Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

This study extends the CGAN-based MODIS cloud vertical-profile (64×64-scene, about 70km width×15km height) retrieval technique developed by Leinonen et al. (2019) [1] to construct seamless 3D cloud fields for the MODIS granules [2]. Firstly, the accuracy and spatial continuity of the Leinonen et al. [1] retrievals are statistically evaluated. Then, according to the characteristics of the retrieval error, a spatially overlapping-scene ensemble generation method and a bi-directional Ensemble Binning Probability Fusion (CGAN-BEBPF) technique are developed, which improves the CGAN retrieval accuracy and support to construct seamless 3D clouds. The CGAN-BEBPF technique involves three steps: cloud masking, intensity scaling, and optimal value selection. It ensures adequate coverage of the low reflectivity areas while preserving the high reflectivity cloud cores. The technique is applied to retrieve the 3D cloud fields of Typhoon Chaba and a multi-cell convective system. The cloud structures of the CGAN-BEBPF results are highly consistent with the ground-based radar observations. It can retrieve weak clouds at the top levels of convective storms and hurricanes that were missed by ground-based radars and fill the gaps of the ground-based radar lower-level PPI scan. Overall, CGAN-BEBPF can be automated to retrieve the rich informative 3D structures of typhoons and severe convective systems over the oceans along the MODIS swath, which certainly presents great value for improving maritime and near-shore typhoons and convection prediction and other cloud-sensitive applications.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Classifying network flow subsequences in an Industrial IoT gateway is an effective method for identifying Industrial IoT faults. This paper proposes a subsequence classification algorithm SSGBUL-IKNN based on unsupervised learning encoding to address the problem of low classification accuracy. Firstly, we built a network module based on unsupervised learning to encode the flow sequence of the Industrial IoT gateway. In the encoding module, a subsequence calibration algorithm controls the increasing error during the coding process. Then, the specific fault type is obtained through an improved KNN classification algorithm based on the indication distance source from the integrated coding sequences converted by multi-dimensional network flow sequences. The test result on three Industrial IoT datasets of a sewage treatment plant shows that the accuracy of SSGBUL-IKNN in this paper exceeds 92%, significantly higher than the algorithm DTW and TSF. It reaches the classification requirements of Industrial IoT fault diagnosis.

This review provides a systematic analysis of the literature data on the electrodeposition of composite coatings using plating baths based on a new generation of room-temperature ionic liquids, known as deep eutectic solvents (DESs). Such systems offer several advantages over traditionally used aqueous electrolytes and organic solvent-based electrolytes. The colloidal-chemical properties of suspension and colloidal electrolytes for composite deposition are thoroughly examined. New theories describing the kinetics of co-deposition of composite layers are characterized. The kinetics and mechanism of electrochemical deposition processes of composite coatings with metallic matrices are discussed. Case studies regarding the electrodeposition of composite coatings based on electrodeposited copper, silver, zinc, tin, nickel, cobalt, and chromium from DES-assisted electroplating baths are described and systematized. The main prospective directions for further research in the discussed scientific area are highlighted.

Existing studies often lack a systematic solution for Unmanned Aerial Vehicles (UAV) inspection system, which hinders their widespread application in crack detection. To enhance its practicality, this study proposes a formal and systematic framework for UAV inspection systems, specifically designed for automatic crack detection and pavement distress evaluation. The framework integrates UAV data acquisition, deep learning based crack identification, and road damage assessment in a comprehensive and orderly manner. Firstly, the flight control strategy is presented, and road crack data is collected using the DJI Mini 2 UAV imagery, establishing a high-quality UAV crack image datasets with ground truth information. Secondly, a validation and comparison study is conducted to enhance the automatic crack detection capability and provide an appropriate deployment scheme for UAV inspection systems. This study develops automatic crack detection models based on mainstream deep learning algorithms(namely, Faster-RCNN, YOLOv5s, YOLOv7-tiny, and YOLOv8s) in urban road scenarios. The results demonstrate that the Faster-RCNN algorithm achieves the highest accuracy and is suitable for online data collection of UAV and offline inspection at work stations. Meanwhile, the YOLO models, while slightly lower in accuracy, are the fastest algorithm and are suitable for lightweight deployment of UAV with online collection and real-time inspection. Quantitative measurement methods for road cracks are presented to assess road damage, which will enhance the application of UAV inspection systems and provide factual evidence for maintenance decisions made by road authorities.

The accurate and timely assessment of lymph node involvement is paramount in the management of patients with malignant tumors, owing to its direct correlation with cancer staging, therapeutic strategy formulation, and prognostication. Dual-energy computed tomography (DECT), as a burgeoning imaging modality, has shown promising results in the diagnosis and prediction of preoperative metastatic lymph nodes in recent years. This article aims to explore the application of DECT in identifying metastatic lymph nodes (LNs) across various cancer types, including but not limited to thyroid carcinoma (focusing on papillary thyroid carcinoma), lung cancer, and colorectal cancer. Through this narrative review, we aim to elucidate the clinical relevance and utility of DECT in the detection and predictive assessment of lymph node metastasis in malignant tumors, thereby contributing to the broader academic discourse in oncologic radiology and diagnostic precision.

A thermal system in very deep Lake Tazawa (maximum depth, 423 m) was investigated by estimating the heat budget. In the heat budget estimate, the net heat input at lake surface and the heat input by river inflow and groundwater inflow were considered. Then, the heat loss by snowfall onto lake surface was taken into account. Meanwhile, lake water temperature was monitored at 0.2 m to the bottom by mooring temperature loggers for more than two years. The heat storage change of the lake from the loggers was calibrated by frequent vertical measurements of water temperature at every 0.1 m pitch by a profiler with high accuracy (± 0.01 °C). The heat storage change (W/m2) obtained by the temperature loggers reasonably accords to that from the heat budget estimate. In the heat budget, the net heat input at lake surface dominates the heat storage change, but the significant heat loss by river inflow sporadically occurred, which is caused by the relatively large discharge from a reservoir in the upper region. How deep the vertical water circulation in the lake occurs in winter was judged by the differences between water temperatures at 0.2 m depth and bottom and between vertical profiles of dissolved oxygen over winter. It is strongly suggested that the whole water circulation does not occur every winter, if any, very weak.

In recent years, there has been a growing interest in the prediction of facial age due to its diverse applications in fields such as security, entertainment, and healthcare. The current scourge of underaged voting in Nigeria is a problem and this research delves into the realm of facial age prediction by employing four well-known convolutional neural network (CNN) architectures, namely VGG16, ResNet50, Mobile Net, and VGG19 to predict chronological ages from facial pictures of person. The objective is to achieve precise age estimation from facial images, utilizing two datasets: UTKFace and CASIA African Facial Datasets. The results of this investigation are noteworthy. Specifically, the VGG16 model which demonstrated remarkable performance, yielding a Mean Absolute Error (MAE) of 1.76 when applied to the UTK-Face dataset. Additionally, when utilizing Mobile-Net, an unprecedented MAE of 1.10 was achieved for the Casia Africa Face Dataset. Notably, this marks the first instance of employing the dataset for facial age detection with CNNs, and this approach outperformed previous works, yielding the lowest MAE among all the studies reviewed.

The precise determination of the State-of-Health (SOH) of lithium-ion batteries is critical in the domain of battery management systems. The proposed model in this research paper emulates any deep learning or machine learning model by utilizing a Look Up Table (LUT) memory to store all activation inputs and their corresponding outputs. The operation that follows the completion of training is referred to as the LUT memory preparation procedure. The lookup operation performed on this method simply substitutes for the inference process. This is achieved by discretizing the input data and features before binarizing them. The term for the aforementioned operation is the LUT inference method. The procedure was evaluated in this study using two distinct neural network architectures: a bidirectional long short-term memory (LSTM) architecture and a standard fully connected neural network (FCNN). It is anticipated that considerably greater efficiency and velocity will be achieved during the inference procedure when the pre-trained deep neural network architecture is inferred directly. The principal aim of this research is to construct a lookup table that effectively establishes correlations between the SOH of lithium-ion batteries and ensures a degree of imprecision that is tolerable. According to the results obtained from the NASA PCoE lithium-ion battery dataset, the proposed methodology exhibits performance that is largely comparable to that of the initial machine learning models. Utilising the error assessment metrics RMSE, MAE, and (MAPE), the accuracy of SOH prediction has been quantitatively evaluated. The indicators mentioned above demonstrate a significant degree of accuracy when predicting SOH.

Scaffoldings play a critical role as temporary structures in supporting construction processes. Accidents at construction sites frequently stem from issues related to scaffoldings, including insufficient support caused by deviations from the construction design, insecure rod connections, or absence of cross bracing, which result in uneven loading and potential collapse, leading to casualties. In this study, we introduce a deep-learning-based, augmented reality (AR)-enabled system called scaffolding assembly deficiency detection system (SADDS) to assist field inspectors in identifying deficiencies in scaffolding assemblies. Inspectors have the flexibility to utilize SADDS through various devices, such as video cameras, mobile phones, or AR goggles (i.e., Microsoft HoloLens 2), for automated detection of deficiencies in scaffolding assemblies. The training test yielded satisfactory results, with a mean average precision of 0.89 and individual precision values of 0.96, 0.82, 0.90, and 0.89 for “qualified” frames and frames with the “missing cross-tie rod,” “missing lower-tie rod,” and “missing footboard” deficiencies, respectively. Field tests conducted at two construction sites demonstrated improved system performance compared to that in the training test. However, these field tests also revealed certain limitations of the SADDS system.

Space exploration presents vast prospects for scientific, industrial, and economic progress. This paper introduces the MeSat mission as a pioneering approach to Mars exploration. MeSat aims to deepen our understanding of Martian conditions and resources by employing an optimized Earth-to-Mars trajectory, enabling a comprehensive study of the Martian atmosphere and surface. The mission comprises a Cargo Microsatellite hosting three 6U CubeSats and two 3U CubeSats, deployed into four separate Mars orbits forming a constellation. Each CubeSat carries distinct payloads: a THz radiometer for water detection, a high-resolution surface camera, a top-tier spectrometer, and a Fourier Transform Spectrometer (FTS) for wind speed readings. This paper focuses on two pivotal innovations: the development of a 183GHz radiometer payload for detecting water on Mars and a optimal mission design algorithm that analyzes a fuel-efficient low-thrust trajectory from Earth to Mars. Regarding the THz payload for water detection, a subharmonic Schottky diode-based mixer is meticulously designed to efficiently down-convert radio signals. The down-converted signals are carefully analyzed using a customized Do-It-Yourself (DIY) spectrum meter, which facilitated the capture and processing of acquired data. To provide the necessary Local Oscillator signals for the mixer, a Tripler employing three-anode Schottky diodes is developed. Additionally, the Tripler requires a signal generator for its entry frequency, which is addressed by developing a DIY signal generator. Together, these components, comprising the Schottky diode mixer, Tripler, and DIY circuits, collectively form the complete THz payload, demonstrating exceptional power efficiency with a total consumption of only 3.7W. The study employs a dual-step hybrid optimization algorithm (PSO-Homotopy) to analyze fuel-efficient low-thrust trajectories from Earth to Mars, incorporating the Ephemeris dynamics model to account for gravitational perturbations in the entire solar system. In practical mission design, crucial factors like hyperbolic excess velocity, diverse opportunities for Earth launch and Mars rendezvous, varied propulsion systems, and Time of Flight (TOF) play vital roles in trajectory optimization.

