Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for monsoon region. We develop a deep neural network composed of convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the ECMWF-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including 1) quantile mapping, 2) support vector machine, and 3) convolutional neural network. To test the robustness of the model and its applicability in practical forecast, we apply the trained network for precipitation prediction forced by retrospective forecasts from ECMWF model. Compared to ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead time from 1 day up to 2 weeks. This superiority decreases along forecast lead time, as GCM’s skill in predicting atmospheric dynamics being diminished by the chaotic effect. At last, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is just slightly worse than the observed precipitation forced simulation (NSE=0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

This study introduces a comparative analysis of two deep learning (multilayer perceptron neural networks (MLP-NN) and the long short term memory networks (LSTMN)) models for transit travel time prediction. The two models were trained and tested using one-year worth of data for a bus route in Blacksburg, Virginia. In this study, the travel time was predicted between each two successive stations to all the model to be extended to include bus dwell times. Additionally, two additional models were developed for each category (MLP of LSTM): one for only segments including controlled intersections (controlled segments) and another for segments with no control devices along them (uncontrolled segments). The results show that the LSTM models outperform the MLP models with a RMSE of 17.69 sec compared to 18.81 sec. When splitting the data into controlled and uncontrolled segments, the RMSE values reduced to 17.33 sec for the controlled segments and 4.28 sec for the uncontrolled segments when applying the LSTM model. Whereas, the RMSE values were 19.39 sec for the controlled segments and 4.67 sec for the uncontrolled segments when applying the MLP model. These results demonstrate that the uncertainty in traffic conditions introduced by traffic control devices has a significant impact on travel time predictions. Nonetheless, the results demonstrate that the LSTMN is a promising tool that can has the ability to account for the temporal correlation within the data. The developed models are also promising tools for reasonable travel time predictions in transit applications.

Speech emotion recognition (SER) is a technology that can be applied in distance education to analyze speech patterns and evaluate speakers’ emotional states in real-time. It provides valuable insights and can be used to enhance the learning experience by enabling the assessment of instructors’ emotional stability, a factor that significantly impacts information delivery effectiveness. Students demonstrate different engagement levels during learning activities, and assessing this engagement is an important aspect of controlling the learning process and improving e-learning systems. An important aspect that may influence student engagement is the emotional states of their instructors. Accordingly, this research uses deep learning techniques to create an automated system for recognizing instructors’ emotions in their speech when delivering distance learning. This methodology entails integrating Transformer, convolutional neural network, and long short-term memory architectures into an ensemble to enhance SER. Feature extraction from audio data used Mel-frequency cepstral coefficients, chroma, Mel spectrogram, zero crossing rate, spectral contrast, centroid, bandwidth, roll-off, and root-mean square, with subsequent optimization processes adding noise to, conducting time stretching, and shifting the audio data. Notably, several Transformer blocks were incorporated, and a multi-head self-attention mechanism was employed to identify the relationships between the input sequence segments. The pre-processing and data augmentation methodologies significantly enhanced the precision of the results in that the model achieved accuracy rates of 96.3%, 99.86%, 96.5%, and 85.3% on the Ryerson Audio-Visual Database of Emotional Speech and Song, Berlin Database of Emotional Speech, Surrey Audio-Visual Expressed Emotion, and Interactive Emotional Dyadic Motion Capture datasets. Furthermore, it achieved 83% accuracy on another dataset created for this research—the Saudi Higher Education Instructor Emotions dataset. The results demonstrate this model’s considerable accuracy in detecting emotions in speech data across different languages and datasets.

Multivariate predictive analysis of the Stream-Water (SW) parameters (discharge, water level, temperature, dissolved oxygen, pH, turbidity, and specific conductance) is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the meteorological and climatic features have a significant impact on the temporal distribution of the SW variables in recent days making the SW variables forecasting even more complicated for diversified water-related issues. To predict the SW variables, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-informed analysis and prediction, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, a comprehensive Explorative Data Analysis (EDA) and feature engineering were performed to prepare the dataset to obtain the best performance of the predictive model. Long Short-Term Memory (LSTM) neural network regression model is trained using over several years of daily data to predict the SW variables up to one week ahead of time (lead time) with satisfactory performance. The performance of the proposed model is found highly adequate through the comparison of the predicted data with the observed data, visualization of the distribution of the errors, and a set of error matrices. Higher performance is achieved through the increase in the number of epochs and hyperparameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time SW variables prediction.

In cutting processes tool condition affects the quality of the manufactured parts. As such an essential component to prevent unplanned downtime and to assure machining quality is having information about the state of the cutting tool. The primary function of it is to alert the operator that the tool has reached or is reaching a level of ware beyond which behavior is unreliable. In this paper the tool condition is being monitored by analyzing the electric current on the main spindle via an artificial intelligence model utilizing a LSTM neural network. In the current study the tool is monitored while working on a cylindrical raw piece made of AA6013 aluminum alloy with a custom polycrystalline diamond tool, for the purposes of monitoring the ware of these tools. Spindle current characteristics were obtained using external measuring equipment to not influence the operation of the machine included in a larger production line. As a novel approach, an artificial intelligence model based on a LSTM neural network is utilized for the analysis of the spindle current obtained during a manufacturing cycle and assessing the tool ware range in real time. The neural network was designed and trained to notice significant char-acteristics of the captured current signal. The conducted research serves as a proof of concept for use of a LSTM neural network-based model as a method of monitoring the condition of cutting tools.

Creating intelligent systems capable of recognizing emotions is a difficult task, especially when looking at emotions in animals. This paper describes the process of designing a “proof of concept” system to recognize emotions in horses. This system is formed by two elements, a detector and a model. The detector is a fast region-based convolutional neural network that detects horses in an image. The model is a convolutional neural network that predicts the emotions of those horses. These two elements were trained with multiple images of horses until they achieved high accuracy in their tasks. 400 images of horses were collected and labeled to train both the detector and the model while 80 were used to validate the system. Once the two components were validated, they were combined into a testable system that would detect equine emotions based on established behavioral ethograms indicating emotional affect through head, neck, ear, muzzle and eye position. The system showed an accuracy of between 69% and 74% on the validation set, demonstrating that it is possible to predict emotions in animals using autonomous intelligent systems. Such a system has multiple applications including further studies in the growing field of animal emotions as well as in the veterinary field to determine the physical welfare of horses or other livestock.

The prediction of hydrological flows (rainfall-depth or rainfall-discharge) is becoming increasingly important in the management of hydrological risks such as floods. In this study, the Long Short-Term Memory (LSTM) network, a state-of-the-art algorithm dedicated to time series, is applied to predict the daily water level of lake Nokoue in Benin. This paper aims to provide an effective and reliable method enable of reproducing the future daily water level of Lake Nokoue, which is influenced by a combination of two phenomena: rainfall and river flow (runoff from the Ouémé River, the Sô River, the Porto-Novo lagoon, and the Atlantic Ocean). Performance analysis based on the forecasting horizon indicates that LSTM can predict the water level of Nokoué Lake up to a forecast horizon of t+10 days. Performance metrics such as Root Mean Square Error (RMSE), coefficient of correlation (R²), Nash-Sutcliffe Efficiency (NSE), and Mean Absolute Error (MAE) agree on a forecast horizon of up to t+3 days. The values of these metrics remain stable for forecast horizons of t+1 days, t+2 days, and t+3 days. The values of R² and NSE are greater than 0.97 during the training and testing phases in the Nokoué Lake basin. Based on the evaluation indices used to assess the model's performance for the appropriate forecast horizon of water level in the Nokoué lake basin, the forecast horizon of t+3 days is chosen for predicting future daily water levels.

With the escalation of size and complexity of modern Denial of Service attacks, there is a need for research in the context of Machine Learning (ML) used in attack execution and defense against such attacks. This paper investigates the potential use of ML in generating behavioral telemetry data using Long-Short Term Memory network and spoofing requests for the analyzed traffic to look legitimate. For this research, a custom testing environment was built, that listens for mouse and keyboard events and analyzes them accordingly. While the economic feasibility of this attack currently limits its immediate threat, advancements in technology could make it more cost-effective for attackers in the future. Therefore, proactive development of countermeasures remains essential to mitigate potential risks and stay ahead of evolving attack methods.

With the rapid development of technology and the advancement of Internet technology, various social networking platforms are gradually coming into people's view and occupying a higher and higher position. In the recommendation scenario, the user-item interaction naturally forms a bipartite heterogeneous graph structure and with the development of graph embedding and graph neural network technologies based on deep learning to process graph domain information, the combination of graph information and recommendation systems shows strong research potential and application prospects. The methodological improvement of the recommendation algorithm based on collaborative filtering takes advantage of the nature that user-items can form a bipartite graph in the recommendation scenario. The existing methods still have some shortcomings. The methods that only use weights or convolutional recurrent neural networks to implicitly model different historical behaviors lack explicit modeling of video switching relationships in serialized behaviors. The user's interest is changing all the time, so it is not possible to recommend based on the user's history, and it is necessary to consider both the long-term and short-term interest of the user according to the video content in order to achieve accurate recommendation of short videos. In this paper, we design a recommendation model based on graph neural network, which models users' long-term and short-term interests by two vector propagation methods, respectively.

Deep underground laboratories offer advantages for conducting high-precision observations of weak geophysical signals, benefitting from a low background noise level. It is both valuable and feasible to enhance strong, noisy ground electromagnetic (EM) field data using synchronously recorded underground EM signals, which typically exhibit a high signal-to-noise ratio. In this study, we propose an EM field reconstruction method employing a Long Short-Term Memory (LSTM) recurrent neural network with referenced deep underground EM observations. Initially, a deep learning model was developed to capture the time-varying features of underground multi-component EM fields using the LSTM recurrent neural network. Subsequently, this model was applied to process synchronously observed strong, noisy data from other conventional observation systems, such as those at surface, to achieve noise suppression through signal reconstructions. Both theoretical analysis and practical observational data suggest that the proposed method effectively suppresses noise and reconstructs clean EM signals. This method is efficient and time-saving, representing an effective approach to fully utilizing the advantages of deep underground observation data. Furthermore, this method could be extended to the processing and analysis of other geophysical data.

