Search

Skin cancer has a significant impact on the lives of many individuals annually and is recognized as the most prevalent type of cancer. In the United States, an estimated annual incidence of approximately 3.5 million people receiving a diagnosis of skin cancer underscores its widespread prevalence. Furthermore, the prognosis for individuals afflicted with advancing stages of skin cancer experiences a substantial decline in survival rates. This paper is dedicated to aiding healthcare experts in distinguishing between benign and malignant skin cancer cases by employing a range of machine learning and deep learning techniques and different feature extractors and feature selectors to enhance the evaluation metrics. In this paper, different transfer learning models are employed as feature extractors, and to enhance the evaluation metrics, a feature selection layer is designed, which includes diverse techniques such as Univariate, Mutual Information, ANOVA, PCA, XGB, Lasso, Random Forest, and Variance. Among transfer models, DenseNet-201 was selected as the primary feature extractor to identify features from data. Subsequently, the Lasso method was applied for feature selection, utilizing diverse machine learning approaches such as MLP, XGB, RF, and NB. To optimize accuracy and precision, ensemble methods were employed to identify and enhance the best-performing models. The study provides accuracy and sensitivity rates of 87.72% and 92.15%, respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is a significant cause of female cancer-related deaths in the US. Checking how severe the cancer is helps in planning treatment. Modern AI methods are good at grading cancer, but they are not used much in hospitals yet. We developed and utilized ensemble deep learning algorithms for addressing the tasks of classifying (1) breast cancer subtype and (2) breast cancer invasiveness from whole slide image (WSI) histopathology slides. The ensemble models used were based on convolutional neural networks (CNNs) known for extracting distinctive features crucial for accurate classification. In this paper, we provide a comprehensive analysis of these models and the used methodology for breast cancer diagnosis tasks. Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens. [ABSTRACT FROM AUTHOR]

This paper analyzes and combs the application and research status of artificial intelligence technology in the field. of military intelligence, in order to provide reference for subsequent military intelligence research. This paper summarizes the development and application of artificial intelligence in military intelligence work from the aspects of intelligence analysis and military command decision-making. Based on the intelligence workflow, the military intelligence service model under artificial intelligence technology is analyzed. This paper systematically combs the research and development status of typical projects of intelligent intelligence systems in the United States, and analyzes the key development trends and technical difficulties of artificial intelligence in the military intelligence field. [ABSTRACT FROM AUTHOR]

The prolonged COVID-19 pandemic has tied up significant medical resources, and its management poses a challenge for the public health care decision making. Accurate predictions of the hospitalizations are crucial for the decision makers to make informed decision for the medical resource allocation. This paper proposes a method named County Augmented Transformer (CAT). To generate accurate predictions of four-week-ahead COVID-19 related hospitalizations for every states in the United States. Inspired by the modern deep learning techniques, our method is based on a self-attention model (known as the transformer model) that is actively used in Natural Language Processing. Our transformer based model can capture both short-term and long-term dependencies within the time series while enjoying computational efficiency. Our model is a data based approach that utilizes the publicly available information including the COVID-19 related number of confirmed cases, deaths, hospitalizations data, and the household median income data. Our numerical experiments demonstrate the strength and the usability of our model as a potential tool for assisting the medical resources allocation. [ABSTRACT FROM AUTHOR]

Research has shown that climate change creates warmer temperatures and drier conditions, leading to longer wildfire seasons and increased wildfire risks in the United States. These factors have, in turn, led to increases in the frequency, extent, and severity of wildfires in recent years. Given the danger posed by wildland fires to people, property, wildlife, and the environment, there is an urgent need to provide tools for effective wildfire management. Early detection of wildfires is essential to minimizing potentially catastrophic destruction. To that end, in this paper, we present our work on integrating multiple data sources into SmokeyNet, a deep learning model using spatiotemporal information to detect smoke from wildland fires. We present Multimodal SmokeyNet and SmokeyNet Ensemble for multimodal wildland fire smoke detection using satellite-based fire detections, weather sensor measurements, and optical camera images. An analysis is provided to compare these multimodal approaches to the baseline SmokeyNet in terms of accuracy metrics, as well as time-to-detect, which is important for the early detection of wildfires. Our results show that incorporating weather data in SmokeyNet improves performance numerically in terms of both F1 and time-to-detect over the baseline with a single data source. With a time-to-detect of only a few minutes, SmokeyNet can be used for automated early notification of wildfires, providing a useful tool in the fight against destructive wildfires. [ABSTRACT FROM AUTHOR]

