Search

The colorimetric method is usually used to test the concentration of substances. However, this method has a big error since different people have different sensitivities to colors. In this paper, in order to solve the identification problem of the color and the concentration of the test paper, firstly, we found out that the concentration of substance is correlated with the color reading by using the Pearson's Chi-squared test method. And by the concentration coefficient of Pearson correlation analysis, the concentration of substance and color reading is highly correlated. Secondly, according to the RGB value of the paper image, the color moments of the image are calculated as the characteristics of the image, and the Levenberg–Marquardt (LM) neural network is established to classify the concentration of the substance. The accuracy of the training set model is 94.5%, and the accuracy of the test set model is 87.5%. The model precision is high, and the model has stronger generalization ability. Therefore, according to the RGB value of the test paper image, it is effective to establish the LM neural network model to identify the substance concentration. [ABSTRACT FROM AUTHOR]

This paper constructs a neural machine translation model for Chinese and English using encoder feature extraction with migration learning, allowing the machine to automatically perform feature migration learning, transforming Chinese and English data into word vectors using a centralized representation, and using neural networks to achieve a direct mapping between Chinese and English languages. In this paper, we study the construction of a neural machine translation model by the neural network structure. Firstly, the neural machine translation model is constructed using the neural network structure, which is simplified based on the neural network structure and achieves good performance while reducing the training complexity. To address the problem that neural machine translation cannot make good use of linguistic knowledge, a neural machine translation model with lexical sequence information is proposed. Based on the translation model of a bidirectional neural network incorporating attention mechanism, syntactic analysis is performed to obtain lexical sequence information, and then it is incorporated into the encoder part of the translation model in the form of bidirectional encoding, and the background vector is formed together by vector splicing. To address the problem that the Chinese-English language sequences of any length in the encoder part are encoded into a fixed dimensional background vector, an attention mechanism is introduced to dynamically adjust the degree of influence of the context at the source language end on the target language sequences to improve the translation model's ability to deal with long-distance dependencies. To better reflect the contextual information, this paper further proposes a machine translation model based on migration learning and neural network and conducts a comparative analysis for various translation models to verify the effectiveness of the model performance improvement. [ABSTRACT FROM AUTHOR]

This paper aims to propose an improved image classification model to reduce the cost of model construction. Aiming at the problem that network training usually requires the support of a large number of labeled samples, an image classification model based on semi-supervised deep learning is proposed, which uses labeled samples to guide the network to learn unlabeled samples. A convolutional neural network model for simultaneous processing of labeled and unlabeled data is constructed. The tagged data is used to train the Softmax classifier and provide the initial K-means clustering center for the untagged data. The nonsubsampling contourlet layer is used to replace the first convolutional layer of the full convolutional neural network to extract multi-scale depth features, and the nonsubsampling contourlet full convolutional neural network is constructed. The network can extract multi-scale information of the images to be classified, and extract more discriminative deep image features. In addition, the parameters of the nonsubsampled contourlet layers are pre-set and do not require network training. The proposed method has higher classification accuracy than the contrast method on polarimetric SAR images using the nonsubsampled contourlet full convolutional neural network. [ABSTRACT FROM AUTHOR]

The Π -shaped open section girder is a very common section, which has been widely used in the construction of modern bridges. However, compared with a streamlined box girder, it is easy to cause vortex-induced vibration (VIV) in bridges due to its bluff section shape and poor aerodynamic stability. In this paper, a typical open section with a height–width ratio of 10:1 is taken as the research object. Through wind tunnel tests and numerical simulation technology, the time-history data of VIV of the Π -shaped section are obtained. By selecting three different neural network models to establish the relationship between external parameters (wind attack angle, wind speed, turbulence) and structural response parameters (the onset wind speed of VIV, the length of the lock-in interval). After comparing different machine learning methods, the most suitable machine learning model is selected to predict the VIV response characteristics of the main girder. The research results show that the typical open section has a serious VIV phenomenon. The BP neural network model has the best performance in predicting the VIV performance of the open section in terms of calculation speed, prediction accuracy and solving nonlinear adaptability. At the same time, it is found that different characteristic parameters of the incoming wind field have different influences on the prediction results of the VIV response. Among them, the wind attack angle is the key parameter that affects the onset wind speed of VIV, but the turbulence intensity has a greater impact on the maximum amplitude of VIV. At the same time, the optimized BP model can predict the characteristic parameters of VIV response under unknown wind fields. This paper provides a new idea to study the effect of different incoming flow parameters on the performance of section VIV and further improves people's understanding of VIV system. [ABSTRACT FROM AUTHOR]

The paper considers a class of discrete-time cellular neural networks (DT-CNNs) obtained by applying Euler's discretization scheme to standard CNNs. Let T be the DT-CNN interconnection matrix which is defined by the feedback cloning template. The paper shows that a DT-CNN is convergent, i.e. each solution tends to an equilibrium point, when T is symmetric and, in the case where T + E n is not positive-semidefinite, the step size of Euler's discretization scheme does not exceed a given bound ( E n is the n × n unit matrix). It is shown that two relevant properties hold as a consequence of the local and space-invariant interconnecting structure of a DT-CNN, namely: (1) the bound on the step size can be easily estimated via the elements of the DT-CNN feedback cloning template only; (2) the bound is independent of the DT-CNN dimension. These two properties make DT-CNNs very effective in view of computer simulations and for the practical applications to high-dimensional processing tasks. The obtained results are proved via Lyapunov approach and LaSalle's Invariance Principle in combination with some fundamental inequalities enjoyed by the projection operator on a convex set. The results are compared with previous ones in the literature on the convergence of DT-CNNs and also with those obtained for different neural network models as the Brain-State-in-a-Box model. Finally, the results on convergence are illustrated via the application to some relevant 2D and 1D DT-CNNs for image processing tasks. [ABSTRACT FROM AUTHOR]

