Search

In recent years, the increasing popularity of smart mobile devices has made the interaction between devices and users, particularly through voice interaction, more crucial. By enabling smart devices to better understand users’ emotional states through voice data, it becomes possible to provide more personalized services. This paper proposes a novel machine learning model for speech emotion recognition called CLDNN, which combines convolutional neural networks (CNN), long short-term memory neural networks (LSTM), and deep neural networks (DNN). To design a system that closely resembles the human auditory system in recognizing audio signals, 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 are extracted as the input of the model. Local feature learning blocks (LFLBs) composed of one-dimensional CNNs are employed to calculate the feature values of the data. As audio signals are time-series data, the resulting feature values from LFLBs are then fed into the LSTM layer to enhance learning on the time-series level. Finally, fully connected layers are used for classification and prediction. The experimental evaluation of the proposed model utilizes three databases: RAVDESS, EMO-DB, and IEMOCAP. The results demonstrate that the LSTM model effectively models the features extracted from the 1D CNN due to the time-series characteristics of speech signals. Additionally, the data augmentation method applied in this paper proves beneficial in improving the recognition accuracy and stability of the systems for different databases. Furthermore, according to the experimental results, the proposed system achieves superior recognition rates compared to related research in speech emotion recognition.

This paper presents a novel low-cost integrated system prototype, called School Violence Detection system (SVD), based on a 2D Convolutional Neural Network (CNN). It is used for classifying and identifying automatically violent actions in educational environments based on shallow cost hardware. Moreover, the paper fills the gap of real datasets in educational environments by proposing a new one, called Daily School Break dataset (DSB), containing original videos recorded in an Italian high school yard. The proposed CNN has been pre-trained with an ImageNet model and a transfer learning approach. To extend its capabilities, the DSB was enriched with online images representing students in school environments. Experimental results analyze the classification performances of the SVD and investigate how it performs through the proposed DSB dataset. The SVD, which achieves a recognition accuracy of 95%, is considered computably efficient and low-cost. It could be adapted to other scenarios such as school arenas, gyms, playgrounds, etc.

Social media has evolved into a platform for the dissemination of information, including fake news. There is a lot of false information about the current situation of the Coronavirus Disease 2019 (COVID-19) pandemic, such as false information regarding vaccination. In this paper, we focus on sentiment analysis for Malaysian COVID-19-related news on social media such as Twitter. Tweets in Malaysia are often a combination of Malay, English, and Chinese with plenty of short forms, symbols, emojis, and emoticons within the maximum length of a tweet. The contributions of this paper are twofold. Firstly, we built a multilingual COVID-19 Twitter dataset, comprising tweets written from 1 September 2021 to 12 December 2021. In particular, we collected 108,246 tweets, with over67%in Malay language,27%in English,2%in Chinese, and4%in other languages. We then manually annotated and assigned the sentiment of 11,568 tweets into three-class sentiments (positive, negative, and neutral) to develop a Malay-language sentiment analysis tool. For this purpose, we applied a data compression method using Byte-Pair Encoding (BPE) on the texts and used two deep learning approaches, i.e., the Multilingual Bidirectional Encoder Representation for Transformer (M-BERT) and convolutional neural network (CNN). BPE tokenization is used to encode rare and unknown words into smaller meaningful subwords. With the CNN, we converted the labeled tweets into image files. Our experiments explored different BPE vocabulary sizes with our BPE-Text-to-Image-CNN and BPE-M-BERT models. The results show that the optimal vocabulary size for BPE is 12,000; any values beyond that would not contribute much to the F1-score. Overall, our results show that BPE-M-BERT slightly outperforms the CNN model, thereby showing that the pre-trained M-BERT network has the advantage for our multilingual dataset.

The survival rate for sudden cardiac arrest (SCA) is low, and patients with long-term risks of SCA are not adequately alerted. Understanding SCA’s characteristics will be key to developing preventive strategies. Many lives could be saved if SCA’s early onset could be detected or predicted. Monitoring heart signals continuously is essential for diagnosing sporadic cardiac dysfunction. An electrocardiogram (ECG) can be used to continuously monitor heart function without having to go to the hospital. A zeolite-based dry electrode can provide safe on-skin ECG acquisition while the subject is out-of-hospital and facilitate long-term monitoring. To the ECG signal, a low-power 1 μW read-out circuit was designed and implemented in our prior work. However, having long-term ECG monitoring outside the hospital, i.e., high battery life, and low power consumption while transmission and reception of ECG signal are crucial. This paper proposes a prototype with a 10-bit resolution ADC and nRF24L01 transceivers placed 5 m apart. The system uses the 2.4 GHz worldwide ISM frequency band with GFSK modulation to wirelessly transmit digitized ECG bits at 250 kbps data rate to a physician’s computer (or similar) for continuous monitoring of ECG signals; the power consumption is only 11.2 mW and 4.62 mW during transmission and reception, respectively, with a low bit error rate of ≤0.1%. Additionally, a subject-wise cross-validated, three-fold, optimized convolutional neural network (CNN) model using the Physionet-SCA dataset was implemented on NVIDIA Jetson to identify the irregular heartbeats yielding an accuracy of 89% with a run time of 5.31 s. Normal beat classification has an F1 score of 0.94 and a ROC score of 0.886. Thus, this paper integrates the ECG acquisition and processing unit with low-power wireless transmission and CNN model to detect irregular heartbeats.

The study of neuroimaging is a very important tool in the diagnosis of central nervous system tumors. This paper presents the evaluation of seven deep convolutional neural network (CNN) models for the task of brain tumor classification. A generic CNN model is implemented and six pre-trained CNN models are studied. For this proposal, the dataset utilized in this paper is Msoud, which includes Fighshare, SARTAJ, and Br35H datasets, containing 7023 MRI images. The magnetic resonance imaging (MRI) in the dataset belongs to four classes, three brain tumors, including Glioma, Meningioma, and Pituitary, and one class of healthy brains. The models are trained with input MRI images with several preprocessing strategies applied in this paper. The CNN models evaluated are Generic CNN, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, and EfficientNetB0. In the comparison of all CNN models, including a generic CNN and six pre-trained models, the best CNN model for this dataset was InceptionV3, which obtained an average Accuracy of 97.12%. The development of these techniques could help clinicians specializing in the early detection of brain tumors.

In this paper, anomaly detection of wheel flats based on signal processing and deep learning techniques is analyzed. Wheel flats mostly affect running stability and ride comfort. Currently, domestic railway companies visually inspect wheel flats one by one with their eyes after railway vehicles enter the railway depots for maintenance. Therefore, CBM (Condition-Based Maintenance) is required for wheel flats resolution. Anomaly detection for wheel flat signals of railway vehicles using Order analysis and STFT (Short Time Fourier Transform) is studied in this paper. In the case of railway vehicles, it is not easy to obtain actual failure data through running vehicles in a university laboratory due to safety and cost issues. Therefore, vibration-induced acceleration was obtained using a multibody dynamics simulation software, SIMPACK. This method is also proved in the other paper by rig tests. In addition, since the noise signal was not included in the simulated vibration, the noise signal obtained from the Seoul Metro Subway Line 7 vehicle was overlapped with the simulated one. Finally, to improve the performance of both detection rate and real-time of characteristics based on existing LeNet-5 architectures, spectrogram images transformed from time domain data were proceeded with the LeNet deep learning model modified with the pooling method and activation function. As a result, it is validated that the method using the spectrogram with a deep learning approach yields higher accuracy than the time domain data.