Human falls, especially for elderly people, can cause serious injuries that might lead to permanent disability. Approximately 20–30% of the aged people in the United States who experienced fall accidents suffer from head trauma, injuries, or bruises. Fall detection is becoming an important public healthcare problem. Timely and accurate fall incident detection could enable the instant delivery of medical services to the injured. New advances in vision-based technologies, including deep learning, have shown significant results in action recognition, where some focus on the detection of fall actions. In this paper, we propose an automatic human fall detection system using multi-stream convolutional neural networks with fusion. The system is based on a multi-level image-fusion approach of every 16 frames of an input video to highlight movement differences within this range. This results of four consecutive preprocessed images are fed to a new proposed and efficient lightweight multi-stream CNN model that is based on a four-branch architecture (4S-3DCNN) that classifies whether there is an incident of a human fall. The evaluation included the use of more than 6392 generated sequences from the Le2i fall detection dataset, which is a publicly available fall video dataset. The proposed method, using three-fold cross-validation to validate generalization and susceptibility to overfitting, achieved a 99.03%, 99.00%, 99.68%, and 99.00% accuracy, sensitivity, specificity, and precision, respectively. The experimental results prove that the proposed model outperforms state-of-the-art models, including GoogleNet, SqueezeNet, ResNet18, and DarkNet19, for fall incident detection. [ABSTRACT FROM AUTHOR]

Wind power is a popular renewable energy source, and the accurate prediction of wind speed plays an important role in improving the power generation efficiency of wind turbines and ensuring the normal operation of wind power equipment. Due to the instability and randomness of wind speed, it is difficult to achieve accurate prediction by traditional prediction methods. To improve the power generation efficiency of wind turbines and realize the predictability of wind speed, a hybrid wind speed prediction model based on GRUs (gated recurrent units) was constructed in this paper based on a deep neural network and feature extraction method. The hybrid model feature extraction module was implemented based on a combination of Tsfresh (a python package for time series feature extraction) and sparse PCA (sparse principal component analysis), and the network structure and other hyperparameters of the GRU module were determined through experiments. The model was validated using actual wind measurement data from a wind farm on the west coast of the United States. The results showed that the proposed model had less computational time and higher computational accuracy than the SARIMAX (seasonal auto-regressive integrated moving average with exogenous factors) and LSTM (long short-term memory) models. [ABSTRACT FROM AUTHOR]

The development of a new type of international relations is the advancement and improvement of diplomatic thinking among contemporary nations. It also serves as a crucial yardstick for assessing the future global pattern and the direction of order changes. Proper interaction between major powers can foster the growth of new international relations and has a significant impact on advancing global cooperation and the promotion of human peace. The goal of this essay is to examine how friendly interactions between major powers have affected the development of new international relations. A deep learning network model is presented for this purpose. The deep learning model was used to identify the emotions of the survey results, analyze each person's emotional tendencies, and summarize and compare the data. Relevant questionnaire surveys were conducted using the online questionnaire survey method on individuals in various countries. The survey results in this paper demonstrate that 96.5 percent of Chinese, 89.3 percent of Russians, and 81.6 percent of Americans support friendly relations between major nations. Only a very small percentage of the investigators supported hostile relations, with their support being 1.06 percent, 3.11 percent, and 2.94 percent, respectively. Therefore, creating a win-win partnership between major powers is exactly what the people of all nations are calling for. In contrast to the past, it is no longer hostile and violent. People anticipate that more great powers will coexist peacefully. [ABSTRACT FROM AUTHOR]

Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited-use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network's prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve-receiver operating characteristic (AUC-ROC). [ABSTRACT FROM AUTHOR]