Accurately predicting electrical signals of three-phase Direct Torque Control (DTC) induction motors is crucial for optimal motor performance and effective condition monitoring. However, multiple DTC motors’ complexity and operating conditions’ variations pose challenges for traditional prediction methods. To overcome these challenges, we propose an innovative approach that combines Fast Fourier Transform (FFT) to transform electrical motor simulation data and a Bi-directional Long Short-Term Memory (Bi-LSTM) network to forecast processed motor data. By transforming the DTC induction motor signals from the time domain to the frequency domain, we enhance the capability of learning models to capture subtle differences and generate various input features. The Bi-LSTM model effectively captures both forward and backward dependencies in time series data, enabling accurate prediction of electrical signals. We evaluate the proposed approach using our simulated dataset and compare the proposed method to a state-of-the-art model, the Gated Recurrent Unit (GRU), demonstrating its effectiveness in improving the accuracy and reliability of induction motor signals forecasting. The finding provides valuable insights for advancing motor control and operation in industrial applications.

Objective: The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, poles and skis contact and swing time) in cross-country roller ski skating on the field, using a single deported inertial measurement unit (IMU). Methods: The developed method is based on long short-term memory neural networks to detect poles and skis initial and final contact with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as reference system. Results: The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with an accuracy ranging from 49 to 55 ms and the corresponding inner-cycles parameters were calculated with a precision of 63 to 68 ms. The method detected 95% of the events for the poles and 87% of the events for the skis. Conclusion: The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller ski skating showing the potential of using a deported IMU to estimate different spatio-temporal parameters of human locomotion.

River flow prediction is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the climatic variables e.g., precipitation has a significant impact on the temporal distribution of the river discharge in recent days making the discharge forecasting even more complicated for diversified water-related issues e.g., flood prediction and irrigation planning. To predict the discharge, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-driven predictions, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, Long Short-term Memory (LSTM) neural network regression model is trained using over 80 years of daily data to forecast the discharge time series up to 3 days ahead of time. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.09. Higher performance is achieved through the increase in the number of epochs and hyper parameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time river discharge prediction.

Detecting and understanding emotions is critical for our daily activities. As emotion recognition (ER) systems develop, we start looking at more difficult cases than just acted adult audio-visual speech. In this work, we investigate automatic classification of audio-visual emotional speech of children. Our interest is, specifically, in the improvement of the utilization of the cross-modal relationships between the selected modalities: video and audio. To underscore the importance of developing ER systems for the real-world environment, we present a corpus of children’s emotional audio-visual speech that we collected. We select a state-of-the-art model as a baseline for the purposes of comparison and present several modifications focused on a deeper learning of the cross-modal relationships. By conducting experiments with our proposed approach and the selected baseline model, we observe a relative improvement in performance by 2%. Finally, we conclude that focusing more on the cross-modal relationships may be beneficial for building ER systems for child-machine communications and the environments where qualified professionals work with children.

MIMO (multiple-input multiple-output) radar provides much more flexibility than the traditional radar for its ability to realize far more observation channels than the actual number of T/R (transmit and receive) elements. Designing the array of MIMO imaging radar, the commonly used virtual array theory generally assumes that all elements are placed on the same line. However, due to the physical size of the antennas and coupling effect between T/R elements, a certain height difference between T/R arrays is essential, resulting in the defocusing of edge points of the scene. On the other hand, the virtual array theory implies far-field approximation, leading to inevitable high grating lobes in the imaging result of near-field edge points of the scene observed by common MIMO array. To tackle these problems, this paper derives the relationship between target’s PSF (point spread function) and pattern of T/R arrays, by which the design criterion of near-field imaging MIMO array is presented. Firstly, the proper height between T/R arrays is designed to focus the near-field edge points well. Secondly, the far-field array is modified to suppress the grating lobes in the near-field area. Finally, the validity of the proposed methods is verified by simulations and an experiment.

The global demand for energy has been steadily increasing due to population growth, urbanization, and industrialization. Numerous researchers worldwide are striving to create precise forecasting models for predicting energy consumption to manage supply and demand effectively. In this research, a time-series forecasting model based on multivariate multilayered long short-term memory (LSTM) is proposed for forecasting energy consumption and tested using data obtained from commercial buildings in Melbourne, Australia: the Advanced Technologies Center, Advanced Manufacturing and Design Center, and Knox Innovation, Opportunity, and Sustainability Center buildings. This research specifically identifies the best forecasting method for subtropical conditions and evaluates its performance by comparing it with the most used methods at present, including LSTM, bidirectional LSTM, and linear regression. The proposed multivariate multilayered LSTM model was assessed by comparing mean average error (MAE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) values with and without labeled time. Results indicate that the proposed model exhibits optimal performance with improved precision and accuracy. Specifically, the proposed LSTM model achieved a decrease in MAE by 30%, RMSE by 25%, and MAPE by 20% compared to the LSTM method. Moreover, it outperformed the bidirectional LSTM method with a reduction in MAE by 10%, RMSE by 20%, and MAPE by 18%. Furthermore, the proposed model surpassed linear regression with a decrease in MAE by 2%, RMSE by 7%, and MAPE by 10%. These findings highlight the significant performance increase achieved by the proposed multivariate multilayered LSTM model in energy consumption forecasting.

Data augmentation techniques recently gained more adoption in speech processing, including speech emotion recognition. Although more data tends to be more effective, there may be a trade-off in which more data will not provide a better model. This paper reports experiments on investigating the effects of data augmentation in speech emotion recognition. The investigation aims at finding the most useful type of data augmentation and the number of data augmentations for speech emotion recognition. The experiments are conducted on the Japanese Twitter-based emotional speech corpus. The results show that for speaker-independent data, two data augmentations with glottal source extraction and silence removal exhibited the best performance among others, even with more data augmentation techniques. For the text-independent data (including speaker and text-independent), more data augmentations tend to improve speech emotion recognition performances. The results highlight the trade-off between the number of data augmentation and the performance of speech emotion recognition showing the necessity to choose a proper data augmentation technique for a specific application.

Objectives: In order to solve the problem that most of the existing research focuses on the binary tactile attributes of objects,which ignores the tactile attribute strength and category recognition,an attribute strength and category recognition method based on convolutional neural network matrix-label is proposed. Methods:Firstly,in the data preparation stage,we preprocess the raw data and determine the matrix labels to build the haptic dataset.Secondly,in the feature extraction stage,we fuse the haptic data of two fingers and use the convolutional neural network to extract the attribute strength features.Finally,in the attribute strength and category recognition stage,all channel haptic data is fused to predict the attribute strength and category.Results:We compared with the multi-label convolutional neural network method in terms of elastic strength,hardness strength and category,and compared the attribute strength recognition capabilities of the two methods using novel objects outside the haptic dataset.The results show that the accuracy of the last 20 iterations of the matrix-label method has an average elastic strength of 96.73%,hardness strength of 97.34%,and category of 96.67%.The performance is better.When the Euclidean distance between the prediction of the novel object and the real label is less than 1,the accuracy of the elastic strength is best to reach 100%,and the hardness strength is best to reach 100%.The performance is better. Conclusions:The effectiveness of the method has been verified.Comparing with the convolutional neural network method,our method can effectively recognize the attribute strength and category of objects.

The deaf-mute and individuals with hearing disabilities who communicate through sign language should not be overlooked or excluded. It is a social responsibility to strive for an inclusive world without inequality. Advances in technology offer various solutions to address the communication gap, one of which is the use of computer-based sign language recognition systems. This project proposes a Malaysian Sign Language recognition model utilizing MobileNetV1, a convolutional neural network-based algorithm, to interpret sign language in real-time settings through a website application using Streamlit. The outcome of the model test shows that it has achieved a recognition rate of 96 percent. Although the proposed model has demonstrated the ability to recognize sign language, it is suggested that further improvement can be achieved by enhancing the quality and diversity of the dataset. The implementation of a more comprehensive dataset would lead to improved performance and increased accuracy of the model. This project underscores the importance of considering and accommodating the needs of the deaf-mute and individuals with hearing disabilities and highlights the potential of technology to bridge communication barriers and achieve a more inclusive society.

Significant progress has made in pattern recognition technology. However, one obstacle that has not yet overcome is the recognition of words in the Brahmi script, specifically the identification of characters, compound characters, and word. This study proposes the use of the deep convolutional neural network with dropout to recognize the Brahmi words. This study also proposed a DCNN for Brahmi word recognition and a series of experiments are performed on standard Brahmi dataset. The practical operation of this method was systematically tested on accessible Brahmi image database, achieving 92.47% recognition rate by CNN with dropout respectively which is among the best while comparing with the ones reported in the literature for the same task.

Deep Learning (DL) has made significant advances in computer vision with the advent of Vision Transformers (ViT). Unlike Convolutional Neural Networks (CNNs), ViTs use self-attention to extract both local and global features from image data, and then use residual connections to feed these features directly into a fully networked multilayer perceptron head. In hospitals, hematologists prepare peripheral blood smears (PBSs) and read them under a medical microscope to detect abnormalities in blood counts such as leukemia. However, this task is time-consuming and prone to human error. This study investigates the transfer learning process of Google ViT and ImageNet CNNs to automate the reading of PBSs. The study used two online PBS datasets, PBC and BCCD, and transferred them into balanced datasets to investigate the influence of data amount and noise immunity on both neural networks. The PBC results show that Google ViT is an excellent DL neural solution for data scarcity. The BCCD results show that Google ViT is superior to ImageNet CNNs in dealing with unclean, noisy image data because it is able to extract both global and local features and use residual connections, despite the additional time and computational overhead.

The electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way, failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes to perform a failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The Long Short-Term Memory (LSTM) model will be evaluated to obtain a forecast result that can be used by the electric power utility to organize the maintenance teams. The Wavelet transform shows to be promising in improving the predictive ability of the LSTM, making the Wavelet LSTM model suitable for the study at hand. The results show that the proposed approach has better results regarding the evaluation of the error in prediction and has robustness when a statistical analysis is performed.

Accurate forecasts of ocean waves energy can not only reduce costs for investment but it is also essential for management and operation of electrical power. This paper presents an innovative approach based on the Long Short Term Memory (LSTM) to predict the power generation of an economical wave energy converter named “Searaser”. The data for analyzing is provided by collecting the experimental data from another study and the exerted data from numerical simulation of searaser. The simulation is done with Flow-3D software which has high capability in analyzing the fluid solid interactions. The lack of relation between wind speed and output power in previous studies needs to be investigated in this field. Therefore, in this study the wind speed and output power are related with a LSTM method. Moreover, it can be inferred that the LSTM Network is able to predict power in terms of height more accurately and faster than the numerical solution in a field of predicting. The network output figures show a great agreement and the root mean square is 0.49 in the mean value related to the accuracy of LSTM method. Furthermore, the mathematical relation between the generated power and wave height was introduced by curve fitting of the power function to the result of LSTM method.

