A Two Phase Smart Code Editor

A comprehensive deep learning model for motor phenotypes of Parkinson's disease using three-dimensional kinect V2 detectors.

BACKGROUND Intracranial germ cell tumors (iGCTs) are divided into germinomas (GEs) and nongerminomatous germ cell tumors (NGGCTs), each having distinct treatments and prognoses. However, predictive biomarkers for differentiation are limited. Here, we aim to develop a deep learning (DL) model that can automatically differentiate GEs from NGGCTs using preoperative magnetic resonance (MR) images and analyzing how our model improved clinical decision making among five physicians. METHODS: This multicenter study included patients with pathology-confirmed iGCTs for the developed set (total n = 280), which was split into training (n = 200) and testing datasets (n= 80), and three independent validation datasets (n = 64), respectively. We developed a DL model based on 3D nnU-Net and preoperative MR images to differentiate GEs from NGGCTs. To evaluate the clinical value of the DL model, five physicians' accuracy and level of consistency in identifying tumor types were compared in the testing and three validation datasets, with and without referring to the DL model’s output. RESULTS The DL model achieved AUCs of 0.950, 0.921, 0.869, and 0.905 in the testing and three validation datasets, respectively, which is superior to using conventional information including MR features and clinical information (AUC=0.768, P=0.009). The physicians’ diagnostic performance improved from an average AUC of 0.695 without reference to the DL output to 0.842 using the DL output in the testing and independent validation datasets (21.2% improvement, P=0.014). CONCLUSIONS We developed and validated a DL model using a large dataset to accurately differentiate GEs from NGGCTs using preoperative MR images.

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

Code completion is an important feature in Integrated Development Environments (IDEs). These years, researchers have been making efforts for intelligent code completion. However, existing work on intelligent code completion either only considered production code, or did not distinguish between production code and test code. It is unclear how effective existing completion models are for test code completion, nor whether we can further improve it. In this work, we focus on the completion of test code. We first find through experiments that completion models for production code are suboptimal for test code completion. Then we analyze the specific characteristics of test code, and observe that test code has inter- and intra-project similarities, and a strong relationship with its focal class and other production classes depending on the focal class (i.e., focal-related code). By incorporating test code from other projects to fine-tune existing models, we leverage the inter-project similarity of test code to improve the completion of tokens specific to test code. By introducing a local component and constructing existing test code as well as the focal-related code in the project as references, we enhance existing code completion models with the intra-project similarity and the focal-related code of test code. Experiments show that each characteristic of test code we exploit can bring substantial improvement to test code completion and our integrated framework outperforms other baseline frameworks. Compared to the base completion model, on token-level completion, our optimal model for test code completion relatively improves all-token and identifier completion accuracy by 7.68% and 19.96%, respectively; on line-level completion, it relatively improves edit-distance similarity and exact-match metrics by 8.89% and 22.82%, respectively. Moreover, we perform error analysis and point out potential directions for future work.

Autistic people are often disadvantaged in employment, education, etc. In fact, autistic students/employees face several challenges navigating and communicating with their superiors and colleagues. Mobile applications for people with Autism Spectrum Disorder (ASD apps for short) have been increasingly being adapted to help autistic people manage their conditions and daily activities. User feedback analysis is an effective method that can be used to improve ASD apps' services. In this article, we investigate the usage of ASD apps to improve the quality of life for autistic students/employees based on user feedback analysis. For this purpose, we analyze user reviews suggested on highly ranked ASD apps for college students, and workers. A total of 97,051 reviews have been collected from 13 ASD apps available on Google Play and Apple App stores. The collected reviews have been classified into negative, positive, and neutral opinions. This analysis has been performed using machine learning and deep learning models. The best performances were provided by combining RNN and LSTM models with an accuracy of 96.58% and an AUC of 99.41%. Finally, we provide some recommendations to improve ASD apps to assist developers in upgrading the main services provided by their apps.

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

Heating, ventilation, and air-conditioning (HVAC) systems are among the most energy-intensive components in commercial buildings. Accurate forecasting of HVAC energy consumption is essential for implementing energy-efficient control strategies. This study provides a detailed comparative analysis of classical machine learning (ML) and deep learning (DL) models for forecasting HVAC energy consumption using both predicted and actual indoor temperature data. Leveraging an open-source, high-resolution dataset from the Oak Ridge National Laboratory's FRP-2 multizone building, we implement a two-stage framework. The first stage involves temperature prediction using relative humidity and airflow data, while the second stage forecasts HVAC energy consumption using either predicted or actual temperature inputs. We evaluate Linear Regression, Random Forest, Support Vector Machine, GRU, and LSTM models. The results reveal that while models with actual temperature inputs yield superior accuracy (R² up to 0.884), models using predicted temperatures still achieve competitive performance. Our findings suggest that ML and DL models, particularly LSTM, offer promising capabilities for real-time energy forecasting in smart building environments.