Recent years have witnessed wider prevalence of vertebral column pathologies due to lifestyle changes, sedentary behaviors, or injuries. Spondylolisthesis and scoliosis are two of the most common ailments with an incidence of 5% and 3% in the United States population, respectively. Both of these abnormalities can affect children at a young age and, if left untreated, can progress into severe pain. Moreover, severe scoliosis can even lead to lung and heart problems. Thus, early diagnosis can make it easier to apply remedies/interventions and prevent further disease progression. Current diagnosis methods are based on visual inspection by physicians of radiographs and/or calculation of certain angles (e.g., Cobb angle). Traditional artificial intelligence-based diagnosis systems utilized these parameters to perform automated classification, which enabled fast and easy diagnosis supporting tools. However, they still require the specialists to perform error-prone tedious measurements. To this end, automated measurement tools were proposed based on processing techniques of X-ray images. In this paper, we utilize advances in deep transfer learning to diagnose spondylolisthesis and scoliosis from X-ray images without the need for any measurements. We collected raw data from real X-ray images of 338 subjects (i.e., 188 scoliosis, 79 spondylolisthesis, and 71 healthy). Deep transfer learning models were developed to perform three-class classification as well as pair-wise binary classifications among the three classes. The highest mean accuracy and maximum accuracy for three-class classification was 96.73% and 98.02%, respectively. Regarding pair-wise binary classification, high accuracy values were achieved for most of the models (i.e., > 98%). These results and other performance metrics reflect a robust ability to diagnose the subjects' vertebral column disorders from standard X-ray images. The current study provides a supporting tool that can reasonably help the physicians make the correct early diagnosis with less effort and errors, and reduce the need for surgical interventions. [ABSTRACT FROM AUTHOR]

Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause of cancer death in the United States. Predicting tumors like PDACs (including both classification and segmentation) from medical images by deep learning is becoming a growing trend, but usually a large number of annotated data are required for training, which is very labor-intensive and time-consuming. In this paper, we consider a partially supervised setting, where cheap image-level annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxel-level classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier. Experimental results show that our IAG-Net boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Due to the strong propagation causality of delays between airports, this paper proposes a delay prediction model based on a deep graph neural network to study delay prediction from the perspective of an airport network. We regard airports as nodes of a graph network and use a directed graph network to construct airports' relationship. For adjacent airports, weights of edges are measured by the spherical distance between them, while the number of flight pairs between them is utilized for airports connected by flights. On this basis, a diffusion convolution kernel is constructed to capture characteristics of delay propagation between airports, and it is further integrated into the sequence-to-sequence LSTM neural network to establish a deep learning framework for delay prediction. We name this model as deep graph-embedded LSTM (DGLSTM). To verify the model's effectiveness and superiority, we utilize the historical delay data of 325 airports in the United States from 2015 to 2018 as the model training set and test set. The experimental results suggest that the proposed method is superior to the existing mainstream methods in terms of accuracy and robustness. [ABSTRACT FROM AUTHOR]

Background: Prescription medication (PM) misuse/abuse has emerged as a national crisis in the United States, and social media has been suggested as a potential resource for performing active monitoring. However, automating a social media-based monitoring system is challenging-requiring advanced natural language processing (NLP) and machine learning methods. In this paper, we describe the development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter.Methods: We experimented with state-of-the-art bi-directional transformer-based language models, which utilize tweet-level representations that enable transfer learning (e.g., BERT, RoBERTa, XLNet, AlBERT, and DistilBERT), proposed fusion-based approaches, and compared the developed models with several traditional machine learning, including deep learning, approaches. Using a public dataset, we evaluated the performances of the classifiers on their abilities to classify the non-majority "abuse/misuse" class.Results: Our proposed fusion-based model performs significantly better than the best traditional model (F1-score [95% CI]: 0.67 [0.64-0.69] vs. 0.45 [0.42-0.48]). We illustrate, via experimentation using varying training set sizes, that the transformer-based models are more stable and require less annotated data compared to the other models. The significant improvements achieved by our best-performing classification model over past approaches makes it suitable for automated continuous monitoring of nonmedical PM use from Twitter.Conclusions: BERT, BERT-like and fusion-based models outperform traditional machine learning and deep learning models, achieving substantial improvements over many years of past research on the topic of prescription medication misuse/abuse classification from social media, which had been shown to be a complex task due to the unique ways in which information about nonmedical use is presented. Several challenges associated with the lack of context and the nature of social media language need to be overcome to further improve BERT and BERT-like models. These experimental driven challenges are represented as potential future research directions. [ABSTRACT FROM AUTHOR]

