An Improved Archimedes Optimization-aided Multi-scale Deep Learning Segmentation with dilated ensemble CNN classification for detecting lung cancer using CT images.

Early detection of lung cancer is necessary to prevent deaths caused by lung cancer. But, the identification of cancer in lungs using Computed Tomography (CT) scan based on some deep learning algorithms does not provide accurate results. A novel adaptive deep learning is developed with heuristic improvement. The proposed framework constitutes three sections as (a) Image acquisition, (b) Segmentation of Lung nodule, and (c) Classifying lung cancer. The raw CT images are congregated through standard data sources. It is then followed by nodule segmentation process, which is conducted by Adaptive Multi-Scale Dilated Trans-Unet3+. For increasing the segmentation accuracy, the parameters in this model is optimized by proposing Modified Transfer Operator-based Archimedes Optimization (MTO-AO). At the end, the segmented images are subjected to classification procedure, namely, Advanced Dilated Ensemble Convolutional Neural Networks (ADECNN), in which it is constructed with Inception, ResNet and MobileNet, where the hyper parameters is tuned by MTO-AO. From the three networks, the final result is estimated by high ranking-based classification. Hence, the performance is investigated using multiple measures and compared among different approaches. Thus, the findings of model demonstrate to prove the system's efficiency of detecting cancer and help the patient to get the appropriate treatment.

Crystallographic phase identifier of a convolutional self-attention neural network (CPICANN) on powder diffraction patterns.

Spectroscopic data, particularly diffraction data, are essential for materials characterization due to their comprehensive crystallographic information. The current crystallographic phase identification, however, is very time consuming. To address this challenge, we have developed a real-time crystallographic phase identifier based on a convolutional self-attention neural network (CPICANN). Trained on 692 190 simulated powder X-ray diffraction (XRD) patterns from 23 073 distinct inorganic crystallographic information files, CPICANN demonstrates superior phase-identification power. Single-phase identification on simulated XRD patterns yields 98.5 and 87.5% accuracies with and without elemental information, respectively, outperforming JADE software (68.2 and 38.7%, respectively). Bi-phase identification on simulated XRD patterns achieves 84.2 and 51.5% accuracies, respectively. In experimental settings, CPICANN achieves an 80% identification accuracy, surpassing JADE software (61%). Integration of CPICANN into XRD refinement software will significantly advance the cutting-edge technology in XRD materials characterization.

Toward the design of persuasive systems for a healthy workplace: a real-time posture detection.

Persuasive technologies, in connection with human factor engineering requirements for healthy workplaces, have played a significant role in ensuring a change in human behavior. Healthy workplaces suggest different best practices applicable to body posture, proximity to the computer system, movement, lighting conditions, computer system layout, and other significant psychological and cognitive aspects. Most importantly, body posture suggests how users should sit or stand in workplaces in line with best and healthy practices. In this study, we developed two study phases (pilot and main) using two deep learning models: convolutional neural networks (CNN) and Yolo-V3. To train the two models, we collected posture datasets from creative common license YouTube videos and Kaggle. We classified the dataset into comfortable and uncomfortable postures. Results show that our YOLO-V3 model outperformed CNN model with a mean average precision of 92%. Based on this finding, we recommend that YOLO-V3 model be integrated in the design of persuasive technologies for a healthy workplace. Additionally, we provide future implications for integrating proximity detection taking into consideration the ideal number of centimeters users should maintain in a healthy workplace.

DNN-BP: a novel framework for cuffless blood pressure measurement from optimal PPG features using deep learning model.

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( R 2 ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.

Tissue of origin detection for cancer tumor using low-depth cfDNA samples through combination of tumor-specific methylation atlas and genome-wide methylation density in graph convolutional neural networks.

BACKGROUND: Cell free DNA (cfDNA)-based assays hold great potential in detecting early cancer signals yet determining the tissue-of-origin (TOO) for cancer signals remains a challenging task. Here, we investigated the contribution of a methylation atlas to TOO detection in low depth cfDNA samples. METHODS: We constructed a tumor-specific methylation atlas (TSMA) using whole-genome bisulfite sequencing (WGBS) data from five types of tumor tissues (breast, colorectal, gastric, liver and lung cancer) and paired white blood cells (WBC). TSMA was used with a non-negative least square matrix factorization (NNLS) deconvolution algorithm to identify the abundance of tumor tissue types in a WGBS sample. We showed that TSMA worked well with tumor tissue but struggled with cfDNA samples due to the overwhelming amount of WBC-derived DNA. To construct a model for TOO, we adopted the multi-modal strategy and used as inputs the combination of deconvolution scores from TSMA with other features of cfDNA. RESULTS: Our final model comprised of a graph convolutional neural network using deconvolution scores and genome-wide methylation density features, which achieved an accuracy of 69% in a held-out validation dataset of 239 low-depth cfDNA samples. CONCLUSIONS: In conclusion, we have demonstrated that our TSMA in combination with other cfDNA features can improve TOO detection in low-depth cfDNA samples.

Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples.

Adversarial attacks are still a significant challenge for neural networks. Recent efforts have shown that adversarial perturbations typically contain high-frequency features, but the root cause of this phenomenon remains unknown. Inspired by theoretical work on linear convolutional models, we hypothesize that translational symmetry in convolutional operations together with localized kernels implicitly bias the learning of high-frequency features, and that this is one of the main causes of high frequency adversarial examples. To test this hypothesis, we analyzed the impact of different choices of linear and non-linear architectures on the implicit bias of the learned features and adversarial perturbations, in spatial and frequency domains. We find that, independently of the training dataset, convolutional operations have higher frequency adversarial attacks compared to other architectural parameterizations, and that this phenomenon is exacerbated with stronger locality of the kernel (kernel size) end depth of the model. The explanation for the kernel size dependence involves the Fourier Uncertainty Principle: a spatially-limited filter (local kernel in the space domain) cannot also be frequency-limited (local in the frequency domain). Using larger convolution kernel sizes or avoiding convolutions (e.g., by using Vision Transformers or MLP-style architectures) significantly reduces this high-frequency bias. Looking forward, our work strongly suggests that understanding and controlling the implicit bias of architectures will be essential for achieving adversarial robustness.

Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization.

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an open challenge. We aim to enable systematic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired "self-repairing" mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaptation to structural and synaptic weight modifications introduced by the first step during the RSNN architectural "evolution." We demonstrate that the proposed automatic architecture optimization leads to significant performance gains over existing manually designed RSNNs: we achieve 96.44% on TI46-Alpha, 94.66% on N-TIDIGITS, 90.28% on DVS-Gesture, and 98.72% on N-MNIST. To the best of the authors' knowledge, this is the first work to perform systematic architecture optimization on RSNNs.

NoC simulation steered by NEST: McAERsim and a Noxim patch.

Introduction: Great knowledge was gained about the computational substrate of the brain, but the way in which components and entities interact to perform information processing still remains a secret. Complex and large-scale network models have been developed to unveil processes at the ensemble level taking place over a large range of timescales. They challenge any kind of simulation platform, so that efficient implementations need to be developed that gain from focusing on a set of relevant models. With increasing network sizes imposed by these models, low latency inter-node communication becomes a critical aspect. This situation is even accentuated, if slow processes like learning should be covered, that require faster than real-time simulation. Methods: Therefore, this article presents two simulation frameworks, in which network-on-chip simulators are interfaced with the neuroscientific development environment NEST. This combination yields network traffic that is directly defined by the relevant neural network models and used to steer the network-on-chip simulations. As one of the outcomes, instructive statistics on network latencies are obtained. Since time stamps of different granularity are used by the simulators, a conversion is required that can be exploited to emulate an intended acceleration factor. Results: By application of the frameworks to scaled versions of the cortical microcircuit model-selected because of its unique properties as well as challenging demands-performance curves, latency, and traffic distributions could be determined. Discussion: The distinct characteristic of the second framework is its tree-based source-address driven multicast support, which, in connection with the torus topology, always led to the best results. Although currently biased by some inherent assumptions of the network-on-chip simulators, the results suit well to those of previous work dealing with node internals and suggesting accelerated simulations to be in reach.

Emergent perceptual biases from state-space geometry in trained spiking recurrent neural networks.

A stimulus held in working memory is perceived as contracted toward the average stimulus. This contraction bias has been extensively studied in psychophysics, but little is known about its origin from neural activity. By training recurrent networks of spiking neurons to discriminate temporal intervals, we explored the causes of this bias and how behavior relates to population firing activity. We found that the trained networks exhibited animal-like behavior. Various geometric features of neural trajectories in state space encoded warped representations of the durations of the first interval modulated by sensory history. Formulating a normative model, we showed that these representations conveyed a Bayesian estimate of the interval durations, thus relating activity and behavior. Importantly, our findings demonstrate that Bayesian computations already occur during the sensory phase of the first stimulus and persist throughout its maintenance in working memory, until the time of stimulus comparison.

Artificial intelligence derived categorizations significantly improve HOMA IR/ß indicators: Combating diabetes through cross-interacting drugs.

