Dependent Data Research Articles

Diagnosis of atrial fibrillation based on AI-detected anomalies of ECG segments

Early detection of atrial fibrillation (AF) is crucial for its effective management and prevention. Various methods for detecting AF using deep learning (DL) based on supervised learning with a large labeled dataset have a remarkable performance. However, supervised learning has several problems, as it is time-consuming for labeling and has a data dependency problem. Moreover, most of the DL methods do not provide any clinical evidence to physicians regarding the analysis of electrocardiography (ECG) for classification or detection of AF. To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG. Two independent datasets, PTB-XL and China, were used in three experiments. We used a long short-term memory (LSTM)-based autoencoder to train the segments of the normal ECG. Based on the threshold of anomaly scores using mean squared error (MSE), it distinguished between normal and AF segments. In Experiment A, the best score was that of PreQ, which detected AF with an AUROC score of 0.96. In Experiment B and C for cross validation of each dataset, the best scores were also of PreQ, with AUROC scores of 0.9 and 0.95, respectively. To verify the significance of the anomaly score in distinguishing between AF and normal segments, we utilized an XG-Boosted model after generating anomaly scores in the three segments. The XG-Boosted model achieved an AUROC score of 0.98 and an F1 score of 0.94. AF detection using DL has been controversial among many physicians. However, our study differentiates itself from previous studies in that we can demonstrate evidence that distinguishes AF from normal segments based on the anomaly score.

Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network

AbstractWith the diversification of users’ energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper proposes a multi‐energy load forecasting method based on bidirectional long short‐term memory (BiLSTM) and parallel feature extraction networks. Firstly, residual network and convolutional block attention module were used to extract the spatial coupling features of multi‐energy load data. Secondly, BiLSTM is used to capture the temporal features and long‐term dependencies in the load data, and the spatial coupling features are fused to obtain non‐linear prediction results. Finally, the non‐linear prediction results and the linear prediction results obtained by using multi‐energy linear regression were linearly superimposed to obtain the final prediction results. In this paper, IES load data of Tempe Campus of Arizona State University was used to verify and compared with several existing methods, and the results showed that Weighted Mean Absolute Percentage Error decreased by more than 20%.

A generalizable and robust deep learning method for atrial fibrillation detection from long-term electrocardiogram

The reliable detection of atrial fibrillation (AF) is important for diagnosing the disease, tracking its progression, and developing individualized care strategies. However, models based on limited data are prone to data dependency due to differences in data feature distribution, which generally degrades their performance on unseen external datasets. In this work, we propose a multi-input fusion AF detection network (MIF-AFNet), which cascades residual convolutional neural networks and bidirectional long short-term memory networks to capture the deep features of electrocardiogram (ECG) and RR intervals (RRIs), respectively. Additionally, the ECG signals use a data augmentation method to alleviate the morphological imbalance. MIF-AFNet learns a robust feature representation for accurate AF detection by fusing the available information from RRIs and ECG. The proposed method was developed and evaluated using 5 long-term ECG datasets (CPSC2021, AFDB, LTAF, MITDB, and NSRDB) from PhysioNet. The subject-wise five-fold cross-validation was performed on CPSC2021, and the proposed method achieved an AF detection accuracy of 98.63%. The generalization performance is further evaluated on four external independent datasets (AFDB, LTAF, MITDB, and NSRDB), achieving accuracies of 98.63%, 97.04%, 98.07%, and 100%, respectively. The results show that the proposed method can accurately detect AF from long-term ECG recordings. In addition, the low complexity of the model makes it less demanding on computing resources. Therefore, it has the potential to improve the automatic diagnosis and management of AF in wearable device-based long-term home monitoring.