Cervical cancer (CC) has become one of the serious and deadly diseases in women around the world. Predicting a CC is at risk because testing is not possible at the early stage. Doctors predict the types of cancer by collecting cervical cells and by intervening in person. This approach affects the level of prediction due to human negligence, high cost, and is time consuming. In this paper, we propose the automatic cancer classification using deep neural network to overcome this problem. The proposed work has four stages namely, pre-processing, outlier elimination, dimensionality reduction, and classification. Initially, the missing test data should be removed. Second, the inconsistent data are eliminated based on identical values. Third, principal component analysis (PCA) is used to overcome the limitations caused by high-volume data. Finally, enter the reduced size database in the proposed neural network (DNN) classifier and classify the input data as normal or abnormal. We implement the suggested method using Python and we inspect the performance in terms of different metrics. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have revolutionized various fields through their ability to model complex patterns, yet their performance critically hinges on the availability of large-scale, accurately labeled datasets. The costly and time-consuming process of creating such datasets has motivated research into Learning with Noisy Labels (LNL), which aims to reduce reliance on perfect labels. This paper introduces CoFix, an innovative LNL framework that integrates sample selection with semi-supervised learning techniques to address the challenge of noisy labels in training. CoFix employs a Gaussian Mixture Model (GMM) to dynamically segment the training data into clean and noisy subsets, leveraging semi-supervised learning approaches on both. Inspired by the FixMatch algorithm, CoFix refines consistent regularization and pseudo-labeling strategies, enhancing augmentation strategies and temperature sharpening techniques. Additionally, CoFix explores label smoothing to augment the loss function, further refining model performance. Our experiments demonstrate CoFix's superiority over state-of-the-art methods, achieving significant improvements in fewer training epochs, particularly in lower noise scenarios. The robustness and versatility of CoFix are evident through its consistent performance across various benchmark datasets and noise levels. The contributions of this paper include a novel LNL method with enhanced generalization capability, an investigation into the impact of label smoothing on the loss function, and extensive testing that confirms CoFix's efficiency and adaptability to different noise levels. [ABSTRACT FROM AUTHOR]

Continuous fire models are not suitable for the implementation of hardware units for applications and hence, suitable discrete versions need to be selected. Moreover, the nonlinear components in the neuronal equations reduce system performance (in the case of frequency and number of resources). This research paper focuses on implementing efficient Spiking Neural Networks (SNNs) using Field-Programmable Gate Array (FPGA), with a specific emphasis on the Leaky Integrate and Fire (LIF) neuron model. Its objective is to optimize the mathematical equations of the LIF model by approximating nonlinear functions. This approach enables the development of a simple, cost-effective and high-speed design. Existing LIF Neuron Hardware Blocks (NHBs) are based on the approximation of continuous models by standard difference schemes such as the Euler method or R–K method etc. Mathematically, such approximations do not exactly represent all dynamics of continuous systems. There are good approximations for small step sizes but they behave oddly when the approximation step size increases. Hence, the corresponding discrete, digital versions are not suitable for applications in all cases. This paper utilizes a Nonstandard Finite Difference (NSFD) scheme for the hardware (FPGA) implementation of the exact model of LIF-based NHB that works for all step sizes. The model presented here has a speed of 438.686MHz which is more than other existing models presented in this paper. It is multiplier-less, unlike earlier models. Further, it is implemented for SNN for basic pattern recognition and established that the proposed model works properly for given patterns. The system was evaluated using large datasets such as MNIST handwritten digit recognition, achieving a classification accuracy of 97.8%. Additionally, it underwent testing for COVID-19 chest CT scan image classification, demonstrating an 84% accuracy rate which is 6% more compared to existing Spiking Neural Networks (SNNs). [ABSTRACT FROM AUTHOR]

This paper introduces a method to solve the 2D irregular packing problem using Deep Reinforcement Learning (Deep RL) for logistics. Our method employs a Q agent trained to predict the best placement within a container, maximizing available space. Unlike previous Deep RL algorithms, our method introduces a dense reward function at each packing step, providing immediate feedback and accelerating learning. To our knowledge, this is the first approach to use a dense reward to address the 2D irregular packing problem. Building on our earlier work, we improve the deep neural network by incorporating the Double Deep Q-Network (DDQN) framework to enhance our deep Q-learning approach, reducing overestimation biases and improving decision-making reliability. Simulation results show the method's effectiveness in completing the online 2D irregular packing tasks, achieving promising volume efficiency and packed piece metrics. This research extends our initial findings, highlighting the practical importance of DDQN and dense reward in advancing 2D irregular packing problem-solving. These advancements not only broaden the applications of deep learning but also hold practical importance for real-world logistics challenges. [ABSTRACT FROM AUTHOR]

Binary classification with an imbalanced dataset is challenging. Models tend to consider all samples as belonging to the majority class. Although existing solutions such as sampling methods, cost-sensitive methods, and ensemble learning methods improve the poor accuracy of the minority class, these methods are limited by overfitting or cost parameters that are difficult to decide. This paper proposes a hybrid approach with dimension reduction that consists of data block construction, dimensionality reduction, and ensemble learning with deep neural network classifiers. The performance is evaluated on eight imbalanced public datasets in terms of recall, G-mean, AUC, F-measure, and balanced accuracy. The results show that the proposed model outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Forecasting traffic congestion has become an important issue than ever before. Information provided by traffic congestion prediction methods becomes helpful to traffic management agencies to take suitable actions in due time. On the other hand, with prior information, passengers can plan their trip routes accordingly. In this paper, we tackle the problem of mixed traffic congestion prediction and develop a new Bi-State Prediction Network (BiSPNet). Two heads form BiSPNet. Each head information passed through the layers of three-dimensional convolution (Conv3D), two-dimensional convolutional long short-term memory (ConvLSTM2D), and two-dimensional convolution (Conv2D). Then the dense layer merges both head outputs. These layers capacitate the model to capture the characteristics of multiple inputs. The proposed model is validated by the ground truth data collected by the video cameras installed on the roadways in Delhi, India. Experimental results confirm that the prediction accuracy of the BiSPNet model surpasses that of several state-of-the-art benchmark models. In particular, the BiSPNet reduces mean absolute error by 53.23%, 40.95%, and 0.38%, respectively, in congestion score prediction for 5, 10, and 15-min time horizons compared to the mixed deep learning network (MDLNet). The source data and code can be accessed on GitHub at the following link: https://github.com/amanojup/. [ABSTRACT FROM AUTHOR]