Background: Genome-wide association studies (GWAS) have shed light on various complex diseases and traits, by detecting more than 400,000 associated genetic loci. This number is expected to drastically increase because of the use of novel artificial intelligence methods offering new ways to study the effects of variants. Deep learning using artificial neural networks (ANN) is a sub-field of artificial intelligence, which simulates how the human brain learns. We aimed at assessing the potential of deep learning in human genetic studies of Alzheimer’s Disease (AD) and how these compare to the traditional statistical methods used in GWAS, by simultaneously testing the two approaches on the same dataset, while discovering new genetic loci associated to AD. Methods: To address this aim, phenotypic and genome-wide SNP data from the UK Biobank was analysed on a binary outcome, AD diagnosis, in two different data balance options, of one-to-one and one-to-two case-control datasets, using 2,764 cases vs 2,764 controls and 5,528 controls respectively matched on gender, age, ethnicity, PC1-20 and genotyping array. Genetic data handling and GWAS were performed using PLINK, whereas neural networks were trained using GenNet, a new ANN tool, with the same datasets, separated into training (60%), validation (20%) and test (20%) sets. Neural network layers were determined using biological knowledge, by annotating SNPs to genes and genes to AD related pathways, using ANNOVAR annotations followed by GeneSCF and KEGG. Results: Significant associations were detected between four SNPs linked to two different genes and AD for the 1 to 1 case-control study design and six SNPs linked to four different genes for the 1 to 2 case-control study design by using PLINK. All identified regions have been previously associated to AD. GenNet identified twelve SNPs on seven genes to be associated with AD, all with biological plausibility, achieving an AUC of 0.80 when using three biologically determined layers and 0.73 when using two layers at the neural networks. No common top SNPs were identified between the machine learning and GWAS models. Conclusion: This is one of the first studies attempting to compare the traditional GWAS to more sophisticated state-of-art methods for understanding the genetic architecture of complex phenotypes using the same dataset. More systematic comparisons with such approaches on real data are needed to enable best practises for machine learning in the analysis of genome-wide genetic data.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum Tuberorsum L.) crops. In this paper, we present a mobile application for potato crop pest detection based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes. An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.76%, with MobileNetv2. Based on the results obtained, an offline mobile application was implemented, supported on devices with Android 4.1 or later, also featuring an information section on the 27 pests affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of pests affecting the same plant.

Capsizing accidents are regarded as marine accidents with a high rate of casualties per accident. Approximately 89% of all such accidents occur in small ships (vessels with gross tonnage less than 10 tons). Stability calculations are critical for assessing the risk of capsizing incidents and evaluating a ship's seaworthiness. Despite the high frequency of capsizing accidents involving small ships, they are generally exempt from adhering to stability regulations, thus remaining systemically exposed to the risk of capsizing. Moreover, the absence of essential design documents complicates direct ship stability calculations. This study utilizes hull form feature data—obtained from the general arrangement of small ships—as input for a deep learning model. The model is structured as a multilayer neural network and aims to infer hydrostatic curves, which is required data for stability calculations.

Academic researchers publish their work in various formats, such as papers, patents, and research reports, on different academic sites. When searching for a particular researcher's work, it can be challenging to pinpoint the right individual, especially when there are multiple researchers with the same name. In order to handle this issue, we propose a name disambiguation scheme of researchers with the same name based on heterogeneous academic sites. The proposed scheme collects and integrates research results from these varied academic sites, focusing on attributes crucial for disambiguation. It then employs clustering techniques to identify individuals who share the same name. Additionally, the proposed rule-based algorithm name disambiguation method and the existing deep learning-based identification method. This approach allows for the selection of the most accurate disambiguation scheme, taking into account the metadata available in the academic sites, using a multiclass classification approach. To demonstrate the effectiveness of the proposed method, we conduct various performance evaluations, measuring accuracy, recall, and the F1-measure, highlighting the scheme's superior performance in the name disambiguation.

Generative AI has gained enormous interest nowadays due to new applications like chatGPT, DALL E, Stable Difussion and Deep Fake. Particularly DALL E, Stable Difussion and others (Adobe Firefly, ImagineArt...) are able to create images from a text prompt and are also able to recreate real photographs. Due to this fact, intense research has arisen to create new image forensics applications able to distinguish between real captured images and videos and artificial ones. Detecting forgeries made with Deep Fake is one of the most researched issues. This paper is about another kind of forgery detection. The purpose of this research aims to detect photo realistic AI created images versus real photos coming from a physical camera. For this purpose, techniques that perform a pixel level feature extraction are used. First one is Photo Response Non-Uniformity (PRNU). PRNU is a special noise due to imperfections on the camera sensor that is used for source camera identification. The underlying idea is that AI images will have a different PRNU pattern. Second one is Error level analysis (ELA). This is other type of feature extraction traditionally used for detecting image editions. In fact, ELA is being used nowadays by photographers to detect manually AI created images. Both kinds of features are used to train Convolutional Neural Networks to differentiate between AI images and real photographs. Good results are obtained achieving accuracy rates over 95%. Both extraction methods are carefully assessed by computing precision/recall and F1-score measurements.

The rising number of unknown-type attacks on the Internet emphasizes the significance of developing efficient intrusion detection systems, even if machine learning-based techniques can detect unknown types of attacks. The necessity for innovative techniques is highlighted by the possibility that traditional machine learning techniques will not be sufficient for identifying these unknown types of attacks. In this research, we address this difficulty by proposing a deep learning-based solution: the log-cosh variational autoencoder (LVAE). When it comes to understanding intricate data distributions and creating freshly reconstructed data, LVAE inherits the strong modeling skills of the variational autoencoder (VAE). To better imitate discrete features of actual attacks and generate unknown types of attacks, this study develops an effective reconstruction loss term employing the logarithmic hyperbolic cosine (log-cosh) function in the log-cosh variational autoencoder (LVAE). When compared to conventional VAEs, LVAE exhibits promising potential for effectively generating data that closely resembles an unknown attack, a crucial capability for increasing the unknown attack detection rate. To categorize the generated unknown-type data, eight feature extraction and classification techniques were used. Using the most recent CICIDS2017 dataset, numerous experiments were carried out, training under varying amounts of real and unknown-type attacks. Our optimal experimental results outperformed several state-of-the-art techniques with accuracy and average F1 scores of 99.89% and 99.83%, respectively. Outstanding results were also shown by the suggested LVAE strategy for producing unknown attack data. In general, our work sets a strong basis for the accurate and efficient identification of unknown types of attacks and contributes to the development of intrusion detection techniques.

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.

With the escalating water scarcity in agriculture, a novel water-saving technique has emerged: drip irrigation with plastic-film mulch (DI). Root function is crucial for sustaining rice production, and understanding its response to DI is essential. However, few studies have evaluated root systems in rice varietals and examined which kind of root system contributes to improving rice grain yield and water productivity in DI. To fill this knowledge gap, we conducted a two-year field experiment comparing two irrigation systems: continuous flooding (CF) and DI. We analyzed their effectiveness with four rice varieties, including upland, F1 lowland, animal feed lowland, and lowland varieties. Vertical root distribution, root bleed-ing rate, photosynthetic-associated parameters, water productivity, and yield performance were analyzed. In our study, the average grain yield of varieties in the DI system (6.4t/ha) was equivalent to those in the CF system (6.6 t/ha). Compared to CF, DI demonstrated significant water-saving potential, saving approximately 35% of the total water supplied, resulting in higher water productivity. Among the varieties, the deep-root weight of the upland variety significantly increased by 51%. The deep-root ratio was positively correlated to transpiration rate, grain yield, and water productivity, which suggested that it contributed to high transpiration, thus maintaining a high carbon assimilation rate resulting in high yield and water productivity. Therefore, deep roots deserve consideration as a trait potentially corresponding to high yield under DI.

Three new polyketides (penidihydrocitrinins A–C, 1–3) and 14 known compounds (4–17) were isolated from the deep-sea-derived Penicillium citrinum W17. Their structures were elucidated by comprehensive analyses of 1D and 2D NMR, HRESIMS, and ECD calculations. Compounds 1–17 were evaluated for their anti-inflammatory and anti-osteoporotic bioactivities. All isolates exhibited significant inhibitory effects on microglial activation in LPS-stimulated BV-2 cells in a dose-response manner. Notably, compound 14 displayed the strongest effect with the IC50 value of 4.7 µM. Moreover, compounds 6, 7, and 8 not only suppressed osteoclastogenesis, but also promoted osteoblast mineralization.

In recent years, applying deep learning to solve physics problems has attracted much attention. Data-driven deep learning methods produce operators that can learn solutions to the whole system of partial differential equations. However, the existing methods are only evaluated on simple flow equations (e.g., Burger's equation), and only consider the generalization ability on different initial conditions. In this paper, we construct CFDBench, a benchmark with four classic problems in computational fluid dynamics (CFD): lid-driven cavity flow, laminar boundary layer flow in circular tubes, dam flows through the steps, and periodic Karman vortex street. Each flow problem includes data with various boundary conditions, fluid physical properties, and domain geometries. Compared to existing datasets, the advantages of CFDBench are (1) comprehensive. It contains common physical parameters such as velocity, pressure, and cavity fraction. (2) realistic. It is very suitable for deep learning solutions of fluid mechanics equations. (3) challenging. It has a certain learning difficulty, prompting to find models with strong learning ability. (4) standardized. CFDBench facilitates a comprehensive and fair comparison of different deep learning methods for CFD. We make appropriate modifications to popular deep neural networks to apply them to CFDBench and enable the accommodation of more changing inputs. The evaluation on CFDBench reveals some new shortcomings of existing works and we propose possible directions for solving such problems.