In this paper, we propose bag of adversarial features (BAFs) for identifying mild traumatic brain injury (MTBI) patients from their diffusion magnetic resonance images (MRIs) (obtained within one month of injury) by incorporating unsupervised feature learning techniques. MTBI is a growing public health problem with an estimated incidence of over 1.7 million people annually in USA. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. Unlike most of the previous works, which use hand-crafted features extracted from different parts of brain for MTBI classification, we employ feature learning algorithms to learn more discriminative representation for this task. A major challenge in this field thus far is the relatively small number of subjects available for training. This makes it difficult to use an end-to-end convolutional neural network to directly classify a subject from MRIs. To overcome this challenge, we first apply an adversarial auto-encoder (with convolutional structure) to learn patch-level features, from overlapping image patches extracted from different brain regions. We then aggregate these features through a bag-of-words approach. We perform an extensive experimental study on a dataset of 227 subjects (including 109 MTBI patients, and 118 age and sex-matched healthy controls) and compare the bag-of-deep-features with several previous approaches. Our experimental results show that the BAF significantly outperforms earlier works relying on the mean values of MR metrics in selected brain regions. [ABSTRACT FROM AUTHOR]

Highlights • Two data fusion approaches for combining time-series with text data are proposed. • Text data is modeled using word embeddings, convolutional layers and attention. • Proposed models are applied to taxi demand prediction in event areas in New York. • Text information about events is shown to significantly reduce prediction error. • Proposed models are shown to substantially outperform traditional approaches. Abstract Accurate time-series forecasting is vital for numerous areas of application such as transportation, energy, finance, economics, etc. However, while modern techniques are able to explore large sets of temporal data to build forecasting models, they typically neglect valuable information that is often available under the form of unstructured text. Although this data is in a radically different format, it often contains contextual explanations for many of the patterns that are observed in the temporal data. In this paper, we propose two deep learning architectures that leverage word embeddings, convolutional layers and attention mechanisms for combining text information with time-series data. We apply these approaches for the problem of taxi demand forecasting in event areas. Using publicly available taxi data from New York, we empirically show that by fusing these two complementary cross-modal sources of information, the proposed models are able to significantly reduce the error in the forecasts. [ABSTRACT FROM AUTHOR]

Malignancy is the tendency of a medical condition to progressively become fatal and generally refers to the presence of cancerous cells that can spread, invade, and destroy tissues. In the United States, a new cancer diagnosis is given every 30 s, and the rates of diagnosis are not indicating any slowdown. The number of cancer cases is projected to increase by 35% over the next decade. Increasing cancer cases have attracted researchers to find new approaches for their identification and characterization. Skin diseases are a significant healthcare burden, affecting millions of people globally. The early detection and diagnosis of skin diseases are essential to prevent adverse health consequences, including the development of malignant skin tumors. Dermoscopy-based diagnosis of skin diseases is a time-consuming process, particularly in resource-limited healthcare settings. Recent advancements in computer vision algorithms have led to the development of several smartphone-based applications for early skin disease prognosis. In this paper, we have utilized a set of 16 distinctive convolutional neural network models, based on deep learning, to process over 45,000 high-quality images from the HAM10000 dataset, encompassing seven categories of skin diseases. Our models were able to effectively identify and classify skin diseases using lesion images as input. Dermoscopy-based diagnosis of skin diseases is a time-consuming process, particularly in resource-limited healthcare settings. Our proposed application for early skin disease detection aims to prevent unintended health consequences, which can result in wastage of operating hours, resources, and, in some cases, compromised patient health. We have benchmarked our models against one another to evaluate their effectiveness and efficiency, using performance measures such as accuracy, precision, sensitivity, specificity, F-score, and G-Mean. Our results demonstrate that most deployed models achieve an accuracy of up to 99%. [ABSTRACT FROM AUTHOR]

Opioid overdose (OD) has become a leading cause of accidental death in the United States, and overdose deaths reached a record high during the COVID-19 pandemic. Combating the opioid crisis requires targeting high-need populations by identifying individuals at risk of OD. While deep learning emerges as a powerful method for building predictive models using large scale electronic health records (EHR), it is challenged by the complex intrinsic relationships among EHR data. Further, its utility is limited by the lack of clinically meaningful explainability, which is necessary for making informed clinical or policy decisions using such models. In this paper, we present LIGHTED, an integrated deep learning model combining long short term memory (LSTM) and graph neural networks (GNN) to predict patients' OD risk. The LIGHTED model can incorporate the temporal effects of disease progression and the knowledge learned from interactions among clinical features. We evaluated the model using Cerner's Health Facts database with over 5 million patients. Our experiments demonstrated that the model outperforms traditional machine learning methods and other deep learning models. We also proposed a novel interpretability method by exploiting embeddings provided by GNNs to cluster patients and EHR features respectively, and conducted qualitative feature cluster analysis for clinical interpretations. Our study shows that LIGHTED can take advantage of longitudinal EHR data and the intrinsic graph structure of EHRs among patients to provide effective and interpretable OD risk predictions that may potentially improve clinical decision support. • A multi-stage deep learning model for opioid overdose risk prediction was developed. • The model is based on LSTM and Heterogeneous Relational Graph Neural Network. • The combined model can learn the temporal progression of disease development and relations between patients and features. • A ranking of clinical features is provided for interpretation. • The proposed model is useful to support clinical decision. [ABSTRACT FROM AUTHOR]