DSPM: Dual sequence prediction model for efficient energy management in micro-grid

Power generation and consumption predictions are fundamental for smart grid operations, addressing challenges posed by renewable energy variability and irregular consumer demand. This study introduces the Dual Sequence Predictive Model (DSPM) based on Spatiotemporal CNN (STCNN) architecture, offering a holistic solution for forecasting Electricity Generation (EG) and Electricity Consumption (EC) collectively. Leveraging STCNN, the DSPM efficiently extracts spatial and temporal information, improving prediction accuracy and processing speed. A 1D spatial attention module is added to capture crucial spatial dependencies in historical data. Incorporating shared historical weather information streamlines learning process and reduces model complexity. Extensive benchmark evaluations demonstrate the DSPM superior performance, achieving the lowest error rates compared to baseline models. The DSPM also employs the Kullback–Leibler Divergence (KLD) algorithm for power generation and consumption matching, ensuring efficient power distribution within smart and microgrids. Furthermore, the DSPM is evaluated alongside Single Sequence Prediction (SSP) models, providing a comprehensive analysis of its capabilities and comparisons with state-of-the-art models. The SSP model achieved an average RMSE reduction of 17.3% for solar EG data and 15.86% for IHEPC residential EC data, while DSPM reduced RMSE by 7.57% over PowerGrid dataset compared to baseline models.

Feature-enhanced fusion of U-NET-based improved brain tumor images segmentation

The field of medical image segmentation, particularly in the context of brain tumor delineation, plays an instrumental role in aiding healthcare professionals with diagnosis and accurate lesion quantification. Recently, Convolutional Neural Networks (CNNs) have demonstrated substantial efficacy in a range of computer vision tasks. However, a notable limitation of CNNs lies in their inadequate capability to encapsulate global and distal semantic information effectively. In contrast, the advent of Transformers, which has established their prowess in natural language processing and computer vision, offers a promising alternative. This is primarily attributed to their self-attention mechanisms that facilitate comprehensive modeling of global information. This research delineates an innovative methodology to augment brain tumor segmentation by synergizing UNET architecture with Transformer technology (denoted as UT), and integrating advanced feature enhancement (FE) techniques, specifically Modified Histogram Equalization (MHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Modified Bi-histogram Equalization Based on Optimization (MBOBHE). This integration fosters the development of highly efficient image segmentation algorithms, namely FE1-UT, FE2-UT, and FE3-UT. The methodology is predicated on three pivotal components. Initially, the study underscores the criticality of feature enhancement in the image preprocessing phase. Herein, techniques such as MHE, CLAHE, and MBOBHE are employed to substantially ameliorate the visibility of salient details within the medical images. Subsequently, the UT model is meticulously engineered to refine segmentation outcomes through a customized configuration within the UNET framework. The integration of Transformers within this model is instrumental in imparting contextual comprehension and capturing long-range data dependencies, culminating in more precise and context-sensitive segmentation. Empirical evaluation of the model on two extensively acknowledged public datasets yielded accuracy rates exceeding 99%.

A generic fundus image enhancement network boosted by frequency self-supervised representation learning.

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement.

Machine Learning Algorithm for Stock Market Prediction – A Comparison

The prediction about the stock market serves as an effort to forecast the value of the market, an individual stock, or a particular industrial sector. The prediction or forecast is usually done by using several approaches and analyzing the fundamental or technical details of an industry, an economy, or both. Predicting stock markets is very essential, as successful prediction can help in proper decision-making as well as in increasing the profit of the business. As prediction of the stock market is a bit complicated and challenging, conventional methods do not consistently forecast the changes with absolute certainty. For this reason, the proposed study has come up with a comparison of the machine learning models for forecasting the market changes. The aim of the study is to compare two machine learning models: the decision tree (DT) algorithm, which excels at handling nonlinear relationships and feature interaction, and the long short-term memory (LSTM) algorithm, which could efficiently capture long-range dependencies in sequential data. The Yahoo Finance dataset was used for performing the comparison. The results observed will be utilized to analyze the stock expenses and their predictions in the future.

Traffic Flow Forecast using Time Series Analysis based on Machine Learning Algorithm