Facial emotion detection is a challenging task that deals with emotion recognition. It has applications in various domains, such as behavior analysis, surveillance systems and human-computer interaction (HCI). Numerous studies have been implemented to detect emotions, including classical machine learning algorithms and advanced deep learning algorithms. For the machine learning algorithm, the hand-crafted feature needs to be extracted, which is a tiring task and requires human effort. Whereas in deep learning models, automated feature extraction is employed from samples. Therefore, in this study, we have proposed a novel and efficient deep learning model based on Neural Architecture Search Network utilizing superior artificial networks such as RNN and child networks. We performed the training utilizing the FER 2013 dataset comprising seven classes: happy, angry, neutral, sad, surprise, fear, and disgust. Furthermore, we analyzed the robustness of the proposed model on CK+ datasets and comparing with existing techniques. Due to the implication of reinforcement learning in the network, most representative features are extracted from the sample network. It extracts all key features without losing the key information. Our proposed model is based on one stage classifier and performs efficient classification. Our technique outperformed the existing models attaining an accuracy of 98.14%, recall of 97.57%, and precision of 97.84%.

One of the most prevalent brain diseases, epilepsy is characterized by recurring seizures that happen quite frequently. During seizures, a patient suffers uncontrollable muscle contractions that cause loss of motion and balance, which could lead to harm or even death. Establishing an automatic method for warning patients about impending seizures requires extensive research. It is possible to anticipate seizures by analyzing the Electroencephalogram (EEG) signal from the scalp region of the human brain. Time domain-based features such as Hurst exponent (Hur), Tsallis Entropy (TsEn), improved permutation entropy (impe), and amplitude-aware permutation entropy (AAPE) were extracted from EEG signals. In order to diagnose epileptic seizure children from normal children automatically, this study conducted two sessions, in the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), while in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers including a gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional (BiLSTM). The EEG dataset obtained from the Neurology Clinic at the Ibn-Rushd Training Hospital. In this regard, detailed explanations and research from the time domain and entropy characteristics show that using GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All−time−entropy fusion feature improves the final classification results.

In an ever-evolving landscape of higher education, this study delves into the transformative potential of merging deep learning principles and meaningful pedagogy in language acquisition, aided by artificial intelligence (AI) technologies. Drawing from a qualitative research design, it navigates the post-pandemic educational landscape, examining shifts in language education, student perspectives, and adaptations. Through comprehensive data collection methods, including literature review, interviews, and classroom observations, the study presents insights from 30 participants from SMC. The qualitative findings reveal emerging themes related to deep learning, meaningful learning, AI integration, and language acquisition, underscoring their profound impact on teaching methods and student engagement. This research contributes to the field by shedding light on innovative approaches that elevate language acquisition in an AI-evolving educational environment. The study concludes with implications for school administrators, teachers, and students, offering recommendations for future research directions, ultimately striving to enhance language education in the modern era.

This paper explores the use of different deep learning models for predicting precipitation in 56 meteorological stations in Jilin Province, China. The models used include Stacked-LSTM, Transformer, and SVR, and Gaussian noise is added to the data to improve their robustness. Results show that the Stacked-LSTM model performs the best, achieving high prediction accuracy and stability. The study also conducts variable attribution analysis using LightGBM and finds that temperature, dew point, precipitation in previous days, and air pressure are the most important factors affecting precipitation prediction, which is consistent with traditional meteorological theory. The paper provides detailed information on the data processing, model training, and parameter settings, which can serve as a reference for future precipitation prediction tasks. The findings suggest that adding Gaussian noise to the dataset can improve the model's generalization ability, especially for predicting days with zero precipitation. Overall, this study provides useful insights into the application of deep learning models in precipitation prediction and can contribute to the development of meteorological forecasting and applications.

With the rise of the Internet of Things (IOT), mobile devices and Location-Based Social Network (LBSN), an abundant amount of trajectory data has made research on location prediction more popular. The check-in data shared through LBSN hides information related to life patterns, obtaining this information is helpful for location prediction. However, the trajectory data recorded by mobile devices is different from check-in data that has semantic information. In order to obtain the user’s semantic, relevant studies match the stay point to the nearest Point of Interest (POI), but location error may lead to wrong semantic matching. Therefore, we propose A Self-Attention for Next Location Prediction based on Semantic Mining to predict the next location. When calculating the semantic feature of a stay point, the first step is to search for the k nearest POI, then use the reciprocal of the distance from the stay point to the k nearest POI and the number of categories as weights. Finally, we use the probability to express semantic without losing other important semantic information. Furthermore, this research combined with sequential pattern mining can bring richer semantic features. In order to better perceive the trajectory, temporal features learn periodicity of time series by sine function. In terms of location features, we build a directed weighted graph and regard the frequency of users visiting locations as the weight, so the location features are rich in contextual information. We then adopt the Self-Attention model to capture long-term dependencies in long trajectory sequences. Experiments in Geolife show that the semantic matching of this study improved by 45.78% in TOP@1 compared with the closest distance search for POI. Compared with the baseline, the model proposed in this study improved by 2.5% in TOP@1.

Medium-deep Borehole Heat exchanger (MBHE) has been widely paid attention for building heating. In order to avoid the thermal interference of adjacent MBHEs, temperature distribution characteristics of medium-deep rock-soil was investigated in this work. The evolution on maximum rock-soil thermal affected radius (MTAR) in full life cycle was further analyzed. The results showed that the rock-soil thermal affected area (RTAA) continuously expands in both radial and vertical directions during a heating season. Several factors of thermal extraction load, fluid velocity, geothermal gradient and pipe length have main impacts on the RTAA in vertical direction. Rock-soil thermal conductivity affects the RTAA in both radial and vertical directions. In non-heating season, temperature difference of rock-soil in radial direction dominates the temperature recovery in the first year while geothermal flow nearly dominates temperature recovery after 20 years. The thermal affected radius (TAR) in the 30 th year could be determined as an effective MTAR in full life cycle. In order to decrease installed distance of adjacent MBHEs, a new well layout form by deflecting borehole was proposed. The recommended deflection angle is equal to or larger than 4 times TAR angle. This work provides scientific reference for promoting application of multiple MBHE arrays.

Taste determination in small molecules is critical in food chemistry, but traditional experimental methods can be time-consuming. Consequently, computational techniques have emerged as val-uable tools for this task. In this study, we explore taste prediction using various molecular feature representations and assess the performance of different machine learning algorithms on a dataset comprising 2,601 molecules. The results reveal that GNN-based models outperform other ap-proaches in taste prediction. Moreover, consensus models that combine diverse molecular repre-sentations demonstrate improved performance. Among these, molecular fingerprints + GNN con-sensus model emerges as the top performer, highlighting the complementary strengths of GNNs and molecular fingerprints. These findings have significant implications for food chemistry research and related fields. By leveraging these computational approaches, taste prediction can be expedited, leading to advancements in understanding the relationship between molecular structure and taste perception in various food components and related compounds.

The definition of artificial intelligence (AI) is the capacity of a computer or machine to mimic or simulate human intelligence. AI has been applied in different areas, including medicine. In cardiology, AI techniques have revolutionized the field of cardiac diagnosis, enabling the detection and prediction of cardiovascular diseases to be more accurate and efficient. This article provides an overview of machine learning, deep learning, and neural networks as they pertain to cardiac diagnosis. We will investigate how these techniques harness the power of data and algorithms to analyze complex patterns in cardiac data, thereby facilitating early detection, risk assessment, and treatment decision-making.

With the continuous development of network technology, complex network systems generate massive unbalanced attack traffic. Due to the severe imbalance in the quantities of normal samples and attack samples, as well as among different types of attack samples, intrusion detection systems suffer from low detection rates for rare class attack data. In this paper, we propose a geometric synthetic minority oversampling technique based on optimized kernel density estimation algorithm. This method can generate diverse rare class attack data by learning the distribution of rare class attack data while maintaining similarity with the original sample features. Meanwhile, the balanced data is input to a feature extraction module built upon multiple denoising autoencoders, reducing information redundancy in high-dimensional data and improving the detection performance for unknown attacks. Subsequently, a soft voting ensemble learning technique is utilized for multi-class anomaly detection on the balanced and dimensionally reduced data. Finally, an intrusion detection system is constructed based on data preprocessing, imbalance handling, feature extraction, and anomaly detection modules, and validated on the NSL-KDD and N-BaIoT datasets. Comparative experiments with baseline models and other state-of-the-art methods demonstrate that the proposed system improves the detection rate of rare class attack data. Furthermore, it achieves a good overall detection rate on the Internet of Things dataset (N-BaIoT), indicating its strong applicability.

With the developments of smart technologies, the use of rare earth elements (REEs) knows a widespread use, thus, their importance as valuable and strategic metals boosted to levels never known before. Due to their scarcity in Earth crust, the recovery of these elements from secondary resources also knows further developments. Traditional pyrometallurgical and hydrometallurgical processing, though of wide use, in the recovery of these REEs, have some environmental drawbacks, thus, the development of new recovery approaches are under developments. Here, Solvometallurgy appeared as a friendly environmental technology, and ionic liquids and deep eutectic solvents re-sulted as a first-row chemicals to be used in the different unit operations used in solvometallurgical processing: leaching, liquid-liquid extraction, ion exchange (adsorption), precipitation and elec-trolysis. This manuscript reviewed the most recent literature concerning the use of ionic liquids and deep eutectic solvents in the recovery of REEs from various sources.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

This study chose the indoor soil column test as the main method and the field test as the validation test to investigate the effects of various straw mulching techniques (surface, deep and straw mulching + deep burial) on evaporation and salt dynamics in saline soils. The results showed that straw mulching treatment could effectively reduce soil water evaporation, promote desalination in the stage of leaching infiltration and alleviate salt return in the stage of water evaporation, and the effect of straw mulching + deep burial treatment was better than that of single-layer straw mulching treatment. The indoor soil column test showed that S2D1 treatment (a 2:1 ratio of soil surface cover to the amount of straw buried 40cm below the soil surface) had the best effect on the suppression of soil moisture evaporation, and the cumulative evaporation of soil moisture was reduced by 65.85% compared with that of the CK, and the rate of salinity return in the evaporation stage was effectively reduced by 92.04% compared with that of the CK. In addition, there is a significant positive correlation between cumulative evaporation of soil moisture and cumulative soil salinity, which implies that cumulative soil salinity increases with cu-mulative evaporation of soil moisture. The results of the field experiment were consistent with the soil column test, and the S2D1 treatment was able to maintain high soil moisture content in all soil layers in all periods of the experiment and kept soil salinity in the 0-40 cm soil layer at a low level. However, in the 40-80 cm soil layer, the soil salinity suppression effect of DB treatment (straw buried at 40 cm below soil surface) was the best. So in summary, the S2D1 treatment had the best salinity and evapo-transpiration suppression effect in saline soils. This study is of great significance for the resource uti-lization of straw waste, improvement of water utilization and efficiency, and soil salinization manage-ment.

