DNA-DISK: Automated end-to-end data storage via enzymatic single-nucleotide DNA synthesis and sequencing on digital microfluidics.

In the age of information explosion, the exponential growth of digital data far exceeds the capacity of current mainstream storage media. DNA is emerging as a promising alternative due to its higher storage density, longer retention time, and lower power consumption. To date, commercially mature DNA synthesis and sequencing technologies allow for writing and reading of information on DNA with customization and convenience at the research level. However, under the disconnected and nonspecialized mode, DNA data storage encounters practical challenges, including susceptibility to errors, long storage latency, resource-intensive requirements, and elevated information security risks. Herein, we introduce a platform named DNA-DISK that seamlessly streamlined DNA synthesis, storage, and sequencing on digital microfluidics coupled with a tabletop device for automated end-to-end information storage. The single-nucleotide enzymatic DNA synthesis with biocapping strategy is utilized, offering an ecofriendly and cost-effective approach for data writing. A DNA encapsulation using thermo-responsive agarose is developed for on-chip solidification, not only eliminating data clutter but also preventing DNA degradation. Pyrosequencing is employed for in situ and accurate data reading. As a proof of concept, DNA-DISK successfully stored and retrieved a musical sheet file (228 bits) with lower write-to-read latency (4.4 min of latency per bit) as well as superior automation compared to other platforms, demonstrating its potential to evolve into a DNA Hard Disk Drive in the future.

GloEC: a hierarchical-aware global model for predicting enzyme function.

The annotation of enzyme function is a fundamental challenge in industrial biotechnology and pathologies. Numerous computational methods have been proposed to predict enzyme function by annotating enzyme labels with Enzyme Commission number. However, the existing methods face difficulties in modelling the hierarchical structure of enzyme label in a global view. Moreover, they haven't gone entirely to leverage the mutual interactions between different levels of enzyme label. In this paper, we formulate the hierarchy of enzyme label as a directed enzyme graph and propose a hierarchy-GCN (Graph Convolutional Network) encoder to globally model enzyme label dependency on the enzyme graph. Based on the enzyme hierarchy encoder, we develop an end-to-end hierarchical-aware global model named GloEC to predict enzyme function. GloEC learns hierarchical-aware enzyme label embeddings via the hierarchy-GCN encoder and conducts deductive fusion of label-aware enzyme features to predict enzyme labels. Meanwhile, our hierarchy-GCN encoder is designed to bidirectionally compute to investigate the enzyme label correlation information in both bottom-up and top-down manners, which has not been explored in enzyme function prediction. Comparative experiments on three benchmark datasets show that GloEC achieves better predictive performance as compared to the existing methods. The case studies also demonstrate that GloEC is capable of effectively predicting the function of isoenzyme. GloEC is available at: https://github.com/hyr0771/GloEC.

sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure.

MOTIVATION: Coding and noncoding RNA molecules participate in many important biological processes. Noncoding RNAs fold into well-defined secondary structures to exert their functions. However, the computational prediction of the secondary structure from a raw RNA sequence is a long-standing unsolved problem, which after decades of almost unchanged performance has now re-emerged due to deep learning. Traditional RNA secondary structure prediction algorithms have been mostly based on thermodynamic models and dynamic programming for free energy minimization. More recently deep learning methods have shown competitive performance compared with the classical ones, but there is still a wide margin for improvement. RESULTS: In this work we present sincFold, an end-to-end deep learning approach, that predicts the nucleotides contact matrix using only the RNA sequence as input. The model is based on 1D and 2D residual neural networks that can learn short- and long-range interaction patterns. We show that structures can be accurately predicted with minimal physical assumptions. Extensive experiments were conducted on several benchmark datasets, considering sequence homology and cross-family validation. sincFold was compared with classical methods and recent deep learning models, showing that it can outperform the state-of-the-art methods.

An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph.

Identifying the potential compound-protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound-protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE.

Discovery of an End-to-End Pattern for Contaminant-Oriented Advanced Oxidation Processes Catalyzed by Biochar with Explainable Machine Learning.