In this paper, an example of an intelligent security system based on deep learning approach has been analyzed and described. Security is an important element in many aspects of human life. Depending on customer requirements, different levels of security may be required and implemented. Nowadays, artificial intelligence is becoming an indispensable part in many areas of human life and accordingly security systems are also based on the new achievements in this field. In this paper, an intelligent security system based on two methods for identifying persons, gait recognition and face recognition, was described. The two methods mentioned above can be used to give persons access to different buildings, facilities, institutions, etc. or to different indoor or outdoor areas. In light of the above, the aforementioned system uses face and gait recognition to identify persons who should be granted access to a facility or a specific area within the facility. Accordingly, two deep learning models for gait and face recognition have been developed and described. The analysis, the settings defined and the results obtained in relation to the models developed were also described. [ABSTRACT FROM AUTHOR]

Current healthcare applications commonly incorporate the Internet of Things (IoT) and cloud computing ideas. IoT devices provide massive amounts of patient data in the healthcare industry. These data stored in the cloud are analyzed using mobile devices' built-in storage and processing power. The Internet of Medical Healthcare Things (IoMHT) integrates health monitoring components including sensors and medical equipment to remotely monitor patient records in order to provide more intelligent and sophisticated healthcare services. In this research, we analyze one of the deadliest illnesses with a high fatality rate worldwide, the chronic kidney disease (CKD), to provide the finest healthcare services possible to users of e-health and m-health applications by presenting the IoTC services based on healthcare delivery system for the prediction and observation of CKD with its severity level. The suggested architecture gathers patient data from linked IoT devices and saves it in the cloud alongside real-time data, pertinent medical records that are collected from the UCI Machine Learning Repository, and relevant medical documents. We further use a Deep Neural Network (DNN) classifier to predict CKD and its severity. To boost the effectiveness of the DNN classifier, a Particle Swarm Optimization (PSO)-based feature selection technique is also applied. We compare the performance of the proposed model using different classification measures utilizing different classifiers. A Quick Flower Pollination Algorithm (QFPA)- (DNN)-based IoT and cloud-based CKD diagnosis model, is presented in this paper. The CKD diagnosis steps in the QFPA- DNN model involve data gathering, preparation, feature selection and classification stages. [ABSTRACT FROM AUTHOR]

Indoor localization for livestock is important as it facilitates effective monitoring and management of animals within confined spaces, such as barns or stables. By accurately tracking the position of individual animals, farmers and livestock managers can gain valuable insights into their behavior, health, and welfare. This information enables the early detection of potential issues, such as diseases or injuries, allowing for prompt intervention and treatment. While GPS sensors offer global position estimation, they are limited to outdoor environments and inherently exhibit inaccuracies of several meters. In indoor spaces, alternative sensors like lasers and cameras can estimate positions, but they necessitate maps and substantial computational resources to process complex algorithms. Presently, Wireless Networks (WN) are extensively accessible in indoor environments, providing efficient global localization with relatively low cost and computing demands. This paper presents a novel approach to estimate the location of cows in a given area using Deep Neural Networks (DNNs) applied to LQI data. This method aims to improve the efficiency of livestock management, particularly in large-scale farming operations, by enabling precise tracking and monitoring of individual animals. Our proposed model leverages data from wireless sensor networks (WSNs) and demonstrates promising results in terms of accuracy and computational efficiency. This study contributes to the ongoing research in smart agriculture and the application of advanced technologies in the livestock industry. [ABSTRACT FROM AUTHOR]

With the development of emerging information technology, the traditional management methods of marine fishes are slowly replaced by new methods due to high cost, time-consumption and inaccurate management. The update of marine fishes management technology is also a great help for the creation of smart cities. However, some new methods have been studied that are too specific, which are not applicable for the other marine fishes, and the accuracy of identification is generally low. Therefore, this paper proposes an ecological Internet of Things (IoT) framework, in which a lightweight Deep Neural Networks model is implemented as a image recognition model for marine fishes, which is recorded as Fish-CNN. In this study, multi-training and evaluation of Fish-CNN is accomplished, and the accuracy of the final classification can be fixed to 89.89%–99.83%. Moreover, the final evaluation compared with Rem-CNN, Linear Regression and Multilayer Perceptron also verify the stability and advantage of our method. [ABSTRACT FROM AUTHOR]

Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed, imaging resolution, and imaging flux. This paper proposes a deep neural network based on a generative adversarial network (GAN). The generator employs a U-Net-based network, which integrates DenseNet for the downsampling component. The proposed method has excellent properties, for example, the network model is trained with several different datasets of biological structures; the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging; and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets. In addition, experimental results showed that the method improved the resolution of caveolin-coated pits (CCPs) structures from 264 nm to 138 nm, a 1.91-fold increase, and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels. [ABSTRACT FROM AUTHOR]

This paper studies cluster dependence and synchronization in multilayer directed networks. Based on network quotient graphs, we provide a more efficient way to identify dependencies between clusters. By considering the relationships and interactions between clusters at a higher level of abstraction, this analysis can reduce the computational effort without requiring extensive computation on the original network. Furthermore, this paper investigates the impact of structural perturbations on network synchronization capabilities within a multilayer framework. Specifically, for the case where perturbations are applied to the dominant group, we study how changes in the network structure affect its cluster synchronization (CS) behavior. Finally, we employe a multilayer neural network model to validate the findings presented in this paper. [ABSTRACT FROM AUTHOR]

A novel ensemble machine learning approach for predicting energy consumption in smart appliances is presented in this paper. The main objective is minimizing the number of necessary sensors and improving the prediction accuracy at the same time. The proposed method combines the Fuzzy C-Means method with a multi-stream deep neural network to achieve this goal. The method focuses on prediction accuracy and aims to extract the minimum number of essential features from the dataset corresponding to the required sensors. These selected features are then scatter-reduced and homogenized into subsets. Each subset is used to train a cluster-specific deep neural network designed exclusively for that subset. The final prediction is obtained by computing the fuzzy-weighted sum of these cluster-specific network outputs. Numerical results show that the proposed prediction method outperforms conventional methods in terms of root mean square error and mean absolute percentage error criteria, despite using fewer sensors. This improvement can be attributed to the reduced dataset scatter, which improves the learning speed and model performance. Furthermore, the fuzzy combination of the outputs improves the final prediction accuracy. Overall, the proposed approach provides a more cost-effective and accurate solution for predicting the energy consumed by smart appliances. [ABSTRACT FROM AUTHOR]

