Deep learning with coherent nanophotonic circuits

Context-based object recognition causally relies on both scene- and object-selective cortex, with scene-selective cortex generating expectations (at 160-200 ms after onset) that disambiguate object representations in object-selective cortex (at 260-300 ms after onset).

Purpose In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Design/methodology/approach In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Findings In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Originality/value In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.

Corona virus disease 19 (COVID-19) is an infectious disease which is having a significant health and economic impact across the world. The primary source for the transmission of the disease, its detection and treatment methods are still unknown. Hence, a scientific response to this new corona virus is being hampered by a lack of knowledge on how it spreads, possible prevention measures and vaccinations, which all need to be investigated further. Artificial intelligence (AI) and computer communication networks have a role to play, especially machine learning (ML) due to its learning-from samples capability and applicability over distributed computer systems and networks. This special issue features eight selected papers with high quality. The article, ‘Prediction of COVID-19 active cases using exponential and non-linear growth models,’ compares different AI models against a newly proposed one (Mahanty et al., 2022). The main objective of this paper was discovering the rate of infection spread in India, Pakistan, Myanmar, Brazil, Italy, and Germany, in addition to designing a susceptible-infectious-recovered (SIR), Verhulst, Gompertz, and proposed model for the assessment of the disease spread. And finally, providing a prediction method for the COVID-19 outbreak using all the said models. The article titled ‘Value of medical imaging artificial intelligence in the diagnosis and treatment of new coronavirus pneumonia’ applies AI to medical imaging, combined with embedded technology, RFID technology and signal processing technology, and applies the new coronavirus pneumonia image to the AI environment after processing, assisting doctors in diagnosis of the disease, and providing relevant information about patients record and manage the diagnosis and save and accumulate the experience and knowledge of famous doctors through the expert system, and then perform corresponding operations and analysis (Jia et al., 2022). Through the medical image intelligent analysis system, the risk of medical imaging AI diagnosis is reduced from 81% to 11%, which greatly reduces the hidden safety hazards for doctors and patients, reduces the workload of doctors, and also reduces the cost of medical care by 79%. In the article with the title ‘Endoscopic image recognition method of gastric cancer based on deep learning model’, Qiu et al. (2022) aim to improve the efficiency of gastric cancer (GC) diagnosis. So deep learning (DL) algorithms are tentatively used to assist doctors in the diagnosis of gastric cancer. In the experiment, the collected 3591 gastroscopic images were divided into network training set and experimental verification test set. The lesion samples in the image are all marked by many endoscopists with many years of clinical experience. In order to improve the experimental effect, 5261 endoscopic images were obtained by expanding the training set. Then the obtained training set is fed into the convolutional neural network (CNN) for training, and finally get the algorithm model DLU-Net. Authors concluded that the DL algorithm model constructed in this paper can effectively identify the staging characteristics of cancer and other similar diseases as well as the gastroscopic images, greatly improve efficiency, and effectively assist physicians in the diagnosis of GC under gastroscopy. The article titled ‘Fuzzy logic control theory in clinical anesthesia’, mainly studies the application of fuzzy logic control theory in clinical anaesthesia (Tian et al., 2022). First, after introducing the basic content of fuzzy logic control theory, the determination method of commonly used membership functions, the relevant knowledge of clinical anaesthesia, and the fuzzy logic code rate control model, this article describes in detail the basic principle diagram of the clinical anaesthesia control system and the clinical anaesthesia process. The mathematical model of clinical anaesthesia control system is constructed based on the data fusion technology of the parameters of anaesthesia depth monitoring. The parameters in the model are adjusted by the time domain analysis method to measure the dynamic characteristics, and the stability of the system is analysed by root locus method. The heart rate does not change significantly when it is lower than 1MAC, and the heart rate increases when it reaches 1.5 ~ 2MAC. Experimental results show that the application of fuzzy logic control theory to clinical anaesthesia can reduce the risk of clinical anaesthesia. By means of the CNN, the article ‘Medical image analysis of multiple myeloma based on convolutional neural network’, provides the application of neural network algorithm in multiple myeloma (He & Zhang, 2022). As such, the CNN model is constructed using existing medical data, and the retained case image data are input into the constructed CNN to verify the accuracy of the neural network. The results show that the accuracy rate of the neural network model constructed in this study is 0.87, which is higher than the accuracy rate of manual detection of 0.77. It can be concluded that using magnetic resonance imaging (MRI) to classify multiple myeloma has a high accuracy rate. Therefore, it has been proved that the CNN model established in this paper is effective. The proposed results prove that the neural network algorithm can be applied to MRI analysis, which helps to improve the efficiency of multiple myeloma diagnosis not only in COVID-19 related studies, but many other medical fields as well. On the other hand, existing and utilized neural networks security are not fully considered image segmentation. Therefore, the article, titled ‘Image segmentation