Keywords: Convolutional Neural Network, Deep Learning, Skin cancer, Generative Adversarial Network

Target recognition mainly includes three approaches: optical image-based, echo detection-based, and passive signal analysis-based methods. Among them, the passive signal-based method is closely integrated with practical applications due to its strong environmental adaptability. Based on passive radar signal analysis, we design an "end-to-end" model that cascades a noise estimation network with a recognition network to identify working modes in noise environment. The noise estimation network is implemented based on U-Net, which adopts a method of feature extraction and reconstruction to adaptively estimate the noise mapping level of the sample, which can help the recognition network to reduce noise interference. Focusing on the characteristics of radar signal, the recognition network is realized based on Multi-Scale Convolutional Attention Network (MSCANet). Firstly, the deep group convolution is used to isolate the channel interaction in the shallow network. Then, through the multi-scale convolution module, finer-grained features of the signal are extracted without increasing the complexity of the model. Finally, the self-attention mechanism is used to suppress the influence of low-correlation and negative-correlation channels and spaces. This method overcomes the problem that the conventional method is seriously disturbed by noise. We validated the proposed method in 81 kinds of noise environments, achieving an average accuracy of 94.65%. Additionally, we discussed the performance of six machine learning algorithms and four deep learning algorithms. Compared to these methods, proposed MSCANet achieved an accuracy improvement of approximately 17%. Our method demonstrates better generalization and robustness.

Modern power system integrates more and more new energy and use a large number of power electronic equipment. This makes it face more challenges in online optimization and real-time control. Deep reinforcement learning(DRL) has the ability of processing big data and high-dimensional features, as well as the ability of independently learning and optimizing decision-making in complex environments. In this paper, we explore DRL based online combination optimization method of grid section for large complex power system. In our method, to improve the convergence speed of the model, we propose to discretize the output action of the unit and simplify the action space. We also design a reinforcement learning loss function with strong constraints to further improve the convergence speed of the model and facilitate the algorithm to obtain the stable solution. Moreover, to avoid the local optimal solution problem caused by the discretization of the output action, we propose to use the annealing optimization algorithm to make the granularity of the unit output finer. We verify our method on IEEE 118-bus system. The experimental results show that our model has fast convergence speed and better performance, and can obtain stable solutions.

With the continuous progress of remote sensing image object detection tasks in recent years, researchers in this field have gradually shifted the focus of their research from horizontal object detection to the study of object detection in arbitrary directions. It is worth noting that some properties are different from the horizontal object detection during oriented object detection that researchers have yet to notice much. This article presents the design of a straightforward and efficient arbitrary-oriented detection system, leveraging the inherent properties of the orientation task, including the rotation angle and box aspect ratio. In the detection of low aspect ratio objects, the angle is of little importance to the orientation bounding box, and it is even difficult to define the angle information in extreme categories. Conversely, in the detection of objects with high aspect ratios, the angle information plays a crucial role and can have a decisive impact on the quality of the detection results. By exploiting the aspect ratio of different targets, this letter proposes a ratio-balanced angle loss that allows the model to make a better trade-off between low-aspect ratio objects and high-aspect ratio objects. The rotation angle of each oriented object, which we naturally embed into a two-dimensional Euclidean space for regression, thus avoiding an overly redundant design and preserving the topological properties of the circular space. The performance of the UCAS-AOD, HRSC2016, and DLR-3K datasets show that the proposed model in this paper achieves a leading level in terms of both accuracy and speed. The code is released at https://github.com/minghuicode/Periodic-Pseudo-Domain.

Artificial Intelligence (AI) has many advantages over humans in that it can detect incredibly subtle patterns within large quantities of data. This study suggests using AI algorithms in user research tasks for mining variables ranging from the tone of voice, image banks, historical records, and product use to determine where brands sit and where there could be competitive advantages. This study reviews the current design processes of User Experience (UX) designers and the advancements in Deep Learning (DL). It identifies potential areas of automation in the Preparation, Incubation and Illumination stages of the design process. It recognises the possibility of using Long Short-Term Memory (LSTM) models to automate design feedback and the creation of alternate designs with Generative Adversarial Networks (GANs).

Deep learning has been widely used in various tasks such as computer vision, natural language processing, and predictive analysis, recommendation systems in the past decade. However, practical scenarios often lack labeled data, posing challenges for traditional supervised methods. Semi-supervised classification methods address this by leveraging both labeled and unlabeled data to enhance model performance, but they face challenges in effectively utilizing unlabeled data and distinguishing reliable information from unreliable sources. This paper introduces ReliaMatch, a semi-supervised classification method that addresses these challenges by using a confidence threshold. It incorporates a curriculum learning stage, feature filtering, and pseudo-label filtering to improve classification accuracy and reliability. The feature filtering module eliminates ambiguous semantic features by comparing labeled and unlabeled data in the feature space. The pseudo-label filtering module removes unreliable pseudo-labels with low confidence, enhancing algorithm reliability. ReliaMatch employs a curriculum learning training mode, gradually increasing training dataset difficulty by combining selected samples and pseudo-labels with labeled data. This supervised approach enhances classification performance. Experimental results show that ReliaMatch effectively overcomes challenges associated with the underutilization of unlabeled data and the introduction of error information, outperforming the pseudo-label strategy in semi-supervised classification.

Digital images have become an important carrier for people to access information in the information age. However, with the development of the technology, digital images are vulnerable to illegal access and tampering, to the extent that they pose a serious threat to personal privacy, social order and national security. Therefore, image forensic techniques have become an important research topic in the field of multimedia information security. In recent years, deep learning technology has been widely applied in the field of image forensics and the performance achieved has significantly exceeded the conventional forensic algorithms. This survey compares the state-of-the-art image forensic techniques based on deep learning in recent years. The image forensic techniques are divided into passive and active forensics. In passive forensics, forgery detection techniques are reviewed, and the basic framework, evaluation metrics and commonly used datasets for forgery detection are presented. The performance, advantages and disadvantages of existing methods are also compared and analyzed according to different types of detection. In active forensics, robust image watermarking techniques are overviewed, the evaluation metrics and basic framework of robust watermarking techniques are presented. The technical characteristics and performance of existing methods are analyzed based on the different types of attacks on images. Finally, future research directions and conclusions are given to provide useful suggestions for people in image forensics and related research fields.

Lamb wave-based structural health monitoring is widely acknowledged as a reliable 11 method for damage identification, classification, localization and quantification. However, due to 12 the complexity of Lamb wave signals, especially after interacting with structural components and 13 defects, interpreting these waves and extracting useful information about the structure's health is 14 still a major challenge. However, deep learning-based strategy offers a great opportunity to address 15 such challenges as the algorithm can operate directly on raw discrete time-domain signals. Unlike 16 traditional methods, which often require careful feature engineering and preprocessing, deep learn-17 ing can automatically extract relevant features from the raw data. This paper proposes an autoen-18 coder based on a bidirectional long short-term memory network with maximal overlap discrete 19 wavelet transform layer to detect the signal anomaly and determine the location of the damage in 20 the composite structure. This approach has the potential to greatly enhance our ability to detect and 21 locate structural damage in composite structures, thereby increasing safety and efficiency.

With the growing popularity of smartphones, user identification has become an essential component of maintaining security and privacy. This study investigates how smartphone accelerometer data can be used to identify users, and it makes recommendations for the ideal application parts. Accelerometer data from the HMOG public dataset was used to train deep learning, conventional classifiers, and voting classifiers, which were then utilized to identify users. To enhance performance, feature selection and pre-processing techniques were researched. The results show that RFE feature selection outperforms other approaches and that LSTM followed by XGBoost has the best identification performance as indicated by a relatively large number of machine learning performance measures. The proposed identification system nevertheless performed well and outperformed existing methods, which were principally created and tested on the same HMOG public smartphone dataset, even with a larger number of users. Further work would be necessary for such an application to reach its full potential, though.

Grain yield prediction affects policy making in various aspects such as agricultural production planning, food security assurance, and adjustment of foreign trade. Accurately predicting grain yield is of great significance in ensuring global food security. This paper is based on the MODIS remote sensing image data products from 2010 to 2020, and adds band information such as vegetation index and temperature to form composite remote sensing data as a data set. Aiming at the lack of models for large-scale forecasting and the need for human intervention in traditional models, this paper proposes a grain production estimation model based on deep learning. First, image cropping and yield mapping techniques are used to process the data to generate training samples. Then the channel and spatial attention mechanism (Convolutional Block Attention Module, CBAM) is added for extracting spatial information in different remote sensing bands to improve the efficiency of the model. Long Short-Term Memory (LSTM) neural networks is also added to obtain feature information in the time dimension. Finally, a national-scale grain yield prediction model is constructed. The proposed model was tested on data from 2018 to 2020 showing an average R2 of 0.940 and an average RMSE of 80,020 tons, indicating that it can predict Chinese grain yield better. The model proposed in this paper extracts grain yield information directly from the composite remote sensing data, and solves the problem of small-scale research and imprecise yield prediction in an end-to-end manner.

Forest fires are one of the world's deadliest natural disasters. Early detection of forest fires can help minimize the damage to ecosystems and forest life. In this paper, we propose an improved fire detection method YOLOv5-IFFDM for YOLOv5. Firstly, the fire and smoke detection accuracy and the network perception accuracy of small targets are improved by adding attention mechanism in the backbone network. Secondly, the loss function is improved and the SoftPool pyramid pooling structure is used to improve the regression accuracy and detection effect of the model and the robustness of the model. In addition, random Mosaic augmentation technique is used to enhance the data to increase the generalization ability of the model, and re-clustering of flame and smoke detection a priori frames are used to improve the accuracy and speed. Finally, the parameters of the convolutional and normalization layers of the trained model are homogeneously merged to further reduce the model responsibility to improve the detection speed. Experimental results on homemade forest fire and smoke datasets show that this algorithm has high detection accuracy and fast detection speed, with average accuracy of fire up to 90.5% and smoke up to 84.3%, and detection speed up to 75 FPS (frames per second transmission), which can meet the requirements of real-time and efficient fire detection.

With the development of health service, animal husbandry, aquaculture and chemical industry, more and more pollutants are discharged into the water environment, including antibiotics and heavy metal ions. These hazard substances pose a great threat to environment safety and human health. As two kinds of new green solvents, ionic liquids (ILs) and deep eutectic solvents (DESs) are widely used in various fields including separation and environmental engineering, which are attracting huge attention from academia and industry. In this study, the optimal ionic liquid and deep eutectic solvent were selected and their complex with β-cyclodextrin (β-CD) were firstly prepared by simple and effective inclusion way. After necessary characterization and analysis, two kinds of complex were applied to prepare a special sorbent disc with two different sides by adding diluent (excipient) and pressing under 5~15 MPa. As the result, the IL and DES could be stably immobilized on the disc and play the key role in selective adsorption for targets. Besides that, the experiments of different hazardous substances achieved the expected results. Based on this study, the complex disc showed a lot of merits in the separation performance, easy preparation and use, simple operation, and good stability. It was believed to be a useful tool for water purification and detection.