Battery energy storage technology is an important part of the industrial parks to ensure the stable power supply, and its rough charging and discharging mode is difficult to meet the application requirements of energy saving, emission reduction, cost reduction, and efficiency increase. As a classic method of deep reinforcement learning, the deep Q-network is widely used to solve the problem of user-side battery energy storage charging and discharging. In some scenarios, its performance has reached the level of human expert. However, the updating of storage priority in experience memory often lags behind updating of Q-network parameters. In response to the need for lean management of battery charging and discharging, this paper proposes an improved deep Q-network to update the priority of sequence samples and the training performance of deep neural network, which reduces the cost of charging and discharging action and energy consumption in the park. The proposed method considers factors such as real-time electricity price, battery status, and time. The energy consumption state, charging and discharging behavior, reward function, and neural network structure are designed to meet the flexible scheduling of charging and discharging strategies, and can finally realize the optimization of battery energy storage benefits. The proposed method can solve the problem of priority update lag, and improve the utilization efficiency and learning performance of the experience pool samples. The paper selects electricity price data from the United States and some regions of China for simulation experiments. Experimental results show that compared with the traditional algorithm, the proposed approach can achieve better performance in both electricity price systems, thereby greatly reducing the cost of battery energy storage and providing a stronger guarantee for the safe and stable operation of battery energy storage systems in industrial parks. [ABSTRACT FROM AUTHOR]

Hurricanes are among the most devastating natural disasters in the United States, causing billions of dollars of property damage and insured losses. During extreme wind events, unsecured objects in jobsites can easily become airborne debris, which results in substantial loss to construction projects and neighboring communities. Towards a systematic disaster preparedness in construction jobsites, this paper presents a novel vision-based digital twinning and threat assessment framework. We encode the context of disaster risk into deep-learning architectures to identify and analyze the characteristics and impacts of potential wind-borne debris in construction site digital twin models. Case studies on nine piles of construction materials are presented to demonstrate and discuss the fidelity of the proposed computational modules. The proposed methods are expected to help provide heads up for practitioners to quickly recognize, localize, and assess potential wind-borne derbies in construction jobsites, and thereby implementing hurricane preparedness in an effective and timely manner. • A new AI-based framework for construction site disaster preparedness. • Digital twinning of potential wind-borne debris and 3D point cloud segmentation. • Case studies were conducted to evaluate the performance of the proposed method. • Potential for effective risk-informed decision making for disaster preparedness. [ABSTRACT FROM AUTHOR]

This paper proposes an automated active fire detection framework using Sentinel-2 imagery. The framework is made up of three basic parts including data collection and preprocessing, deep-learning-based active fire detection, and final product generation modules. The active fire detection module is developed on a specifically designed dual-domain channel-position attention (DCPA)+HRNetV2 model and a dataset with semi-manually annotated active fire samples is constructed over wildfires that commenced on the east coast of Australia and the west coast of the United States in 2019–2020 for the training process. This dataset can be used as a benchmark for other deep-learning-based algorithms to improve active fire detection accuracy. The performance of active fire detection is evaluated regarding the detection accuracy of deep-learning-based models and the processing efficiency of the whole framework. Results indicate that the DCPA and HRNetV2 combination surpasses DeepLabV3 and HRNetV2 models for active fire detection. In addition, the automated framework can deliver active fire detection results of Sentinel-2 inputs with coverage of about 12,000 km2 (including data download) in less than 6 min, where average intersections over union (IoUs) of 70.4% and 71.9% were achieved in tests over Australia and the United States, respectively. Concepts in this framework can be further applied to other remote sensing sensors with data acquisitions in SWIR-NIR-Red ranges and can serve as a powerful tool to deal with large volumes of high-resolution data used in future fire monitoring systems and as a cost-efficient resource in support of governments and fire service agencies that need timely, optimized firefighting plans. [ABSTRACT FROM AUTHOR]