Higher accuracy and meticulousness are highly demandable in modern industrial field during micro-machining performances by electrochemical discharge machining (ECDM) process. The paper deals with the experimental fuzzy logic control (FLC) analysis as well as artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) analysis during micro-channel fabrication on silica glass. A comparative analysis of FLC, ANN as well as ANFIS has been performed and experimental error prediction has been propounded to estimate minimum error possibilities such as mean absolute error (MAE), root mean square error (RMSE) and regression value (R). Computational time training dataset, minimum sample size and prediction time are also illustrated in this paper. In this paper, ANN, FLC and ANFIS models are analyzed for tool wear rate (TWR) and heat-affected zone (HAZ). 3D Rule Viewer and regression analysis as well as validation of test results and characteristics graph between performances with number of epochs of ANN model also are included in this paper for TWR and HAZ. Influence of process parameters like voltage, duty ratio, pulse frequency and electrolyte concentration on Surface Viewer of TWR and HAZ is also illustrated. It is found that ANFIS has great effectiveness of prediction of error during micro-ECDM process. [ABSTRACT FROM AUTHOR]

Deep learning is a popular topic among machine learning researchers nowadays, with great strides being made in recent years to develop robust artificial neural networks for faster convergence to a reasonable accuracy. Network architecture and hyperparameters of the model are fundamental aspects of model convergence. One such important parameter is the initial values of weights, also known as weight initialization. In this paper, we perform two research tasks concerned with the weights of neural networks. First, we develop three novel weight initialization algorithms inspired by the neuroscientific construction of the mammalian brains and then test them on benchmark datasets against other algorithms to compare and assess their performance. We call these algorithms the lognormal weight initialization, modified lognormal weight initialization, and skewed weight initialization. We observe from our results that these initialization algorithms provide state-of-the-art results on all of the benchmark datasets. Second, we analyze the influence of training an artificial neural network on its weight distribution by measuring the correlation between the quantitative metrics of skewness and kurtosis against the model accuracy using linear regression for different weight initializations. Results indicate a positive correlation between network accuracy and skewness of the weight distribution but no affirmative relation between accuracy and kurtosis. This analysis provides further insight into understanding the inner mechanism of neural network training using the shape of weight distribution. Overall, the works in this paper are the first of their kind in incorporating neuroscientific knowledge into the domain of artificial neural network weights. [ABSTRACT FROM AUTHOR]

Model pruning is one of the main methods of deep neural network model compression. However, the existing model pruning methods are inefficient, there is still a lot of redundancy in the network, and the pruning has a great impact on the accuracy. In addition, the traditional pruning process usually needs to fine-tune the network to restore accuracy, and fine-tuning has a limited effect on accuracy recovery, so it is difficult to achieve a high level of accuracy. In this paper, we propose a new neural network pruning framework: the channel sparsity is realized by introducing a scale factor, and the sparse network is pruned by setting a global threshold, which greatly improves the efficiency of pruning. After pruning, this paper proposes a rewind method to restore the accuracy, that is, save the weight after training, and then reload it on the network for training to restore the accuracy. In addition, we also study the best rewind point of the three networks. The experimental results show that our method significantly reduces the number of parameters and FLOPs without affecting or even improving the accuracy, and the rewind method proposed by us achieves a better accuracy recovery effect than fine-tuning. At the same time, we find that the epoch with the highest accuracy is the best rewind point, and the accuracy is the highest after saving its corresponding weight and retraining the model. [ABSTRACT FROM AUTHOR]

In this paper, we analyzed the deep neural network (DNN) model and proposed a DNN-based method to build the training model for professional farmers. This paper aims to construct the vocational farmer cultivation model and seek a better path for transforming farmers into new experienced farmers by analyzing each training body involved in the cultivation of vocational farmers and studying their respective problems and reasons. The conceptual and logical structures of the system database were designed, and MySQL was selected for database implementation to complete the information of professional farmers. The system network topology and logical architecture are created, and the functions of view, control, business logic and data access layers are divided. This paper combines the DNN with the vocational farmer training enhancement decision tree. The experimental results of this model are most intuitive and accurate. This paper reconstructs the neural network model using the global average pooling layer to better model the vocational farmer training model to replace the fully connected layer in the original convolutional neural network. At the same time, to make the network model produce a lower probability of overfitting, a dropout layer is added to the layer after the fully connected layer to improve the efficiency of the neural network further to enhance vocational farmer training. The experimental content of this paper provides a new research direction for the estimation of vocational farmer cultivation. The above modeling is used to improve the vocational farmer cultivation model and accelerate the process of vocational farmer cultivation. [ABSTRACT FROM AUTHOR]

EEG has been proved to be an effective tool for researchers' cognition and mental workload by detecting the changes of brain activity potential. The mental workload of pilots in aviation flight is closely related to the characteristics of flight tasks. The previous methods have problems such as lack of objectivity, low EEG analysis ability and lack of real-time analysis ability. In order to solve these problems, this paper proposes a multi-dimensional data fusion brain workload calculation method based on flight effect evaluation, which integrates vision, operational behavior and visual gaze, and classifies and analyzes them in combination with EEG data. This method evaluates the mental workload of pilots from three aspects: visual gaze behavior, control behavior and flight effect in the simulated flight experimental environment, and realizes a more objective mental workload analysis. Then, the synchronously collected EEG data are segmented and sampled to form a dataset, and an LSTM neural network model integrating attention mechanism is established, in which the attention mechanism is used to improve the feature processing ability of the network model for the classification of complex EEG data. After machine learning training, the final model can achieve 94% detection accuracy for 2-s EEG data, and has the ability of real-time analysis in the application environment. Compared with the previous similar LSTM model, the accuracy is improved by 6%, which also shows the effectiveness of the model. [ABSTRACT FROM AUTHOR]

The article discusses papers in the current issue of "International Journal of Information Technology & Decision Making," including a paper on Internet and Internet subsystem intelligence quotients (IQs) over search engines, a paper on Factor Neural Network (FNN) and a paper on a decision model for evaluating Cloud Computing Services.