In foggy weather scenarios, the scattering and absorption of light by water droplets and particulate matter cause object features in images to become blurred or lost, presenting a significant challenge for target detection in autonomous driving vehicles. To tackle this problem, this study proposes a foggy weather detection method, YOLOv5s-Fog, based on the YOLOv5s framework. The model enhances the feature extraction and expression capabilities of YOLOv5s by introducing a novel target detection layer, SwinFocus. Additionally, this research incorporates decoupled head into the model and replaces the conventional non-maximum suppression method with Soft-NMS. Experimental results demonstrate that these improvements effectively enhance the detection performance for blurry objects and small targets in foggy weather conditions. Compared to the baseline model YOLOv5s, YOLOv5s-Fog achieves a 5.4% increase in mAP on the RTTS dataset, reaching 73.4%. This method provides technical support for rapid and accurate target detection in adverse weather conditions, such as foggy weather, for autonomous driving vehicles.

This paper applies a new artificial intelligence architecture, the Temporal Fusion Transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows to visualize persistent temporal patterns and to identify significant events and different regimes. Third, it provides quantile regressions and permits to train the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country is domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future.

Automatic and real-time pose estimation is important in monitoring animal behavior, health and welfare. In this paper, we utilized pose estimation for monitoring farrowing process to prevent piglet mortality and preserve the health and welfare of sow. State-of-the-art Deep Learning (DL) methods have lately been used for animal pose estimation. The aim of this paper was to probe the generalization ability of five common DL networks (ResNet50, ResNet101, MobileNet, EfficientNet and DLCRNet) for sow and piglet pose estimation. These architectures predict body parts of several piglets and the sow directly from input video sequences. Real farrowing data from a commercial farm was used for training and validation of the proposed networks. The experimental results demonstrated that MobileNet was able to detect seven body parts of the sow with median test error of 0.61 pixels.

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.

This paper presents an improved SOC estimation method for lithium ion batteries in Electric Vehicles using Bayesian optimized feedforward network. This innovative bayesian optimized neural network method attempts to minimize a scalar objective function by extracting hyperpa-rameters (hidden neurons in both layers) using a surrogate model. Furthemore, the hyperparameters are built and data samples are trained and validated. The performance of the proposed deep learning neural network is evaluated. Two reasonable size data samples are ex-tracted from Panasonic 18650PF Li-ion Mendeley datasets that are used for training and valida-tion. RNN and LSTM neural network algorithms offer the common core property of retaining past information and/or hidden states for better SOC estimation. However, the feature of this pro-posed method is the inclusion of Bayesian optimization that chooses optimal double layer hidden neurons. Analysis of results shows that Bayesian optimized feedforward algorithm with average MAPE (0.20%) is the lowest and is the best selection compared with average MAPE for other five deep learning algorithms. In the last quarter of fuel gauge, where fuel anxiety is severe, feed-forward with Bayesian Optimization algorithm is still the best selection (with MAPE of 0.64%).

Newly build offshore wind farms (OWFs) render a collision risk between ships and installations. The paper proposed a real-time traffic monitoring method based on machine vision and deep learning technology to improve the efficiency and accuracy of the traffic monitoring system in the vicinity of offshore wind farms. Specifically, the method employs real automatic identification system (AIS) data to train a machine vision model, which is then used to identify passing ships in OWF waters. Furthermore, the system utilizes stereo vision techniques to track and locate the positions of passing ships. The method is tested in offshore water in China to validate its reliability. The results prove that the system sensitively detects the dynamic information of the passing ships, such as the distance between ships and OWFs, ship speed and course. Overall, this study provides a novel approach to enhancing the safety of OWFs, which is increasingly important as the number of such installations continues to grow. By employing advanced machine vision and deep learning techniques, the proposed monitoring system offers an effective means of improving the accuracy and efficiency of ship monitoring in challenging offshore environments.

Advances in computing technology provide an opportunity to grow and develop an effective crop protection system. This study is a new way of diagnosing plant diseases using a deep and convolutional neural network. Deep learning is the strengthened method of machine learning. It uses a neural network that imitates like a human brain and gains certain information. Although powerful, its training process necessitates millions of tagged data points. The study's Methodology consists of three key stages: data acquisition, pre-processing, and Model Building.

Disease control programs need to identify breeding sites of mosquitoes which transmit malaria and other diseases to target interventions and identify environmental risk factors. Increasing availability of very high resolution drone data provides new opportunities to find and characterize these vector breeding sites. Within this study, we identified land cover types associated with malaria vector breeding sites in West Africa. Drone images from two malaria endemic regions in Burkina Faso and Côte d’Ivoire were assembled and labeled using open-source tools. We developed and applied a workflow using region of interest-based and deep learning methods to classify these habitat types from very high resolution natural color imagery. Analysis methods achieved a dice coefficient ranging between 0.68 and 0.88 for different vector habitat types; however, this classifier consistently identified the presence of specific habitat types of interest. This establishes a framework for developing deep learning approaches to identify vector breeding sites and highlights the need to evaluate how results will be used by control programs.

Antimicrobial peptides (AMPs) are a promising alternative to antibiotics to combat drug resistance in pathogenic bacteria. However, the development of AMPs with high potency and specificity remains a challenge, and new tools to evaluate antimicrobial activity are needed to accelerate the discovery process. As a step toward direct prediction of the experimental minimum inhibitory concentration (MIC) of AMPs, we proposed MBC-Attention, a combination of a multi-branch CNN architecture and attention mechanism. Using a curated dataset of 3929 AMP against Escherichia coli, the optimal MBC-Attention model achieved an average Pearson correlation coefficient of 0.775 and an RMSE of 0.533 (log μM) in three independent tests of 393 sequences each. This results in a 5–12% improvement in PCC and 7–13% improvement in RMSE compared with RF and SVM models. Ablation studies confirmed that both attention mechanisms contributed to performance improvement.

Deep learning (DL) models have been recently widely used to extract task-oriented patterns from large scale of datasets, and to improve the data image understanding and analysis accuracy in many different decision-making processes for tasks such as image classification, segmentation, detection, and so on. However, in practice, the performances of DL models are easily affected by environmental illumination conditions. Conversely, DL models can also be utilized for extracting the illumination hints from the images, and these hints are critically useful for improving the model robustness, classifying the environmental scenes, estimating scene depth information, and rendering 3D objects. In this study, an extensive and exhaustive review is carried out for DL based color constancy, indoor and outdoor illumination estimation, and image depth estimations with the considerations of strengths and weaknesses of DL models. This study also explores the different network designs and the paradoxes in parameter optimization during the model training. Current technology barriers involved in implementing these models and recommendations to overcome these barriers are also suggested in the review.

A detailed literature review is performed in this study to address solutions for the full-body design and control of an aerial manipulator. Deep Reinforcement Learning methods are growing to be utilized recently to cope with various uncertainties. The pros and cons of these theories will be explained as well as introducing the advantages of Fuzzy Reinforcement Learning methods. State-of-the-Art, possible challenges, potential approaches, and a summary of desired precision devices are discussed in this study.

The dynamics of suspended sediment involves inherent non-linearity and complexity as a result of the presence of both spatial variability of the basin characteristics and temporal climatic patterns. As a result of this complexity, the conventional sediment rating curve (SRC) and other empirical methods produce inaccurate predictions. Deep neural networks (DNNs) have emerged as one of the advanced modeling techniques capable of addressing inherent non-linearity in hydrological processes over the last few decades. DNN algorithms are used to perform predictive analysis and investigate the interdependencies among the most pivotal water quantity and quality parameters i.e., discharge, suspended sediment concentration (SSC), and turbidity. In this study, the Long short-term memory (LSTM) algorithm of DNNs is used to model the discharge-suspended sediment relationship for the Stony Clove Creek. The simulations were run using primary data on discharge, SSC and turbidity. For the development of the DNN models and examining the effects of input vectors, combinations of different input vectors (namely discharge, and SSC) for the current and previous days are considered. Furthermore, a suitable modelling approach with an appropriate model input structure is suggested based on model performance indices for the training and testing phases. The performance of developed models is assessed using statistical indices such as root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Statistically, the performance of DNN-based models in simulating the daily SSC performed well with observed sediment concentration series data. The study demonstrates the suitability of the DNN approach for simulation and estimation of daily SSC, opening up new research avenues for applying hybrid soft computing models in hydrology.

Vegetation indexes help perform precision farming because they provide useful information regarding moisture, nutrient content, and crop health. Primary sources of those indexes are satellites and unmanned aerial vehicles equipped with expensive multispectral sensors. Reducing the price of obtaining such information would increase the availability of precision farming for small farms. Several studies have proposed deep neural network methods to estimate the indexes from RGB color images. However, these methods report relatively large errors for mature plants when highly non-linear relationships of images and vegetation indexes arise. One could apply multilayer random forest-based models (Deep Forests) to solve this problem, but the discriminative power of such models is limited: they cannot catch complex dependencies between image features. In this paper, we propose a method that combines ideas of deep forests, random forests of kernel trees, and global pruning of random forests to tackle the problem. As a result, the method considers the properties of objects with a complex structure: the presence of relationships between groups of features, displacement, and scaling of objects. The experimental results show that the proposed method outperforms neural network-based solutions in several datasets.

Skin cancer is an uncommon but serious malignancy. Dermoscopic images examination and biopsy are required for cancer detection. Deep learning (DL) is extremely effective in learning characteristics and predicting malignancies. However, DL requires a large number of images to train. Image augmentation and transferring learning were employed to overcome the lack of images issue. In this study we divided images into two categories: benign and malignant. To train and test our models, we used the public ISIC 2020 database. Melanoma is classified as malignant in the ISIC 2020 dataset. Along with categorization, the dataset was studied to demonstrate variation. The performance of three top pretrained models was then benchmarked in terms of training and validation accuracy. Three optimizers were employed to optimize the loss: RMSProp, SGD, and ADAM. Using ResNet, VGG16, and MobileNetV2, we obtained training accuracy of 98.73%, 99.12%, and 99.76%, respectively. Using these three pretrained models, we attained a validation accuracy of 98.39%.

3D object detection is crucial for autonomous driving to understand the driving environment. Since the pooling operation causes information loss in the standard CNN, we have designed a wavelet multiresolution analysis-based 3D object detection network without a pooling operation. Additionally, instead of using a single filter like the standard convolution, we use the lower-frequency and higher-frequency coefficients as a filter. These filters capture more relevant parts than a single filter, enlarging the receptive field. The model comprises a discrete wavelet transform (DWT) and an inverse wavelet transform (IWT) with skip connections to encourage feature reuse for contrasting and expanding layers. The IWT enriches the feature representation by fully recovering the lost details during the downsampling operation. Element-wise summation is used for the skip connections to decrease the computational burden. We train the model for the Haar and Daubechies (Db4) wavelets. The two-level wavelet decomposition result shows that we can build a lightweight model without losing significant performance. The experimental results on the KITTI’s BEV and 3D evaluation benchmark show our model outperforms the Pointpillars base model by up to 14 \% while reducing the number of trainable parameters. Code will be released.