Time series forecasting plays a critical role in predicting future trends and making informed decisions across various domains. In this research paper, we present a multi-model approach to improve the accuracy and robustness of time series forecasting. Our methodology involves integrating two powerful models, Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA), to capture complex temporal patterns and seasonality in the data. We leverage real-world traffic data from different junctions and employ a comprehensive pipeline for data preprocessing, including data selection, resampling, and sequence generation. Our study focuses on four junctions, and for each junction, we individually train LSTM models, followed by SARIMA models for comparison. The LSTM models are designed to capture long-term dependencies in the time series data, while the SARIMA models are tailored to handle seasonality and autocorrelation. We implement a custom sequence generation process and split the dataset into training and testing sets for model evaluation. The LSTM models are trained using Pytorch, optimizing them for accurate short-term predictions. Our results show that the combination of LSTM and SARIMA models yields superior forecasting performance compared to using each model individually. We present a detailed analysis of the forecasted results, including Root Mean Square Error (RMSE) calculations and visualizations to demonstrate the effectiveness of our multi-model approach. This research contributes to the field of time series forecasting by showcasing the benefits of combining deep learning and classical statistical methods. The proposed approach provides a flexible and robust framework applicable to various time series prediction tasks, offering improved accuracy and reliability in forecasting future trends.

Differentially private trajectory event streams publishing under data dependence constraints

Differential Privacy (DP), as a de facto privacy-preserving paradigm, can be widely applied in numerous event streams publishing schemes to protect private events (i.e., trajectory points of users). However, most existing schemes assume these events are independent, which is a vulnerable assumption that can lead to unforeseeable privacy degradation. The privacy-preserving for event streams publishing under data dependence is still challenging because existing dependence quantify models cannot dynamically measure the degree of dependent relationships between events. In this paper, we investigate the privacy degradation issue of trajectory event streams publishing and propose (Θ,ϵ)-dependent privacy mechanism to mitigate this issue. Specifically, we introduce spatial dependence to model the dependent relationship between events in trajectory data and extend it to quantify the influence of multiple dependent events on the target event. We define the notion of max dissimilarity to formalize the privacy level of DP mechanisms in trajectory event streams publishing. The proposed notion of global dependent coefficient helps the private mechanism to provide the expected privacy level by calibrating the added noise. We further achieve ω-event privacy protection over trajectory event streams under data dependence constraints with (Θ,ϵ)-dependent privacy mechanism. Theoretical analysis proves our scheme provides the expected privacy guarantee under data dependence constraints. Extensive experiments validate our scheme is efficient and effective.

Solubility of mesalazine in pseudo-binary mixtures of choline chloride/ethylene glycol deep eutectic solvent and water at 293.15 K to 313.15 K

Mesalazine (5-ASA) is a medication utilized to treat inflammatory bowel diseases involving ulcerative colitis and Crohn’s disease. Mesalazine has fewer side effects but the low solubility and bioavailability of it is responsible for its delayed onset of action. Hence, the goal of this study is to determine the molar solubility of 5-ASA in aqueous pseudo-binary mixtures containing low toxic biocompatible choline chloride/ethylene glycol deep eutectic solvent (ChCl/EG DES) with DES mass fraction of 0.0–1.0 using a shake-flask technique at 293.2–313.2 K and approximately 85 kPa. The experimental results indicated that the solubility of 5-ASA enhanced by addition of DES mass fraction and also increasing temperature. The molarity values of 5-ASA were then modelled by some traditional cosolvency models, and regressed each model parameters. The back-computed molarity of 5-ASA using the selected cosolvency models presented a good consistency with the experimental data (lower mean percentage deviation than 5.14%). Moreover, the Gibbs and van’t Hoff equations were employed to compute the thermodynamic functions of 5-ASA dissolution process in ChCl/EG DES + water from the temperature dependency of solubility data. This analysis presented an endothermic and entropy-driven process of 5-ASA dissolution in ChCl/EG DES + water. Furthermore, enthalpy-entropy compensation analysis represented non-linear enthalpy dissolution vs. Gibbs free energy compensation plots with positive and negative slopes for 5-ASA whereas the positive and negative slopes were probably due to the enhance in solvation of 5-ASA by ChCl/EG DES molecules and the solvent-structure loosing, respectively.