This paper frames itself in the realm of smart energy technologies that can be utilized to satisfy the electricity demand of consumers. In this environment, demand response programs and the intelligent management of energy consumption that are offered by utility providers will play a significant role in implementing smart energy. One of the approaches to implementing smart energy is to analyze consumption data and provide targeted contracts to consumers based on their individual consumption characteristics. To that end, the identification of individual consumption features is important for suppliers and utilities. Given the complexity of smart home load profiles, an appliance-based identification is nearly impossible. In this paper, we propose a different approach by grouping appliances based on their rooms, thus, we provide a room-based identification of energy consumption. To this end, this paper presents and tests an intelligent consumption identification methodology, that can be implemented in the form of an ensemble of artificial intelligence tools. The ensemble, which comprises four convolutional neural networks (CNNs) and four k-nearest neighbor (KNN) algorithms, is fed with smart submeter data and outputs the identified type of room in a given dwelling. Results obtained from real-world data exhibit the superiority of the ensemble, with respect to accuracy, as compared with individual CNN and KNN models.

In the last 10 years, the demand for robot-based depalletization systems has constantly increased due to the growth of sectors such as logistics, storage, and supply chains. Since the scenarios are becoming more and more unstructured, characterized by unknown pallet layouts and stock-keeping unit shapes, the classical depalletization systems based on the knowledge of predefined positions within the pallet frame are going to be substituted by innovative and robust solutions based on 2D/3D vision and Deep Learning (DL) methods. In particular, the Convolutional Neural Networks (CNNs) are deep networks that have proven to be effective in processing 2D/3D images, for example in the automatic object detection task, and robust to the possible variability among the data. However, deep neural networks need a big amount of data to be trained. In this context, whenever deep networks are involved in object detection for supporting depalletization systems, the dataset collection represents one of the main bottlenecks during the commissioning phase. The present work aims at comparing different training strategies to customize an object detection model aiming at minimizing the number of images required for model fitting, while ensuring reliable and robust performances. Different approaches based on a CNN for object detection are proposed, evaluated, and compared in terms of the F1-score. The study was conducted considering different starting conditions in terms of the neural network’s weights, the datasets, and the training set sizes. The proposed approaches were evaluated on the detection of different kinds of paper boxes placed on an industrial pallet. The outcome of the work validates that the best strategy is based on fine-tuning of a CNN-based model already trained on the detection of paper boxes, with a median F1-score greater than 85.0%.

To improve the efficiency of social garbage classification, a garbage classification method based on a small convolutional neural network (CNN) is proposed in this paper. For low accuracy caused by light and shadow interference, an adaptive image-brightening algorithm is developed to average the brightness of the background in the image preprocessing stage, and a threshold replacement method is used to reduce shadow noise. Then, the Canny operator is used to assist in cropping the blank background in the image. For debugging low efficiency caused by the complex network, the neural network is optimized based on the MLH-CNN model to make its results simpler and equally efficient. Experimental results show the preprocessing in this study can improve the accuracy of model garbage classification. The CNN model in this study can achieve an accuracy of 96.77% on the self-built dataset and 93.72% on the TrashNet dataset, which is higher than the 92.6% accuracy of the MLC-CNN model. The network optimizer can also enhance the classification ability of the network model using the Adamax optimization algorithm based on Adam variants. In this paper, the network model derived from training is combined with the host computer software to design a garbage detection page so the model has a wider range of uses, which has a good effect on promoting the development of social environmental protection and improving residents’ awareness of environmental protection.

Anomaly detection and multi-attack classification are major concerns for cyber defense. Several publicly available datasets have been used extensively for the evaluation of Intrusion Detection Systems (IDSs). However, most of the publicly available datasets may not contain attack scenarios based on evolving threats. The development of a robust network intrusion dataset is vital for network threat analysis and mitigation. Proactive IDSs are required to tackle ever-growing threats in cyberspace. Machine learning (ML) and deep learning (DL) models have been deployed recently to detect the various types of cyber-attacks. However, current IDSs struggle to attain both a high detection rate and a low false alarm rate. To address these issues, we first develop a Center for Cyber Defense (CCD)-IDSv1 labeled flow-based dataset in an OpenStack environment. Five different attacks with normal usage imitating real-life usage are implemented. The number of network features is increased to overcome the shortcomings of the previous network flow-based datasets such as CIDDS and CIC-IDS2017. Secondly, this paper presents a comparative analysis on the effectiveness of different ML and DL models on our CCD-IDSv1 dataset. In this study, we consider both cyber anomaly detection and multi-attack classification. To improve the performance, we developed two DL-based ensemble models: Ensemble-CNN-10 and Ensemble-CNN-LSTM. Ensemble-CNN-10 combines 10 CNN models developed from 10-fold cross-validation, whereas Ensemble-CNN-LSTM combines base CNN and LSTM models. This paper also presents feature importance for both anomaly detection and multi-attack classification. Overall, the proposed ensemble models performed well in both the 10-fold cross-validation and independent testing on our dataset. Together, these results suggest the robustness and effectiveness of the proposed IDSs based on ML and DL models on the CCD-IDSv1 intrusion detection dataset.

Since the 20th century, a rapid process of motorization has begun. The main goal of researchers, engineers and technology companies is to increase the safety and optimality of the movement of vehicles, as well as to reduce the environmental damage caused by the automotive industry. The difficulty of managing traffic flows is that cars are driven by a person and their behavior, even in similar situations, is different and difficult to predict. To solve this problem, ground-based unmanned vehicles are increasingly being developed and implemented; however, like any other intelligent system, it is necessary to train different road scenarios. Currently, an engineer is driving an unmanned vehicle for training and thousands of kilometers are being driven for training. Of course, this approach to training unmanned vehicles is very long, and it is impossible to reproduce all the scenarios that can be found in real operations on a real road. Based on this, we offer a simulator of a realistic urban environment which allows you to reduce the training time and allows you to generate all kinds of events. To implement such a simulator, it is necessary to develop a method that would allow recreating a realistic world in one passage with cameras (monocular) installed on board the vehicle. Based on this, the purpose of this work is to develop an intelligent vehicle recognition system using convolutional neural networks, which allows you to create mesh objects for further placement in the simulator. It is important to note that the resulting objects should be optimal in size so as not to overload the system, since a large number of road infrastructure objects are stored there. Also, neural complexity should not be excessive. In this paper, the general concept and classification of convolutional neural networks are given, which allow solving the problem of recognizing 3D objects in images. Based on the analysis, the existing neural network architectures do not solve the problems mentioned above. In this connection, the authors first of all carried out the design of the system according to the methodology of modeling business processes, and also modified and developed the architecture of the neural network, which allows classifying objects with sufficient accuracy, obtaining optimized mesh objects and reducing computational complexity. The methods proposed in this paper are used in a simulator of a realistic urban environment, which reduces the time and computational costs when training unmanned transport systems.