As one of the critical state parameters of the battery management system, lithium battery state of charge (SOC) can provide an essential reference for battery safety management, charge/discharge control, and energy management of electric vehicles. To analyze the application of deep learning in electric vehicle power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, structural characteristics, advantages and disadvantages of lithium battery SOC estimation in deep learning method. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Secondly, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of four types of deep learning methods, were concluded using the structure of neural network used for training as the classification criterion. Finally, the challenges and future development directions of lithium battery SOC estimation in deep learning method were explained.

3D reconstruction from a single 2D input is a classic problem in the field of computer vision. With the advancements in deep learning, the performance of 3D reconstruction has also significantly improved. The reconstruction task is more difficult for objects with no textures or complex deformations. This paper serves as a review of recent literature on 3D reconstruction from a single view, with a focus on deep learning methods from 2018 to 2021. Due to lack of standard datasets or 3D shape representation methods, it is hard make direct comparisons between all reviewed methods. However, this paper reviews different approaches for reconstructing 3d shape as depth maps, surface normals, point clouds and meshes; along with various loss functions and evaluation metrics used to train and evaluate these methods.

Facial expressions play a key role in interpersonal communication when it comes to negotiating our emotions and intentions, as well as interpreting those of others. Research has shown that we can connect to other people better when we exhibit signs of empathy and facial mimicry. However, the relationship between empathy and facial mimicry is still debated. Among the factors contributing to the difference in results across existing studies is the use of different instruments for measuring both empathy and facial mimicry, as well as often ignoring the differences across various demographic groups. This study first looks at the differences in empathetic abilities of people across different demographic groups based on gender, ethnicity and age. The empathetic ability is measured based on the Empathy Quotient capturing a balanced representation of both emotional and cognitive empathy. Using statistical and machine learning methods, the study then investigates the correlation between the empathetic ability and facial mimicry of subjects in response to images portraying different emotions displayed on a computer screen. Unlike the existing studies measuring facial mimicry using electromyography, this study employs a technology detecting facial expressions based on video capture and deep learning. This choice was made in the context of increased online communication during and post the COVID-19 pandemic. The results of this study confirm the previously reported difference in the empathetic ability between females and males. However, no significant difference in the empathetic ability was found across different age and ethnic groups. Furthermore, no strong correlation was found between empathy and facial reactions to faces portraying different emotions shown on a computer screen. Overall, the results of this study can be used to inform the design of online communication technologies and tools for training empathy team leaders, educators, social, and health care providers.

Malignant growth is the most widely recognized repulsive infections winning around the world, and the patients with disease are saved just when the malignant growth is distinguished at the beginning phase. Each kind of disease is interesting, with its own arrangement of development properties and hereditary changes. This paper presents the lung knob division and disease characterization by proposing an enhancement calculation. The general technique of the created approach includes four stages, such as pre-processing, division, highlight extraction, and the order. From the outset, the CT picture of the lung is taken care of to the division. When the division is done, the highlights are extricated through morphological and measurable and surface highlights like LOOP and LGP. At long last, the extricated highlights are given to the order step. Here, the characterization is done dependent on the Deep Belief Network (DBN) which is prepared by utilizing the proposed Chicken-Sine Cosine Algorithm (CSCA) which distinguish the lung tumor, giving two classes in particular, knob or non-knob. The presentation assessment of lung knob division and malignant growth grouping dependent on CSCA is figured utilizing three measurements to be specific, precision, affectability, and the explicitness.

Deep learning has shown remarkable results in every field, especially in the biomedical field, due to its ability to exploit large-scale datasets. A convolutional neural network (CNN) is a widely used deep learning approach to solve medical imaging problems. Over the past few years, many studies have focused on CNN-based techniques for brain tumor diagnosis. There are, however, still some critical challenges that CNNs face towards clinic application. This study presents a comprehensive review of current literature that involves CNN architectures for brain tumor classification. We compare the key achievements in the performance evaluation metrics of the applied classification algorithms. In addition, this review assesses the clinical effectiveness of the included studies to elaborate on the limitations and directions of this area for future work. No review focusing on the clinical effectiveness of previous works in this field has been published. We believe that this study has the potential to elevate the application of CNN-based deep learning methods in clinical practice and also can be a quick reference for biomedical researchers who are interested in this field.

False positives on multiparametric (mp)-MRI result in a large number of unnecessary biopsies in men with clinically insignificant diseases. This study investigates whether quantitative diffusion MRI can improve differentiation between false positives, true positives and normal tis-sue. Twenty-three patients underwent mp-MRI and Vascular, Extracellular and Restricted Diffu-sion for Cytometry in Tumours (VERDICT)-MRI, followed by transperineal biopsy. The patients were categorised into two groups following biopsy: (1) significant cancer - true positive (2) atro-phy/inflammation/high-grade prostatic intraepithelial neoplasia (PIN) - false positive. The clinical apparent diffusion coefficient (ADC) values of the lesions were obtained, and the intravoxel inco-herent motion (IVIM), diffusion kurtosis imaging (DKI) and VERDICT models were fitted using a deep learning approach. Significant differences (p < 0.05) between true positive and false positive lesions were found in ADC, IVIM perfusion fraction (f) and diffusivity (D), DKI diffusivity (DK) and kurtosis (K) and VERDICT intracellular volume fraction (fIC), extracellular-extravascular vol-ume fraction (fEES) and diffusivity (dEES) values. Significant differences between false positives and normal tissue were only found for the VERDICT fIC. These results demonstrate that model-based diffusion MRI could reduce the number of unnecessary biopsies due to false positive prostate lesions and shows promising sensitivity to benign diseases that mimic cancer.

When computers start to become a dominant part of technology around the 1950s, fundamental questions about reliable designs and robustness were of great relevance. Their development gave rise to the exploration of new questions such as what made brains reliable (since neurons can die) and how computers could get inspiration from neural systems. In parallel, the first Artificial Neural Networks came to life. Since then, the comparative view between brains and computers has been developed in new, sometimes unsuspected directions. With the rise of deep learning and the development of connectomics, an evolutionary look at how both hardware and neural complexity have evolved or designed is required. In this paper, we argue that important similarities have resulted both from convergent evolution (the inevitable outcome of architectural constraints) and inspiration of hardware and software principles guided by toy pictures of neurobiology. Moreover, dissimilarities and gaps originate from the lack of major innovations that have paved the way to biological computing (including brains) that are completely absent within the artificial domain. As it occurs within synthetic biocomputation, we can also ask whether alternative minds can emerge from A.I.\ designs. Here we take an evolutionary view of the problem and discuss the remarkable convergences between living and artificial designs and what are the pre-conditions to achieve artificial intelligence.

Following the occurrence of a typhoon, quick damage assessment related to residents can facilitate quick dispatch of house repair and disaster insurance works. Employing a deep learning method, this study used aerial photos of the Chiba prefecture obtained following the Typhoon Faxai in 2019 to automatically detect and evaluate the roof damage. This study comprised three parts: training deep learning model, detecting the roof damage using trained model, and classifying the level of roof damage. The detection object comprised roof outline, blue tarps, and roof completely destroyed. The roofs were divided into three categories: roof without damage, roof with blue tarps and roof completely destroyed. the F value obtained using the proposed method was higher than those obtained using other methods. In addition, it can be further divided into 5 levels from level 0 to 4. Finally, the spatial distribution of the roof damage was analyzed using ArcGIS tools. The proposed method is expected to provide certain reference for the real-time detection of the roof damage after the occurrence of a typhoon.

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of missing insights of the automatically derived decisions. In order to increase trust in these methods, this paper presents approaches that help to interpret and explain the results of deep learning algorithms by depicting the anatomical areas which influence the decision of the algorithm most. Moreover, this research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models and generate visual interpretations and explanations for clinicians to corroborate their clinical findings. In addition, this will aid in gaining confidence in such methods. The framework builds on existing interpretability and explainability techniques that are currently focusing on classification models, extending them to segmentation tasks. In addition, these methods have been adapted to 3D models for volumetric analysis. The proposed framework provides methods to quantitatively compare visual explanations using infidelity and sensitivity metrics. This framework can be used by data scientists to perform post-hoc interpretations and explanations of their models, develop more explainable tools and present the findings to clinicians to increase their faith in such models. The proposed framework was evaluated based on a use case scenario of vessel segmentation models trained on Time-of-fight (TOF) Magnetic Resonance Angiogram (MRA) images of the human brain. Quantitative and qualitative results of a comparative study of different models and interpretability methods are presented. Furthermore, this paper provides an extensive overview of several existing interpretability and explainability methods.

In this review we summarize existing trends of flow control used to improve the aerodynamic efficiency of wings. We first discuss active methods to control turbulence, starting with flat-plate geometries and building towards the more complicated flow around wings. Then, we discuss active approaches to control separation, a crucial aspect towards achieving high aerodynamic efficiency. Furthermore, we highlight methods relying on turbulence simulation, and discuss various levels of modelling. Finally, we thoroughly revise data-driven methods, their application to flow control, and focus on deep reinforcement learning (DRL). We conclude that this methodology has the potential to discover novel control strategies in complex turbulent flows of aerodynamic relevance.

Among many research areas to which Ron Yager contributed are decision making under uncertainty (in particular, under interval and fuzzy uncertainty) and aggregation – where he proposed, analyzed, and utilized the use of Ordered Weighted Averaging (OWA). The OWA algorithm itself provides only a specific type of data aggregation. However, it turns out that if we allows several OWA stages one after another, we get a scheme with a universal approximation property – moreover, a scheme which is perfectly equivalent to deep neural networks. In this sense, Ron Yager can be viewed as a (grand)father of deep learning. We also show that the existing schemes for decision making under uncertainty are also naturally interpretable in OWA terms.

Making computing machines mimic living organisms has captured the imagination of many since the dawn of digital computers. However, today’s artificial intelligence technologies fall short in replicating even the basic autopoietic and cognitive behaviors found in primitive biological systems. According Charles Darwin, the difference in mind between humans and the higher animals, great as it is, certainly is one of degree and not of kind. Autopoiesis refers to the behavior of a system that replicates itself and maintains its own identity and stability while facing fluctuations caused by external influences. Cognitive behaviors model the system’s state, sense internal and external changes, analyze, predict and take action to mitigate any risk to its functional fulfilment. How did intelligence evolve? what is the relationship between the mind and body? Answers to these questions should guide us to infuse autopoietic and cognitive behaviors into digital machines. In this paper we use recent advances in our understanding of general theory of information, and the role of structures in managing the transformations between information and knowledge to pave the path to infuse autopoietic and cognitive functions into digital computing and build a new class of intelligent machines going beyond the current state of the art.