RNN-BIRNN-LSTM based spectrum sensing for proficient data transmission in cognitive radio

With the advancements that are taking place in the wireless communications field, the number of users who are utilizing resources is also increasing; as a result, the wireless spectrum is scarce. In this article, RNN-BIRNN-LSTM with Gaussian noise (RBRLG)-based spectrum sensing (SS) for QAM16, CPFSK, QPSK, and BPSK modulation schemes has been proposed. Recurrent Neural Networks for sequential data use recurrent connections to capture temporal dependencies; BIRNN extends RNN by processing input in both forward and backward directions, capturing past and future context; and finally, LSTM, using specialized memory cells, efficiently manages long-term dependencies in sequential data. In order to create a spectrum sensing model, RNN units, BIRNN units, and LSTM units were cascaded in this paper. Open-source dataset RadioML2016.10B has been used for the investigation. The experimental results show that the proposed RBRLG-based SS has higher accuracy on the dataset especially at -20 dB, a lower probability of miss detection percentage of 7.19 %, and a lower sensing error (SE) percentage of 10.80 % for QAM16. The evaluation of performance indicators for our suggested model, such as the F1 Score, Jaccard Index, and Matthew's correlation coefficient, demonstrates that the proposed model provides improved SS performance.

On Data Dependency and Solutions of Nonlinear Fredholm Integral Equations with the Three-Step Iteration Method

In this study, the solution of the second type of homogeneous nonlinear Fredholm integral equations is investigated using a three-step iteration algorithm. In other words, it has been shown that the sequences obtained from this algorithm converge to the solution of the mentioned equations. Also, data dependency is obtained for the second type of homogeneous nonlinear Fredholm integral equations and this result is supported by an example.

A health status estimation method based on interpretable neural network observer for HVs

Estimating the health status is a crucial step in learning about the health of hypersonic vehicles beforehand. The estimation results can be used to detect abnormal states and provide data reference for fault diagnosis. However, certain conventional neural network-based estimate techniques rely heavily on data and have limited model interpretability, which challenges the accuracy of the estimation results. This research aims to address the problems of data dependency and model interpretability in estimation models. In this study, a block interpretable neural network model with constraints on the trajectory and attitude equations is established. On the basis of the interpretable neural network model, two health status estimation methods are proposed: one that is unsupervised and the other that is supervised. Additionally, in the supervised health status estimate approach, an FC-LN-Mish structure is created to fit the relationship between the fault residual and the fault state parameters. The results indicate that the proposed estimation methods can fit the system mechanism relationship more accurately, improve the model interpretability, reduce data dependency, and ensure high estimation efficiency and precision. The FC-LN-Mish structure can reduce the missed detection rate and false detection rate to some extent, and perform better than other models under the low fault deviation degree. In conclusion, the interpretable neural network model-based observers accurately observe the health status parameters of rudders and RCS, reduce data dependence and data processing costs, and have better performance under high uncertainty interference. It provides effective method for online health estimation.

Parkinson's disease classification with CWNN: Using wavelet transformations and IMU data fusion for improved accuracy.

Parkinson's disease (PD) is a chronic neurodegenerative disorder characterized by motor impairments and various other symptoms. Early and accurate classification of PD patients is crucial for timely intervention and personalized treatment. Inertial measurement units (IMUs) have emerged as a promising tool for gathering movement data and aiding in PD classification. This paper proposes a Convolutional Wavelet Neural Network (CWNN) approach for PD classification using IMU data. CWNNs have emerged as effective models for sensor data classification. The objective is to determine the optimal combination of wavelet transform and IMU data type that yields the highest classification accuracy for PD. The proposed CWNN architecture integrates convolutional neural networks and wavelet neural networks to capture spatial and temporal dependencies in IMU data. Different wavelet functions, such as Morlet, Mexican Hat, and Gaussian, are employed in the continuous wavelet transform (CWT) step. The CWNN is trained and evaluated using various combinations of accelerometer data, gyroscope data, and fusion data. Extensive experiments are conducted using a comprehensive dataset of IMU data collected from individuals with and without PD. The performance of the proposed CWNN is evaluated in terms of classification accuracy, precision, recall, and F1-score. The results demonstrate the impact of different wavelet functions and IMU data types on PD classification performance, revealing that the combination of Morlet wavelet function and IMU data fusion achieves the highest accuracy. The findings highlight the significance of combining CWT with IMU data fusion for PD classification using CWNNs. The integration of CWT-based feature extraction and the fusion of IMU data from multiple sensors enhance the representation of PD-related patterns, leading to improved classification accuracy. This research provides valuable insights into the potential of CWT and IMU data fusion for advancing PD classification models, enabling more accurate and reliable diagnosis.