Code completion has become an essential component of integrated development environments. Contemporary code completion methods rely on the abstract syntax tree (AST) to generate syntactically correct code. However, they cannot fully capture the sequential and repetitive patterns of writing code and the structural information of the AST. To alleviate these problems, we propose a new code completion approach named CCAG, which models the flattened sequence of a partial AST as an AST graph. CCAG uses our proposed AST Graph Attention Block to capture different dependencies in the AST graph for representation learning in code completion. The sub-tasks of code completion are optimized via multi-task learning in CCAG, and the task balance is automatically achieved using uncertainty without the need to tune task weights. The experimental results show that CCAG has superior performance than state-of-the-art approaches and it is able to provide intelligent code completion.

A hybrid deep learning framework for urban air quality forecasting

Prediction of sea surface temperature is important for the study of marine ecosystems in the oceanic area. The sea surface temperature is a major parameter for analysing extreme atmospheric events. Sea surface temperature determines how heat from the sun is redistributed across the world’s oceans and will directly affect large- and small-scale weather and climate patterns. Comparison studies of two different learning (shallow and deep) models are employed for the forecasting of sea surface temperature. In most cases, the deep learning model also manages to overcome the limitations of the prior shallow learning models depending on the complexity of the problem, which helps to impede efficient training and discrete representations of multi-dimensional training data. The deep learning-based LSTM model is considered for the quick prediction of sea surface temperature with higher accuracy than the usual shallow learning-based feedforward model. Two different monthly SST time series data are applied for the estimation of sea surface temperature in the eastern Arabian Sea (AS) as well as Bay of Bengal (BOB) whose grid points are (70°E, 15°N) and (90°E, 15°N) respectively. LSTM and feedforward models are trained with 80% data and tested with different hidden units and epoch values to acquire a minimum error. For the 20% testing set, AS time-series data using the feedforward model gave more error. Performances of the prediction models are assessed by using root mean square error (RMSE). The results suggest that the temporal LSTM model outperforms the feedforward model specifically on sea surface temperature time series forecasting.KeywordsSea surface temperature (SST)Deep learningShallow learningArabian SeaBay of Bengal

Sign Language Recognition (SLR) systems have gained significant popularity in recent years. Despite the existence of various Deep Learning (DL) models to classify sign languages, the deployment of these models on resource-constrained devices remains a challenge. Majority of the research on SLR focuses on popular sign languages, such as American Sign Language (ASL), German Sign Language (GSL) etc., while Kannada Sign Language (KSL) remains significantly underexplored. This study focuses on creating a word-level custom dataset of 33 classes consisting of 2319 videos and training three DL models, namely, LSTM, BiLSTM, and Encoder-only Transformer for dynamic KSL recognition. Trained models were then optimized with quantization techniques and converted to .tflite format, for efficient deployment on resource-constrained devices like smartphones. Dynamic Post Training Quantization (PTQ) model, for the BiLSTM model achieved the highest accuracy of 95.71%, followed by the LSTM model with 94.7%, and the Transformer-based architecture achieved 94.19%. Transformer model deployed on smartphone achieved the smallest inference time of 16.2 ms with a model size of 1097.77 KB, followed by LSTM recording 19.6 ms as inference time with a model size of 1254.49 KB and BiLSTM recording the highest inference time of 27.8 ms with a model size of 3862.01 KB.

Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion

Automated classification of coronary atherosclerotic plaque in optical frequency domain imaging based on deep learning

In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of ≤2.16 m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as 1.55 m and 1.97 m with 83.33% and 81.05% of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability.

PurposeTo conduct a head-to-head comparison between deep learning (DL) and radiomics models across institutions for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) and to investigate the model robustness and generalizability through rigorous internal and external validation.MethodsThis retrospective study included 2304 preoperative images of 576 HCC lesions from two centers, with MVI status determined by postoperative histopathology. We developed DL and radiomics models for predicting the presence of MVI using B-mode ultrasound, contrast-enhanced ultrasound (CEUS) at the arterial, portal, and delayed phases, and a combined modality (B + CEUS). For radiomics, we constructed models with enlarged vs. original regions of interest (ROIs). A cross-validation approach was performed by training models on one center’s dataset and validating the other, and vice versa. This allowed assessment of the validity of different ultrasound modalities and the cross-center robustness of the models. The optimal model combined with alpha-fetoprotein (AFP) was also validated. The head-to-head comparison was based on the area under the receiver operating characteristic curve (AUC).ResultsThirteen DL models and 25 radiomics models using different ultrasound modalities were constructed and compared. B + CEUS was the optimal modality for both DL and radiomics models. The DL model achieved AUCs of 0.802–0.818 internally and 0.667–0.688 externally across the two centers, whereas radiomics achieved AUCs of 0.749–0.869 internally and 0.646–0.697 externally. The radiomics models showed overall improvement with enlarged ROIs (P < 0.05 for both CEUS and B + CEUS modalities). The DL models showed good cross-institutional robustness (P > 0.05 for all modalities, 1.6–2.1% differences in AUC for the optimal modality), whereas the radiomics models had relatively limited robustness across the two centers (12% drop-off in AUC for the optimal modality). Adding AFP improved the DL models (P < 0.05 externally) and well maintained the robustness, but did not benefit the radiomics model (P > 0.05).ConclusionCross-institutional validation indicated that DL demonstrated better robustness than radiomics for preoperative MVI prediction in patients with HCC, representing a promising solution to non-standardized ultrasound examination procedures.