Modeling brain dynamics to better understand and control complex behaviors underlying various cognitive brain functions are of interests to engineers, mathematicians, and physicists from the last several decades. With a motivation of developing computationally efficient models of brain dynamics to use in designing control-theoretic neurostimulation strategies, we have developed a novel data-driven approach in a long short-term memory (LSTM) neural network architecture to predict the temporal dynamics of complex systems over an extended long time-horizon in future. In contrast to recent LSTM-based dynamical modeling approaches that make use of multi-layer perceptrons or linear combination layers as output layers, our architecture uses a single fully connected output layer and reversed-order sequence-to-sequence mapping to improve short time-horizon prediction accuracy and to make multi-timestep predictions of dynamical behaviors. We demonstrate the efficacy of our approach in reconstructing the regular spiking to bursting dynamics exhibited by an experimentally-validated 9-dimensional Hodgkin-Huxley model of hippocampal CA1 pyramidal neurons. Through simulations, we show that our LSTM neural network can predict the multi-time scale temporal dynamics underlying various spiking patterns with reasonable accuracy. Moreover, our results show that the predictions improve with increasing predictive time-horizon in the multi-timestep deep LSTM neural network.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

To address the challenge of recognizing ship states accurately amidst the complexities of marine environments, this study proposes a novel ship state recognition approach leveraging a graph convolutional neural network (GCNN). Initially, the method extracts canonical and efficient ship motion trajectories from AIS data. Subsequently, a state recognition network tailored for ship motion trajectories is devised and implemented employing graph convolution. Notably, the accuracy of this model is enhanced through the introduction of novel weights and optimization of the Adj parameter. Experimental evaluations conducted on a ship state dataset demonstrate significant performance improvements. Specifically, the proposed recognition network achieves a recognition accuracy of 98.3% for regulated ship trajectories, marking an impressive 8.4% enhancement over traditional convolutional neural networks. This advancement holds promise for enhancing ship state recognition accuracy across diverse maritime applications including maritime supervision, navigation safety, and ship management.

herein, we have compared the performance of SVM and MLP in emotion recognition using speech and song channels of the RAVDESS dataset. We have undertaken a journey to extract various audio features, identify optimal scaling strategy and hyperparameter for our models. To increase sample size, we have performed audio data augmentation and addressed data imbalance using SMOTE. Our data indicate that optimised SVM outperforms MLP with an accuracy of 82 compared to 75%. Following data augmentation, the performance of both algorithms was identical at ~79%, however, overfitting was evident for the SVM. Our final exploration indicated that the performance of both SVM and MLP were similar in which both resulted in lower accuracy for the speech channel compared to the song channel. Our findings suggest that both SVM and MLP are powerful classifiers for emotion recognition in a vocal-dependent manner.

In recent years, with the popularity of smart mobile devices, the interaction between devices and users, especially in the form of voice interaction, has become increasingly important. If smart devices can understand more users' emotional states through voice data, more customized services can be provided for users. This paper proposes a novel machine learning model for speech emotion recognition, which combines convolutional neural networks (CNN), long short-term memory neural networks (LSTM), and deep neural networks (DNN), called CLDNN. To make the designed system can recognize the audio signal closer to the human auditory system does, this article uses the Mel frequency cepstral coefficients (MFCCs) of audio data as the input of the machine learning model. First, the MFCCs of the voice signal is extracted as the input of the model, and the feature values of the data are calculated using several local feature learning blocks (LFLB) composed of one-dimensional CNN. Because the audio signals are time-series data, the feature values obtained from LFLBs then input into LSTM layer to enhance the learning on time-series level. Finally, fully connected layers are used for classification and prediction. Three databases RAVDESS, EMO-DB and IEMOCAP are used for the experiments in this paper. The experimental results show that the proposed method can improve the accuracy compared to other related researches in speech emotion recognition.

Accurate and robust deep learning models for facial expression recognition are challenging to achieve, given the diversity of human faces and variations in images, including different facial poses and lighting conditions. In this work, we proposed a clock-driven convolutional Spiking Neural Network (SNN) and STDP fine-tune architecture, meticulously calibrated its hyperpa-rameters, and experimented with various optimization methods. The best model resulted was trained and evaluated on the Fer2013 and FER+ database, obtaining an accuracy of 61.87% and 79.97% without requiring auxiliary training data or face registration. To our best knowledge, the proposed SNN achieved comparable accuracy to CNNs of similar depth and possessed advantages of low energy consumption and high computational efficiency. The computational efficiency of the proposed SNN is approximately three times that of CNNs. Along with this, we introduced the very recent cumulative spike guided encoder visualization technique and revealed the strong encoding capability of the proposed SNN.

Human and Computer interaction has been a part of our day-to-day life. Speech is one of the essential and comfortable ways of interacting through devices as well as a human being. The device, particularly smartphones have multiple sensors in camera and microphone, etc. speech recognition is the process of converting the acoustic signal to a smartphone as a set of words. The efficient performance of the speech recognition system highly enhances the interaction between humans and machines by making the latter more receptive to user needs. The recognized words can be applied for many applications such as Commands & Control, Data entry, and Document preparation. This research paper highlights speech recognition through ANN (Artificial Neural Network). Also, a hybrid model is proposed for audio-visual speech recognition of the Tamil and Malay language through SOM (Self-organizing map0 and MLP (Multilayer Perceptron). The Effectiveness of the different models of NN (Neural Network) utilized in speech recognition will be examined.

In this work, a novel approach is presented for the multivariate prediction of hydrological variables, employing a specialized type of recurrent neural network (RNN) known as the long-term memory network (LSTM).The central objective is to develop a flood prediction model using data collected from two hydrological stations situated along the Atrato River in the Choc´o Department, Colombia. The interconnected variables of water level, water flow, and water precipitation are analyzed in this model to enhance flood prediction accuracy. The LSTM model, integrated into an RNN structure, is designed to capture the complex dynamics and cross-correlations inherent in these hydrological variables. Validation involves a comparison with linear and nonlinear Nonlinear AutoRegressive with eXogenous input (NARX) models, considering factors such as estimation error and computational time. Additionally, the study conducts further analysis for water level prediction under two scenarios: utilizing only outflow and inflow measurements or predicting outflow alongside measuring inflow, with the objective of utilizing the proposed approach as a flood early warning system. † This article is a revised and expanded version of a paper entitled Multivariable NARX based Neural Networks Models for Short-term Water Level Forecasting, which was presented at International Conference on Time Series and Forecasting (ITISE-2023), Gran Canaria, Spain, 12th-14th July, 2023.

Traffic congestion and frequent traffic accidents have become main problems affecting urban traffic. Effective location prediction of vehicle trajectory can help alleviate traffic congestion, reduce the occurrence of traffic accidents, and optimize the urban traffic system. Vehicle trajectory is closely related to the surrounding Points of Interest (POI). POI can be considered as the spatial feature and can be fused with trajectory points to improve prediction accuracy. A Local Dynamic Graph Spatiotemporal- Long Short-Term Memory (LDGST-LSTM) is proposed in this paper to extract and fuse the POI knowledge and realize next location prediction. POI semantic information is learned by constructing the traffic knowledge graph, and spatial and temporal features are extracted by combining Graph Attention Network (GAT) and temporal attention mechanism. Moreover, the weights of POI that influence location prediction are visualized to improve the interpretability of the proposed model. The effectiveness of LDGST-LSTM is verified on two datasets, including Chengdu taxi trajectory data in October 2018 and August 2014. The accuracy and robustness of the proposed model are significantly improved compared with the benchmark models.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.

This study proposes a machine-learning-based framework for detecting mechanical damage in pipelines, utilizing physics-informed datasets collected from simulations for mechanical damage. The framework provides an effective workflow from dataset generation to damage detection and identification for three types of pipeline events: welds, clamps, and corrosion defects. While the study initially focused on optimizing the CNN structure using various advanced optimizers, it also investigated the impact of sensing systems on data classification and the effect of noise on classification performance. The study's analysis highlights the importance of selecting the appropriate sensing system for the specific application. The authors also found that the proposed framework is robust to experimentally relevant levels of noise, suggesting its applicability in real-world scenarios where noise is present. Overall, this study contributes to the development of a more reliable and effective method for detecting mechanical damage in pipelines. The proposed framework provides an effective workflow for damage detection and identification, and the findings on the impact of sensing systems and noise on classification performance add to its robustness and reliability.

We study the short−term memory capacity of ancient readers of the original New Testament written in Greek, of its translations to Latin and modern languages. To model the short–term capacity, we have considered the number of words per interpunctions, the “word interval” , because this parameter can model how the human mind memorizes “chunks” of information. Since can be calculated for any alphabetical text, we can perform experiments − otherwise impossible − with ancient readers by studying the literary works they used to read. The “experiments” compare the of texts of a language/translation to those of another language/translation by measuring the minimum average probability of finding joint readers (those who can read both texts because of their similar short–-term memory capacity) and by defining an “overlap index”. We also define a population of universal readers who can read any the New Testament written in alphabetical language. More than 50% of the readers of specific languages overlap with the universal readers with probability . Future work is vast, with many research tracks, because alphabetical literatures are very large and allow many experiments, such as comparing authors, translations or even texts written by artificial intelligence tools.

This paper proposes an encryption scheme for high pixel density images. Based on the application of the quantum random walk algorithm, the Long short-term memory (LSTM) can effectively solve the problem of low efficiency of the quantum random walk algorithm in generating large-scale pseudorandom matrices, and further improve the statistical properties of the pseudorandom matrices required for encryption. The LSTM is then divided into columns and fed into the LSTM in order for training. Due to the randomness of the input matrix, the LSTM cannot be trained effectively, so the output matrix is predicted to be highly random. The LSTM prediction matrix of the same size as the key matrix is generated based on the pixel density of the image to be encrypted, which can effectively complete the encryption of the image. In the statistical performance test, the proposed encryption scheme achieves an average information entropy of 7.9992, an average number of pixels changed rate (NPCR) of 99.6231%, an average uniform average change intensity (UACI) of 33.6029% and an average correlation of 0.0032. Finally, various noise simulation tests are also conducted to verify its robustness in real-world applications where common noise and attack interference are encountered.