This paper plans to implement a novel detection model of maliciously encrypted internet protocol network flow using the deep structured concept. The major processing levels are (i) data collection, (ii) feature extraction, (iii) optimal feature selection, and (iv) detection. In the beginning, the standard dataset is taken from online databases. The deep convolutional neural network (DCNN) is introduced for the deep feature extraction process. The accurate features are chosen by the crossover decision-based krill herd algorithm (CD-KHA) which helps to minimize the training complexity of the deep structured architecture. These selected features are given to the hybridized deep learning with long short-term memory (LSTM) and deep neural network (DNN). Here, the structural design of the model is improved by the same CD-KHA. Through the comparison and analysis, the accuracy rate of the offered method shows higher performance than the other baseline approaches. [ABSTRACT FROM AUTHOR]

Transfer-based attacks, a type of adversarial attack, have become a growing threat in recent years with the proliferation of cloud services. Deep neural networks that exploit human cognitive bias (Loosely Symmetric-Deep Neural Network, LS-DNN) are known as a defensive technique against transfer-based attacks. LS-DNN can prevent malfunctions caused by adversarial examples with a high probability by incorporating human learning characteristics into the neural network's nodes. However, maintaining accuracy against normal data and reducing Training Time is challenging. This paper proposes a new model called "LS+-DNN" inspired by the Dropout method to solve this problem. Evaluation experiments on two datasets show that the proposed model can achieve both in high dimensions. In addition, we analyze the proposed model focusing on the variance and confidence score of the training parameters of the proposed model. As a result, we point out that the confidence score is an important indicator of robust models against transfer-based attacks. [ABSTRACT FROM AUTHOR]

Recent advances in speaker embeddings promote a great development of speaker diarization. However, determining 'who spoke when' in the meeting scenarios is still challenging due to similar speaker voices and unknown speaker quantity. In this paper, this research proposes enhanced discriminative features for speaker diarization, including discriminative speaker-specific features based on Siamese networks, and a speaker re-verification method. With Siamese architecture, SiamTDNN, this research first explores latent representations which is capable of modeling intra-class and inter-class differences between speakers, by training with audio pairs. Then, the re-verification method is introduced with a local-global strategy to identify speakers in a multi-person talking scene. Our method provides a novel speaker embedding with enhanced discriminative power for disambiguated speakers and achieves an elevated upper bound on the number of speakers. The proposed speaker embedding achieved an EER of 1.1% and a minDCF of 0.1192 on VoxCeleb1 for the speaker verification task. Extensive experiments on AiShell-4, ICSI, AMI and VoxConverse demonstrate the effectiveness of the proposed method with an average DER reduction of 3% and an RTF of 0.0792. [ABSTRACT FROM AUTHOR]

This paper investigates the possibility for implementing machine learning-aided prediction in analyzing the buckling phenomena of ballasted railway tracks induced by extreme temperature. In this study, artificial neural networks (ANNs) have been developed to identify the relationship between various ballasted track conditions and outputs, namely safe temperature and buckling temperature. The variables included in the objective function of the optimization problems are the lateral resistance of ballasted track provided by ballast-sleeper interaction, torsional resistance provided by fastening systems, and misalignment of the track. Due to its complexity in parameter combinations, the objective of this study is to create predictive models with the aim of minimizing the usage of scarce resources. Thus, this paper is the first to develop a novel machine learning-aided prediction of railway track buckling due to extreme temperature. Comprehensively, all 353 datasets of the safe and buckling temperatures derived from previous finite element (FE) simulation results have been collected and trained. Note that the mean squared error (MSE) and the coefficient of determination ( R 2) are considered to quantify the performance of the ANN architectures. The optimal ANN architecture with a very high rate of accuracy has been determined and highlighted. Thus, the suggested neural network model can be applied conveniently to help estimate safe and buckling temperatures of the complex track models in order to improve track conditions and thus prevent track buckling in summer. [ABSTRACT FROM AUTHOR]

This paper introduces the use of an extra X current conveyor (EXCCII) for realizing logic operations, suited for mixed signal design, without necessitating separate digital blocks. The NOR and OR logic functions are thus shown to be realized using the current-mode analog building block operable at a low voltage. The use of ± 0. 7 5 V supply makes the new circuits operable at low voltage. The EXCCII bias current used in the design is 25 μ A. The input currents for defining logic 0 and logic 1 are, respectively, taken as 0 mA and 0.5 mA. The proposed circuits' delay is found to be 10 ns for low-to-high transition, while 2 ns for high-to-low transition for NOR gate under capacitive loading conditions. The use of the current-mode approach makes the new proposed circuit apt for current-mode signal processing. The new proposed logic function circuits are compatible with analog circuits, thus providing an easy merger for mixed signal systems design, paving the way to a modular design approach. As an extended application in artificial neural networks, the proposed circuit is shown to generate a sigmoid activation function with convincing results. Several results are included by varying the reference current, and the circuit's robustness aspect is also tested in the presence of fluctuation in the bias current of EXCCII. The novel approach of utilizing an analog building block for realizing digital functions is, therefore, verified with promising future applications. [ABSTRACT FROM AUTHOR]

This document serves as a preface to a special issue of the International Journal on Artificial Intelligence Tools (IJAIT). The articles in this issue build upon papers presented at the 36th International Florida AI Research Society Conferences in May 2023. The lead article introduces the theme of the special issue, which is explainable, fair, and Trustworthy AI. Other articles in the issue cover topics such as improving the bounds of a neuron's Boolean function, ethical explanations and transparency in AI systems, fairness measurement and mitigation in deep learning systems, and the dynamics of human-agent collaboration in ad hoc teams. The paper emphasizes the importance of positive and negative contrastive explanations in enhancing motivation and performance. It also addresses the challenges of fairness and reliability in predictive policing systems, with a focus on reducing bias related to race, age, and sex. The authors propose tailoring predictive models to specific causal queries and utilizing causal structure instead of relying solely on pre-trained models. The paper also explores how machine learning models can balance accuracy and understandability, as well as ensure fairness. The findings indicate that more complex models tend to outperform current guidelines, but fair models have lower complexity. The paper concludes by expressing gratitude to the reviewers for their contributions and support. [Extracted from the article]