Uyghur text detection and recognition in images with simple backgrounds is still a challenging task for Uyghur image content analysis. In this paper, we propose a new effective Uyghur text detection method based on channel-enhanced MSERs and the CNN classification model. In order to extract more complete text components, a new text candidate region extraction algorithm is put forward, which is based on the channel-enhanced MSERs according to the characteristics of Uyghur text. In order to effectively prune the non-text regions, we design a CNN classification network according to the LeNet-5, which gains the description characteristics automatically and avoids the tedious and low efficiency artificial characteristic extraction work. For Uyghur text recognition in images, we improved the traditional CRNN network, and to verify its effectiveness, the networks trained on a synthetic dataset and evaluated on the text recognition datasets. The experimental results indicated that the Uyghur text detection method in this paper is robust and applicable, and the recognition result by improvedCRNN was better than the original CRNN network.

The convolutional neural network (CNN) has been widely used in the field of self-driving cars. To satisfy the increasing demand, the deeper and wider neural network has become a general trend. However, this leads to the main problem that the deep neural network is computationally expensive and consumes a considerable amount of memory. To compress and accelerate the deep neural network, this paper proposes a filter pruning method based on feature maps clustering. The basic idea is that by clustering, one can know how many features the input images have and how many filters are enough to extract all features. This paper chooses Retinanet and WIDER FACE datasets to experiment with the proposed method. Experiments demonstrate that the hierarchical clustering algorithm is an effective method for filtering pruning, and the silhouette coefficient method can be used to determine the number of pruned filters. This work evaluates the performance change by increasing the pruning ratio. The main results are as follows: Firstly, it is effective to select pruned filters based on feature maps clustering, and its precision is higher than that of a random selection of pruned filters. Secondly, the silhouette coefficient method is a feasible method for finding the best clustering number. Thirdly, the detection speed of the pruned model improves greatly. Lastly, the method we propose can be used not only for Retinanet, but also for other CNN models. Its effect will be verified in future work.

Despite the rapid evolution of Internet protocol-based messaging services, SMS still remains an indisputable communication service in our lives until today. For example, several businesses consider that text messages are more effective than e-mails. This is because 82% of SMSs are read within 5 min., but consumers only open one in four e-mails they receive. The importance of SMS for mobile phone users has attracted the attention of spammers. In fact, the volume of SMS spam has increased considerably in recent years with the emergence of new security threats, such as SMiShing. In this paper, we propose a hybrid deep learning model for detecting SMS spam messages. This detection model is based on the combination of two deep learning methods CNN and LSTM. It is intended to deal with mixed text messages that are written in Arabic or English. For the comparative evaluation, we also tested other well-known machine learning algorithms. The experimental results that we present in this paper show that our CNN-LSTM model outperforms the other algorithms. It achieved a very good accuracy of 98.37%.

Various defects are formed on the workpiece surface during the production process. Workpiece surface defects are classified according to various characteristics, which includes a bumped surface, scratched surface and pit surface. Suppliers analyze the cause of workpiece surface defects through the defect types and thus determines the subsequent processing. Therefore, the correct classification is essential regarding workpiece surface defects. In this paper, a multi-classifier decision-level fusion classification model for workpiece surface defects based on a convolutional neural network (CNN) was proposed. In the proposed model, the histogram of oriented gradient (HOG) was used to extract the features of the second fully connected layer of the CNN, and the features of the HOG were further extracted by using the local binary patterns (LBP), which was called the HOG&ndash, LBP feature extraction. Finally, this paper designed a symmetry ensemble classifier, which was used to classify the features of the last fully connected layer of the CNN and the features of the HOG&ndash, LBP. The comprehensive decision was made by fusing the classification results of the symmetry structure channels. The experiments were carried out, and the results showed that the proposed model could improve the accuracy of the workpiece surface defect classification.

In this paper, a hybrid neural network (HNN) that combines a convolutional neural network (CNN) and long short-term memory neural network (LSTM) is proposed to extract the high-level characteristics of materials for critical temperature (Tc) prediction of superconductors. Firstly, by obtaining 73,452 inorganic compounds from the Materials Project (MP) database and building an atomic environment matrix, we obtained a vector representation (atomic vector) of 87 atoms by singular value decomposition (SVD) of the atomic environment matrix. Then, the obtained atom vector was used to implement the coded representation of the superconductors in the order of the atoms in the chemical formula of the superconductor. The experimental results of the HNN model trained with 12,413 superconductors were compared with three benchmark neural network algorithms and multiple machine learning algorithms using two commonly used material characterization methods. The experimental results show that the HNN method proposed in this paper can effectively extract the characteristic relationships between the atoms of superconductors, and it has high accuracy in predicting the Tc.

Artificial Intelligence (AI) combines computer science and robust datasets to mimic natural intelligence demonstrated by human beings to aid in problem-solving and decision-making involving consciousness up to a certain extent. From Apple’s virtual personal assistant, Siri, to Tesla’s self-driving cars, research and development in the field of AI is progressing rapidly along with privacy concerns surrounding the usage and storage of user data on external servers which has further fueled the need of modern ultra-efficient AI networks and algorithms. The scope of the work presented within this paper focuses on introducing a modern image classifier which is a light-weight and ultra-efficient CNN intended to be deployed on local embedded systems, also known as edge devices, for general-purpose usage. This work is an extension of the award-winning paper entitled ‘CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems’ published for the 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC). The proposed neural network dubbed CondenseNeXtV2 utilizes a new self-querying augmentation policy technique on the target dataset along with adaption to the latest version of PyTorch framework and activation functions resulting in improved efficiency in image classification computation and accuracy. Finally, we deploy the trained weights of CondenseNeXtV2 on NXP BlueBox which is an edge device designed to serve as a development platform for self-driving cars, and conclusions will be extrapolated accordingly.