The utilization of biochar-catalyzed peroxymonosulfate in advanced oxidation processes (BC-PMS AOPs) is widely acknowledged as an effective and economical method for mitigating emerging contaminants (ECs). Especially, state-of-the-art machine learning (ML) technology has been employed to accurately predict the reaction rate constants of EC degradation in BC-PMS AOPs, primarily focusing on three aspects: performance prediction, operating condition optimization, and mechanism interpretation. However, its real application in specific degradation optimization targeting different ECs is seldom considered, hindering the realization of contaminant-oriented BC-PMS AOPs. Herein, we propose a hierarchical ML pipeline to achieve an end-to-end (E2E) pattern for addressing this issue. First, the overall XGB model, trained with the comprehensive data set, can perform well in predicting the reaction constants of EC degradation in BC-PMS AOPs, additionally providing the basis for further analysis of various ECs. Then, the submodels trained with different EC clusters can offer specific strategies for the selection of the optimum option for BC-PMS AOPs of specific ECs with different HOMO-LUMO gaps, thus forming an E2E operating pattern for BC-PMS AOPs. This study not only increases our understanding of contaminant-oriented optimization of AOPs but also successfully bridges the gap between ML model development and its environmental application.

Computational frameworks integrating deep learning and statistical models in mining multimodal omics data.

BACKGROUND: In health research, multimodal omics data analysis is widely used to address important clinical and biological questions. Traditional statistical methods rely on the strong assumptions of distribution. Statistical methods such as testing and differential expression are commonly used in omics analysis. Deep learning, on the other hand, is an advanced computer science technique that is powerful in mining high-dimensional omics data for prediction tasks. Recently, integrative frameworks or methods have been developed for omics studies that combine statistical models and deep learning algorithms. METHODS AND RESULTS: The aim of these integrative frameworks is to combine the strengths of both statistical methods and deep learning algorithms to improve prediction accuracy while also providing interpretability and explainability. This review report discusses the current state-of-the-art integrative frameworks, their limitations, and potential future directions in survival and time-to-event longitudinal analysis, dimension reduction and clustering, regression and classification, feature selection, and causal and transfer learning.

Assessing the influence of parameters on tissue welding in small bowel end-to-end anastomosis in vitro and in vivo.

BACKGROUND: The use of high-frequency electric welding technology for intestinal end-to-end anastomosis holds significant promise. Past studies have focused on in vitro, and the safety and efficacy of this technology is uncertain, severely limiting the clinical application of this technology. This study investigates the impact of compression pressure, energy dosage, and duration on anastomotic quality using a homemade anastomosis device in both in vitro and in vivo settings. METHODS: Two hundred eighty intestines and 5 experimental pigs were used for in vitro and in vivo experiments, respectively. The in vitro experiments were conducted to study the effects of initial pressure (50-400 kpa), voltage (40-60 V), and time (10-20 s) on burst pressure, breaking strength, thermal damage, and histopathological microstructure of the anastomosis. Optimal parameters were then inlaid into a homemade anastomosis and used for in vivo experiments to study the postoperative porcine survival rate and the pathological structure of the tissues at the anastomosis and the characteristics of the collagen fibers. RESULTS: The anastomotic strength was highest when the compression pressure was 250 kPa, the voltage was 60 V, and the time was 15 s. The degree of thermal damage to the surrounding tissues was the lowest. The experimental pigs had no adverse reactions after the operation, and the survival rate was 100%. 30 days after the operation, the surgical site healed well, and the tissues at the anastomosis changed from immediate adhesions to permanent connections. CONCLUSION: High-frequency electric welding technology has a certain degree of safety and effectiveness. It has the potential to replace the stapler anastomosis in future and become the next generation of new anastomosis device.

Safety and effectivity of Kono-S anastomosis in Crohn's patients: a systematic review and Meta-analysis.