[Display omitted] • A new convolutional recurrent neural network is used for spatiotemporal prediction. • A new probabilistic deep learning model is proposed for solar radiation prediction. • A data preprocessing method for solar radiation uncertainty assessment is proposed. • The developed model performs very well in accuracy and uncertainty. High-quality and reliable solar radiation spatiotemporal probabilistic prediction is very significant for the planning and management of solar energy. In this paper, convolutional shared weight long short-term memory network is proposed to deal with solar radiation spatiotemporal prediction problems. The model can minimize the training time of model without significantly reducing prediction accuracy. Furthermore, a spatiotemporal probabilistic prediction model that combines convolutional shared weight long short-term memory network and deep ensemble method is proposed to deal with the solar radiation probabilistic prediction problem. The model obtains the uncertainty estimation of predictands by adjusting the network structure and optimizes the uncertainty by employing a proper scoring rule. In addition, a combination of ensembles are used in the model to improve the robustness of probabilistic prediction. The new spatiotemporal probabilistic prediction model is applied to predict solar radiation in a real area of the United States. Five state-of-the-art models and seven evaluation indicators are used for comparation. The comparation results show the proposed model is able to provide accurate point prediction, reasonable prediction interval and reliable probabilistic prediction results for a whole area. [ABSTRACT FROM AUTHOR]

Malignant melanoma accounts for about 1–3% of all malignancies in the West, especially in the United States. More than 9000 people die each year. In general, it is difficult to characterize a skin lesion from a photograph. In this paper, we propose a deep learning-based computer-aided diagnostic algorithm for the classification of malignant melanoma and benign skin tumors from RGB channel skin images. The proposed deep learning model constitutes a tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to classify skin lesions in dermoscopy images. We implement an algorithm to classify malignant melanoma and benign tumors using skin lesion images and expert labeling results from convolutional neural networks. The U-Net model achieved a dice similarity coefficient of 81.1% compared to the expert labeling results. The classification accuracy of malignant melanoma reached 80.06%. As a result, the proposed AI algorithm is expected to be utilized as a computer-aided diagnostic algorithm to help early detection of malignant melanoma. [ABSTRACT FROM AUTHOR]

While the use of crime data has been widely advocated in the literature, its availability is often limited to large urban cities and isolated databases that tend not to allow for spatial comparisons. This paper presents an efficient machine learning framework capable of predicting spatial crime occurrences, without using past crime as a predictor, and at a relatively high resolution: the U.S. Census Block Group level. The proposed framework is based on an in-depth multidisciplinary literature review allowing the selection of 188 best-fit crime predictors from socio-economic, demographic, spatial, and environmental data. Such data are published periodically for the entire United States. The selection of the appropriate predictive model was made through a comparative study of different machine learning families of algorithms, including generalized linear models, deep learning, and ensemble learning. The gradient boosting model was found to yield the most accurate predictions for violent crimes, property crimes, motor vehicle thefts, vandalism, and the total count of crimes. Extensive experiments on real-world datasets of crimes reported in 11 U.S. cities demonstrated that the proposed framework achieves an accuracy of 73% and 77% when predicting property crimes and violent crimes, respectively. [ABSTRACT FROM AUTHOR]

Patients with advanced cancer are burdened physically and psychologically, so there is an urgent need to pay more attention to their health-related quality of life (HRQOL). With an expected clinical endpoint prediction, over-treatment can be effectively eliminated by the means of palliative care at the right time. This paper develops a deep learning based approach for cancer clinical endpoint prediction based on patient's electronic health records (EHR). Due to the pervasive existence of categorical information in EHR, it brings unavoidably obstacles to the effective numerical learning algorithms. To address this issue, we propose a novel cross-field categorical attributes embedding (CCAE) model to learn a vectorized representation for cancer patients in attribute-level by orders, in which the strong semantic coupling among categorical variables are well exploited. By transforming the order-dependency modeling into a sequence learning task in an ingenious way, recurrent neural network is adopted to capture the semantic relevance among multi-order representations. Experimental results from the SEER-Medicare EHR dataset have illustrated that the proposed model can achieve competitive prediction performance compared with other baselines. [ABSTRACT FROM AUTHOR]