Situational awareness is the ability of pilots to master flight status, which is of great significance to aviation flight safety and flight effect. According to the information processing model, the pilot's main steps of processing information are feeling, perception and execution. There are many problems in situation awareness analysis guided by visual gaze, such as large analysis deviation and high delay due to various influencing factors and complex characteristics. In order to solve this problem, this paper proposes a situation awareness assessment method based on artificial intelligence neural network and integrating visual gaze and flight control. First, this paper carries out simulated flight training experiments for flight cadets, and collects the data of eye movement, line of sight tracking, flight control and flight parameters of pilot cadets. Then, aiming at the flight subjects, a situation awareness analysis method based on events is established, and the situation awareness state in the experiment is evaluated and analyzed through the flight parameter data. Then, the visual gaze and flight control data are sliced in the unit of situational awareness events, and the data set is constructed. Finally, this paper designs a multi-channel sequence data classification and analysis model based on transformer, in which the situation awareness characteristics of visual gaze and operation behavior are analyzed through the attention mechanism. The experimental results show that the accuracy of situation awareness classification of the designed neural network model to the experimental data set is 96%, and can classify and evaluate the pilot's situation awareness state in 5 s. [ABSTRACT FROM AUTHOR]

The exchange rate dynamics affect national economies because fluctuations in currency prices distort their economic activity. To maintain an optimal exchange rate policy, these dynamics are crucial for countries with a trade economy. Due to the difficulty in predicting the participants behavior in some complex economic systems, which might throw the system into chaos, a novel stochastic exchange rate dynamics (SERD) model is introduced and investigated in this paper. Furthermore, a neural network approach is proposed and examined as a control chaos method to address the problem of stabilizing SERD through central bank interventions. Derived from power activation feed-forward neuronets, a 2-input weights-and-structure-determination-based neuronet (2I-WASDBN) model for controlling chaos in SERD under central bank intervention is presented in this paper. Six simulation experiments on stabilizing the chaotic behavior of the SERD model show that the 2I-WASDBN model outperforms other well-performing neural network models and that it is more effective than traditional methods for controlling chaos. By examining the volume of necessary intervention predicted by the 2I-WASDBN model, central banks can better comprehend exchange rate fluctuations and, in conjunction with their monetary policies, can make more precise decisions regarding the strategy of their interventions. [ABSTRACT FROM AUTHOR]

No abstract received. [ABSTRACT FROM AUTHOR]

A calendar of events related to computer science to be held between September 2009 and December 2010 is presented, which includes the 18th International Symposium on Methodologies for Intelligent Systems, the 19th International Conference on Artificial Neural Network, and the International Conference on Intelligent Computing.

With the increasing demand for security in many fastest growing applications, biometric recognition is the most prominent authentication system. User authentication through speech and face recognition is the important biometric technique to enhance the security. This paper proposes a speech and facial feature-based multi-modal biometric recognition technique to improve the authentication of any system. Mel Frequency Cepstral Coefficients (MFCC) is extracted from audio as speech features. In visual recognition, this paper proposes cascade hybrid facial (visual) feature extraction method based on static, dynamic and key-point salient features of the face and it proves that the proposed feature extraction method is more efficient than the existing method. In this proposed method, Viola–Jones algorithm is used to detect static and dynamic features of eye, nose, lip, Scale Invariant Feature Transform (SIFT) algorithm is used to detect some stable key-point features of face. In this paper, a research on the audio-visual integration method using AND logic is also made. Furthermore, all the experiments are carried out using Artificial Neural Network (ANN) and Support Vector Machine (SVM). An accuracy of 94.90% is achieved using proposed feature extraction method. The main objective of this work is to improve the authenticity of any application using multi-modal biometric features. Adding facial features to the speech recognition improve system security because biometric features are unique and combining evidence from two modalities increases the authenticity as well as integrity of the system. [ABSTRACT FROM AUTHOR]

In classification of fashion article images based on e-commerce image recommendation system, the classification accuracy and computation time cannot meet the actual requirements. Herein, for the first time to our knowledge, we present two diverse image recognition approaches for classification of fashion article images called random-forest method based on genetic algorithm (GA-RF) and Visual Geometry Group-Image Enhancement algorithm (VGG-IE) to solve classification accuracy and computation time problem. In GA-RF, the number of segmentation times and the decision trees are the key factors affecting the classification results. Improved genetic algorithm is introduced into the parameter optimization of forests to determine the optimal combination of the two parameters with minimal manual intervention. Finally, we propose six different Deep Neural Network architectures, including VGG-IE, to improve classification accuracy. The VGG-IE algorithm uses batch normalization and seven kinds training-data augmentation for ease and promotion of learning process. We investigate the effectiveness of the proposed method using Fashion-MNIST dataset and 70 000 pictures, Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 10 categories of image recognition, our VGG algorithm has the shortest computational time when it satisfies certain classification accuracy. VGG-IE approach has the highest classification accuracy. [ABSTRACT FROM AUTHOR]

Deep neural networks are vulnerable to adversarial examples. While there are many methods for generating adversarial examples using neural networks, creating such examples with high perceptual quality and improved training remains an area of active research. In this paper, we propose the Iterative Training Attack (ITA), a black-box attack based on a perturbation generative network for generating adversarial examples. ITA generates such examples by randomly initializing the perturbation generative network multiple times, iteratively training and optimizing a refined loss function. Compared to other neural network-based attacks, our proposed method generates adversarial examples with higher attack rates and within a small perturbation range even when the advanced defense is employed. Despite being a black-box attack, ITA outperforms gradient-based white-box attacks even under basic standards. The authors evaluated their method on a TRADES robust model trained with the MNIST dataset and achieved a robust accuracy of 92.46%, the highest among the evaluated methods. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have emerged as a prominent model in medical image segmentation, achieving remarkable advancements in clinical practice. Despite the promising results reported in the literature, the effectiveness of DNNs necessitates substantial quantities of high-quality annotated training data. During experiments, we observe a significant decline in the performance of DNNs on the test set when there exists disruption in the labels of the training dataset, revealing inherent limitations in the robustness of DNNs. In this paper, we find that the neural memory ordinary differential equation (nmODE), a recently proposed model based on ordinary differential equations (ODEs), not only addresses the robustness limitation but also enhances performance when trained by the clean training dataset. However, it is acknowledged that the ODE-based model tends to be less computationally efficient compared to the conventional discrete models due to the multiple function evaluations required by the ODE solver. Recognizing the efficiency limitation of the ODE-based model, we propose a novel approach called the nmODE-based knowledge distillation (nmODE-KD). The proposed method aims to transfer knowledge from the continuous nmODE to a discrete layer, simultaneously enhancing the model's robustness and efficiency. The core concept of nmODE-KD revolves around enforcing the discrete layer to mimic the continuous nmODE by minimizing the KL divergence between them. Experimental results on 18 organs-at-risk segmentation tasks demonstrate that nmODE-KD exhibits improved robustness compared to ODE-based models while also mitigating the efficiency limitation. [ABSTRACT FROM AUTHOR]