Plant diseases pose a severe threat to crop yield. This necessitates the rapid identification of diseases affecting various crops using modern technologies. Many researchers have developed solutions to the problem of identifying plant diseases, but it is still considered a critical issue due to the lack of infrastructure in many parts of the world. This paper focuses on detecting and classifying diseases present in the leaf images by adopting a hybrid learning model. The proposed hybrid model uses k-means clustering for detecting the disease area from the leaf and a Convolutional Neural Network (CNN) for classifying the type of disease based on comparison between sampled and testing images. The images of leaves under consideration may be symmetrical or asymmetrical in shape. In the proposed methodology, the images of various leaves from diseased plants were first pre-processed to filter out the noise present to get an enhanced image. This improved image enabled detection of minute disease-affected regions. The infected areas were then segmented using k-means clustering algorithm that locates only the infected (diseased) areas by masking the leaves’ green (healthy) regions. The grey level co-occurrence matrix (GLCM) methodology was used to fetch the necessary features from the affected portions. Since the number of fetched features was insufficient, more synthesized features were included, which were then given as input to CNN for training. Finally, the proposed hybrid model was trained and tested using the leaf disease dataset available in the UCI machine learning repository to examine the characteristics between trained and tested images. The hybrid model proposed in this paper can detect and classify different types of diseases affecting different plants with a mean classification accuracy of 92.6%. To illustrate the efficiency of the proposed hybrid model, a comparison was made against the following classification approaches viz., support vector machine, extreme learning machine-based classification, and CNN. The proposed hybrid model was found to be more effective than the other three.

This paper describes the implementation of real time human activity recognition systems in public areas. The objective of the study is to develop an alarm system to identify people who do not care for their surrounding environment. In this research, the actions recognized are limited to littering activity using two methods, i.e., CNN and CNN-LSTM. The proposed system captures, classifies, and recognizes the activity by using two main components, a namely camera and mini-PC. The proposed system was implemented in two locations, i.e., Sekanak River and the mini garden near the Sekanak market. It was able to recognize the littering activity successfully. Based on the proposed model, the validation results from the prediction of the testing data in simulation show a loss value of 70% and an accuracy value of 56% for CNN of model 8 that used 500 epochs and a loss value of 10.61%, and an accuracy value of 97% for CNN-LSTM that used 100 epochs. For real experiment of CNN model 8, it is obtained 66.7% and 75% success for detecting littering activity at mini garden and Sekanak River respectively, while using CNN-LSTM in real experiment sequentially gives 94.4% and 100% success for mini garden and Sekanak river.

This paper suggests an algorithm for extracting the location of a building from satellite imagery and using that information to modify the roof content. The materials are determined by measuring the conditions where the building is located and detecting the position of a building in broad satellite images. Depending on the incomplete roof or material, there is a greater possibility of great damage caused by disaster situations or external shocks. To address these problems, we propose an algorithm to detect roofs and classify materials in satellite images. Satellite imaging locates areas where buildings are likely to exist based on roads. Using images of the detected buildings, we classify the material of the roof using a proposed convolutional neural network (CNN) model algorithm consisting of 43 layers. In this paper, we propose a CNN structure to detect areas with buildings in large images and classify roof materials in the detected areas.

Hospitals need to invest a lot of manpower to manually input the contents of medical invoices (nearly 300,000,000 medical invoices a year) into the medical system. In order to help the hospital save money and stabilize work efficiency, this paper designed a system to complete the complicated work using a Gaussian blur and smoothing&ndash, convolutional neural network combined with a recurrent neural network (GBS-CR) method. Gaussian blur and smoothing (GBS) is a novel preprocessing method that can fix the breakpoint font in medical invoices. The combination of convolutional neural network (CNN) and recurrent neural network (RNN) was used to raise the recognition rate of the breakpoint font in medical invoices. RNN was designed to be the semantic revision module. In the aspect of image preprocessing, Gaussian blur and smoothing were used to fix the breakpoint font. In the period of making the self-built dataset, a certain proportion of the breakpoint font (the font of breakpoint is 3, the original font is 7) was added, in this paper, so as to optimize the Alexnet&ndash, Adam&ndash, CNN (AA-CNN) model, which is more suitable for the recognition of the breakpoint font than the traditional CNN model. In terms of the identification methods, we not only adopted the optimized AA-CNN for identification, but also combined RNN to carry out the semantic revisions of the identified results of CNN, meanwhile further improving the recognition rate of the medical invoices. The experimental results show that compared with the state-of-art invoice recognition method, the method presented in this paper has an average increase of 10 to 15 percentage points in recognition rate.

Arterial hypertension (HT) is a chronic condition of elevated blood pressure (BP), which may cause increased incidence of cardiovascular disease, stroke, kidney failure and mortality. If the HT is diagnosed early, effective treatment can control the BP and avert adverse outcomes. Physiological signals like electrocardiography (ECG), photoplethysmography (PPG), heart rate variability (HRV), and ballistocardiography (BCG) can be used to monitor health status but are not directly correlated with BP measurements. The manual detection of HT using these physiological signals is time consuming and prone to human errors. Hence, many computer-aided diagnosis systems have been developed. This paper is a systematic review of studies conducted on the automated detection of HT using ECG, HRV, PPG and BCG signals. In this review, we have identified 23 studies out of 250 screened papers, which fulfilled our eligibility criteria. Details of the study methods, physiological signal studied, database used, various nonlinear techniques employed, feature extraction, and diagnostic performance parameters are discussed. The machine learning and deep learning based methods based on ECG and HRV signals have yielded the best performance and can be used for the development of computer-aided diagnosis of HT. This work provides insights that may be useful for the development of wearable for continuous cuffless remote monitoring of BP based on ECG and HRV signals.

The fingerprint is one of the leading biometric modalities that is used worldwide for authenticating the identity of persons. Over time, a lot of research has been conducted to develop automatic fingerprint verification techniques. However, due to different authentication needs, the use of different sensors and the fingerprint verification systems encounter cross-sensor matching or sensor interoperability challenges, where different sensors are used for the enrollment and query phases. The challenge is to develop an efficient, robust and automatic system for cross-sensor matching. This paper proposes a new cross-matching system (SiameseFinger) using the Siamese network that takes the features extracted using the Gabor-HoG descriptor. The proposed Siamese network is trained using adversarial learning. The SiameseFinger was evaluated on two benchmark public datasets FingerPass and MOLF. The results of the experiments presented in this paper indicate that SiameseFinger achieves a comparable performance with that of the state-of-the-art methods.

Recently, unmanned aerial vehicles (UAVs) have been broadly applied to the remote sensing field. For a great number of UAV images, deep learning has been reinvigorated and performed many results in agricultural applications. The popular image datasets for deep learning model training are generated for general purpose use, in which the objects, views, and applications are for ordinary scenarios. However, UAV images possess different patterns of images mostly from a look-down perspective. This paper provides a verified annotated dataset of UAV images that are described in data acquisition, data preprocessing, and a showcase of a CNN classification. The dataset collection consists of one multi-rotor UAV platform by flying a planned scouting routine over rice paddies. This paper introduces a semi-auto annotation method with an ExGR index to generate the training data of rice seedlings. For demonstration, this study modified a classical CNN architecture, VGG-16, to run a patch-based rice seedling detection. The k-fold cross-validation was employed to obtain an 80/20 dividing ratio of training/test data. The accuracy of the network increases with the increase of epoch, and all the divisions of the cross-validation dataset achieve a 0.99 accuracy. The rice seedling dataset provides the training-validation dataset, patch-based detection samples, and the ortho-mosaic image of the field.