PURPOSE: Kono-S anastomosis, an antimesenteric, functional, end-to-end handsewn anastomosis, was introduced in 2011. The aim of this meta-analysis is to evaluate the safety and effectivity of the Kono-S technique. METHODS: A comprehensive search of MEDLINE (PubMed), Embase (Elsevier), Scopus (Elsevier), and Cochrane Central (Ovid) from inception to August 24th, 2023, was conducted. Studies reporting outcomes of adults with Crohn's disease undergoing ileocolic resection with subsequent Kono-S anastomosis were included. PRISMA and Cochrane guidelines were used to screen, extract and synthesize data. Primary outcomes assessed were endoscopic, surgical and clinical recurrence rates, as well as complication rates. Data were pooled using random-effects models, and heterogeneity was assessed with I² statistics. ROBINS-I and ROB2 tools were used for quality assessment. RESULTS: 12 studies involving 820 patients met the eligibility criteria. A pooled mean follow-up time of 22.8 months (95% CI: 15.8, 29.9; I2 = 99.8%) was completed in 98.3% of patients. Pooled endoscopic recurrence was reported in 24.1% of patients (95% CI: 9.4, 49.3; I2 = 93.43%), pooled surgical recurrence in 3.9% of patients (95% CI: 2.2, 6.9; I2 = 25.97%), and pooled clinical recurrence in 26.8% of patients (95% CI: 14, 45.1; I2 = 84.87%). The pooled complication rate was 33.7%. The most common complications were infection (11.5%) and ileus (10.9%). Pooled anastomosis leakage rate was 2.9%. CONCLUSIONS: Despite limited and heterogenous data, patients undergoing Kono-S anastomosis had low rates of surgical recurrence and anastomotic leakage with moderate rates of endoscopic recurrence, clinical recurrence and complications rate.

Analysis of postdisaster economy using high-resolution disaster and economy simulations.

We present an integrated framework that utilizes high-resolution seamless simulations of disasters and national economies for estimating the economic impacts of disasters. The framework consists of three components: a physics-based simulator to simulate the disaster and estimate the response of the infrastructure; a tool that estimates the losses suffered by the infrastructure based on its response; and an agent-based economic model (ABEM) that simulates the national economy considering the infrastructure damage and postdisaster decisions of the economic entities. The ABEM used in the framework has been implemented in a high-performance computing environment to simulate large economies at 1:1 scale. Furthermore, it has been calibrated to the Japanese economy using publicly available macroeconomic data and validated to the Japanese economy under the business-as-usual scenario. We demonstrate the integrated framework by simulating a potential Nankai-trough earthquake disaster and estimating its impacts on the Japanese economy. The seismic response of 1.8 million buildings of the Osaka-bay area has been estimated using a large-scale earthquake disaster simulator and corresponding repair costs are estimated using the Performance Assessment Calculation Tool. As per our estimates, repair costs amount to approximately 15 trillion Yen. Considering the investments made by impacted households and firms toward recovery, the postdisaster economy is simulated using the ABEM for 5 years under two recovery scenarios. Industrial production is expected to recover in three quarters whereas 10-13 quarters will be required to finish all the repair work.

Characteristics of breathing-adapted gating using surface guidance for use in particle therapy: A phantom-based end-to-end test from CT simulation to dose delivery.

To account for intra-fractional tumor motion during dose delivery in radiotherapy, various treatment strategies are clinically implemented such as breathing-adapted gating and irradiating the tumor during specific breathing phases. In this work, we present a comprehensive phantom-based end-to-end test of breathing-adapted gating utilizing surface guidance for use in particle therapy. A commercial dynamic thorax phantom was used to reproduce regular and irregular breathing patterns recorded by the GateRT respiratory monitoring system. The amplitudes and periods of recorded breathing patterns were analysed and compared to planned patterns (ground-truth). In addition, the mean absolute deviations (MAD) and Pearson correlation coefficients (PCC) between the measurements and ground-truth were assessed. Measurements of gated and non-gated irradiations were also analysed with respect to dosimetry and geometry, and compared to treatment planning system (TPS). Further, the latency time of beam on/off was evaluated. Compared to the ground-truth, measurements performed with GateRT showed amplitude differences between 0.03 ± 0.02 mm and 0.26 ± 0.03 mm for regular and irregular breathing patterns, whilst periods of both breathing patterns ranged with a standard deviation between 10 and 190 ms. Furthermore, the GateRT software precisely acquired breathing patterns with a maximum MAD of 0.30 ± 0.23 mm. The PCC constantly ranged between 0.998 and 1.000. Comparisons between TPS and measured dose profiles indicated absolute mean dose deviations within institutional tolerances of ±5%. Geometrical beam characteristics also varied within our institutional tolerances of 1.5 mm. The overall time delays were <60 ms and thus within both recommended tolerances published by ESTRO and AAPM of 200 and 100 ms, respectively. In this study, a non-invasive optical surface-guided workflow including image acquisition, treatment planning, patient positioning and gated irradiation at an ion-beam gantry was investigated, and shown to be clinically viable. Based on phantom measurements, our results show a clinically-appropriate spatial, temporal, and dosimetric accuracy when using surface guidance in the clinical setting, and the results comply with international and institutional guidelines and tolerances.