This paper presents an approach to improve the file fragment classification by proposing new features for classification and evaluating them on a dataset that includes both low- and high-entropy file fragments. High-entropy fragments, belonging to compressed and encrypted files, are particularly challenging to classify because they lack exploitable patterns. To address this challenge, the proposed feature vectors are constructed based on the byte frequency distribution (BFD) of file fragments, along with discrete Fourier transform coefficients and several randomness measures. These feature vectors are tested using three machine learning models: Support vector machines (SVMs), artificial neural networks (ANNs), and random forests (RFs). The proposed approach is evaluated on the govdocs1 dataset, which is freely available and widely used in this field, to enable reproducibility and fair comparison with other published research. The results show that the proposed approach outperforms existing methods and achieves better classification accuracy for both low- and high-entropy file fragments. [ABSTRACT FROM AUTHOR]

Item−item collaborative filtering is a sub-type of a recommender system that applies the items' similarities for recommending a new set of items to the user. Usually, a traditional recommender system utilizes items' ratings given by the user for deducing their preferences for recommending items. However, for the popularity of social platforms, users are now more familiar to write textual comments known as reviews about items based on their experiences rather than giving a rating, because rating any item limits a user to manifest the degree of satisfaction towards the item. As a result, the items' reviews become a precious source of information that could enhance the system's performance. In this paper, a novel recommendation approach has been proposed by applying a recurrent neural network to incorporate items' reviews with the recommender system. The recurrent neural network is a deep learning-based approach that can distribute the text to the relevant classes. Thus, the proposed approach has applied long short-term memory which is a modern formation of recurrent neural network that is applied to compute items' rating scores from the items' reviews. Then, the score is used to define the uniformity of items by using the Jaccard and Pearson correlation coefficient. The proposed approach has been evaluated by two familiar datasets named Yelp & Amazon datasets. Also, it is found that the proposed approach surpasses the traditional techniques and also improved the accuracy of prediction for the Yelp dataset by approximately in respect of 1.37% mean absolute error, 2.17% precision, 2.08% recall, and 2.11% f-measure. Furthermore, the proposed approach increased the recommendation performance for Amazon dataset on average in term of 1.34% mean absolute error, 2.09% precision, 2.53% recall, and 2.32% f-measure, respectively. [ABSTRACT FROM AUTHOR]

In the actual cotton planting environment, rapid change of light within a day, reflection from different backgrounds and different weather conditions can affect the imaging of cotton. Therefore, the crop object segmentation is difficult. Images which were captured in 12 natural scenes during cotton planting, including three weather conditions, such as sunny, cloudy and rainy and four soil cover conditions, such as white mulch film, black mulch film, straw and bare soil were regarded as the research objects. This paper presents the cotton leaf segmentation method based on Immune algorithm and pulse coupled neural networks (PCNN). First, 17 color components of white mulch film, black mulch film, straw, bare soil and cotton under the conditions of sunny, cloudy and rainy days were analyzed by using statistical method. Three high feasible and anti-light color components were selected by histogram statistical with mean gray value. Second, the optimal parameters of PCNN model and the optimal number of iterations were determined by using immune algorithm optimization theory, and the method in this paper was tested by using 1200 cotton images which were captured under 12 natural scenes. Finally, the test results showed that this method can distinguish cotton target region from soil and other background regions. Meanwhile, for reflection of mulch film, crop shadow, dark light, complex background, noise, etc. which are often appeared in natural scene, four image segmentation methods of Otsu algorithm, -Means algorithm, FCM algorithm and PCNN were compared with the proposed method in this paper. The segmentation result showed that the proposed method has good resistance to change of light and complex background. The average of the proposed method is 6.5%, significantly lower than that of other four methods and the performance is better than other four methods. This method can segment cotton images in different weather conditions and different backgrounds accurately under complex natural conditions. It will contribute to the subsequent growth status determination and pest diagnosis of cotton. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method for Lane Detection (LD) to reduce the impact of some issues associated with Autonomous Driving Cars (ADCs). It relies on the fact that self-driving will be the getaway of the transportation future. The ADC technology has expanded as it does not require human assistance. For ACD to be fully utilized, Machine Learning (ML) tools, such as Deep Neural Networks (DNNs), are required. However, ACD technology uses tools like a camera, GPS, Ultrasonic Sensor (US), and others, which work together to produce accurate ACDs. While adopting ACD, several issues need to be addressed such as carves, blurry, unclean, shadow, sunlight, pedestrians, and weather conditions. The paper proposes a new method to detect when a portion of a road line is missing due to weather conditions or old marking, protecting pedestrians and cars. For lane detection, the DNN model and Hough transform are used. CULane datasets including training and testing samples were used in the experiments. The results show high accuracy levels of 92%, indicating the ability to detect road lanes. [ABSTRACT FROM AUTHOR]

Heterogeneous multicore system could provide high flexibility for applications through integrating different types of cores. As the number of cores increases, more and more transistors are integrated which could lead to the rise of chip temperature, thus have a negative impact on the system performance. At present, the typical method to tackle this problem is dynamic voltage and frequency scaling (DVFS) which reduces the voltage and frequency to achieve cooling. However, DVFS will make the heterogeneous multicore system unable to take full advantage of its performance. This paper proposes a dynamic mapping method called TspDM which maximizes the system performance target under the premise of satisfying the temperature safety power. TspDM exploits the runtime performance counters of running threads to dynamically adjust thread mapping. Specifically, a lightweight Artificial Neural Network (ANN) model is proposed to obtain the thread-to-core type mapping when a remapping process is activated. Subsequently, TspDM determines the specific core locations of threads according to the number of threads mapped to a certain core type and the thermal safety power computation. The experimental results show that the proposed method is 21% better than that of PCMig while ensuring the thermal safety of heterogeneous platform. In addition, TspDM outperforms recent performance constrained and power constrained literature in terms of system throughput. [ABSTRACT FROM AUTHOR]