Enhancing Electrical Load Prediction Using a Bidirectional LSTM Neural Network

Precise anticipation of electrical demand holds crucial importance for the optimal operation of power systems and the effective management of energy markets within the domain of energy planning. This study builds on previous research focused on the application of artificial neural networks to achieve accurate electrical load forecasting. In this paper, an improved methodology is introduced, centering around bidirectional Long Short-Term Memory (LSTM) neural networks (NN). The primary aim of the proposed bidirectional LSTM network is to enhance predictive performance by capturing intricate temporal patterns and interdependencies within time series data. While conventional feed-forward neural networks are suitable for standalone data points, energy consumption data are characterized by sequential dependencies, necessitating the incorporation of memory-based concepts. The bidirectional LSTM model is designed to furnish the prediction framework with the capacity to assimilate and leverage information from both preceding and forthcoming time steps. This augmentation significantly bolsters predictive capabilities by encapsulating the contextual understanding of the data. Extensive testing of the bidirectional LSTM network is performed using multiple datasets, and the results demonstrate significant improvements in accuracy and predictive capabilities compared to the previous simpleRNN-based framework. The bidirectional LSTM successfully captures underlying patterns and dependencies in electrical load data, achieving superior performance as gauged by metrics such as root mean square error (RMSE) and mean absolute error (MAE). The proposed framework outperforms previous models, achieving a remarkable RMSE, attesting to its remarkable capacity to forecast impending load with precision. This extended study contributes to the field of electrical load prediction by leveraging bidirectional LSTM neural networks to enhance forecasting accuracy. Specifically, the BiLSTM’s MAE of 0.122 demonstrates remarkable accuracy, outperforming the RNN (0.163), LSTM (0.228), and GRU (0.165) by approximately 25%, 46%, and 26%, in the best variation of all networks, at the 24-h time step, while the BiLSTM’s RMSE of 0.022 is notably lower than that of the RNN (0.033), LSTM (0.055), and GRU (0.033), respectively. The findings highlight the significance of incorporating bidirectional memory and advanced neural network architectures for precise energy consumption prediction. The proposed bidirectional LSTM framework has the potential to facilitate more efficient energy planning and market management, supporting decision-making processes in power systems.

Intelligent Diagnostic System Development based on Artificial Intelligence Technology

Intelligent diagnosis is an important scenario in smart healthcare, with conversational diagnostic scenarios being the most common. The process of collecting symptom information through conversations with users and inferring diseases based on symptoms. Through a dialogue based diagnostic system, it can meet some of the medical consultation needs of residents, thereby freeing doctors from some basic consultations and greatly alleviating the shortage of medical resources. In the actual diagnosis process, the symptoms reported by patients are often insufficient to support accurate diagnosis. It is necessary to ask the user if they have any other symptoms through dialogue to form a diagnostic conclusion. Existing research mainly adopts reinforcement learning methods, which gradually learn the dialogue process between traditional Chinese medicine students and patients in real medical scenarios, and obtain strategies for symptom inquiry and disease diagnosis. Despite the advantages of reinforcement learning in dealing with temporal decision problems, the diagnostic accuracy is still low and data dependency is strong. In this article, a medical dialogue robot architecture based on medical dialogue diagnosis technology, medical knowledge graph technology, and "inference machine" technology is proposed to build an intelligent diagnosis architecture. Secondly, in terms of algorithm, this article proposes a disease diagnosis algorithm based on Naive Bayes Classification and a symptom screening algorithm based on symptom set differences for symptom query process, This algorithm increases the interpretability of diagnostic results by simulating the questioning and diagnostic process of doctors, and combines it with the medical dialogue robot architecture to achieve intelligent diagnosis throughout the entire process.