Nowadays, and with the mechanization of life, speech processing has become so crucial for the interaction between humans and machines. Deep neural networks require a database with enough data for training. The more features are extracted from the speech signal, the more samples are needed to train these networks. Adequate training of these networks can be ensured when there is access to sufficient and varied data in each class. If there is not enough data; it is possible to use data augmentation methods to obtain a database with enough samples. One of the obstacles to developing speech emotion recognition systems is the Data sparsity problem in each class for neural network training. The current study has focused on making a cycle generative adversarial network for data augmentation in a system for speech emotion recognition. For each of the five emotions employed, an adversarial generating network is designed to generate data that is very similar to the main data in that class, as well as differentiate the emotions of the other classes. These networks are taught in an adversarial way to produce feature vectors like each class in the space of the main feature, and then they add to the training sets existing in the database to train the classifier network. Instead of using the common cross-entropy error to train generative adversarial networks and to remove the vanishing gradient problem, Wasserstein Divergence has been used to produce high-quality artificial samples. The suggested network has been tested to be applied for speech emotion recognition using EMODB as training, testing, and evaluating sets, and the quality of artificial data evaluated using two Support Vector Machine (SVM) and Deep Neural Network (DNN) classifiers. Moreover, it has been revealed that extracting and reproducing high-level features from acoustic features, speech emotion recognition with separating five primary emotions has been done with acceptable accuracy.

Recognition of the human interaction on the unconstrained videos taken from cameras and remote sensing platforms like a drone is a challenging problem. This study presents a method to resolve issues of motion blur, poor quality of videos, occlusions, the difference in body structure or size, and high computation or memory requirement. This study contributes to the improvement of recognition of human interaction during disasters such as an earthquake and flood utilizing drone videos for rescue and emergency management. We used Support Vector Machine (SVM) to classify the high-level and stationary features obtained from Convolutional Neural Network (CNN) in key-frames from videos. We extracted conceptual features by employing CNN to recognize objects from first and last images from a video. The proposed method demonstrated the context of a scene, which is significant in determining the behaviour of human in the videos. In this method, we do not require person detection, tracking, and many instances of images. The proposed method was tested for the University of Central Florida (UCF Sports Action), Olympic Sports videos. These videos were taken from the ground platform. Besides, camera drone video was captured from Southwest Jiaotong University (SWJTU) Sports Centre and incorporated to test the developed method in this study. This study accomplished an acceptable performance with an accuracy of 90.42%, which has indicated improvement of more than 4.92% as compared to the existing methods.

Coastal wave modeling and forecasting are essential in oceanography, sustainable marine energy, and ocean engineering. Precise forecasting of wave speed and direction are crucial for offshore operations, marine energy, risk management, environmental management, coastal and sustainable maritime management. The coastline of Brunei Darussalam can generate between 15 and 126 Giga Watt of wave energy. In this experimental research, we used two numerical approaches, the finite difference, and spectral element methods, to model and simulate wave speed and direction. We calculated the mean error between numerical and analytical solutions. We proposed a novel, promising, univariate time series forecasting model by combining the Long Short-Term (LSTM) with KerasTuner hyperparameters tuning and optimization techniques. This method helps us to improve the accuracy and efficiency of time-series forecasting.. The experimental data was computed from high-precision Acoustic Doppler Current Profiler (ADCP) sensor data. This research is part of the preliminary feasibility analysis of wave energy production in Brunei Darussalam and net zero commitment for a sustainable environment. Seven independent forecast experiments were performed for wave speed and direction in degree and radian units for 1, 3, 6, 8, 10, 12, and 24 hours. Mean squared error (MSE) was adopted as a metric for both training and testing. The experimental results reveal that the wave speed forecast has the lowest MSE compared to direction, regardless of the unit of measure, but has a longer duration. In addition, the direction forecast in the degree unit has the lowest errors compared to the unit of radians; the latter has a longer running time than the former. The model has delivered optimal results throughout the experiments with minor training and test errors. We conducted a thorough evaluations on two benchmark time series datasets, which include the study dataset and air quality index dataset, to validate the performance of the proposed model with other models. The proposed model outperforms cutting-edge forecasting models, such as the conventional LSTM, ARIMA, and Prophet. The model has the slightest forecast error compared to the existing literature’s result.

A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF) in this article. The proposed model integrates radial basis function neural network (RBFNN), support vector regression (SVR), and adaptive annealing learning algorithm (AALA). In the proposed methodology, firstly, the initial structure of RBFNN is determined by using SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVR-RBFNN). In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO) is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from Taiwan Power Company (TPC). Simulation results reveal that the proposed AALA-SVR-RBFNN can achieve a better load forecasting precision as compared to various RBFNNs.

Modelling both long and short-term user interests from historical data is crucial for accurate recommendations. However, unifying these metrics across multiple application domains can be challenging, and existing approaches often rely on complex, intertwined models which can be difficult to interpret. To address this issue, we propose a lightweight, plug-and-play interest enhancement module that fuses interest vectors from two independent models. After analyzing the dataset, we identify deviations in the recommendation performance of long and short-term interest models. To compensate for these differences, we use feature enhancement and loss correction during training. In the fusion process, we explicitly split long-term interest features with longer duration into multiple local features. We then use a shared attention mechanism to fuse multiple local features with short-term interest features to obtain interaction features. To correct for bias between models, we introduce a comparison learning task that monitors the similarity between local features, short-term features, and interaction features. This adaptively reduces the distance between similar features. Our proposed module combines and compares multiple independent long-term and short-term interest models on multiple domain datasets. As a result, it not only accelerates the convergence of the models but also achieves outstanding performance in challenging recommendation scenarios.

The Covid-19 pandemic and the subsequent implementation of lockdown measures have significantly impacted global electricity consumption, necessitating accurate energy consumption forecasts for optimal energy generation and distribution during a pandemic. In this study, we propose a new forecasting model called the Multivariate Multilayered LSTM with Covid-19 case injection ($\proposedModel$) for improved energy forecast during the next occurrence of a similar pandemic. We utilize data from commercial buildings in Melbourne, Australia during the Covid-19 pandemic to predict energy consumption and evaluate the model's performance against commonly used methods such as LSTM, Bi-LSTM, Linear Regression, Support Vector Machine and the previously published work of Multilayered LSTM (M-LSTM). The proposed forecasting model was analyzed using the following metrics of mean percent absolute error (MPAE), normalized root mean square error (NRMSE), and $R^2$ score values. The model $\proposedModel$ demonstrates superior performance, achieving the lowest MPAE values of 0.061, 0.093, and 0.158 for data sets from 3 different buildings, respectively. Our results highlight the improved precision and accuracy of the model, providing valuable information for energy management and decision-making during the challenges posed by the occurrence of a pandemic like Covid-19 in the future.

Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains where real-world time series data often exhibit complex, non-linear patterns. Our approach advocates for utilizing Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models for precise time series forecasting. To ensure a fair evaluation, we compare the performance of our proposed approach with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM, Bi-LSTM, and other machine learning methods are implemented for a comprehensive assessment. Experimental results consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. Addressing the imbalance between activations by consumer and prosumer groups, our predictions show superior performance compared to several traditional forecasting methods, such as the Autoregressive Integrated Moving Average model (ARIMA) and Seasonal Autoregressive Integrated Moving Average model (SARIMA). Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data.

This paper proposes two max-pooling engines, named the RTB-MAXP engine and the CMB-MAXP engine, with a scalable window size parameter for FPGA-based convolutional neural network (CNN) implementation. The max-pooling operation for the CNN can be decomposed into two stages, i.e., a horizontal axis max-pooling operation and a vertical axis max-pooling operation. These two one-dimensional max-pooling operations are performed by tracking the rank of the values within the window in the RTB-MAXP engine and cascading the maximum operations of the values in CMB-MAXP engine. Both the RBM-MAXP engine and the CMB-MAXP engine were implemented using VHSIC Hardware Description Language (VHDL) and verified by simulations. They have been employed for and tested in our CNN accelerator targeting at the CNN model YOLOv4-CSP-S-Leaky for object detection.

Working memory refers to the capability of the nervous system to selectively retain short-term memories in an active state. The long-standing viewpoint is that neurons play an indispensable role and working memory is encoded by synaptic plasticity. Furthermore, some recent studies have shown that calcium signaling assists the memory processes and the working memory might be affected by the astrocyte density. Over the last few decades, growing evidence has also revealed that astrocytes exhibit diverse coverage of synapses which are considered to participate in neuronal activities. However, very little effort has yet been made to attempt to shed light on the potential correlations between these observations. Hence, in this article we will leverage a computational neuron-astrocyte model to study the short-term memory performance subject to various astrocytic coverage and we will demonstrate that the short-term memory is susceptible to this factor. Our model may also provide plausible hypotheses for the various sizes of calcium events as they are reckoned to be correlated with the astrocytic coverage.

Parkinson’s Disease (PD) is a neurodegenerative and progressive disease that impacts the nerve cells in the brain and varies from person to person. The exact cause of PD is still unknown, and the diagnosis of PD does not include a specific objective test with certainty. Although deep learning has made great progress in medical neuroimaging analysis, these methods are very susceptible to biases present in neuroimaging datasets. An innovative decorrelated deep learning technique is introduced to mitigate class bias and scanner bias while simultaneously focusing on finding distinguishing characteristics in resting-state functional MRI (rs-fMRI) data, which assist in recognizing the PD with good accuracy. The decorrelation function reduces the non-linear correlation between features and bias in order to learn bias-invariant features. The Parkinson’s Progression Markers Initiative (PPMI) dataset, referred to as a single scanner imbalanced dataset in this study used to validate our method. The imbalanced dataset problem affects the performance of the deep learning framework by overfitting to the majority class. To resolve this problem, we propose a new Decorrelated Convolutional Neural Networks (DcCNN) framework by applying decorrelation-based optimization to Convolutional Neural Networks(CNN). An analysis of evaluation metrics comparisons shows that integrating the decorrelation function boosts the performance of PD recognition by removing class bias. Specifically, our DcCNN model performs significantly better than existing traditional approaches to tackle the imbalance problem. Finally, the same framework can be extended to create scanner invariant features without significantly impacting the performance of a model. The obtained dataset is a multi-scanner dataset which leads to scanner bias due to the differences in acquisition protocols and scanners. The multi-scanner dataset is a combination of two datasets, namely PPMI and FTLDNI - frontotemporal lobar degeneration neuroimaging initiative (NIFD) dataset. The results of t-distributed stochastic neighbor embedding (t-SNE) and scanner classification accuracy of our proposed Feature Extraction-DcCNN (FE-DcCNN) model validated the effective removal of scanner bias. Our method achieves an average accuracy of 77.80% on a multi-scanner dataset for differentiating PD from healthy control, which is superior to the DcCNN model trained on a single scanner imbalanced dataset.