Web 2.0 technology enables customers to share electronic word of mouth (eWOM) about their experiences. eWOM offers great market insights to the organization, and important for organization’s success. eWOM monitoring and management is one of the major contemporary challenges for the organization, because of high volume and frequency of the content. It is nearly impossible for an organization to manually monitor content generated by each user. In this paper, we propose sentiment analysis as an alternative method for analysis of emotions and behavioral intentions in real-time data. Sentiment analysis is performed on women’s e-clothing reviews collected from the Kaggle data repository. The dataset consists of 23,486 reviews, comprising ten feature variables. This study applied artificial neural network techniques to determine polarity of the data in terms of positive or negative. Sentiment analysis was performed by using two artificial neural networks, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), to classify the review as recommended (positive) or not recommended (negative). The proposed models have been evaluated on these performance measuring parameters: accuracy, recall, specificity, F1-score and roc-curve. The LSTM method outperformed CNN and achieved classification accuracy of 91.69%, specificity 92.81%, sensitivity 76.95%, and 56.67% F1-score. Based on results of this study, LSTM technique is highly recommended for the sentiment analysis of unstructured text-based user-generated content.

Lung cancer causes more deaths globally than any other type of cancer. To determine the best treatment, detecting EGFR and KRAS mutations is of interest. However, non-invasive ways to obtain this information are not available. Furthermore, many times there is a lack of big enough relevant public datasets, so the performance of single classifiers is not outstanding. In this paper, an ensemble approach is applied to increase the performance of EGFR and KRAS mutation prediction using a small dataset. A new voting scheme, Selective Class Average Voting (SCAV), is proposed and its performance is assessed both for machine learning models and CNNs. For the EGFR mutation, in the machine learning approach, there was an increase in the sensitivity from 0.66 to 0.75, and an increase in AUC from 0.68 to 0.70. With the deep learning approach, an AUC of 0.846 was obtained, and with SCAV, the accuracy of the model was increased from 0.80 to 0.857. For the KRAS mutation, both in the machine learning models (0.65 to 0.71 AUC) and the deep learning models (0.739 to 0.778 AUC), a significant increase in performance was found. The results obtained in this work show how to effectively learn from small image datasets to predict EGFR and KRAS mutations, and that using ensembles with SCAV increases the performance of machine learning classifiers and CNNs. The results provide confidence that as large datasets become available, tools to augment clinical capabilities can be fielded.

Understanding atmospheric motions and projecting climate changes depends significantly on cloud types, i.e., different cloud types correspond to different atmospheric conditions, and accurate cloud classification can help forecasts and meteorology-related studies to be more effectively directed. However, accurate classification of clouds is challenging and often requires certain manual involvement due to the complex cloud forms and dispersion. To address this challenge, this paper proposes an improved cloud classification method based on a densely connected hybrid convolutional network. A dense connection mechanism is applied to hybrid three-dimensional convolutional neural network (3D-CNN) and two-dimensional convolutional neural network (2D-CNN) architectures to use the feature information of the spatial and spectral channels of the FY-4A satellite fully. By using the proposed network, cloud categorization solutions with a high temporal resolution, extensive coverage, and high accuracy can be obtained without the need for any human intervention. The proposed network is verified using tests, and the results show that it can perform real-time classification tasks for seven different types of clouds and clear skies in the Chinese region. For the CloudSat 2B-CLDCLASS product as a test target, the proposed network can achieve an overall accuracy of 95.2% and a recall of more of than 82.9% for all types of samples, outperforming the other deep-learning-based techniques.

HAR technology uses computer and machine vision to analyze human activity and gestures by processing sensor data. The 3-axis acceleration and gyro sensor data are particularly effective in measuring human activity as they can calculate movement speed, direction, and angle. Our paper emphasizes the importance of developing a method to expand the recognition range of human activity due to the many types of activities and similar movements that can result in misrecognition. The proposed method uses 3-axis acceleration and gyro sensor data to visually define human activity patterns and improve recognition accuracy, particularly for similar activities. The method involves converting the sensor data into an image format, removing noise using time series features, generating visual patterns of waveforms, and standardizing geometric patterns. The resulting data (1D, 2D, and 3D) can simultaneously process each type by extracting pattern features using parallel convolution layers and performing classification by applying two fully connected layers in parallel to the merged data from the output data of three convolution layers. The proposed neural network model achieved 98.1% accuracy and recognized 18 types of activities, three times more than previous studies, with a shallower layer structure due to the enhanced input data features.

The dairy industry has a long supply chain that involves dairy farmers, enterprises, consumers, and the government. The stable growth of consumer groups is the driving force for the sustainable development of the dairy industry. However, in recent years, sustainable development of the dairy industry has faced great challenges due to the constant changes in the global climate environment and the increasing uncertainty of the international economic environment. Therefore, it is essential to systematically monitor and accurately predict the consumption market of dairy products to ensure that the government, dairy enterprises, and dairy farmers can share information in a timely manner and take effective measures to cope with the changes in the dairy consumption market without disturbing the normal pricing mechanism of the dairy market. The purpose of the conducted research is to systematically monitor and accurately predict the dairy product consumption market while consistently delivering dependable forecasts of consumer behavior in the dairy industry. In this paper, we proposed a raw milk price prediction framework (RMP-CPR) to analyze consumer behavior based on the relationship between milk price and dairy consumption. This study concludes that dairy consumption behavior can be predicted accurately by predicting the price of raw milk based on the proposed framework (RMP-CPR). Our research explores a new angle for studying consumer behavior. The results can assist dairy enterprises in developing accurate marketing strategies based on the forecast results of dairy consumption, thereby enhancing their competitiveness in the market. Policymakers can also use the forecast results of the development trend of the dairy consumption market to adjust corresponding policies in a timely manner. This can help to balance the interests among consumers, dairy enterprises, dairy farmers, and other relevant stakeholders and effectively maintain the sustainable and healthy development of the dairy market.

A bearing is a key component in rotating machinery. The prompt monitoring of a bearings’ condition is critical for the reduction of mechanical accidents. With the rapid development of artificial intelligence technology in recent years, machine learning-based intelligent fault diagnosis (IFD) methods have achieved remarkable success in the field of bearing condition monitoring. However, most algorithms are developed based on computer platforms that focus on analyzing offline, rather than real-time, signals. In this paper, an edge intelligence diagnosis method called S-AlexNet, which is based on a parameter transplantation convolutional neural network (CNN), is proposed. The method deploys the lightweight IFD method in a low-cost embedded system to monitor the bearing status in real time. Firstly, a lightweight IFD algorithm model is designed for embedded systems. The model is trained on a PC to obtain optimal parameters, such as the model’s weights and bias. Finally, the optimal parameters are transplanted into the embedded system model to identify the bearing status on the edge side. Two datasets were used to validate the performance of the proposed method. The validation using the CWRU dataset shows that the proposed method achieves an average prediction accuracy of 94.4% on the test set. The validation using self-built data shows that the proposed method can identify bearing operating status in embedded systems with an average prediction accuracy of 99.81%. The results indicate that the proposed method has the advantages of high recognition accuracy, low model complexity, low cost, and high portability, which allow for the simple and effective implementation of the edge IFD of bearings in embedded systems.