Virtual screening - predicting which compounds within a specified compound library bind to a target molecule, typically a protein - is a fundamental task in the field of drug discovery. Doing virtual screening well provides tangible practical benefits, including reduced drug development costs, faster time to therapeutic viability, and fewer unforeseen side effects. As with most applied computational tasks, the algorithms currently used to perform virtual screening feature inherent tradeoffs between speed and accuracy. Furthermore, even theoretically rigorous, computationally intensive methods may fail to account for important effects relevant to whether a given compound will ultimately be usable as a drug. Here we investigate the virtual screening performance of the recently released Gnina molecular docking software, which uses deep convolutional networks to score protein-ligand structures. We find, on average, that Gnina outperforms conventional empirical scoring. The default scoring in Gnina outperforms the empirical AutoDock Vina scoring function on 89 of the 117 targets of the DUD-E and LIT-PCBA virtual screening benchmarks with a median 1% early enrichment factor that is more than twice that of Vina. However, we also find that issues of bias linger in these sets, even when not used directly to train models, and this bias obfuscates to what extent machine learning models are achieving their performance through a sophisticated interpretation of molecular interactions versus fitting to non-informative simplistic property distributions.

Depression is considered by WHO as the main contributor to global disability and it poses dangerous threats to approximately all aspects of human life, in particular public and private health. This mental disorder is usually characterized by considerable changes in feelings, routines, or thoughts. With respect to the fact that early diagnosis of this illness would be of critical importance ineffective treatment, some development has occurred in the purpose of depression detection. EEG signals reflect the working status of the human brain by which are considered the most proper tools for a depression diagnosis. Deep learning algorithms have the capacity of pattern discovery and extracting features from the raw data which is fed into them. Owing to this significant characteristic of deep learning, recently, these methods have intensely utilized in the diverse field of researches, specifically medicine and healthcare. Thereby, in this article, we aimed to review all papers concentrated on using deep learning to detect or predict depressive subjects with the help of EEG signals as input data. Regarding the adopted search method, we finally evaluated 22 articles between 2016 and 2021. This article which is organized according to the systematic literature review (SLR) method, provides complete summaries of all exploited studies and compares the noticeable aspects of them. Moreover, some statistical analysis performs to gain a depth perception of the general ideas of the latest researches in this area. A pattern of a five-step procedure was also established by which almost all reviewed articles fulfilled the goal of depression detection. Finally, open issues and challenges in this way of depression diagnosis or prediction and suggested works as the future directions discussed.

Background. Artificial Intelligence (AI) is an advanced technology for the latest 20 years. Machine learning (ML) and deep learning (DL) are the major innovations for AI, which has been applied for multiple fields. Ophthalmology has become to be one of the most significant disciplines for human healthcare. Methodology. This study utilizes methods of text mining and bibliometric analysis to explore applications of AI to ophthalmology. 179 related articles from Web of Science (WOS) and 96 papers from China National Knowledge Infrastructure (CNKI) are explored during the period of 2000 to 2021. A descriptive analysis of major trends, journal releasing, topic mapping and quotation relationships is implemented in this paper. Leading authors, journals, institutions, nations and references in the related research are identified. Results. Findings show that the application of AI technologies in ophthalmologic diagnosis with optical coherence tomography (OCT) fundus images is the core topic for this area’s studies, especially for diabetic retinopathy (DR), aged macular degeneration (AMD) and glaucoma. It is also be predicted as the core direction over the recent years. Besides, The USA, England and China is the most competitive countries in this scientific filed. Journals of Ophthalmology, Investigative Ophthalmology and Visual Science, Eye, Acta Ophthalmologica and Scientific Reports are the top five journal related to the research area. There is a significant difference between WOS and CNKI databases pertaining to the application of Artificial Intelligence (AI) to ophthalmology, especially for the historic development, topic mapping and discipline category. Finally, the potential academic value of interdisciplinary subject of “AI in Ophthalmology” and tradition Chinese medicine (TRM) is discussed. Limitations and suggestions for the future research is indicated at the end of this paper.

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides ground for technology development for computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive and clinically-oriented overview of DL-based segmentation studies for bladder, prostate, cervical and rectal cancers, highlighting the key findings, challenges and limitations.

Diabetic retinopathy is the most common microvascular complication of diabetes mellitus and one of the leading causes of blindness globally. Due to the progressive nature of the disease, earlier detection and timely treatment can lead to substantial reductions in the incidence of irreversible vision-loss. Artificial intelligence (AI) screening systems have offered clinically acceptable and quicker results in detecting diabetic retinopathy from retinal fundus and optical coherence tomography (OCT) images. Thus, this systematic review and meta-analysis of relevant investigations was performed to document the performance of AI screening systems that were applied to fundus and OCT images of patients from diverse geographic locations including North America, Europe, Africa, Asia, and Australia. A systematic literature search on Medline, Global Health, and PubMed was performed and studies published between October 2015 and January 2020 were included. The search strategy was based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines, and AI-based investigations were mandatory for studies inclusion. The abstracts, titles, and full-texts of potentially eligible studies were screened against inclusion and exclusion criteria. Twenty-one studies were included in this systematic review; 18 met inclusion criteria for the meta-analysis. The pooled sensitivity of the evaluated AI screening systems in detecting diabetic retinopathy was 0.93 (95% CI: 0.92-0.94) and the specificity was 0.88 (95% CI: 0.86-0.89). The included studies detailed training and external validation datasets, criteria for diabetic retinopathy case ascertainment, imaging modalities, DR-grading scales, and compared AI results to those of human graders (e.g., ophthalmologists, retinal specialists, trained nurses, and other healthcare providers) as a reference standard. The findings of this study showed that the majority AI screening systems demonstrated clinically acceptable levels of sensitivity and specificity for detecting referable diabetic retinopathy from retinal fundus and OCT photographs. Further improvement depends on the continual development of novel algorithms with large and gradable sets of images for training and validation. If cost-effectiveness ratios can be optimized, AI can become a financially sustainable and clinically effective intervention that can be incorporated into the healthcare systems of low-to-middle income countries (LMICs) and geographically remote locations. Combining screening technologies with treatment interventions such as anti-VEGF therapy, acellular capillary laser treatment, and vitreoretinal surgery can lead to substantial reductions in the incidence of irreversible vision-loss due to proliferative diabetic retinopathy.

The colossal depths of the deep neural network sometimes suffer from ineffective backpropagation of the gradients through all its depths. Whereas, The strong performance of shallower multilayer neural structures prove their ability to increase the gradient signals in the early stages of training which easily gets backpropagated for global loss corrections. Shallow neural structures are always a good starting point for encouraging the sturdy feature characteristics of the input. In this research, a shallow, deep neural structure called PrimeNet is proposed. PrimeNet is aimed to dynamically identify and encourage the quality visual indicators from the input to be used by the subsequent deep network layers and increase the gradient signals in the lower stages of the training pipeline. In addition to this, the layerwise training is performed with the help of locally generated errors which means the gradient is not backpropagated to previous layers, and the hidden layer weights are updated during the forward pass, making this structure a backpropagation free variant. PrimeNet has obtained state-of-the-art results on various image datasets, attaining the dual objective of (1) compact dynamic deep neural structure, which (2) eliminates the problem of backwards-locking. The PrimeNet unit is proposed as an alternative to traditional convolution and dense blocks for faster and memory-efficient training, outperforming previously reported results aimed at adaptive methods for parallel and multilayer deep neural systems.

Laboratory medicine has evolved from a mainly manual profession, providing few selected test results to a highly automated and standardized medical discipline, generating millions of test results per year. As next inevitable evolutional step, artificial intelligence (AI) algorithms will need to assist us in structuring and making sense of the masses of diagnostic data collected today. Such systems will be able to connect clinical and diagnostic data and to provide valuable suggestions in diagnosis, prognosis or therapeutic options. They will merge the often so separated worlds of the laboratory and the clinics. When used correctly, it will be a tool, capable of freeing the physicians time so that he/she can refocus on the patient. In this narrative review I therefore aim to provide an overview of what AI is, what applications currently are available in healthcare and in laboratory medicine in particular. I will discuss the challenges and pitfalls of applying AI algorithms and I will elaborate on the question if healthcare workers will be replaced by such systems in the near future.

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between January 1, 2010, and December 31, 2019, from two medical centers in Taiwan. We constructed a deep learning algorithm, consisting of a segmentation model for cropping cornea images and a classification model that applies convolutional neural networks to differentiate between FK and BK. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heatmap of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved an average diagnostic accuracy of 80.00%. The diagnostic accuracy for BK ranged from 79.59% to 95.91% and that for FK ranged from 26.31% to 63.15%. DenseNet169 showed the best model performance, with an AUC of 0.78 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

Obesity and overweight is a foremost concern around the globe for each group of age. This can be accelerated by the current imposed lockdown. However, excessive weight gain may result in other chronic diseases. This study has been considering the age group of 25 to 55 years as the sample populations and monitoring them from July, 2020 to November, 2020. The lifestyle of this population, food habit, mental health conditions are explored using deep learning based framework. All these parameters need to be monitored as these have close relation with currently imposed constraints due to COVID-19. A predictive model is constructed using deep learning techniques to predict the risk of gaining weight. The predictive model hybridizes the convolutional layer and gated recurrent neural networks as a unified entity for achieving the objective of early weight gain prediction. The result obtained by this model exhibits an encouraging predictive efficiency of 93.7%.

Recent advancement of deep learning has been elevated the multifaceted nature in various applications of this field. Artificial neural networks are now turning into a genuinely old procedure in the vast area of computer science; the principal thoughts and models are more than fifty years of age. However, in this modern computing era, 3rd generation intelligent models are introduced by scientists. In the biological neuron, actual film channels control the progression of particles over the layer by opening and shutting in light of voltage changes because of inborn current flows and remotely led to signals. A comprehensive 3rd generation, Spiking Neural Network (SNN) is diminishing the distance between deep learning, machine learning, and neuroscience in a biologically-inspired manner. It also connects neuroscience and machine learning to establish high-level efficient computing. Spiking Neural Networks initiate utilizing spikes, which are discrete functions that happen at focuses as expected, as opposed to constant values. This paper is a review of the biological-inspired spiking neural network and its applications in different areas. The author aims to present a brief introduction to SNN, which incorporates the mathematical structure, applications, and implementation of SNN. This paper also represents an overview of machine learning, deep learning, and reinforcement learning. This review paper can help advanced artificial intelligence researchers to get a compact brief intuition of spiking neural networks.

