1

Predicting Chronic Liver Disease and Jaundice Detection an Integrated Approach Using Statistical Feature Extraction and Machine Learning Algorithms

An important health concern with chronic liver disease is early identification, which is essential for management and therapy. This work suggests an integrated method to identify tattoo-induced jaundice and forecast chronic liver disease by combining statistical feature extraction with machine learning techniques. First, we use statistical techniques based on projections to extract pertinent aspects from patient data, such as test results and clinical markers. We then use Artificial Neural Networks (ANN), KNN, and Naive Bayes to categorize individuals according to the probability that they have chronic liver illness and to pinpoint jaundice episodes associated with tattooing. The KNN technique offers interpretability, managing categorical data is made simple by Naive Bayes, and complicated patterns are captured by ANN using layers of neural networks. These models' performance is assessed using the following metrics: F1 score, recall, accuracy, and precision. Our research aims to improve prediction accuracy and offer practical advice for early diagnosis and individualized treatment plans. By utilizing advanced data analysis and machine learning instruments, the integrated strategy shows promise in enhancing healthcare outcomes.

Reduction of Vision-Based Models for Fall Detection.

Due to the limitations that falls have on humans, early detection of these becomes essential to avoid further damage. In many applications, various technologies are used to acquire accurate information from individuals such as wearable sensors, environmental sensors or cameras, but all of these require high computational resources in many cases, delaying the response of the entire system. The complexity of the models used to process the input data and detect these activities makes them almost impossible to complete on devices with limited resources, which are the ones that could offer an immediate response avoiding unnecessary communications between sensors and centralized computing centers. In this work, we chose to reduce the models to detect falls using images as input data. We proceeded to use image sequences as video frames, using data from two open source datasets, and we applied the Sparse Low Rank Method to reduce certain layers of the Convolutional Neural Networks that were the backbone of the models. Additionally, we chose to replace a convolutional block with Long Short Term Memory to consider the latest updates of these data sequences. The results showed that performance was maintained decently while significantly reducing the parameter size of the resulting models.