algorithm of lung cancer based on neural network model’, explores the application of neural network algorithm model in lung imaging, and provides a reference for the application and development of artificial neural network algorithm in lung cancer medical mirroring, while promoting the development of the artificial neural network in this field (He et al., 2022). It is hoped that the application of neural network algorithms in medical imaging can improve the survival rate and cure rate of lung diseases. In this study, an artificial neural network algorithm model was selected to establish a lung cancer recognition model. After determining the lung cancer lesion area, the image segmentation algorithm was used to separately display the lung cancer lesion area, and a comparison experiment was designed to verify the accuracy of the model. Using artificial neural networks to identify lung cancer has a shorter diagnosis time and higher accuracy. Combining image retrieval methods with lung cancer image segmentation algorithms can clearly show the lesion area of lung cancer. Therefore, the lung cancer image segmentation algorithm based on the neural network model has good recognition performance. In the future development of intelligent medical imaging technology, artificial neural networks will be trained to perform medical image recognition and diagnosis tasks, which can reduce diagnosis time and improve diagnosis efficiency. In the article, titled ‘Clinical study of serum procalcitonin in the early diagnosis of burns and sepsis under the background of healthy clouds’, the purpose is to diagnose the sepsis early while utilizing the cloud services (Huang et al., 2022). The clinical symptoms and vital signs of sepsis are not particularly abnormal, and imaging examination may cause the focus of infection to be incorrect. As a result, the positive rate of positive results is low, which seriously affects the timely diagnosis and treatment of patients. Experimental data show that serum PCT of non-septic patients is obvious during the six groups of experiments 1–5 days, 6–10 days, 11–15 days, 16–20 days, 21–25 days, 26–30 days after treatment Serum PCT levels below sepsis. The data recorded during the experiment are in accordance with the relevant principles of statistics to ensure that the experiment is true and effective. The experimental results show that the PCT of burn sepsis group is higher than that of the cured group without burns, and the serum PCT level is crucial for the diagnosis of burn sepsis. Meanwhile, recurrent neural networks (RNN) are extensively used to determine the optimal solutions to the various class recognition problems such as image processing, prediction of biomedical data and speech recognition. With the gradient problems, RNN is losing its shade which is replaced by the long short term memory (LSTM). However, the hardware implementation of the LSTM requires more challenge due to its complexity and high power consumption which makes it unsuitable for implementation in biological internet of things (BIoT) networks for the prediction of medical diseases. Several algorithms were proposed for an effective implementation of LSTM, but hand-offs between the performance and utilization still needs improvisation. The article, titled ‘P-SCADA - A novel area and energy efficient FPGA architectures for LSTM prediction of heart arrthymias in BIoT applications’, proposes the novel energy efficient and high performance architecture pipelined stochastic adaptive distributed architectures (P-SCADA) for LSTM networks (Varadharajan & Nallasamy, 2022). In this architecture, hybrid structure has been developed with the help of new distributed arithmetic stochastic computing (DSC) along with the binary circuits to advance the performance of the FPGA such as energy, area and accuracy. The proposed system has been implemented in ARTIX-7 FPGA with special purpose software has been designed and evaluated with different ECG data sets. For the different series data, area utilization is about 40%–44% and power consumption is about 20%–25% with the prediction of accuracy of 98%. Moreover, the proposed architecture has been compared with the other existing architecture such as SPARSE architectures, normal stochastic architectures in which the proposed architecture excels in terms area, power and efficiency. The guest editors are thankful to the anonymous reviewers for their effort in reviewing the manuscripts. We are also thankful to the Editor-in-Chief, for his supportive guidance during the entire process. Fadi Al-Turjman received his PhD in computer science from Queen's University, Canada, in 2011. He is the associate dean for research and the founding director of the International Research Center for AI and IoT at Near East University, Nicosia, Cyprus. Prof. Al-Turjman is the head of Artificial Intelligence Engineering Dept., and a leading authority in the areas of smart/intelligent IoT systems, wireless, and mobile networks' architectures, protocols, deployments, and performance evaluation in Artificial Intelligence of Things (AIoT). His publication history spans over 400 SCI/E publications, in addition to numerous keynotes and plenary talks at flagship venues. He has authored and edited more than 40 books about cognition, security and wireless sensor networks' deployments in smart IoT environments, which have been published by well-reputed publishers such as Taylor and Francis, Elsevier, IET, and Springer. He has received several recognitions and best papers' awards at top international conferences. He also received the prestigious Best Research Paper Award from Elsevier Computer Communications Journal for the period 2015–2018, in addition to the Top Researcher Award for 2018 at Antalya Bilim University, Turkey. Prof. Al-Turjman has led a number of international symposia and workshops in flagship communication society conferences. Currently, he serves as book series editor and the lead guest/associate editor for several top tier journals, including the IEEE Communications Surveys and Tutorials (IF 23.9) and the Elsevier Sustainable Cities and Society (IF 7.8), in addition to organizing international conferences and symposiums on the most up to date research topics in AI and IoT.