Honeybees are vital to both the agricultural industry and the wider ecological system, most importantly for their role as major pollinators of flowering plants, many of which are food crops. Honeybee colonies are dependent on having a healthy queen for their long-term survival since the queen bee is the only reproductive female in the colony. Thus, as the death or loss of the queen is of great negative impact for the well-being of a honeybee colony, beekeepers need to be aware if a queen has died in any of their hives so that appropriate remedial action can be taken. In this paper, we describe our approaches to using acoustic signals recorded in beehives and machine learning algorithms to identify whether beehives do or do not contain a healthy queen. Our results are extremely positive and should help beekeepers decide whether intervention is needed to preserve the colony in each of their hives.

Speaker Recognition (SR) is a common task in AI-based sound analysis, involving structurally different methodologies such as Deep Learning or “traditional” Machine Learning (ML). In this paper, we compared and explored the two methodologies on the DEMoS dataset consisting of 8869 audio files of 58 speakers in different emotional states. A custom CNN is compared to several pre-trained nets using image inputs of spectrograms and Cepstral-temporal (MFCC) graphs. AML approach based on acoustic feature extraction, selection and multi-class classification by means of a Naïve Bayes model is also considered. Results show how a custom, less deep CNN trained on grayscale spectrogram images obtain the most accurate results, 90.15% on grayscale spectrograms and 83.17% on colored MFCC. AlexNet provides comparable results, reaching 89.28% on spectrograms and 83.43% on MFCC.The Naïve Bayes classifier provides a 87.09% accuracy and a 0.985 average AUC while being faster to train and more interpretable. Feature selection shows how F0, MFCC and voicing-related features are the most characterizing for this SR task. The high amount of training samples and the emotional content of the DEMoS dataset better reflect a real case scenario for speaker recognition, and account for the generalization power of the models.

Creating machines that behave and work in a way similar to humans is the objective of artificial intelligence (AI). In addition to pattern recognition, planning, and problem-solving, computer activities with artificial intelligence include other activities. A group of algorithms called “deep learning” is used in machine learning. With the aid of magnetic resonance imaging (MRI), deep learning is utilized to create models for the detection and categorization of brain tumors. This allows for the quick and simple identification of brain tumors. Brain disorders are mostly the result of aberrant brain cell proliferation, which can harm the structure of the brain and ultimately result in malignant brain cancer. The early identification of brain tumors and the subsequent appropriate treatment may lower the death rate. In this study, we suggest a convolutional neural network (CNN) architecture for the efficient identification of brain tumors using MR images. This paper also discusses various models such as ResNet-50, VGG16, and Inception V3 and conducts a comparison between the proposed architecture and these models. To analyze the performance of the models, we considered different metrics such as the accuracy, recall, loss, and area under the curve (AUC). As a result of analyzing different models with our proposed model using these metrics, we concluded that the proposed model performed better than the others. Using a dataset of 3264 MR images, we found that the CNN model had an accuracy of 93.3%, an AUC of 98.43%, a recall of 91.19%, and a loss of 0.25. We may infer that the proposed model is reliable for the early detection of a variety of brain tumors after comparing it to the other models.

The tremendous growth in online activity and the Internet of Things (IoT) led to an increase in cyberattacks. Malware infiltrated at least one device in almost every household. Various malware detection methods that use shallow or deep IoT techniques were discovered in recent years. Deep learning models with a visualization method are the most commonly and popularly used strategy in most works. This method has the benefit of automatically extracting features, requiring less technical expertise, and using fewer resources during data processing. Training deep learning models that generalize effectively without overfitting is not feasible or appropriate with large datasets and complex architectures. In this paper, a novel ensemble model, Stacked Ensemble—autoencoder, GRU, and MLP or SE-AGM, composed of three light-weight neural network models—autoencoder, GRU, and MLP—that is trained on the 25 essential and encoded extracted features of the benchmark MalImg dataset for classification was proposed. The GRU model was tested for its suitability in malware detection due to its lesser usage in this domain. The proposed model used a concise set of malware features for training and classifying the malware classes, which reduced the time and resource consumption in comparison to other existing models. The novelty lies in the stacked ensemble method where the output of one intermediate model works as input for the next model, thereby refining the features as compared to the general notion of an ensemble approach. Inspiration was drawn from earlier image-based malware detection works and transfer learning ideas. To extract features from the MalImg dataset, a CNN-based transfer learning model that was trained from scratch on domain data was used. Data augmentation was an important step in the image processing stage to investigate its effect on classifying grayscale malware images in the MalImg dataset. SE-AGM outperformed existing approaches on the benchmark MalImg dataset with an average accuracy of 99.43%, demonstrating that our method was on par with or even surpassed them.

This paper proposes an efficient dynamic reconfigurable CNN accelerator (EDRCA) for FPGAs to tackle the issues of limited hardware resources and low energy efficiency in the deployment of convolutional neural networks on embedded edge computing devices. First, a configuration layer sequence optimization method is proposed to minimize the configuration time overhead and improve performance. Second, accelerator templates for dynamic regions are designed to create a unified high-speed interface and enhance operational performance. The dynamic reconfigurable technology is applied on the Xilinx KV260 FPGA platform to design the EDRCA accelerator, resolving the hardware resource constraints in traditional accelerator design. The YOLOV2-TINY object detection network is used to test the EDRCA accelerator on the Xilinx KV260 platform using floating point data. Results at 250 MHz show a computing performance of 75.1929 GOPS, peak power consumption of 5.25 W, and power efficiency of 13.6219 GOPS/W, indicating the potential of the EDRCA accelerator for edge intelligence computing.

In the construction process of an intelligent pumping station, the parameter calibration of the pumping station unit is very important. In actual engineering, the working parameters of the pumping station are affected by complex working conditions and natural factors, so that it is difficult to establish a traditional physical model for the pumping station. This paper uses a data-driven method to apply the hybrid model of the convolutional neural network (CNN) and long-term short-term memory network (LSTM) to water level prediction in pumping stations and adds self-attention mechanism feature selection and a bagging optimization algorithm. Then, after an error analysis of the hybrid model, a performance comparison experiment with the separate model was conducted. The historical data of the pumping station project provided by the Tuancheng Lake Management Office of Beijing South-to-North Water Diversion Project was used to train and verify the proposed pumping station water level prediction model. The results show that the CNN–LSTM model based on the self-attention mechanism has higher accuracy than the separate CNN model and LSTM model, with a correlation coefficient (R2) of 0.72 and a mean absolute error (MAE) of 19.14. The model can effectively solve the problem of water level prediction in the front and rear pools under complex pumping station conditions.