• Temporal and spatial features are used for wind speed forecasting. • A novel probabilistic deep learning model is proposed for wind speed forecasting. • The proposed model shows the best performance compared with other models. • Temporal and spatial uncertainty of the wind speed are estimated based on the model. Reliable and accurate probabilistic forecasting of wind speed is of vital importance for the utilization of wind energy and operation of power systems. In this paper, a probabilistic spatiotemporal deep learning model for wind speed forecasting is proposed. The underlying wind turbines are embedded into a grid space, which fully expresses the spatiotemporal variation process of the airflow. Thus, advanced image recognition methods can be employed to solve the spatiotemporal wind speed forecasting problem. The proposed model is based on a spatial–temporal neural network (STNN) and variational Bayesian inference. The proposed STNN combines the convolutional GRU model and 3D Convolutional Neural Network and uses an encoding-forecasting structure to generate the spatiotemporal predictions. Variational Bayesian inference is employed to obtain the approximated posterior parameter distribution of the model and determine the probability of the prediction. The proposed model is applied in two real-world case studies in United States. The experimental results demonstrate that the proposed model significantly outperforms other models in both forecast skill and forecast reliability. The uncertainty estimation is also shown and it demonstrates that the proposed model is able to provide effective uncertainty estimation in both the time level and space level. [ABSTRACT FROM AUTHOR]

• Successful disaster management requires data describing disaster impact and extent of damage. • Aerial data collection is resource-intensive and requires offline post-processing. • We introduce convolutional neural network (CNN) models for ground object detection. • The models recognize building roofs, cars, vegetation, debris, and flooded areas. • We achieve 80.69% and 74.48% mAP for high and low altitude footage, respectively. Accurate and timely access to data describing disaster impact and extent of damage is key to successful disaster management (a process that includes prevention, mitigation, preparedness, response, and recovery). Airborne data acquisition using helicopter and unmanned aerial vehicle (UAV) helps obtain a bird's-eye view of disaster-affected areas. However, a major challenge to this approach is robustly processing a large amount of data to identify and map objects of interest on the ground in real-time. The current process is resource-intensive (must be carried out manually) and requires offline computing (through post-processing of aerial videos). This research introduces and evaluates a series of convolutional neural network (CNN) models for ground object detection from aerial views of disaster's aftermath. These models are capable of recognizing critical ground assets including building roofs (both damaged and undamaged), vehicles, vegetation, debris, and flooded areas. The CNN models are trained on an in-house aerial video dataset (named Volan2018) that is created using web mining techniques. Volan2018 contains eight annotated aerial videos (65,580 frames) collected by drone or helicopter from eight different locations in various hurricanes that struck the United States in 2017–2018. Eight CNN models based on You-Only-Look-Once (YOLO) algorithm are trained by transfer learning, i.e., pre-trained on the COCO/VOC dataset and re-trained on Volan2018 dataset, and achieve 80.69% mAP for high altitude (helicopter footage) and 74.48% for low altitude (drone footage), respectively. This paper also presents a thorough investigation of the effect of camera altitude, data balance, and pre-trained weights on model performance, and finds that models trained and tested on videos taken from similar altitude outperform those trained and tested on videos taken from different altitudes. Moreover, the CNN model pre-trained on the VOC dataset and re-trained on balanced drone video yields the best result in significantly shorter training time. [ABSTRACT FROM AUTHOR]

What can be learned from the process of community-engaged research (CER) on refugee resettlement? In the following, we share experiences, reflections, and lessons from implementing such a project. We begin with background on refugee resettlement and recent resettlement dynamics in the United States and Wisconsin, as well as literature on the study of refugees and this type of research more generally. Results and discussion are presented though our understanding of, and involvement with, the process via a framework of CER desired process outcomes, which we both propose and utilize to encourage effective efforts with marginalized populations going forward. CER is challenging and must be undertaken thoughtfully. One of the paper's primary contributions is to share successes and failures in a transparent and unvarnished fashion. In particular, researchers need to share power and listen deeply, actions that will reverberate throughout such a process. Doing so comes with certain risks, and may be tangled, but also has strong potential to produce useful data, deep learning for researchers and participants, as well as empowerment of marginalized populations and relationship building that can yield future collaboration towards resilience. [ABSTRACT FROM AUTHOR]