Short-term outcomes of delta-shaped anastomosis versus functional end-to-end anastomosis using linear staplers for colon cancer.

BACKGROUND: Several methods are used for reconstruction in colon cancer surgery, including hand-sewn or stapled anastomosis. However, few reports have compared short-term outcomes among reconstruction methods. This study compared short-term outcomes between delta-shaped anastomosis (Delta) and functional end-to-end anastomosis (FEEA). METHODS: We retrospectively reviewed 1314 consecutive patients who underwent colorectal surgery with FEEA or Delta reconstruction between January 2016 and December 2023. Patients were divided into two groups according to reconstruction by FEEA (F group; n = 1242) or Delta (D group; n = 72). Propensity score matching was applied to minimize the possibility of selection bias and to balance covariates that could affect postoperative complications. Short-term outcomes were compared between groups. RESULTS: Postoperative complications occurred in 215 patients (17.3%) in F group and 8 patients (11.1%) in D group. Before matching, transverse colon cancer was more frequent (p = 0.002), clinical N-positive status was less frequent (44.1% versus 16.7%, p < 0.001), distant metastasis was less frequent (11.7% versus 1.4%, p = 0.003), and laparoscopic approach was more frequent (87.8% versus 100%, p < 0.001) in D group. After matching, no differences in any clinical factor were evident between groups. Blood loss was significantly lower (28 mL versus 10 mL, p = 0.002) in D group, but operation time and postoperative complication rates were similar between groups. CONCLUSIONS: Delta and FEEA were both considered safe as reconstruction methods. Further studies are needed to clarify appropriate case selection for Delta and FEEA.

Usefulness of the one-step technique in functional end-to-end anastomosis for colonic surgery: results of a prospective multicentre cohort study from the Japanese KYCC group.

BACKGROUND: Although functional end-to-end anastomosis (FEEA) using a stapler in the colorectal field has been recognised worldwide, the technique varies by surgeon, and the safety of anastomosis using different techniques is unknown. METHODS: This multicentre prospective observational cohort study was conducted by the KYCC Study Group in Yokohama, Japan, and included patients who underwent colonic resection at seven centres between April 2020 and March 2022. This study compared the incidence of surgery-related abdominal complications (SAC: anastomotic leakage [AL], anastomotic bleeding, intra-abdominal abscess, enteritis, ileus, surgical site infection, and other abdominal complications) between two different methods of FEEA (one-step [OS] method: simultaneous anastomosis and bowel resection; two-step [TS] method: anastomosis after bowel resection). Complications of Clavien-Dindo classification grade 2 or higher were assessed. RESULTS: Among 293 eligible cases, the OS and TS methods were used in 194 (66.2%) and 99 (33.8%) patients, respectively. The baseline characteristics were similar between the groups. The OS method used fewer staplers (three vs. four staplers, p < 0.00001). There were no significant differences in SAC rate between the OS (19.1%) and the TS (16.2%) groups (p = 0.44). The OS group had four cases (2.1%) of AL (two patients; grade 3, two patients; grade 2) while the TS group had one case (1.0%) of grade 2 AL (p = 0.67). Multivariate logistic regression analysis showed that male sex (odds ratio [OR] 3.95; p < 0.00001), an open surgical approach (OR 2.36; p = 0.03), and longer operative duration (OR,2.79; p = 0.002) were independent predictors of complications, whereas the OS method was not an independent predictor (OR 1.17; p = 0.66). CONCLUSIONS: The OS and the TS technique for stapled colonic anastomosis in a FEEA had a similar postoperative complication rate. TRIAL REGISTRATION NUMBER: UMIN000039902 (registration date 23 March 2020).

Enhanced Safety in Autonomous Driving: Integrating a Latent State Diffusion Model for End-to-End Navigation.