This study delves into Personal Narratives (PN), which encompass both oral and written recounting of individual experiences, encompassing facts, events, people, and thoughts. Traditional emotion recognition and sentiment analysis primarily focus on broader categories like utterances or documents. Our research, however, centers on identifying Emotion Carriers (EC), which are specific segments within speech or text that elucidate the narrator's emotional state (e.g.,"losing a parent", "decision-making moments"). Extracting these ECs enriches the representation of a user's emotional state, thereby enhancing natural language understanding and the sophistication of dialogue models. While previous studies have utilized lexical attributes to identify ECs, we argue that incorporating spoken narratives offers a more nuanced view of the context and emotional state. This paper explores the integration of speech and textual embeddings at the word level, alongside both early and late fusion techniques, for improved EC detection in spoken narratives. We employ Residual Neural Networks (ResNet), initially pre-trained on diverse speech emotion datasets and subsequently fine-tuned for EC detection. Our experimental findings demonstrate that late fusion, in particular, significantly enhances EC detection capabilities.

This paper presents a study and implementation of a convolutional neural network to identify and recognize humpback whale specimens from the unique patterns of their tails. Starting from a dataset composed of images of whale tails, all the phases of the process of creation and training of a neural network are detailed – from the analysis and pre-processing of images to the elaboration of predictions, using TensorFlow and Keras frameworks. Other possible alternatives are also explained when it comes to tackling this problem and the complications that have arisen during the process of developing this paper.

Convolutional neural network (CNN), a class of artificial neural network (ANN) is attracting interests of researchers in all research domain. CNN was invented for computer vision. They have also shown to be useful for semantic parsing, sentence modeling and other natural language processing related tasks. Here in this paper we discuss the basics of CNN models and their scope to provide a reference/baseline to the researchers interested in using CNN models in their research.

The real challenge in Human Robot Interaction (HRI) is to build machines capable of perceiving human emotions so that robots can interact with humans in a proper manner. It is well known from the literature that emotion varies accordingly to many factors. Among these, gender represents one of the most influencing one, and so an appropriate gender-dependent emotion recognition system is recommended. In this paper, a two-level hierarchical Speech Emotion Recognition (SER) system is proposed: the first level is represented by the Gender Recognition (GR) module for the speaker’s gender identification; the second is a gender-specific SER block. Specifically for this work, the attention was focused on the optimisation of the first level of the proposed architecture. The system was designed to be installed on social robots for hospitalised and living at home elderly patients monitoring. Hence, the importance of reducing the software computational effort of the architecture also minimizing the hardware bulkiness, in order for the system to be suitable for social robots. The algorithm was executed on the Raspberry Pi hardware. For the training, the Italian emotional database EMOVO was used. Results show a GR accuracy value of 97.8%, comparable with the ones found in literature.

In orthopedics, bone drilling is a crucial part of a surgical method commonly carried out for internal fixation in bone fracture treatment. The primary purpose of bone drilling is the creation of holes for screw insertion to immobilize fractured parts. The bone drilling task depends on the orthopedist and surgeon’s high level of skill and experience. This paper aimed to provide a summary of previously published review studies in the field of bone drilling. This review paper also presents a comprehensive review of the application of machine learning for bone drilling and as a future direction for the automation system. This review can also help medical surgeons and bone drillers understand the latest improvements through parameter selection and optimization strategies to reduce bone damage in bone drilling procedures. Apart from the review study, bone drilling vibration data collected in the University laboratory experiment is also presented in this study. The vibration data consist of three different layers of femur cow bone which are processed and classified using several machine learning methods. LSTM is, used in the bone drilling classification study to prove that the layers of the bone drilling are associated with the vibration signal and can be classified and predicted using the machine learning method.

Coconut is an important multipurpose crop wherein different stages of its maturity are used for different products. Traditional approach of its classification use sound formed by tapping the fruit, and the tapper will base its judgment through the sound he heard. The procedure was highly subjective and attempts had been made by other researchers to automate and classify the adulthood of the coconut objectively. Nowadays, deep learning techniques are being utilized to solve classification problems. One such method is Convolutional Neural Network (CNN) that takes raw pixel data, learns to extract features, and ultimately classifies the input. In this study, a portable device was developed that takes audio signals generated from tapping the fruit mechanically. This audio clip was converted to spectrogram and was used as input to a LeNet CNN architecture. We argue that CNN classifier has improved accuracy compared to the non-deep learning system. Our evaluation confirmed that the use of CNN had improved the accuracy of classifying coconut by about 15%.

The mathematical structure underlying a sentence is made of two independent processing units in series. The conditional probability density function of sentence length (measured in words) recordable in the extended short–term memory (E–STM) buffer made of CF cells is Gaussian. The number of sentences that authors of Italian and English Literatures have written is compared to that theoretically available to them. The multiplicity factor α describes this comparison. α>1 is more likely than α<1 and often α≫1, therefore the same sentence pattern is reused many times. These texts are easier to read. Very few novels show α<1. In these cases, there are enough diverse sentence patters to convey meaning, but most of them are not used. Texts are more difficult to read, as measured by a universal readability index GU. A mismatch index IM synthetically describes the process. α, GU. and IM increase with year of publication. Future work will concern other literatures – including ancient ones as Greek and Latin – to confirm what, in our opinion, is general feature of human mind.

We investigated the role of the human medio-temporal complex (hMT+) in the memory encoding and storage of a sequence of four coherently moving RDKs by applying repetitive transcranial magnetic stimulation (rTMS) during an early or late phase of the retention interval. Moreover, in a second experiment we also tested whether disrupting the functional integrity of hMT+ during the early phase impaired the precision of the encoded motion directions. Overall, results showed that both recognition accuracy and precision were worse in middle serial positions, suggesting the occurrence of primacy and recency effects. We found that rTMS delivered during the early (but not the late) phase of the retention interval was able to impair not only recognition of RDKs, but also the precision of the retained motion direction. However, such impairment occurred only for RDKs presented in middle positions along the presented sequence, where performance was already closer to chance level. Altogether these findings suggest an involvement of hMT+ in the memory encoding of visual motion direction. Given that both position sequence and rTMS modulated not only recognition but also precision of the stored information, these findings are in support of a model of visual short-term memory with a variable resolution of each stored item, consistent with the assigned amount of memory resources, and that such item-specific memory resolution is supported by the functional integrity of area hMT+.

The feeling of emotional self-efficacy helps people understand how to handle positive and negative emotions. Emotion regulation indicates the process that helps modulate emotions, to adapt suitably to the demands of the environment. This study has a two-fold aim. Firstly, it analyses the relationships among emotion regulation; the personality traits of extraversion and emotional stability; and the feeling of efficacy of positive and negative emotions in an adolescent population. Secondly, it analyses the mediating role of personality traits (extraversion and emotional stability) in the relationship between emotion regulation and self-efficacy for positive and negative emotions. There were 703 adolescents who took part (49.9% male and 50.1% female) aged between 15 and 18 years (M=15.86, TD=0.30). The results observe the significant relationships among emotion regulation; the personality traits of extraversion and emotional stability; and self-efficacy for positive and negative emotions. The structural equation model confirms that the link between emotion regulation and self-efficacy is direct and is also mediated by the personality traits of extraversion and emotional stability. The study confirms that emotional self-efficacy beliefs are connected to the emotional regulation strategies used. Effective emotional regulation favours self-perception and emotional coping. There is a discussion about the results, which are connected to previous research.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

Nowadays smartphone utilization for disease diagnosis and remote health care applications has become promising due to their ubiquity. Here, a novel convolutional neural network method for detecting keratoconus that is wholly implemented on a smartphone is proposed. The proposed method provides accurate detection of over 72.9% for all stages of keratoconus. Preliminary results indicate 90%, 83%, 64% and 52% detection rate for severe, advanced, moderate and mild stages of disease, respectively.

The Station logo is a way for a TV station to claim copyright, which can realize the analysis and understanding of the video by the identification of the station logo, so as to ensure that the broadcasted TV signal will not be illegally interfered. In this paper, we design a station logo detection method based on Convolutional Neural Network by the characteristics of the station, such as small scale-to-height ratio change and relatively fixed position. Firstly, in order to realize the preprocessing and feature extraction of the station data, the video samples are collected, filtered, framed, labeled and processed. Then, the training sample data and the test sample data are divided proportionally to train the station detection model. Finally, the sample is tested to evaluate the effect of the training model in practice. The simulation experiments prove its validity.

In recent times, with the increase of Artificial Neural Network (ANN), deep learning has brought a dramatic twist in the field of machine learning by making it more Artificial Intelligence (AI). Deep learning is used remarkably used in vast ranges of fields because of its diverse range of applications such as surveillance, health, medicine, sports, robotics, drones etc. In deep learning, Convolutional Neural Network (CNN) is at the center of spectacular advances that mixes Artificial Neural Network (ANN) and up to date deep learning strategies. It has been used broadly in pattern recognition, sentence classification, speech recognition, face recognition, text categorization, document analysis, scene, and handwritten digit recognition. The goal of this paper is to observe the variation of accuracies of CNN to classify handwritten digits using various numbers of hidden layer and epochs and to make the comparison between the accuracies. For this performance evaluation of CNN, we performed our experiment using Modified National Institute of Standards and Technology (MNIST) dataset. Further, the network is trained using stochastic gradient descent and the backpropagation algorithm.