CORR Synthesis: When Should the Orthopaedic Surgeon Use Artificial Intelligence, Machine Learning, and Deep Learning?

Engineering Applications of Bio-Inspired Artificial Neural Networks

The article explores modern neural network architectures for the automatic detection and recognition of marine surface objects and obstacles of given classes throughout the full image area, applicable for execution in real or near real time on an optoelectronic vision system to au-tomate and improve the safety of civil marine navigation. A formal statement of the problem of automatic detection of objects on images is given. The state-of-the-art algorithms for detecting objects in images based on use of artificial convolutional neural networks were reviewed, their comparison was made and a reasonable choice was made in favor of the most efficient neuralnetwork architecture in terms of computational complexity to recognition accuracy. The subject area is studied, as well as publicly available databases of surface objects suitable for use in the training of algorithms using artificial neural networks. The article concluded that there is insuffi-cient labeled data for training neural network algorithms, as a result of which the authors inde-pendently collected research images and video sequences, prepared and labeled the collected data containing surface marine objects and other obstacles that represent a navigation hazard for ships. Based on the selected neural network architecture, a new neural network algorithm for automatic full-frame detection and recognition of surface objects was developed, and an artificial neural network was trained using the prepared database of images of typical objects. The resulting algorithm was tested by the authors on a validation data set, the quality of its work was estimated using various metrics, and the algorithm’s performance was measured. Conclusions are made about the necessity to expand the collected database of images of typical marine objects, further steps are proposed to improve the accuracy of the developed software and algorithmic complex and its implementation to be used in a marine optoelectronic machine vision system for automa-tion and improving the safety of civil navigation.

Neural networks are the core component in the recent empirical successes of deep learning techniques in challenging tasks. Residual network (ResNet) architectures have been instrumental in improving performance in object recognition and other tasks by enabling training much deeper neural networks. Studies of residual networks reveal that they are robust to removing layers. However, it is still an open question of why residual networks behave well and how they make it feasible to train networks with many layers. In this paper, we show that sparsity of the residual blocks acts as the implicit gating mechanism. When a neuron is inactive, it behaves as a node in an information highway, allowing the information from the previous layer to pass to the next layer unchanged. As the identity function has a derivative of 1, it avoids the exploding or vanishing gradient problem that is known to contribute to the difficulty of training deep neural networks. When a neuron is active, it captures input-output relationships that are necessary to achieve good performance. By using the ReLu activation functions, residual blocks produce sparse outputs for typical inputs. We perform systematic experimental analysis on the residual blocks of trained ResNet models and show that sparsity acts as the implicit gate for deep residual networks.