Improvements in the homeostasis model assessment of insulin resistance (HOMA-IR) and homeostasis model assessment of beta-cell function (HOMA-ß) significantly reduce the risk of disabling diabetic pathies. Nanoparticle (AuNP-AgNP)-metformin are concentration dependent cross-interacting drugs as they may have a synergistic as well as antagonistic effect(s) on HOMA indicators when administered concurrently. We have employed a blend of machine learning: Artificial Neural Network (ANN), and evolutionary optimization: multiobjective Genetic Algorithms (GA) to discover the optimum regime of the nanoparticle-metformin combination. We demonstrated how to successfully employ a tested and validated ANN to classify the exposed drug regimen into categories of interest based on gradient information. This study also prescribed standard categories of interest for the exposure of multiple diabetic drug regimen. The application of categorization greatly reduces the time and effort involved in reaching the optimum combination of multiple drug regimen based on the category of interest. Exposure of optimum AuNP, AgNP and Metformin to Diabetic rats significantly improved HOMA ß functionality (∼63 %), Insulin resistance (HOMA IR) of Diabetic animals was also reduced significantly (∼54 %). The methods explained in the study are versatile and are not limited to only diabetic drugs.

Pairing cellular and synaptic dynamics into building blocks of rhythmic neural circuits. A tutorial.

In this study we focus on two subnetworks common in the circuitry of swim central pattern generators (CPGs) in the sea slugs, Melibe leonina and Dendronotus iris and show that they are independently capable of stably producing emergent network bursting. This observation raises the question of whether the coordination of redundant bursting mechanisms plays a role in the generation of rhythm and its regulation in the given swim CPGs. To address this question, we investigate two pairwise rhythm-generating networks and examine the properties of their fundamental components: cellular and synaptic, which are crucial for proper network assembly and its stable function. We perform a slow-fast decomposition analysis of cellular dynamics and highlight its significant bifurcations occurring in isolated and coupled neurons. A novel model for slow synapses with high filtering efficiency and temporal delay is also introduced and examined. Our findings demonstrate the existence of two modes of oscillation in bicellular rhythm-generating networks with network hysteresis: i) a half-center oscillator and ii) an excitatory-inhibitory pair. These 2-cell networks offer potential as common building blocks combined in modular organization of larger neural circuits preserving robust network hysteresis.

Detection of fake face images using lightweight convolutional neural networks with stacking ensemble learning method.

Images and videos containing fake faces are the most common type of digital manipulation. Such content can lead to negative consequences by spreading false information. The use of machine learning algorithms to produce fake face images has made it challenging to distinguish between genuine and fake content. Face manipulations are categorized into four basic groups: entire face synthesis, face identity manipulation (deepfake), facial attribute manipulation and facial expression manipulation. The study utilized lightweight convolutional neural networks to detect fake face images generated by using entire face synthesis and generative adversarial networks. The dataset used in the training process includes 70,000 real images in the FFHQ dataset and 70,000 fake images produced with StyleGAN2 using the FFHQ dataset. 80% of the dataset was used for training and 20% for testing. Initially, the MobileNet, MobileNetV2, EfficientNetB0, and NASNetMobile convolutional neural networks were trained separately for the training process. In the training, the models were pre-trained on ImageNet and reused with transfer learning. As a result of the first trainings EfficientNetB0 algorithm reached the highest accuracy of 93.64%. The EfficientNetB0 algorithm was revised to increase its accuracy rate by adding two dense layers (256 neurons) with ReLU activation, two dropout layers, one flattening layer, one dense layer (128 neurons) with ReLU activation function, and a softmax activation function used for the classification dense layer with two nodes. As a result of this process accuracy rate of 95.48% was achieved with EfficientNetB0 algorithm. Finally, the model that achieved 95.48% accuracy was used to train MobileNet and MobileNetV2 models together using the stacking ensemble learning method, resulting in the highest accuracy rate of 96.44%.

Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks.

This article provides a unified analysis of the multistability of fraction-order multidimensional-valued memristive neural networks (FOMVMNNs) with unbounded time-varying delays. Firstly, based on the knowledge of fractional differentiation and memristors, a unified model is established. This model is a unified form of real-valued, complex-valued, and quaternion-valued systems. Then, based on a unified method, the number of equilibrium points for FOMVMNNs is discussed. The sufficient conditions for determining the number of equilibrium points have been obtained. By using 1-norm to construct Lyapunov functions, the unified criteria for multistability of FOMVMNNs are obtained, these criteria are less conservative and easier to verify. Moreover, the attraction basins of the stable equilibrium points are estimated. Finally, two numerical simulation examples are provided to verify the correctness of the results.