A block-diagonal fuzzy neural network for short-term load forecasting is proposed. DBD-FELF consists of fuzzy rules with consequent parts that are neural networks with internal recurrence. These networks have a hidden layer which consists of pairs of neurons with feedback connections between them. The overall fuzzy model partitions the input space in partially overlapping fuzzy regions, where the recurrent neural networks of the respective rules operate. The partition of the input space and determination of the fuzzy rule base is performed by use of Fuzzy C-Means clustering algorithm and the RENNCOM constrained optimization method is applied for consequent parameter tuning. The electric load time-series of the Greek power system is examined, and hourly-based forecasting for the whole year is performed. The performance of DBD-FELF is tested via extensive experimental analysis and the results are promising, since an average percentage error of 1.18% is attained, along with an average yearly absolute error of 76.2 MW. Moreover, DBD-FELF is compared with Deep Learning, fuzzy and neurofuzzy rivals, such that its particular attributes are highlighted.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

An application of deep convolutional neural network and recurrence plot for financial market movement prediction is presented. Though it is challenging and subjective to interpret its information, the pattern formed by a recurrence plot provide a useful insight into the dy- namical system. We used a recurrence plot of seven financial time series to train a deep neural network for financial market movement predic- tion. Our approach is tested on our dataset and achieved an average of 53.25% classification accuracy. The result suggests that a well trained deep convolutional neural network can learn a recurrence plot and pre- dict a financial market direction.

With the increase of the Artificial Neural Network (ANN), machine learning has taken a forceful twist in recent times. One of the most spectacular kinds of ANN design is the Convolutional Neural Network (CNN). The Convolutional Neural Network (CNN) is a technology that mixes artificial neural networks and up to date deep learning strategies. In deep learning, Convolutional Neural Network is at the center of spectacular advances. This artificial neural network has been applied to several image recognition tasks for decades and attracted the eye of the researchers of the many countries in recent years as the CNN has shown promising performances in several computer vision and machine learning tasks. This paper describes the underlying architecture and various applications of Convolutional Neural Network.

Availability and continuous operation under critical conditions are very important in electric machine drive systems. However, such systems, are suffering from several type of failures that affect the electric machine or the associated voltage source inverter. Therefore, fault diagnosis and fault tolerance are highly required. This paper presents a new robust deep learning-based approach to diagnosis multiple open-circuit fault in three phase two level voltage source inverter for induction motor drive applications. The proposed approach uses fault diagnosis variables obtained from sigmoid transformation of the motor stator currents. The open-circuit fault diagnosis variables are then introduced to a Bidirectional Long Short-Term Memory algorithm to detect the faulty switch(es). Several simulation and experimental results are presented to show the proposed fault diagnosis algorithm effectiveness and robustness.

This paper propose an original approach of achieving a Cymatics based visual perception of isolated speech commands. The idea is to smartly combine the effective speech processing and analysis methods with the phenomena of Cymatics. In this context, an effective approach for automatic isolated speech based message recognition is proposed. The incoming speech segment is enhanced by applying the appropriate pre-emphasis filtering, noise thresholding and zero alignment operations. The Mel-Frequency Cepstral coefficients (MFCCs), Delta coefficients and Delta-Delta coefficients are extracted from the enhanced speech segment. Later on, the Dynamic Time Warping (DTW) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are used to make the classification decision. The classification decision is transformed into a methodical excitation. Finally, this excitation is converted into the systematic visual perceptions via the phenomenon of Cymatics. The system functionality is tested with an experimental setup and results are presented. The approach is novel and can be employed in various applications like visual art, encryption, education, archeology, architecture, integration of impaired people, etc.

The creation of crop-type maps from satellite data has proven challenging, often impeded by a lack of accurate in-situ data. This paper aims to demonstrate a method for crop-type (ie. Maize, Wheat and Other) recognition based on Convolutional Neural Networks using a bottom-up approach. We trained the model with a highly accurate dataset of crowdsourced labelled street-level imagery. Classification results achieved an AUC of 0.87 for wheat, 0.85 for maize and 0.73 for other. Given that wheat and maize are the two most common food crops globally, combined with an ever-increasing amount of available street-level imagery, this approach could help address the need for improved crop-type monitoring globally. Challenges remain in addressing the noisy aspect of street-level imagery (ie. buildings, hedgerows, automobiles, etc.), where a variety of different objects tend to restrict the view and confound the algorithms

It is a challenging problem that air-written Arabic letters has received a lot of attention in the past decades when compared to commonly spoken languages like English languages. To fill this gap, we propose a strong model that brings together machine learning (ML) and optical character recognition (OCR) methods. The model applied several ML methods, (i.e., Neural Networks (NN), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), with deep convolutional neural networks (CNNs) such as VGG16, VGG19, and SqueezeNet for effective feature extraction. Our study utilizes the AHAWP dataset, which consists of varied writing styles and variations in hand signs, to train and evaluate the model. Preprocessing systems are applied to improve data quality by reduction bias. Besides, OCR methods are combined into our model to sequestrate individual letters from continuous air-written gestures and refine recognition results. Results of this study show that the proposed model has achieved the extreme accuracy of 88.8% using NN with VGG16. This study presents an inclusive approach that combines ML, deep CNNs, and OCR methods to address the issue of Arabic in air writing recognition research.

Seawater density is an important physical property in oceanography that affects the accuracy of calculations such as gravity fields and tidal potentials, and the calibration of acoustic and optical oceanographic sensors. In related studies, constant density values are frequently used, which can introduce significant errors. Therefore, this study employs a basic convolutional neural network model to construct a comprehensive model showing the seawater density distribution across the globe. The model takes into account depth, latitude, longitude, and month as inputs. Numerous real seawater datasets were used to train the model, and it has been shown that the model has an absolute mean error and root mean square error of less than 2 kg/m3 in 99% of the test set samples. The model effectively demonstrates the influence of input parameters on the distribution of seawater density. In this paper, we present a newly developed global model for distributing seawater density which is both comprehensive and accurate, surpassing previous models. The utilization of the model presented in this paper for estimating seawater density can minimize errors in theoretical ocean models and serve as a foundation for designing and analyzing ocean exploration systems.

Handwriting is a form of biometric behavioral characteristic with evident individual distinctiveness. With the surge of the deep learning trend and the demand for forensic identification, handwriting identification has become one of the focal points of research in the field of pattern recognition. The research on handwriting identification in major world languages has reached a mature stage. However, there is still a notable lack of relevant research in the field of Mongolian handwriting identification, despite the fact that Mongolian is used by over 4 million people in China. This paper embarks on an initial exploration of Mongolian handwriting identification by constructing a convolutional neural network named MWInet-12. In this paper, the model evaluation experiments were conducted using a dataset comprising 156,372 samples contributed by 125 authors from the MOLHW dataset. The dataset was divided into training, validation, and test sets in an 8:1:1 ratio. The final results of the experiments reveal impressive accuracy on the test set, achieving a top-1 accuracy of 89.60% and a top-5 accuracy of 97.53%. Furthermore, through comparative experiments involving Resnet, Fragnet, and GRRNN models, this paper establishes that the proposed model yields the most favorable results for Mongolian handwriting identification.

Recognition, decoding and tracking of vortex patterns is of increasing importance in many fields reaching from astronomical observation of distant galaxies to turbulence phenomena in liquids or gases. Currently, coherent light beams with orbital angular momentum (OAM) are of particular interest for optical communication, metrology, micro-machining or particle manipulation. One common task is to identify characteristic spiral patterns in pixelated intensity maps at real-world signal-to-noise ratios. Recently, Fast Fourier Transform (FFT) was applied to the quantitative analysis of spiral interference patterns of OAM beams. Our study considers this approach in more detail. It is demonstrated that specific information can be extracted by combining conformal mapping by polar transform with determining one- or two-dimensional angular frequency spectra either in spatially fixed or scanning mode. Results of proof-of-principle experiments are presented.

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like performance from a single trace. We achieve this directly, by training our single-trace detector against labeled events from an array catalog, and by utilizing a deep temporal convolutional neural network. The training data consists of all arrivals in the International Seismological Centre Catalog for seven seismic arrays over a five year window from 1 Jan 2010 to 1 Jan 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 Jan 2015 to 1 Jan 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the transportability and generalization of the technique to new stations. Detection performance against this test set is outstanding. Fixing a type-I error rate of 1%, the algorithm achieves an overall recall rate of 73% on the 141,095 array beam picks in the test set, yielding 102,394 correct detections. This is more than 4 times the 23,259 detections found in the analyst-reviewed single-trace catalogs over the same period, and represents an 8dB improvement in detector sensitivity over current methods. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

This study presents a novel approach for predicting hierarchical short time series. In this article, our objective was to formulate long-term forecasts for household natural gas consumption by considering the hierarchical structure of territorial units within a country's administrative divisions. For this purpose, we utilized natural gas consumption data from Poland. The length of the time series was an important determinant of the data set. We contrast global techniques, which employ a uniform method across all time series, with local methods that fit a distinct method for each time series. Furthermore, we compare the conventional statistical approach with a machine learning (ML) approach. Based on our analyses, we devised forecasting methods for short time series that exhibit exceptional performance. We have demonstrated that global models provide better forecasts than local models. Among ML models, neural networks yielded the best results, with the MLP network achieving comparable performance to the LSTM network while requiring significantly less computational time.

Human violence recognition is an area of great interest in the scientific community, given its broad spectrum of applications, especially in video surveillance systems, since detecting violence in real-time could prevent criminal acts and save lives. Despite the number of existing proposals and research, most focus on the precision of results, leaving aside efficiency and its practical implementation. Thus, this work proposes a model that is effective and efficient in recognizing human violence in real-time. The proposed model consists of three modules: a first module called Spatial Motion Extractor (SME), in charge of extracting regions of interest from a frame; a second module called Short Temporal Extractor (STC), whose function is to extract temporal characteristics of rapid movements, finally the Global Temporal Extractor (GET) module, responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated regarding efficiency, effectiveness, and ability to operate in real-time. The results obtained on Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to other alternatives. A VioPeru dataset was created to validate real-time applicability with violent and non-violent videos captured by real video surveillance cameras in Peru. The effectiveness results in this dataset outperformed the best existing proposal. Therefore, our proposal has contributions in efficiency, effectiveness, and real-time.