IntroductionIn recent years, machines powered by deep learning have achieved near-human levels of performance in speech recognition. The fields of artificial intelligence and cognitive neuroscience have finally reached a similar level of performance, despite their huge differences in implementation, and so deep learning models can—in principle—serve as candidates for mechanistic models of the human auditory system.MethodsUtilizing high-performance automatic speech recognition systems, and advanced non-invasive human neuroimaging technology such as magnetoencephalography and multivariate pattern-information analysis, the current study aimed to relate machine-learned representations of speech to recorded human brain representations of the same speech.ResultsIn one direction, we found a quasi-hierarchical functional organization in human auditory cortex qualitatively matched with the hidden layers of deep artificial neural networks trained as part of an automatic speech recognizer. In the reverse direction, we modified the hidden layer organization of the artificial neural network based on neural activation patterns in human brains. The result was a substantial improvement in word recognition accuracy and learned speech representations.DiscussionWe have demonstrated that artificial and brain neural networks can be mutually informative in the domain of speech recognition.

The article presents a way of using machine learning algorithms to recognize objects in images. To implement this task, an artificial neural network was used, which has a high adaptability and allows work with a very large set of input data. The neural network was described using a program written in the MATLAB simulation environment. The basic problem faced by the designer of objects recognition is to collect a sufficient training set of images to achieve the high probability of correct recognition. The set of learning patterns in the artificial neural networks may contain from several dozen thousands to one million training samples. In this article at the beginning the neural network was pre-trained trained based on the images included in the publicly available CIFAR 100 database, which are characterized by a small size of 32x32 pixels. It contains 70 000 images assigned to 10 basic categories. Then the author's database, consisting from 1000 pedestrians, cars and road signs was used. The article contains a description of applied algorithm, method of supervised learning and correction of weight coefficients, selection of activation function and operation on max pooling filter. The results of proposed solution are presented in the form of screenshots from calculations and in figures depicting results of recognized objects. Attention was also paid to the impact of used database for learning the network on the speed of calculations and recognition efficiency. The proper selection of number and types of layers, number of neurons, activation function and the value of the learning factor is very important in designing the neural network in application to objects recognition contained in the images. The problems occurring in the process of learning the neural networks and suggestions for their further improvement are also presented.

Spiking neural networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional artificial neural networks (ANNs) due to their inherent high-sparsity activation. Recently, SNNs with backpropagation through time (BPTT) have achieved a higher accuracy result on image recognition tasks than other SNN training algorithms. Despite the success from the algorithm perspective, prior works neglect the evaluation of the hardware energy overheads of BPTT, due to the lack of a hardware evaluation platform for this SNN training algorithm. Moreover, although SNNs have long been seen as an energy-efficient counterpart of ANNs, a quantitative comparison between the training cost of SNNs and ANNs is missing. To address the aforementioned issues, in this work, we introduce a sparsity-aware training accelerator (SATA), a BPTT-based training accelerator for SNNs. The proposed SATA provides a simple and reconfigurable systolic-based accelerator architecture, which makes it easy to analyze the training energy for BPTT-based SNN training algorithms. By utilizing the sparsity, SATA increases its computation energy efficiency by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5.58\times $ </tex-math></inline-formula> compared to the one without using sparsity. Based on SATA, we show quantitative analyses of the energy efficiency of SNN training and make a comparison between the training cost of SNNs and ANNs. The results show that, on Eyeriss-like systolic-based architecture, SNNs consume <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.27\times $ </tex-math></inline-formula> more total energy with considering sparsity (spikes, gradient of firing function, and gradient of membrane potential) when compared to ANNs. We find that such high training energy cost is from time-repetitive convolution operations and data movements during backpropagation. Moreover, to propel the future SNN training algorithm design, we provide several observations on energy efficiency for different SNN-specific training parameters and propose an energy estimation framework for SNN training.