One of the main issues for underwater robots navigation is represented by the accurate vehicle positioning, which heavily depends on the orientation estimation phase. The systems employed to this scope are affected by different noise typologies, mainly related to the sensors and to the irregular noise of the underwater environment. Filtering algorithms can reduce their effect if opportunely configured, but this process usually requires fine techniques and time. This paper presents DANAE++, an improved denoising autoencoder based on DANAE, which is able to recover Kalman Filter IMU/AHRS orientation estimations from any kind of noise, independently of its nature. This deep learning-based architecture already proved to be robust and reliable, but in its enhanced implementation significant improvements are obtained both in terms of results and performance. In fact, DANAE++is able to denoise the three angles describing the attitude at the same time, and that is verified also on the estimations provided by the more performing Extended KF. Further tests could make this method suitable for real-time applications on navigation tasks.

Recently, the application of deep reinforcement learning in recommender system is flourishing and stands out by overcoming drawbacks of traditional methods and achieving high recommendation quality. The dynamics, long-term returns and sparse data issues in recommender system have been effectively solved. But the application of deep reinforcement learning brings problems of interpretability, overfitting, complex reward function design, and user cold start. This paper proposed a tag-aware recommender system based on deep reinforcement learning without complex function design, taking advantage of tags to make up for the interpretability problems existing in recommender system. Our experiment is carried out on MovieLens dataset. The result shows that, DRL based recommender system is superior than traditional algorithms in minimum error and the application of tags has little effect on accuracy when making up for interpretability. In addition, DRL based recommender system has excellent performance on user cold start problems.

A patient will visit physicians when he/she feels ill. This illness is not for COVID-19 but it is a general tendency of human being to visit doctor probably it can not be controlled by general drug. When a patient comes to a doctor, the doctor examines him/her after knowing his/her problem. The physician always asks him/her about some questions related to him/her daily life. For example, if a young male patient comes to a doctor with a symptom of fever and cough, the first question doctor asked him that he has a habit of smoking. Then doctor asks him whether this type of symptom appeared often to him previously or not. If the answers of both questions are yes, then the first one is habit and the second one is that he may suffering from some serious disease or a disease due to the weather. The aim of this paper is to consider habit of the patient as well as he/she has been affected by a critical disease. This information is used to build a model that will predict whether there is any possibility of his/her being affected by COVID-19. This research work contributes to tackle the pandemic situation occurred due to Corona Virus Infectious Disease, 2019 (Covid-19). Outbreak of this disease happens based on numerous factors such as past health records and habits of patients. Health records include diabetes tendency, cardiovascular disease existence, pregnancy, asthma, hypertension, pneumonia; chronic renal disease may contribute to this disease occurrence. Past lifestyles such as tobacco, alcohol consumption may be analyzed. A deep learning based framework is investigated to verify the relationship between past health records, habits of patients and covid-19 occurrence. A stacked Gated Recurrent Unit (GRU) based model is proposed in this paper that identifies whether a patient can be infected by this disease or not. The proposed predictive system is compared against existing benchmark Machine Learning classifiers such as Support Vector Machine (SVM) and Decision Tree (DT).

Mineral identification is an important part of geological analysis. Traditional identification methods rely on either the experiences of the appraisers or the various measuring instruments and the methods are either easily influenced by the experiences or need too much work. To solve the above problems, there have been studies using image recognition and intelligent algorithms to identify minerals. But the current studies can not identify many minerals, and the accuracy is low. To increase the number of identified mineral categories and the accuracy, we proposed the method that uses both the mineral images and the Mohs hardness in the deep neural networks to identify the minerals. The experimental results showed that the method can reach 94.0% Top-1 accuracy and 99.9% Top-5 accuracy for 28 common minerals. The model that combines image and Mohs hardness together can identify more minerals and increase the accuracy using less training data.

This paper presents the results of the experimental research and numerical analysis of three reinforced concrete deep beams with openings, designed by the Strut-and-Tie method according to the EN 1992-1-1 recommendations. All tested specimens were made in full size, with the same geometric characteristics and quality of the materials. The specimens, constructed as simply supported beams, were loaded with two concentrated forces and were tested for bending until failure. Each specimen was reinforced with different reinforcement layout determined by parameter variation within the Strut-and-Tie method. Based on the results of experimental research, it was concluded that the behavior of loaded members was in agreement with the proposed forms of the Strut-and-Tie models that were used for their design.

Landslides impact on human activities and socio-economic development especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides i.e. topographic, hydrologic, soil, forest, and geologic factors are prepared from various sources based on availability and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performing field survey. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories content 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models i.e. Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.757 and the testing accuracy is 0.74. Similarly, training accuracy of XGBoost is 0.756 and testing accuracy is 0.703. The prediction of DNN revealed acceptable agreement between susceptibility map and the existing landslides with training and testing accuracy of 0.855 and 0.802, respectively. The results showed that, the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area

Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of Countries requested peoples to use cashless transaction as far as possible. Practically it is not always possible to use it in all transactions. Since number of such cashless transactions have been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/her previous transactions. Normally banks or other transaction authorities warned their customers about the transaction If any deviation is noticed by them from available patterns. These authorities think that it is possibly of fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining , decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. These approaches is try to find out normal usage pattern of customers based on their past activities. The objective of this paper is to find out such fraud transactions during such unmanageable situation.Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transaction in during money transfer may save customers from financial loss. Mobile based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in this paper that monitors and detects fraudulent activities. Implementing and applying recurrent neural network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.

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.

In the recent years, intelligent data-driven faultdiagnosis methods on gearboxes have been successfully developedand popularly applied in the industries. Currently, most ofthe machine learning techniques require that the training andtesting data are from the same distribution. However, thisassumption is difficult to be met in the real industries, sincethe gearbox operating conditions usually change in practice,which results in significant data distribution gap and diagnosticperformance deteriorations in applying the learned knowledgeon the new conditions. This paper proposes a deep learning-based domain adaptation method to address this issue. Theraw current signals are directly used as the model inputs fordiagnostics, which are easy to collect in the real industries andfacilitate practical applications. The maximum mean discrepancymetric is introduced to the deep neural network, the optimizationof which guarantees the extraction of generalized machineryhealth condition features across different operating conditions.The experiments on a real-world gearbox condition monitoringdataset validate the effectiveness of the proposed method, whichoffers a promising tool for cross-domain diagnosis in the realindustries.

This paper investigates the use of deep learning techniques to perform energy demand forecasting. Specifically, the authors have adapted a deep neural network originally thought for image classification and composed of a convolutional neural network (CNN) followed by a multilayered fully connected artificial neural network (ANN). The convolutional part of the network was fed with a grid of temperature forecasting data distributed in the area of interest in order to extract a featured temperature. The subsequent ANN is then fed with this calculated temperature along with other data related to the timing of the forecast. The proposed structure was first trained and then used in a real setting aimed to provide the French energy demand forecast using ARPEGE forecasting weather data. The results show that the performance of this approach is in the line of the performance provided by the reference RTE subscription-based service, which opens the possibility to obtain high accuracy forecasting using widely accessible deep learning techniques through open-source machine learning platforms.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these type of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand, and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

A regularization approach to model selection, within a generalized HJM framework, is introduced which learns the closest arbitrage-free model to a prespecified factor model. This optimization problem is represented as the limit of a one-parameter family of computationally tractable penalized model selection tasks. General theoretical results are derived and then specialized to affine term-structure models where new types of arbitrage-free machine learning models for the forward-rate curve are estimated numerically and compared to classical short-rate and the dynamic Nelson-Siegel factor models.

The paper presents a synthesis of deep eutectic solvents (DESs) based on choline chloride (ChCl) as hydrogen bond acceptor and phenol (Ph), glycol ethylene (EG), and levulinic acid (Lev) as hydrogen bond donors in 1:2 molar ratio. DESs were successfully used as absorption solvents for removal of dimethyl disulfide from (DMDS) from model biogas steam. Several parameters affecting the absorption capacity and absorption rate has been optimized including kind of DES, temperature, the volume of absorbent, model biogas flow rate, and initial concentration of DMDS. Furthermore, reusability and regeneration of DESs by means of adsorption and nitrogen barbotage followed by the mechanism of absorptive desulfurization by means of density functional theory (DFT) as well as FT-IR analysis were investigated. Experimental results indicate that the most promising DES for biogas purification is ChCl:Ph, due to high absorption capacity, relatively long absorption rate, and easy regeneration. The research on the absorption mechanism revealed that van der Waal interaction is the main driving force for DMDS removal from model biogas.

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

Pedestrian detection is the core of driver assistance system, which collects the road conditions through the radars or cameras on the vehicle, judges whether there is a pedestrian in front of the vehicle, supports decisions such as raising the alarm, automatically slowing down or emergency stopping to keep pedestrians safe, and improves the security when the vehicle is moving. Suffered from weather, lighting, clothing, large pose variations and occlusion, the current pedestrian detection still has a certain distance from the practical applications. In recent years, deep networks have shown excellent performance for image detection, recognition and classification. Some researchers employed deep network for pedestrian detection and achieve great progress, but deep networks need huge computational resources which make it difficult to put into practical applications. In real scenarios of autonomous vehicle, the computation ability is limited. Thus, the shallow networks such as UDN (Unified Deep Networks) is a better choice since it performs well on consuming less computation resources. Base on UDN, this paper proposes a new deep network model named as two-stream UDN, which augments another branch for solving traditional UDN’s indistinction of the difference between trees / telegraph poles and pedestrians. The new branch accepts the upper third part of the pedestrian image as input, and the partial image has less deformation, stable features and more distinguished characters from other objects. For the proposed two-stream UDN, multi-input features including HOG feature, Sobel feature, color feature and foreground regions extracted by GrabCut segmentation algorithms are fed. Compared with the original input of UDN, the multi-input features are more conducive for pedestrian detection since the fused HOG features and significant objects are more significant for pedestrian detection. Two-stream UDN is trained through two steps: First, the two sub-networks are trained until converge; then we fuse results of the two subnets as the final result and feed it back to the two subnets to fine tune network parameters synchronously. To improve the performance, Softplus is adopted as activation function to obtain faster training speed, and positive samples are mirrored and rotated with small angle to make positive and negative samples more balanced.

A pixel-based segmentation method was demonstrated to be confounded by developmental stage in estimation of flowering of mango. Categorization of panicles into three developmental stages was undertaken with a single and a two-stage deep learning framework (YOLO and R2CNN), using either upright or rotated bounding boxes. For a validation image set and for total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R2CNN(-rotated) and R2CNN-upright achieved: (i) RMSEs of 25.6, 16.0, 15.4, 25.8 and 32.3 panicles per tree image, (ii) Mean average precision (mAP) scores of 72.2, 69.1, 65.0, 62.5 and 70.9% and (iii) weighted F1-scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of images involving a different orchard and cultivar and use of a different camera, the R2 for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, models generalised well, but with no consistent benefit from use of rotated over upright bounding boxes. While the YOLOv3-rotated model was superior in terms of total panicle count, the R2CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events.