Background: In an age where information is generally accessible, most of the interest these days has focused on how accessible and convenient technology can be. So small and personal, mobile devices can transform our perception of learning by combining both mobility and convenience. Mobile learning is part of the digital learning landscape alongside e-learning and serious games. However, knowledge about effective design of mobile learning experiences remains of interest with a focus on appropriate design models and the embodiments that can be implemented to achieve the intended educational outcomes. Exploring the instructor's perspective on mobile learning is essential. Therefore, the aim of this study was to investigate the Moroccan instructors' perception and practice of mobile learning to inform the development of an ecologically valid mobile learning integration model. Methods: Higher education Instructors (n=41) were recruited to the study. The Moroccan instructors' perception and their experiences regarding their adoption of mobile learning were collected using an online survey. The analysis focused on their mobile use, perceived IT competency, and opinions on mobile learning. Results: We described most of the instructors' considerations regarding integrating mobile technologies into their teaching activities. We found that most of the mobile learning activities defined by the respondents corresponded to relatively advanced use of mobile devices. More promising, instructors have found innovative ways to use the educational potential of mobile devices. However, the prospect of mobile devices was still to challenge. No or poor Wi-Fi connection, number of devices or limited access, sometimes fees or applications incompatibility were identified as reasons and obstacles to mobile learning usage. Conclusion: Mobile learning is mostly perceived positively among Moroccan instructors allowing many applications and usage to enhance teaching and learning. In this study, a better understanding of aspects and factors influencing the integration of mobile learning in the Moroccan educational context is exposed, helping further the development of an ecologically valid mobile learning integration model. Future work on mobile learning should consider the highly paced evolution of mobile technologies, emphasizing the flexibility of integration frameworks to support instructors and learners.

Background: Different drugs damage the frontal cortices, particularly the prefrontal areas involved in both emotional and cognitive functions, with a consequence of decoding emotion deficits for people with substance abuse. The present study aims to explore the cognitive impairments in drug abusers through facial, body and disgust emotion recognition, expanding the investigation of emotions, processing, measuring accuracy and response velocity. Method: We enrolled 13 addicted to cocaine and 12 alcohol patients attending treatment services in Italy, comparing them with 33 matched controls. Facial emotion and body posture recognition tasks, a disgust rating task, and the Barrat Impulsivity Scale were included in the experimental assessment. Results: We found that emotional processes are differently influenced by cocaine and alcohol, suggesting that these substances impact diverse cerebral systems. Conclusion: The contribution made by the duration of consumption on emotional processing seems far less important than for cognitive processes. Drug abusers seem to be slower on elaboration of emotions and, in particular, of disgust emotion. Considering that the participants were not impaired in cognition, our data support the hypothesis that emotional impairments emerge independently from damage to cognitive functions.

Nowadays the relationship between planning land use and actual land use is not so clear in general. A lot of efforts have been put in the failures of regulation for the expansion of construction land. However, it still lacks an integrated approach to study the effectiveness of land use regulation in terms of different land use types. Furthermore, the existing evaluation of land use plan mainly focuses on a general level, a detailed research on the regulation effectiveness of each construction land use type is absent. Therefore, this research tries to evaluate regulation effectiveness of land use plan, which takes Cangwu country, Guangxi Province as an example. The finding by analysis is that the total area of construction land expansion was about 3494.73 ha, nearly 1.1 times of the plan quota. Moreover, the effectiveness differs greatly in various construction land use types. Town, industrial/mining sites can be well regulated through the quota of land use plan. While, the quota regulation system is not as effective for other type of construction land. Thus, we suggest to improve the regulation effectiveness of construction land through different plan instruments.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

Automatic garments design class identification for recommending the fashion trends is important nowadays because of the rapid growth of online shopping. By learning the properties of images efficiently, a machine can give better accuracy of classification. Several methods, based on Hand-Engineered feature coding exist for identifying garments design classes. But, most of the time, those methods do not help to achieve better results. Recently, Deep Convolutional Neural Networks (CNNs) have shown better performances for different object recognition. Deep CNN uses multiple levels of representation and abstraction that helps a machine to understand the types of data (images, sound, and text) more accurately. In this paper, we have applied deep CNN for identifying garments design classes. To evaluate the performances, we used two well-known CNN models AlexNet and VGGNet on two different datasets. We also propose a new CNN model based on AlexNet and found better results than existing state-of-the-art by a significant margin.

Respiratory rate is an important biomarker that indicates changes in the clinical condition of critically ill patients, so a surveillance tool that can accurately monitor the changing respiratory rate in real time is needed. Through investigating various pairs of machine learning models, we proposed new machine learning model for real-time respiratory rate estimation using photoplethysmogram. New photoplethysmogram-driven respiratory rate dataset(StMary) was collected from surgical intensive care unit of a tertiary referral hospital, using photoplethysmogram signal collector. For 50patients and 50healthy volunteers, 2-minute photoplethysmogram was collected for each subject twice. To evaluate the respiratory rate of subject, it was inputted into the deep neural network model we built, and dataset was splitted into training, validation, testing dataset, then 4-fold cross validation was exploited. Our deep neural network model trained with StMary and two public datasets(BIDMC and CapnoBase) individually, or selectively merged dataset had shown a low error rate in respiration rate measurements. Our model trained with StMary showed low mean absolute error score(1.0273±0.8965), and trained with 3 datasets(CapnoBase, BIDMC and StMary) showed a lower error rate(1.7359±1.6724) than the model trained with CapnoBase and BIDMC(1.9480±1.6751). We could verify the performance of model evaluating respiratory rate from photoplethysmogram, and our dataset could contribute as the clinical research data that supports artificial intelligence models evaluating respiratory rate and surveillance tools to test whether their monitoring function works properly.

Epilepsy is a neurological disorder that affects approximately 1% of the world's population. To diagnose and estimate the occurrence of epilepsy, the analysis of recorded brain activity is performed by a neurologist, which is not only time-consuming and tedious but also occasionally accompanied by human error. Therefore, in recent decades, researchers have aimed to unravel an approach for designing and building an automated method for diagnosing and estimating the occurrence of epilepsy. Accordingly, the present study proposed two new-fangled ways based on brain signals and a convolutional neural network (CNN). Moreover, this research implements a CNN with a sequential three-layer structure. Numerous experiments were performed, and the accuracy of estimating epilepsy using the developed methods was achieved at 95% without feedback and 97% with feedback. The proposed methods were proven to be more accurate than the previous techniques and can be employed as a physician's assistant once entering the field of operation.

The speech-to-song illusion is a type of auditory illusion that the repetition of a part of a sentence would change people’s perception tendency from speech-like to song-like. The study aims to examine how pace, emotion, and language tonality affect people’s experience of the speech-to-song illusion. It uses a between-subject (Pace: fast, normal, vs. slow) and within-subject (Emotion: positive, negative, vs. neutral; language tonality: tonal language vs. non-tonal language) design. Sixty Hong Kong college students were randomly assigned to one of the three conditions characterized by pace. They listened to 12 audio stimuli, each with repetitions of a short excerpt, and rated their subjective perception of the presented phrase, whether it sounded like a speech or a song, on a five-point Likert-scale. Paired-sample t-tests and repeated measures ANOVAs were used to analyze the data. The findings reveal that a faster speech pace could strengthen the tendency of the speech-to-song illusion. Neither emotion nor language tonality show a statistically significant influence on the speech-to-song illusion. This study suggests that the perception of sound should be in a continuum and facilitates the understanding of song production in which speech can turn into music by having repetitive phrases and to be played in a relatively fast pace.

This paper presents a novel approach for the recognition of multiple sclerosis (MS) using wavelet entropy and a Particle Swarm Optimization (PSO)-based neural network. MS is a complex neurological disorder with diverse clinical manifestations, often challenging to diagnose accurately. In this study, we leverage wavelet entropy (WE) as a feature extraction method to capture intricate patterns within brain imaging data. These extracted features are then employed to train a neural network model optimized through PSO to enhance classification accuracy. Experimental results on a dataset comprising MS and healthy control subjects demonstrate the effectiveness of our proposed approach, viz., WE-PSONN, which achieves a sensitivity of 91.95±1.15, a specificity of 92.36±0.88, a precision of 92.28±0.88, an accuracy of 92.16±0.90. The combination of advanced signal processing techniques and machine learning optimization holds promise for improving the early diagnosis and management of MS, offering potential benefits to both patients and healthcare providers.

The time-dependent behavior and long-term stability of deep-buried tunnels in soft rocks have received lots of considerations in tunnel engineering and allied sciences. To better explore and deepen the engineering application of rock creep, extensive research studies are still needed, although fruitful outcomes have already obtained in many related investigations. In this article, the Weilai Tunnel in China’s Guangxi province is studied taking its host rocks as the main research object. In fact, aiming at forecasting the time-varying deformation of this tunnel, a novel elasto-visco-plastic creep constitutive model with two variants is proposed, by exploiting the typical complex load-unload process of rock excavation. The model is well validated and good agreements are found with the relevant experimental data. Moreover, the time-dependent de-formation rules are properly established for the surrounding rocks, by designing two new closed-form solutions based on the proposed creep model and the Hoek-Brown criterion. The convergence deformations calculated from the closed-form solutions conform well to the on-site monitoring data. In only 27 days after excavation, the creep deformation of the Weilai tunnel overtakes 400 mm, which is enormous. To guarantee the long-term stability of this tunnel, a ro-bust support scheme and its long-term monitoring with appropriate remote sensors are strongly suggested.

Brain-Computer Interface (BCI) systems can assist physically challenged people to interact with their surroundings and improve the quality of their lives. Decoding human thoughts is a powerful technique that can assist paralyzed people who have lost their speech production ability. Speaking is a combined process involving synchronizing the brain and the oral articulators. This paper proposed a high-accuracy brain wave pattern recognition based on inner speech using a novel feature extraction method. Only eight EEG electrodes were used in this study, and they were set on selected spots on the scalp. Support Vector Machine (SVM) was employed to decode the recorded EEG dataset into four internally spoken words which are: Up, Down, Left, and Right. The proposed approach achieved overall classification accuracy that ranges between 96.20% to 97.5%. In addition, more performance evaluation metrics were estimated to test the reliability of classifying the EEG-based inner speech data, and we obtained 97.61%, 97.50%, and 97.73% for F1-score, recall, and precision respectively. Furthermore, the Area Under Curve of the Receiver Operating Characteristic (AUC-ROC) proved the strength of the proposed approach for classifying the specified inner speech commands by achieving a macro-average amount of 99.32%. The inner speech classification method using electroencephalography proposed in this work can clinically help improve communication for patients with problems including speech disorder, mutism, cognitive development, executive function, and psychopathology.