The inertial measurement unit (IMU) is a popular sensor device, which is mainly employed to acquire body or hand gesture action information for performing specific recognition tasks. We present a dual-channel artificial neural network (ANN) recognition decision hybridization scheme incorporated with deep leaning of IMU-based spectrogram images for cognition of several common hand gesture intention categorization actions focused on the 6-axis IMU sensing data (containing 3-axis accelerometer and 3-axis gyroscope information) and the 6-axis IMU derived spectrogram images. In this hand gesture intention cognition approach, both symmetric and asymmetric ANN structures are considered for intention action classifications. The proposed dual-channel ANN decision fusion framework contains one ANN recognition channel with inputs of &#x201C;6-axis IMU raw data&#x201D; and the other ANN recognition channel with inputs of &#x201C;IMU spectrogram image derived-critical deep learning features&#x201D;. Recognition decisions estimated from either of these two ANN recognition channels form the fusion framework. Three fusion schemes on dual-channel ANN recognition decisions are presented in this study, channel output layer accumulation, same channel candidate output and same-or-dual channel candidate output. In this study, the well-known deep learning neural network, visual&#xA0;geometry group- convolution neural network (VGG-CNN), is employed to carry out deep learning computations on IMU-based spectrogram images, from which, the critical deep learning feature of each spectrogram image can then be extracted and used as an input for the dual-channel ANN. For recognition performance comparisons, hand gesture intention recognition by the traditional VGG-CNN deep neural network approach (i.e. recognition of IMU spectrogram images using typical deep learning of the CNN model) is also performed. Experiments on classifications of six hand gesture intention actions show that the presented dual-channel ANN decision fusion incorporated with deep learning of IMU spectrum images has competitive performances, reaching better recognition accuracy than traditional CNN deep learning.

Background: To provide ease to diagnose that serious sickness multi-technique model is proposed. Data Analytics and Machine intelligence are involved in the detection of various diseases for human health care. The computer is used as a tool by experts in the medical field, and the computer-based mechanism is used to diagnose different diseases in patients with high Precision. Due to revolutionary measures employed in Artificial Neural Networks (ANNs) within the research domain in the medical area, which appear to be in the data-driven applications usually described in the domain of health care. Cardio sickness according to name is a type of an ailment that is directly connected to the human heart and blood circulation setup, so it should be diagnosed on time because the delay of diagnosing of that disease may lead the sufferer to death. The research is mainly aimed to design a system that will be able to detect cardiovascular sickness in the sufferer using machine learning approaches. Objective: The main objective of the research is to gather information of the six parameters that is age, chest pain, electrocardiogram, systolic blood pressure, fasting blood sugar and serum cholesterol are used by Mamdani fuzzy expert to detect cardiovascular sickness. To propose a type of device which will be successfully used in overcoming the cardiovascular diseases. This proposed model Diagnosis Cardiovascular Disease using Mamdani Fuzzy Inference System (DCD-MFIS) shows 87.05 percent Precision. To delineate an effective Neural Network Model to predict with greater precision, whether a person is suffering from cardiovascular disease or not. As the ANN is composed of various algorithms, some will be handed down for the training of the network. The main target of the research is to make the use of three techniques, which include fuzzy logic, neural network, and deep machine learning. The research will employ the three techniques along with the previous comparisons, and given that, the results will be compared respectively. Methods: Artificial neural network and deep machine learning techniques are applied to detect cardiovascular sickness. Both techniques are applied using 13 parameters age, gender, chest pain, systolic blood pressure, serum cholesterol, fasting blood sugar, electrocardiogram, exercise including angina, heart rate, old peak, number of vessels, affected person and slope. In this research, the ANN-based research is one of the algorithms collections, which is the detection of cardiovascular diseases, is proposed. ANN constitutes of many algorithms, some of the algorithms are employed in the paper for the training of the network used, to achieve the prediction ratio and in contrast of the comparison of the mutual results shown. Results: To make better analysis and consideration of the three frameworks, which include fuzzy logic, ANN, Deep Extreme Machine Learning. The proposed automated model Diagnosis Cardiovascular Disease includes Fuzzy logic using Mamdani Fuzzy Inference System (DCD-MFIS), Artificial Neural Network (DCD–ANN) and Deep Extreme Machine Learning (DCD–DEML) approach using back propagation system. These frameworks help in attaining greater precision and accuracy. Proposed DCD Deep Extreme Machine Learning attains more accuracy with previously proposed solutions that are 92.45%. Conclusion: From the previous comparisons, the propose automated Diagnosis of Cardiovascular Disease using Fuzzy logic, Artificial Neural Network, and deep extreme machine learning approaches. The automated systems DCDMFIS, DCD–ANN and DCD–DEML, the framework proposed as effective and efficient with 87.05%, 89.4% and 92.45 % success ratios respectively. To verify the performance which lies in the ANNs and computational analysis, many indicators determining the precise performance were calculated. The training of the neural networks is made true using the 10 to 20 neurons layers which denote the hidden layer. DEML reveals and indicates a hidden layer containing 10 neurons, which shows the best result. In the last, we can conclude that after making a consideration among the three techniques fuzzy logic, Artificial Neural Network and Proposed DCD Deep Extreme Machine, the Proposed DCD Deep Extreme Machine Learning based solution give more accuracy with previously proposed solutions that are 92.45%.