Financial fraud detection has been an urgent technical demand in cyberspace. It highly relies on clear extraction and deep representation toward complex relationships inside financial social networks. As consequence, this study combines both knowledge graph and deep learning to deal with such issue. Thus, an intelligent financial fraud detection model based on knowledge graph guidance and deep neural network is proposed in this paper. First, a new knowledge graph based on financially related systems is constructed, which includes multiple entities and relationships. Then, an adversarial learning-based neural network structure is formulated to extract financial attributes. Finally, the detection results can be output according to the extracted factors. Empirically, the proposal is implemented on a real-world dataset for performance evaluation. The experimental results show that it has higher accuracy and effectiveness compared to traditional fraud detection methods. The proposed detection model can not only identify known fraudulent behaviors, but also predict potential fraud patterns based on consumer habits, thereby improving the security and reliability of financial transactions. It can also update the knowledge graph in real-time, enabling it to cope with emerging fraud methods and variants. [ABSTRACT FROM AUTHOR]

An earthquake early-warning system (EEWS) is essential for preserving human life. In terms of disaster management and EQ risk reduction, quickly determining the earthquake's (EQ's) magnitude and position is important. To prevent an EQ catastrophe, these parameters can be transmitted over an IoT network. The Evolutionary Gravitational Neocognitron Neural Network (EGNNN), a novel technique for real-time earthquake parameter observation, is introduced in this paper to enhance earthquake early warning (EEW) systems. The proposed framework uses various sophisticated data processing methods to analyze publically accessible earthquake data from sources like the Japan Meteorological Agency. The Morphological Filtering Extended Empirical Wavelet Transformation (MFEEWT) method is first used to pre-process seismic waveform input, significantly lowering noise levels in the data. After that, from the pre-processed waveforms the relevant features are extracted via the Fast Discrete Curvelet Transform with Wrapping (FDCT-WRP) and a Stacked Autoencoder (SAE). The EGNNN, an innovative neural network model created for earthquake parameter prediction, specifically location and magnitude, uses these extracted features as input. The Osprey optimization algorithm (OOA) is employed to enhance the EGNNN model. A crucial component of EEW systems, dependable and quick alert delivery is ensured by the proposed system's integration with an Internet of Things (IoT) framework. The EGNNN swiftly evaluates earthquake parameters and sends this vital data to a centralized IoT system, enabling pertinent entities to act promptly. Performance evaluation is conducted on the Python platform, comparing the proposed technique with existing methods. The proposed method EGNNN-EPO-IoT achieves a higher warning time of 23.34%, 3.45%, and 7.86%; 12.23%, 32.21%, and 22.09% higher accuracy compared to the other existing techniques such as 3S-AE-CNN-EPO-IoT (3 sec-Autoencoder-Convolutional neural network-Earthquake parameter observation-IoT), XGB-EPO-IoT (Extreme Gradient Boosting-EPO-IoT), and SVM-EPO-IoT (Support Vector Machine-EPO-IoT). [ABSTRACT FROM AUTHOR]

Cloud and edge computing are necessary elements in the modern distributed network. To reflect the capacity variances of the system, stochastic capacities and costs of components (arcs and nodes) are considered such that stochastic capacity distributed networks (SCDNs) can be formed in the paper. To learn the capability of the SCDN for system monitoring and management, system reliability can be utilized which is defined as the probability of satisfying demands (data) under a budget for an SCDN. An exact-system reliability algorithm for system reliability is derived in advance for prudent management and decision-making. For immediate control and management, a deep neural network (DNN) architecture is proposed to create a prediction model for system reliability. Enough data points about SCDN information are generated and transformed into an appropriate format for training the prediction model. Note that the labels (system reliability) for all the data points would be calculated using the exact-system reliability algorithm. Necessary hyperparameters for determining the DNN of system reliability of the SCDN are also suggested. The model can be used for the future management of the distributed network. [ABSTRACT FROM AUTHOR]

Real-time images of faces captured in different spectrum bands are considered heterogeneous images. Heterogeneous Face Recognition (HFR) matches faces across domains and is crucial to public safety. This paper proposes an HFR approach based on Deep Neural Networks (DNN). Feature maps are extracted from two images, such as gallery and sketch images, using Squirrel Search Heterogeneous Convolutional-Capsule- Bidirectional Gated Recurrent Unit (S2HConv-Caps-BiGRU). As a method of efficiently recognizing faces, coupled representation similarity metric (CRSM) will use the measure for the similarity of two feature maps. The experimental results will be evaluated to state-of-the-art (SOTA) statistical measures in terms of accuracy, recall, Jaccard score, dice score, mean square error (MSE), image similarity, performance and root mean square error (RMSE). Compared to other SOTA, the model produces the best results. The accuracy value of a CUFS dataset is 98.7%. [ABSTRACT FROM AUTHOR]

With the growth in services supplied over the internet, network infrastructure has become more exposed to cyber-attacks, particularly Distributed Denial of Service (DDoS) attacks, which can easily cause the disruption of services. The key factor for fighting against these attacks is the earlier separation and detection of the traffic in networks. In this paper, a novel approach, named Half Autoencoder-Stacked DNNs (HAE-SDNN) model, is proposed. We suggest using a Stacked Deep Neural Networks (SDNN) model. as a deep learning model, in order to detect DDoS attacks. Our approach allows feature selection from a preprocessed dataset using a Half AutoEncoder (HAE), resulting in a final set of important features. These features are subsequently used to train the DNNs that are stacked together by applying Softmax layer to combine their outputs. Experiments were performed on a benchmark cybersecurity dataset, named CICDDoS2017, containing various DDoS attack types. The experimental results demonstrate that the introduced model attained an overall accuracy rate of 99.95%. Moreover, the HAE-SDNN model outperformed existing models, highlighting its superiority in accurately classifying attacks. [ABSTRACT FROM AUTHOR]