Time-aware personalized graph convolutional network for multivariate time series forecasting

The use of graph structures to model variable dependencies in multivariate time series data holds promise. Probabilistic graph models, sampling discrete graphs from neural network-parameterized distributions, have shown efficacy. However, the current approaches ignore that dependencies are dynamic and constrained by heterogeneous information. For instance, interactions among traffic data’s roads are constrained by traffic volume and network topology. Furthermore, the existing spatio-temporal graph propagation mechanism has failed to account for the impact of the evolutionary patterns of the nodes themselves on future outcomes. To address these limitations, this research introduces a novel approach: a time-aware personalized graph convolutional network (TPGCN) consisting of time-aware discrete graph structure estimation (TADG) and dynamic personalized graph convolutional (DPGC) components. The TADG module confronts the challenge of graph learning by framing it as an inference issue within a heterogeneous information landscape. Through dynamic inputs, it deduces graph structures that are influenced by the varying nature of interactions. DPGC, drawing inspiration from personalized PageRank, models variable effects while considering evolutionary patterns and external factors. By dynamically fusing these two types of information at every information aggregation, our approach outperforms existing state-of-the-art methods, as demonstrated on eight benchmark datasets.

Advancing Financial Forecasts: A Deep Dive into Memory Attention and Long-Distance Loss in Stock Price Predictions

In the context of the rapid evolution of financial markets, the precise prediction of stock prices has become increasingly complex and challenging, influenced by a myriad of factors including macroeconomic indicators, company financial conditions, and market sentiment. A model integrating modern machine learning techniques has been introduced in this study, aimed at enhancing the accuracy of stock price prediction. To more effectively capture long-term dependencies in time series data, a novel memory attention module has been innovatively integrated and a unique long-distance loss function has been designed. Through a series of experimental validations, the effectiveness and superiority of this model in the realm of stock price prediction have been demonstrated, especially evident in the R2 evaluation metric, where an impressive score of 0.97 has been achieved. Furthermore, the purpose, methodology, data sources, and key results of this research have been elaborately detailed, aiming to provide fresh perspectives and tools for the field of stock price prediction and lay a solid foundation for future related studies. Overall, this research has not only enhanced the accuracy of stock price prediction but also made innovative contributions in terms of methodology and practical applications, bringing new thoughts and possibilities to the domain of financial analysis and prediction.

An Intermediate-Centric Dataflow for Transposed Convolution Acceleration on FPGA

Transposed convolution has been prevailing in convolutional neural networks (CNNs), playing an important role in multiple scenarios such as image segmentation and back-propagation process of training CNNs. This mainly benefits from the ability to up-sample the input feature maps by interpolating new information from the input feature pixels. However, the backward-stencil computation constrains its performance and hindered its wide application in diverse platforms. Moreover, in contrast to the efforts on accelerating the convolution, there is a rare investigation on the acceleration of transposed convolution that is identically compute-intensive as the former. For acceleration of transposed convolution, we propose an intermediate-centric dataflow scheme, in which we decouple the generation of the intermediate patch from its further process, aim at efficiently performing the backward-stencil computation . The intermediate-centric dataflow breaks the transposed convolution into several phases/stages, achieving feeding the input feature maps and performing the backward-stencil computation in a pipelining manner. It also provides four-degree computation parallelism and efficient data reuse of input feature maps/weights. Furthermore, we also theoretically analyze the irregular data dependence leveraging the polyhedral model, which constrains the parallel computing of transposed convolution. Additionally, we devise an optimization problem to explore the design space and automatically generate the optimal design configurations for different transposed convolutional layers and hardware platforms. By selecting the representative transposed convolutional layers from DCGAN, FSRCNN, and FCN, we generate the corresponding accelerator arrays of intermediate-centric dataflow on the Xilinx Alveo U200 platform and reach the performance of 3.92 TOPS, 2.72 TOPS, and 4.76 TOPS, respectively.

Detecting security vulnerabilities with vulnerability nets

Detecting security vulnerabilities is a crucial part in secure software development. Many static analysis tools have proved to be effective in finding vulnerabilities, but generally there are some complex and subtle vulnerabilities that can escape from detection. Manual audits are a complementary approach to using tools. Unfortunately, most manual analyses are tedious and error prone. To benefit from both the tools and manual audits, some approaches incorporate the auditor's expertise into a static analysis tool during vulnerability discovery. Following this strategy, this paper presents a representation of source code called a vulnerability net, which is a special Petri net that integrates with data dependence graphs and control flow graphs. The combined representation can facilitate the detection of taint-style vulnerabilities such as buffer overflows and injection vulnerabilities. We test the proposed approach on Securibench Micro and demonstrate that it has the capability to identify a variety of vulnerabilities while keeping the rates of false negatives and positives low.