The brain-inspired neural networks have demonstrated great potential in big data analysis. The spiking neural network (SNN), which encodes the real world data into spike trains, promises great performance in computational ability and energy efficiency. Moreover, it is much more biologically plausible than the traditional artificial neural network (ANN), which keeps the input data in its original form. In this paper, we introduce an RRAM-based energy efficient implementation of STDP-based spiking neural network cascaded with ANN classifier. The recognition accuracy and power consumption are compared between SNN and traditional three-layer ANN. The experiments on the MNIST database demonstrate that the proposed RRAM-based spiking neural network requires only 14% of power consumption compared with RRAM-based artificial neural network with a slight accuracy decay (∼2%).

The review presents a comprehensive analysis of the latest advances in machine learning (ML), artificial neural networks (ANN), and deep learning (DL) in urologic oncology. As part of the study, the Russian and foreign scientific literature was ranked based on PubMed, MEDLINE, E-library, CYBERLENINKA, etc. The data related to the use of ML, ANN, and DL in the diagnosis and treatment of prostate cancer (PCa), bladder cancer (BC), testicular cancer, and kidney cancer was collected. Most often, ANN and ML in PCa were used for early diagnosis, prognosis, and personalized systemic treatment strategy development. ANN and DL models were trained with clinical parameters, NGS-sequencing results, Gleason scores, and digitized radiological, and histological images. Radiomics was also used to diagnose PCa, followed by analysis of special image texture features on a digital slide. In metastatic castration-resistant PCa, artificial intelligence (AI) algorithms were used to predict the response to docetaxel treatment. The prospects of using AI for tumor imaging during radical prostatectomy and when performing robot-assisted kidney resection were also addressed. A diagnostic approach for testicular malignancies based on computed tomography data is proposed using ML. Neuro-fuzzy modeling and ANN were used to diagnose BC. The algorithms were based on molecular biomarkers, including gene expression and methylation. The ML method based on images of cells obtained from urine samples of patients diagnosed with BC showed a diagnostic accuracy of 94%. DL in BC was used for accurate tumor typing based on their response to chemotherapy. Based on the results of deep machine learning, the molecular subtype of BC samples was predicted using histological examination. ML and DL algorithms for diagnosis, differential diagnosis, and prediction of recurrence and survival in kidney cancer were trained on CT texture analysis, genetic mutations, and Fuhrman nuclear grade. In addition to diagnosis, AI is used to optimize the treatment strategy for kidney cancer. In all cases, the ML, ANN, and DL algorithms improved the accuracy of diagnosis, survival assessment, and the effectiveness of pharmacological and surgical treatment of urologic malignancies.

The article describes the results of increasing the efficiency of operational forecast of the forest fire dynamics under nonstationarity and uncertainty through the fire dynamics modeling based on artificial intelligence and deep machine learning. To achieve the goal there were used following methods: system analysis method, theory of neural networks, deep machine learning method, method of operational forecasting of the forest fire dynamics, method of filtering images (modified median filter), MoSCoW method, and ER-method. In the course of study there have been developed forest fire forecasting models (models of treetop and ground fires) using artificial neural networks. The developed models solve the recognition and forecasting problems in order to determine the dynamics of forest fires in successive images and generating images with a forecast of fire spread. There has been given the general logical scheme of the proposed forest fire forecasting models involving five stages: stage 1 - data input; stage 2 - preprocessing of input data (format check; size check; noise removal); stage 3 - object recognition using Convolutional Neural Networks (recognition of fire data; recognition of data on environmental factors; recognition of data on the nature of forest plantations); stage 4 - development of forest fire forecasting; stage 5 - output of the generated image with the operational forecast. To build and train artificial neural networks, a visual forest fire dynamics database was proposed to use. The developed forest fire forecasting models are based on a tree of artificial neural networks in the form of an acyclic graph and identify dependencies between the dynamics of a forest fire and the characteristics of the external and internal environment.