Mittag-Leffler stability and application of delayed fractional-order competitive neural networks.

In the article, the Mittag-Leffler stability and application of delayed fractional-order competitive neural networks (FOCNNs) are developed. By virtue of the operator pair, the conditions of the coexistence of equilibrium points (EPs) are discussed and analyzed for delayed FOCNNs, in which the derived conditions of coexistence improve the existing results. In particular, these conditions are simplified in FOCNNs with stepped activations. Furthermore, the Mittag-Leffler stability of delayed FOCNNs is established by using the principle of comparison, which enriches the methodologies of fractional-order neural networks. The results on the obtained stability can be used to design the horizontal line detection of images, which improves the practicability of image detection results. Two simulations are displayed to validate the superiority of the obtained results.

MRGazer: decoding eye gaze points from functional magnetic resonance imaging in individual space.

Eye-tracking research has proven valuable in understanding numerous cognitive functions. Recently, Frey et al. provided an exciting deep learning method for learning eye movements from functional magnetic resonance imaging (fMRI) data. It employed the multi-step co-registration of fMRI into the group template to obtain eyeball signal, and thus required additional templates and was time consuming. To resolve this issue, in this paper, we propose a framework named MRGazer for predicting eye gaze points from fMRI in individual space. The MRGazer consists of an eyeball extraction module and a residual network-based eye gaze prediction module. Compared to the previous method, the proposed framework skips the fMRI co-registration step, simplifies the processing protocol, and achieves end-to-end eye gaze regression. The proposed method achieved superior performance in eye fixation regression (Euclidean error, EE=2.04°) than the co-registration-based method (EE=2.89°)， and delivered objective results within a shorter time (~0.02 second/volume) than prior method (~0.3 second/volume). The code is available at https://github.com/ustc-bmec/MRGazer.

An end-to-end gait recognition system for covariate conditions using custom kernel CNN.

Gait recognition is the identification of individuals based on how they walk. It can identify an individual of interest without their intervention, making it better suited for surveillance from afar. Computer-aided silhouette-based gait analysis is frequently employed due to its efficiency and effectiveness. However, covariate conditions have a significant influence on individual recognition because they conceal essential features that are helpful in recognizing individuals from their walking style. To address such issues, we proposed a novel deep-learning framework to tackle covariate conditions in gait by proposing regions subject to covariate conditions. The features extracted from those regions will be neglected to keep the model's performance effective with custom kernels. The proposed technique sets aside static and dynamic areas of interest, where static areas contain covariates, and then features are learnt from the dynamic regions unaffected by covariates to effectively recognize individuals. The features were extracted using three customized kernels, and the results were concatenated to produce a fused feature map. Afterward, CNN learns and extracts the features from the proposed regions to recognize an individual. The suggested approach is an end-to-end system that eliminates the requirement for manual region proposal and feature extraction, which would improve gait-based identification of individuals in real-world scenarios. The experimentation is performed on publicly available dataset i.e. CASIA A, and CASIA C. The findings indicate that subjects wearing bags produced 90 % accuracy, and subjects wearing coats produced 58 % accuracy. Likewise, recognizing individuals with different walking speeds also exhibited excellent results, with an accuracy of 94 % for fast and 96 % for slow-paced walk patterns, which shows improvement compared to previous deep learning methods.© 2017 Elsevier Inc. All rights reserved.

Advancements in rice disease detection through convolutional neural networks: A comprehensive review.

This review paper addresses the critical need for advanced rice disease detection methods by integrating artificial intelligence, specifically convolutional neural networks (CNNs). Rice, being a staple food for a large part of the global population, is susceptible to various diseases that threaten food security and agricultural sustainability. This research is significant as it leverages technological advancements to tackle these challenges effectively. Drawing upon diverse datasets collected across regions including India, Bangladesh, Türkiye, China, and Pakistan, this paper offers a comprehensive analysis of global research efforts in rice disease detection using CNNs. While some rice diseases are universally prevalent, many vary significantly by growing region due to differences in climate, soil conditions, and agricultural practices. The primary objective is to explore the application of AI, particularly CNNs, for precise and early identification of rice diseases. The literature review includes a detailed examination of data sources, datasets, and preprocessing strategies, shedding light on the geographic distribution of data collection and the profiles of contributing researchers. Additionally, the review synthesizes information on various algorithms and models employed in rice disease detection, highlighting their effectiveness in addressing diverse data complexities. The paper thoroughly evaluates hyperparameter optimization techniques and their impact on model performance, emphasizing the importance of fine-tuning for optimal results. Performance metrics such as accuracy, precision, recall, and F1 score are rigorously analyzed to assess model effectiveness. Furthermore, the discussion section critically examines challenges associated with current methodologies, identifies opportunities for improvement, and outlines future research directions at the intersection of machine learning and rice disease detection. This comprehensive review, analyzing a total of 121 papers, underscores the significance of ongoing interdisciplinary research to meet evolving agricultural technology needs and enhance global food security.