Knowledge acquisition and reasoning are essential in intelligent welding decisions. However, the challenges of unstructured knowledge acquisition and weak knowledge linkage across phases limit the development of welding intelligence, especially in the integration of domain information engineering. This paper proposes a cognitive model combining image recognition and a knowledge graph. A CNN is used as the perception layer to obtain direct information. Automated logic rules based on a knowledge graph are described to enable information integration in the knowledge reasoning domain. In addition, a welding knowledge graph of the bogie frame was constructed based on entity and relationship recognition. CNN models with different network structures were compared and trained under supervised conditions. In the results, the InceptionV1 network obtained a high score (0.758 for the thickness relation, 0.642 for the groove form, 0.704 for the joint type, and 0.835 for the base material form). The proposed model showed positive performance in terms of accuracy, interpretation, knowledge coverage, scalability, and portability compared with several other methods. The model can effectively address the abovementioned limitations and is important for welding manufacturing with engineering information integration.

Polarimetric synthetic aperture radar (PolSAR) has unique advantages in building extraction due to its sensitivity to building structures and all-time/all-weather imaging capabilities. However, the structure of buildings is complex, and buildings are easily confused with other objects in polarimetric SAR images. The speckle noise of SAR images will affect the accuracy of building extraction. This paper proposes a novel building extraction approach from PolSAR images with statistical texture and polarization features by using a convolutional neural network and superpixel. A feature space that is sensitive to building, including G0 statistical texture and PualiRGB features, is constructed and used as CNN input. Considering that the building boundary of the CNN classification result is inaccurate due to speckle noise, the simple linear iterative cluster (SLIC) superpixel is utilized to constrain the building extraction result. Finally, the effectiveness of the proposed method has been verified by experimenting with PolSAR images from three different sensors, including ESAR, GF-3, and RADARSAT-2. Experiment results show that compared with the other five PolSAR building extraction methods including threshold, SVM, RVCNN, and PFDCNN, our method without superpixel constraint, the F1-score of this method is the highest, reaching 84.22%, 91.24%, and 87.49%, respectively. The false alarm rate of this method is at least 10% lower and the F1 index is at least 6% higher when the building extraction accuracy is comparable. Further, the discussion and method parameter analysis results show that increasing the use of G0 statistical texture parameters can improve building extraction accuracy and reduce false alarms, and the introduction of superpixel constraints can further reduce false alarms.

Examining and predicting skin cancer from skin lesion images is challenging due to the complexity of the images. Early detection and treatment of skin lesion disease can prevent mortality as it can be curable. Computer-aided diagnosis (CAD) provides a second opinion for dermatologists as they can classify the type of skin lesion with high accuracy due to their ability to show various clinical identification features locally and globally. Convolutional neural networks (CNNs) have significantly improved the performance of CAD systems for medical image segmentation and classifications. However, tuning CNNs are challenging since the search space of all possible hyperparameter configurations is substantially vast. In this paper, we adopt a genetic algorithm to automatically configure a CNN model for an accurate, reliable, and robust automated skin lesion classification for early skin lesion diagnosis. The optimized CNN model uses four public datasets to train and be able to detect abnormalities based on skin lesion features in different orientations. The model achieves the best scores for each of the DICE coefficients, precision measure, and F-score. These scores compare better than other existing methods. Considering the success of this optimized model, it could be a valuable method to implement in clinical settings.

The development of robust anomaly-based network detection systems, which are preferred over static signal-based network intrusion, is vital for cybersecurity. The development of a flexible and dynamic security system is required to tackle the new attacks. Current intrusion detection systems (IDSs) suffer to attain both the high detection rate and low false alarm rate. To address this issue, in this paper, we propose an IDS using different machine learning (ML) and deep learning (DL) models. This paper presents a comparative analysis of different ML models and DL models on Coburg intrusion detection datasets (CIDDSs). First, we compare different ML- and DL-based models on the CIDDS dataset. Second, we propose an ensemble model that combines the best ML and DL models to achieve high-performance metrics. Finally, we benchmarked our best models with the CIC-IDS2017 dataset and compared them with state-of-the-art models. While the popular IDS datasets like KDD99 and NSL-KDD fail to represent the recent attacks and suffer from network biases, CIDDS, used in this research, encompasses labeled flow-based data in a simulated office environment with both updated attacks and normal usage. Furthermore, both accuracy and interpretability must be considered while implementing AI models. Both ML and DL models achieved an accuracy of 99% on the CIDDS dataset with a high detection rate, low false alarm rate, and relatively low training costs. Feature importance was also studied using the Classification and regression tree (CART) model. Our models performed well in 10-fold cross-validation and independent testing. CART and convolutional neural network (CNN) with embedding achieved slightly better performance on the CIC-IDS2017 dataset compared to previous models. Together, these results suggest that both ML and DL methods are robust and complementary techniques as an effective network intrusion detection system.

A thorough analysis of sports is becoming increasingly important during the training process of badminton players at both the recreational and professional level. Nowadays, game situations are usually filmed and reviewed afterwards in order to analyze the game situation, but these video set-ups tend to be difficult to analyze, expensive, and intrusive to set up. In contrast, we classified badminton movements using off-the-shelf accelerometer and gyroscope data. To this end, we organized a data capturing campaign and designed a novel neural network using different frame sizes as input. This paper shows that with only accelerometer data, our novel convolutional neural network is able to distinguish nine activities with 86% precision when using a sampling frequency of 50 Hz. Adding the gyroscope data causes an increase of up to 99% precision, as compared to, respectively, 79% and 88% when using a traditional convolutional neural network. In addition, our paper analyses the impact of different sensor placement options and discusses the impact of different sampling frequenciess of the sensors. As such, our approach provides a low cost solution that is easy to use and can collect useful information for the analysis of a badminton game.

This paper investigates eye behaviour through blinks activity during stress conditions. Although eye blinking is a semi-voluntary action, it is considered to be affected by one&rsquo, s emotional states such as arousal or stress. The blinking rate provides information towards this direction, however, the analysis on the entire eye aperture timeseries and the corresponding blinking patterns provide enhanced information on eye behaviour during stress conditions. Thus, two experimental protocols were established to induce affective states (neutral, relaxed and stress) systematically through a variety of external and internal stressors. The study populations included 24 and 58 participants respectively performing 12 experimental affective trials. After the preprocessing phase, the eye aperture timeseries and the corresponding features were extracted. The behaviour of inter-blink intervals (IBI) was investigated using the Markovian Analysis to quantify incidence dynamics in sequences of blinks. Moreover, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) network models were employed to discriminate stressed versus neutral tasks per cognitive process using the sequence of IBI. The classification accuracy reached a percentage of 81.3% which is very promising considering the unimodal analysis and the noninvasiveness modality used.