Ensuring safety in autonomous driving is crucial for effective motion planning and navigation. However, most end-to-end planning methodologies lack sufficient safety measures. This study tackles this issue by formulating the control optimization problem in autonomous driving as Constrained Markov Decision Processes (CMDPs). We introduce an innovative, model-based approach for policy optimization, employing a conditional Value-at-Risk (VaR)-based soft actor-critic (SAC) to handle constraints in complex, high-dimensional state spaces. Our method features a worst-case actor to ensure strict compliance with safety requirements, even in unpredictable scenarios. The policy optimization leverages the augmented Lagrangian method and leverages latent diffusion models to forecast and simulate future trajectories. This dual strategy ensures safe navigation through environments and enhances policy performance by incorporating distribution modeling to address environmental uncertainties. Empirical evaluations conducted in both simulated and real environments demonstrate that our approach surpasses existing methods in terms of safety, efficiency, and decision-making capabilities.

Environmental-Driven Approach towards Level 5 Self-Driving.

As technology advances in almost all areas of life, many companies and researchers are working to develop fully autonomous vehicles. Such level 5 autonomous driving, unlike levels 0 to 4, is a driverless vehicle stage and so the leap from level 4 to level 5 autonomous driving requires much more research and experimentation. For autonomous vehicles to safely drive in complex environments, autonomous cars should ensure end-to-end delay deadlines of sensor systems and car-controlling algorithms including machine learning modules, which are known to be very computationally intensive. To address this issue, we propose a new framework, i.e., an environment-driven approach for autonomous cars. Specifically, we identify environmental factors that we cannot control at all, and controllable internal factors such as sensing frequency, image resolution, prediction rate, car speed, and so on. Then, we design an admission control module that allows us to control internal factors such as image resolution and detection period to determine whether given parameters are acceptable or not for supporting end-to-end deadlines in the current environmental scenario while maintaining the accuracy of autonomous driving. The proposed framework has been verified with an RC car and a simulator.

Synchronous End-to-End Vehicle Pedestrian Detection Algorithm Based on Improved YOLOv8 in Complex Scenarios.

In modern urban traffic, vehicles and pedestrians are fundamental elements in the study of traffic dynamics. Vehicle and pedestrian detection have significant practical value in fields like autonomous driving, traffic management, and public security. However, traditional detection methods struggle in complex environments due to challenges such as varying scales, target occlusion, and high computational costs, leading to lower detection accuracy and slower performance. To address these challenges, this paper proposes an improved vehicle and pedestrian detection algorithm based on YOLOv8, with the aim of enhancing detection in complex traffic scenes. The motivation behind our design is twofold: first, to address the limitations of traditional methods in handling targets of different scales and severe occlusions, and second, to improve the efficiency and accuracy of real-time detection. The new generation of dense pedestrian detection technology requires higher accuracy, less computing overhead, faster detection speed, and more convenient deployment. Based on the above background, this paper proposes a synchronous end-to-end vehicle pedestrian detection algorithm based on improved YOLOv8, aiming to solve the detection problem in complex scenes. First of all, we have improved YOLOv8 by designing a deformable convolutional improved backbone network and attention mechanism, optimized the network structure, and improved the detection accuracy and speed. Secondly, we introduced an end-to-end target search algorithm to make the algorithm more stable and accurate in vehicle and pedestrian detection. The experimental results show that, using the algorithm designed in this paper, our model achieves an 11.76% increase in precision and a 6.27% boost in mAP. In addition, the model maintains a real-time detection speed of 41.46 FPS, ensuring robust performance even in complex scenarios. These optimizations significantly enhance both the efficiency and robustness of vehicle and pedestrian detection, particularly in crowded urban environments. We further apply our improved YOLOv8 model for real-time detection in intelligent transportation systems and achieve exceptional performance with a mAP of 95.23%, outperforming state-of-the-art models like YOLOv5, YOLOv7, and Faster R-CNN.

End-to-End Encrypted Message Distribution System for the Internet of Things Based on Conditional Proxy Re-Encryption.

In light of the existing security vulnerabilities within IoT publish-subscribe systems, our study introduces an improved end-to-end encryption approach using conditional proxy re-encryption. This method not only overcomes limitations associated with the reliance on a trusted authority and the challenge of reliably revoking users in previous proxy re-encryption frameworks, but also strengthens data privacy against potential collusion between the broker and subscribers. Through our innovative encryption protocol, unauthorized re-encryption by brokers is effectively prevented, enhancing secure communication between publisher and subscriber. Implemented on HiveMQ, an open-source MQTT platform, our prototype system demonstrates significant enhancements. Comparison to the state-of-the-art end-to-end encryption work, encryption overhead of our scheme is comparable to it, and the decryption cost is approximately half of it. Moreover, our solution significantly improves overall security without compromising the asynchronous communication and decentralized authorization foundational to the publish-subscribe model.