Benchmarking Deep Learning-Based Image Retrieval of Oral Tumor Histology.

INTRODUCTION:  Oral tumors necessitate a dependable computer-assisted pathological diagnosis system considering their rarity and diversity. A content-based image retrieval (CBIR) system using deep neural networks has been successfully devised for digital pathology. No CBIR system for oral pathology has been investigated because of the lack of an extensive image database and feature extractors tailored to oral pathology. MATERIALS AND METHODS: This study uses a large CBIR database constructed from 30 categories of oral tumors to compare deep learning methods as feature extractors. RESULTS: The highest average area under the receiver operating characteristic curve (AUC) was achieved by models trained on database images using self-supervised learning (SSL) methods (0.900 with SimCLR and 0.897 with TiCo). The generalizability of the models was validated using query images from the same cases taken with smartphones. When smartphone images were tested as queries, both models yielded the highest mean AUC (0.871 with SimCLR and 0.857 with TiCo). We ensured the retrieved image result would be easily observed by evaluating the top 10 mean accuracies and checking for an exact diagnostic category and its differential diagnostic categories. CONCLUSION: Training deep learning models with SSL methods using image data specific to the target site is beneficial for CBIR tasks in oral tumor histology to obtain histologically meaningful results and high performance. This result provides insight into the effective development of a CBIR system to help improve the accuracy and speed of histopathology diagnosis and advance oral tumor research in the future.

A deep learning approach for diagnosis of schizophrenia disorder via data augmentation based on convolutional neural network and long short-term memory.

Schizophrenia (SZ) is a severe, chronic mental disorder without specific treatment. Due to the increasing prevalence of SZ in societies and the similarity of the characteristics of this disease with other mental illnesses such as bipolar disorder, most people are not aware of having it in their daily lives. Therefore, early detection of this disease will allow the sufferer to seek treatment or at least control it. Previous SZ detection studies through machine learning methods, require the extraction and selection of features before the classification process. This study attempts to develop a novel, end-to-end approach based on a 15-layers convolutional neural network (CNN) and a 16-layers CNN- long short-term memory (LSTM) to help psychiatrists automatically diagnose SZ from electroencephalogram (EEG) signals. The deep model uses CNN layers to learn the temporal properties of the signals, while LSTM layers provide the sequence learning mechanism. Also, data augmentation method based on generative adversarial networks is employed over the training set to increase the diversity of the data. Results on a large EEG dataset show the high diagnostic potential of both proposed methods, achieving remarkable accuracy of 98% and 99%. This study shows that the proposed framework is able to accurately discriminate SZ from healthy subject and is potentially useful for developing diagnostic tools for SZ disorder.

Enhanced Multimodal Brain Tumor Classification in MR Images using 2D ResNet as backbone with Explicit Tumor Size Information.

It's a major public health problem of global concern that malignant gliomas tend to grow rapidly and infiltrate surrounding tissues. Accurate grading of the tumor can determine the degree of malignancy to formulate the best treatment plan, which can eliminate the tumor or limit widespread metastasis of the tumor, saving the patient's life and improving their prognosis. To more accurately predict the grading of gliomas, we proposed a novel method of combining the advantages of 2D and 3D Convolutional Neural Networks for tumor grading by multimodality on Magnetic Resonance Imaging. The core of the innovation lies in our combination of tumor 3D information extracted from multimodal data with those obtained from a 2D ResNet50 architecture. It solves both the lack of temporal-spatial information provided by 3D imaging in 2D convolutional neural networks and avoids more noise from too much information in 3D convolutional neural networks, which causes serious overfitting problems. Incorporating explicit tumor 3D information, such as tumor volume and surface area, enhances the grading model's performance and addresses the limitations of both approaches. By fusing information from multiple modalities, the model achieves a more precise and accurate characterization of tumors. The model I s trained and evaluated using two publicly available brain glioma datasets, achieving an AUC of 0.9684 on the validation set. The model's interpretability is enhanced through heatmaps, which highlight the tumor region. The proposed method holds promise for clinical application in tumor grading and contributes to the field of medical diagnostics for prediction.