Hyperspectral imaging (HSI), measuring the reflectance over visible (VIS), near-infrared (NIR), and shortwave infrared wavelengths (SWIR), has empowered the task of classification and can be useful in a variety of application areas like agriculture, even at a minor level. Band selection (BS) refers to the process of selecting the most relevant bands from a hyperspectral image, which is a necessary and important step for classification in HSI. Though numerous successful methods are available for selecting informative bands, reflectance properties are not taken into account, which is crucial for application-specific BS. The present paper aims at crop mapping for agriculture, where physical properties of light and biological conditions of plants are considered for BS. Initially, bands were partitioned according to their wavelength boundaries in visible, near-infrared, and shortwave infrared regions. Then, bands were quantized and selected via metrics like entropy, Normalized Difference Vegetation Index (NDVI), and Modified Normalized Difference Water Index (MNDWI) from each region, respectively. A Convolutional Neural Network was designed with the finer generated sub-cube to map the selective crops. Experiments were conducted on two standard HSI datasets, Indian Pines and Salinas, to classify different types of crops from Corn, Soya, Fallow, and Romaine Lettuce classes. Quantitatively, overall accuracy between 95.97% and 99.35% was achieved for Corn and Soya classes from Indian Pines; between 94.53% and 100% was achieved for Fallow and Romaine Lettuce classes from Salinas. The effectiveness of the proposed band selection with Convolutional Neural Network (CNN) can be seen from the resulted classification maps and ablation study.

Off-grid technologies, such as solar home systems (SHS), offer the opportunity to alleviate global energy poverty, providing a cost-effective alternative to an electricity grid connection. However, there is a paucity of high-quality SHS electricity usage data and thus a limited understanding of consumers’ past and future usage patterns. This study addresses this gap by providing a rare large-scale analysis of real-time energy consumption data for SHS customers (n = 63,299) in Rwanda. Our results show that 70% of SHS users’ electricity usage decreased a year after their SHS was installed. This paper is novel in its application of a three-dimensional convolutional neural network (CNN) architecture for electricity load forecasting using time series data. It also marks the first time a CNN was used to predict SHS customers’ electricity consumption. The model forecasts individual households’ usage 24 h and seven days ahead, as well as an average week across the next three months. The last scenario derived the best performance with a mean squared error of 0.369. SHS companies could use these predictions to offer a tailored service to customers, including providing feedback information on their likely future usage and expenditure. The CNN could also aid load balancing for SHS based microgrids.

The number of grains within a panicle is an important index for rice breeding. Counting manually is laborious and time-consuming and hardly meets the requirement of rapid breeding. It is necessary to develop an image-based method for automatic counting. However, general image processing methods cannot effectively extract the features of grains within a panicle, resulting in a large deviation. The convolutional neural network (CNN) is a powerful tool to analyze complex images and has been applied to many image-related problems in recent years. In order to count the number of grains in images both efficiently and accurately, this paper applied a CNN-based method to detecting grains. Then, the grains can be easily counted by locating the connected domains. The final error is within 5%, which confirms the feasibility of CNN-based method for counting grains within a panicle.

In this paper, a novel short-term load forecasting method amalgamated with quantile regression random forest is proposed. Comprised with point forecasting, it is capable of quantifying the uncertainty of power load. Firstly, a bespoke 2D data preprocessing taking advantage of empirical mode decomposition (EMD) is presented. It can effectively assist subsequent point forecasting models to extract spatial features hidden in the 2D load matrix. Secondly, by exploiting multimodal deep neural networks (DNN), three short-term load point forecasting models are conceived. Furthermore, a tailor-made multimodal spatial–temporal feature extraction is proposed, which integrates spatial features, time information, load, and electricity price to obtain more covert features. Thirdly, relying on quantile regression random forest, the probabilistic forecasting method is proposed, which exploits the results from the above three short-term load point forecasting models. Lastly, the experimental results demonstrate that the proposed method outperforms its conventional counterparts.

The accurate detection of pineapples of different maturity levels in a complex field environment is the key step to achieving the early yield estimation and mechanized picking of pineapple. This study proposes a target detection model based on the improved YOLOv7 to achieve the accurate detection and maturity classification of pineapples in the field. First, the attention mechanism SimAM is inserted into the structure of the original YOLOv7 network to improve the feature extraction ability of the model. Then, the max-pooling convolution (MPConv) structure is improved to reduce the feature loss in the downsampling process. Finally, the non-maximum suppression (NMS) algorithm is replaced by the soft-NMS algorithm, with a better effect at improving the detection effect when pineapple is in occlusion or overlaps. According to the test, the mean average precision (mAP) and recall of the model proposed in this paper are 95.82% and 89.83%, which are 2.71% and 3.41% higher than those of the original YOLOv7, respectively. The maturity classification accuracy of the model and the detection performance under six different field scenarios were analyzed quantitatively. This method provides an effective scheme for the vision system of the field pineapple picking robot.

There are some problems in the shifting process of hydraulic CVT, such as irregularity, low stability and high failure rate. In this paper, the BP neural network and convolutional neural network are used for fault diagnosis of the HMCVT hydraulic system. Firstly, through experiments, 120 groups of pressure and flow data under normal and four typical fault modes were obtained and preprocessed; they were divided into 80 groups of training samples and 40 groups of test samples via random extraction, using the BP neural network model and convolutional neural network model for fault classification. The results show that compared with BP, PSO-BP and other models, the fault diagnosis rate of the BAS-BP neural network model can reach 92.5%, and the average diagnosis accuracy rate of the convolutional neural network can reach 97.5%, which can be effectively applied to the fault diagnosis of the HMCVT hydraulic system and provide some reference for the shifting reliability of hydraulic CVT.

A rapidly spreading epidemic, COVID-19 had a serious effect on millions and took many lives. Therefore, for individuals with COVID-19, early discovery is essential for halting the infection’s progress. To quickly and accurately diagnose COVID-19, imaging modalities, including computed tomography (CT) scans and chest X-ray radiographs, are frequently employed. The potential of artificial intelligence (AI) approaches further explored the creation of automated and precise COVID-19 detection systems. Scientists widely use deep learning techniques to identify coronavirus infection in lung imaging. In our paper, we developed a novel light CNN model architecture with watershed-based region-growing segmentation on Chest X-rays. Both CT scans and X-ray radiographs were employed along with 5-fold cross-validation. Compared to earlier state-of-the-art models, our model is lighter and outperformed the previous methods by achieving a mean accuracy of 98.8% on X-ray images and 98.6% on CT scans, predicting the rate of 0.99% and 0.97% for PPV (Positive predicted Value) and NPV (Negative predicted Value) rate of 0.98% and 0.99%, respectively.

In the past few years, the assessment of Parkinson’s disease (PD) has mainly been based on the clinician’s examination, the patient’s medical history, and self-report. Parkinson’s disease may be misdiagnosed due to a lack of clinical experience. Moreover, it is highly subjective and is not conducive to reflecting a true result. Due to the high incidence rate and increasing trend of PD, it is significant to use objective monitoring and diagnostic tools for accurate and timely diagnosis. In this paper, we designed a low-level feature extractor that uses convolutional layers to extract local information about an image and a high-level feature extractor that extracts global information about an image through the autofocus mechanism. PD is detected by fusing local and global information. The model is trained and evaluated on two publicly available datasets. Experiments have shown that our model has a strong advantage in diagnosing whether people have PD; gait-based analysis and recognition can also provide effective evidence for the early diagnosis of PD.