Integrating Modular Pipelines with End-to-End Learning: A Hybrid Approach for Robust and Reliable Autonomous Driving Systems.

Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved first and second place in the 2023 CARLA Autonomous Driving Challenge's SENSORS and MAP tracks, respectively. These results demonstrate the architecture's effectiveness in both map-based and mapless navigation. We achieved a driving score of 41.56 and the highest route completion of 86.03 in the MAP track of the CARLA Challenge leaderboard 1, and driving scores of 35.36 and 1.23 in the CARLA Challenge SENSOR track with route completions of 85.01 and 9.55, for, respectively, leaderboard 1 and 2. The results of leaderboard 2 raised the hybrid architecture to the first position, winning the edition of the 2023 CARLA Autonomous Driving Competition.

End-to-End Network Intrusion Detection Based on Contrastive Learning.

The network intrusion detection system (NIDS) plays a crucial role as a security measure in addressing the increasing number of network threats. The majority of current research relies on feature-ready datasets that heavily depend on feature engineering. Conversely, the increasing complexity of network traffic and the ongoing evolution of attack techniques lead to a diminishing distinction between benign and malicious network behaviors. In this paper, we propose a novel end-to-end intrusion detection framework based on a contrastive learning approach. We design a hierarchical Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) model to facilitate the automated extraction of spatiotemporal features from raw traffic data. The integration of contrastive learning amplifies the distinction between benign and malicious network traffic in the representation space. The proposed method exhibits enhanced detection capabilities for unknown attacks in comparison to the approaches trained using the cross-entropy loss function. Experiments are carried out on the public datasets CIC-IDS2017 and CSE-CIC-IDS2018, demonstrating that our method can attain a detection accuracy of 99.9% for known attacks, thus achieving state-of-the-art performance. For unknown attacks, a weighted recall rate of 95% can be achieved.

A Multiple Attention Convolutional Neural Networks for Diesel Engine Fault Diagnosis.

Fault diagnosis can improve the safety and reliability of diesel engines. An end-to-end method based on a multi-attention convolutional neural network (MACNN) is proposed for accurate and efficient diesel engine fault diagnosis. By optimizing the arrangement and kernel size of the channel and spatial attention modules, the feature extraction capability is improved, and an improved convolutional block attention module (ICBAM) is obtained. Vibration signal features are acquired using a feature extraction model alternating between the convolutional neural network (CNN) and ICBAM. The feature map is recombined to reconstruct the sequence order information. Next, the self-attention mechanism (SAM) is applied to learn the recombined sequence features directly. A Swish activation function is introduced to solve "Dead ReLU" and improve the accuracy. A dynamic learning rate curve is designed to improve the convergence ability of the model. The diesel engine fault simulation experiment is carried out to simulate three kinds of fault types (abnormal valve clearance, abnormal rail pressure, and insufficient fuel supply), and each kind of fault varies in different degrees. The comparison results show that the accuracy of MACNN on the eight-class fault dataset at different speeds is more than 97%. The testing time of the MACNN is much less than the machine running time (for one work cycle). Therefore, the proposed end-to-end fault diagnosis method has a good application prospect.

The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving.

This study investigates the effects of speed variations and computational delays on the performance of end-to-end autonomous driving systems (ADS). Utilizing 1:10 scale mini-cars with limited computational resources, we demonstrate that different driving speeds significantly alter the task of the driving model, challenging the generalization capabilities of systems trained at a singular speed profile. Our findings reveal that models trained to drive at high speeds struggle with slower speeds and vice versa. Consequently, testing an ADS at an inappropriate speed can lead to misjudgments about its competence. Additionally, we explore the impact of computational delays, common in real-world deployments, on driving performance. We present a novel approach to counteract the effects of delays by adjusting the target labels in the training data, demonstrating improved resilience in models to handle computational delays effectively. This method, crucially, addresses the effects of delays rather than their causes and complements traditional delay minimization strategies. These insights are valuable for developing robust autonomous driving systems capable of adapting to varying speeds and delays in real-world scenarios.