With the widespread of embedded sensing capabilities of mobile devices, there has been unprecedented development of context-aware solutions. This allows the proliferation of various intelligent applications such as those for remote health and lifestyle monitoring, intelligent personalized services, etc. However, activity context recognition based on multivariate time series signals obtained from mobile devices in unconstrained conditions is naturally prone to imbalance class problems. This means that recognition models tend to predict classes with the majority number of samples whilst ignoring classes with the least number of samples, resulting in poor generalization. To address this problem, we propose to augment the time series signals from inertia sensors with signals from ambient sensing to train deep convolutional neural networks (DCNN) models. DCNN provides the characteristics that capture local dependency and scale invariance of these combined sensor signals. Consequently, we developed a DCNN model using only inertial sensor signals and then developed another model that combined signals from both inertia and ambient sensors aiming to investigate the class imbalance problem by improving the performance of the recognition model. Evaluation and analysis of the proposed system using data with imbalanced classes show that the system achieved better recognition accuracy when data from inertial sensors are combined with those from ambient sensors such as environment noise level and illumination, with an overall improvement of 5.3% accuracy.

Camouflage evaluation typically involves human visual search and detection experiments that are time-consuming and expensive. Hence, there is a need for models that compute camouflage effectiveness from digital imagery. Convolutional neural networks are a powerful tool for automatic object detection and recognition. We investigated whether such a network (YOLO) can also provide a measure of camouflage effectiveness that is related to human perception. To this end, human performance measures of camouflage effectiveness such as detection time and target conspicuity were obtained in observer experiments and compared with the performance of the (standard, i.e. pre-trained) YOLO-V4-tiny algorithm. YOLO provides the probability that a detected object is correctly classified, and this is adopted as our measure of camouflage effectiveness. We compared the YOLO-predicted classification probability for a person in camouflage clothing moving through rural and urban scenes to human detection performance. Overall, camouflage effectiveness predicted by YOLO correlates with human observer performance. At close distances, YOLO’s classification performance appears sensitive to high-contrast shape-breaking elements of a camouflage pattern. This suggests that YOLO may be adapted to assess camouflage effectiveness for a wide range of applications, such as evaluating or optimizing one’s signature and predicting optimal hiding locations in a given environment. Further research is required to fully establish YOLO’s limitations and applicability for this purpose.

Estimating plume cloud height is essential for various applications, such as global climate models. Smokestack plume rise is the constant height at which the plume cloud is carried downwind as its momentum dissipates and the plume cloud and the ambient temperatures equalize. Although different parameterizations are used in most air-quality models to predict the plume rise, they have been unable to estimate it properly. This paper proposes a novel framework to monitor smokestack plume clouds and make long-term, real-time measurements of the plume rise. For this purpose, a three-stage framework is developed based on Deep Convolutional Neural Networks (DCNNs). In the first stage, an improved Mask R-CNN, called Deep Plume Rise Network (DPRNet), is applied to recognize the plume cloud. Then, image processing analysis and least squares theory are respectively used to detect the plume cloud’s boundaries and fit an asymptotic model into their centerlines. The y-component coordinate of this model’s critical point is considered the plume rise. In the last stage, a geometric transformation phase converts image measurements into real-life ones. A wide range of images with different atmospheric conditions, including day, night, and cloudy/foggy, have been selected for the DPRNet training algorithm. Obtained results show that the proposed method outperforms widely-used networks in smoke border detection and recognition.

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. The two popular methods of producing a deepfake are based on either convolutional neural networks (CNN), or autoencoders. Deepfakes created using CNN comparatively show higher qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increase usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with accuracies around 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

Alcoholism is attributed to regular or excessive drinking of alcohol and leads to the disturbance of the neuronal system in the human brain. This results in certain malfunctioning of neurons that can be detected by an electroencephalogram (EEG) using several electrodes on a human skull at appropriate positions. It is of great interest to be able to classify an EEG activity as that of a normal person or an alcoholic person using data from the minimum possible electrodes (or channels). Due to the complex nature of EEG signals, accurate classification of alcoholism using only a small data is a challenging task. Artificial neural networks, specifically convolutional neural networks (CNN), provide efficient and accurate results in various pattern-based classification problems. In this work, we apply CNN on raw EEG data, and demonstrate how we achieved 98% average accuracy by optimizing a baseline CNN model and outperforming its results in a range of performance evaluation metrics on the UCI-KDD EGG dataset. This article explains the step-wise improvement of the baseline model using the dropout, batch normalization, and kernel regularization techniques, and provides a comparison of the two models that can be beneficial for aspiring practitioners who aim to develop similar classification models in CNN. A performance comparison is also provided with other approaches using the same dataset.

The diagnosis of a rolling bearing for monitoring its status is critical for maintaining industrial equipment using rolling bearings. The traditional method of diagnosing faults of the rolling bearing has low identification accuracy, which needs artificial feature extraction to enhance the accuracy. 1D-CNN method not only can diagnose bearing faults accurately but also overcome shortcomings of the traditional methods. Different from machine learning and other deep learning models, the 1D-CNN method does not need pre-processing one-dimensional data of rolling bearing’s vibration. Thus, it enhances the processing speed and improves the network structure to have a reasonable design for small sample data sets. This study proposes and tests a 1D-CNN method for diagnosing rolling bearings. By introducing the dropout operation, the method obtains high accuracy and improves the generalizing ability. The experimental results show 99.52% of the average accuracy under a single load and 98.26% under different loads.

To protect power lines, distance relays are used which can rely on a modified distance resistance. But usually the operating range of these relays changes as the network conditions change (network topology, load value, output value, etc.) and leads to false trips, By using methods that can process information and recognize patterns, for example, the use of micro and intelligent processor algorithms can use the new relays with high precision and thus provide adequate protection. In this study, a distance relay was modeled using a neural network, and it was observed that the neural relay had higher accuracy than the conventional relay. In addition to detecting the fault and its location, type and phase of the fault, three-stage simultaneous protection can be performed. As a result, the number of linear relays can be reduced by using relays based on neural technologies. An MLP (multilayer perceptron) neural network is used to model a sequence of distances.

The electroencephalogram (EEG) is a record of brain activity. Brain Computer Interface (BCI) technology formed by the EEG signal has become one of the hotspots at present. How to extract the feature signal of EEG is the most basic research of BCI technology. In this paper, A new method of recognizing fatigue, conscious, concentrated state of human brain is proposed by the combination of discrete wavelet transform and the neural network based on EEG signal. First of all, the law signal is preprocessed by the wavelet denoising method because the law EEG signal contains a large number of high frequency noise, which is decomposed into multi-layer high frequency signal and low frequency signal. thus, δ wave, θ wave, α wave, β wave are obtained by the wavelet transform. And then, frequency band energy of the different wave is regards as the feature signal of EEG. In the experiment, the feature signal is classified by radial basic function (RBF) and annealed chaotic competitive learning network (ACCLN). RBF and ACCLN networks are trained with 500 sets of sample data and are tested by 100 sets of samples in different mental states. The experimental results show that the average accuracy of RBF network under three conditions are 88.75%, 88.25%, 88.5%, respectively, and the correct rate of ACCLN network is 97%, 98%, 98%, respectively.

Accurate and fast traffic flow forecasting is vital in intelligent transportation system because many of the advanced features in intelligent transportation systems are based on it. However, existing methods have poor performance regarding accuracy and computational efficiency in long-term traffic flow forecasting under big data. Hence, we propose an improved Long short-term memory (LSTM) Network and its cluster computing implementation in this paper to address the above challenge. We propose a singular point probability LSTM (SDLSTM) algorithm. The method discards the units of the network according to the singular point probability during the training process and amends the SDLSTM by Autoregressive Integrated Moving Average Model (ARIMA) to achieve the accurate prediction of 24-hour traffic flow data. Furthermore, the paper designs a scheme for implementing this method through cluster computing to shorten the calculation time and improve the system's operating speed. Theoretical analysis and experimental results show that SDLSTM gains a higher accuracy rate and better stability in the long-term traffic flow forecasting compared with previous methods.

In recent years, Edge Intelligence (EI) has emerged, combining edge computing with AI, specifically deep learning, to run AI algorithms directly on edge devices. In practical applications, EI faces challenges related to computational power, power consumption, size, and cost, with the primary challenge being the trade-off between computational power and power consumption. This has rendered traditional computing platforms unsustainable, making heterogeneous parallel computing platforms a crucial pathway for implementing EI. In our research, we leveraged the Xilinx Zynq 7000 heterogeneous computing platform, employed High-Level Synthesis (HLS) for design, and implemented two different accelerators for LeNet-5 using loop unrolling and pipelining optimization techniques. The experimental results show that when running at a clock speed of 100 MHz, the PIPELINE accelerator, compared to the UNROLL accelerator, experiences an 8.09% increase in power consumption but speeds up by 14.972 times, making the PIPELINE accelerator superior in performance. Compared to the CPU, the PIPELINE accelerator reduces power consumption by 91.37% and speeds up by 70.387 times, while compared to the GPU, it reduces power consumption by 93.35%.This study provides two different optimization schemes for edge intelligence applications through design and experimentation, and demonstrates the impact of different quantization methods on FPGA resource consumption. These experimental results can provide a reference for practical applications, thereby providing a reference hardware acceleration scheme for edge intelligence applications.

To solve two key problems in the identification of people who are infected with COVID-19: the first problem is that the identification accuracy is not high enough. The second problem is that present identification method such as nucleic acid testing is expensive in many countries. Methods: So, I decided to design a fast identification method for COVID-19 patients which is based on deep learning. After the model (CoughNet) learns more than 6,000 cough spectrograms of both COVID-19 patients and normal people, the accuracy rate of identification of COVID-19 patients and normal people is higher than 99% in the test set. Structure: This paper is mainly divided into three parts: the first part introduces the main background and research status of the research; The second part introduces the research methods; The third part introduces the specific process of the experiment.

Recently, much attention has been devoted to finding highly efficient and powerful activation functions for CNN layers. Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs. The objective of this study is to examine the performance of CNN ensembles made with different activation functions, including six new ones presented here: 2D Mexican ReLU, TanELU, MeLU+GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The highest performing ensemble was built with CNNs having different activation layers that randomly replaced the standard ReLU. A comprehensive evaluation of the proposed approach was conducted across fifteen biomedical data sets representing various classification tasks. The proposed method was tested on two basic CNN architectures: Vgg16 and ResNet50. Results demonstrate the superiority in performance of this approach. The MATLAB source code for this study will be available at https://github.com/LorisNanni.