Search

Your search keyword '"Guo, Tian-An"' showing total 2,825 results
Start Over Author "Guo, Tian-An"
2,825 results on '"Guo, Tian-An"'

1. HybridDepth: Robust Depth Fusion for Mobile AR by Leveraging Depth from Focus and Single-Image Priors

Author

Ganj, Ashkan, Su, Hang, and Guo, Tian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses the unique challenges of depth estimation for mobile AR, such as scale ambiguity, hardware heterogeneity, and generalizability. HYBRIDDEPTH leverages the camera features available on mobile devices. It effectively combines the scale accuracy inherent in Depth from Focus (DFF) methods with the generalization capabilities enabled by strong single-image depth priors. By utilizing the focal planes of a mobile camera, our approach accurately captures depth values from focused pixels and applies these values to compute scale and shift parameters for transforming relative depths into metric depths. We test our pipeline as an end-to-end system, with a newly developed mobile client to capture focal stacks, which are then sent to a GPU-powered server for depth estimation. Through comprehensive quantitative and qualitative analyses, we demonstrate that HYBRIDDEPTH not only outperforms state-of-the-art (SOTA) models in common datasets (DDFF12, NYU Depth v2) and a real-world AR dataset ARKitScenes but also demonstrates strong zero-shot generalization. For example, HYBRIDDEPTH trained on NYU Depth v2 achieves comparable performance on the DDFF12 to existing models trained on DDFF12. it also outperforms all the SOTA models in zero-shot performance on the ARKitScenes dataset. Additionally, we conduct a qualitative comparison between our model and the ARCore framework, demonstrating that our models output depth maps are significantly more accurate in terms of structural details and metric accuracy. The source code of this project is available at github.

Published
2024

2. Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow

Author

Guo, Tian and Hauptmann, Emmanuel

Subjects
Quantitative Finance - Computational Finance, Computer Science - Machine Learning, Quantitative Finance - Portfolio Management
Abstract

Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks. This paper explores fine-tuning LLMs for stock return forecasting with financial newsflow. In quantitative investing, return forecasting is fundamental for subsequent tasks like stock picking, portfolio optimization, etc. We formulate the model to include text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways. The impact of these different representations on forecasting performance remains an open question. Meanwhile, we compare two simple methods of integrating LLMs' token-level representations into the forecasting module. The experiments on real news and investment universes reveal that: (1) aggregated representations from LLMs' token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios; (2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners. Among the three LLMs studied (DeBERTa, Mistral, Llama), Mistral performs more robustly across different universes; (3) return predictions derived from LLMs' text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores.

Published
2024

3. CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework

Author

Zhao, Yiyang, Liu, Yunzhuo, Jiang, Bo, and Guo, Tian

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

This work presents a novel approach to neural architecture search (NAS) that aims to increase carbon efficiency for the model design process. The proposed framework CE-NAS addresses the key challenge of high carbon cost associated with NAS by exploring the carbon emission variations of energy and energy differences of different NAS algorithms. At the high level, CE-NAS leverages a reinforcement-learning agent to dynamically adjust GPU resources based on carbon intensity, predicted by a time-series transformer, to balance energy-efficient sampling and energy-intensive evaluation tasks. Furthermore, CE-NAS leverages a recently proposed multi-objective optimizer to effectively reduce the NAS search space. We demonstrate the efficacy of CE-NAS in lowering carbon emissions while achieving SOTA results for both NAS datasets and open-domain NAS tasks. For example, on the HW-NasBench dataset, CE-NAS reduces carbon emissions by up to 7.22X while maintaining a search efficiency comparable to vanilla NAS. For open-domain NAS tasks, CE-NAS achieves SOTA results with 97.35% top-1 accuracy on CIFAR-10 with only 1.68M parameters and a carbon consumption of 38.53 lbs of CO2. On ImageNet, our searched model achieves 80.6% top-1 accuracy with a 0.78 ms TensorRT latency using FP16 on NVIDIA V100, consuming only 909.86 lbs of CO2, making it comparable to other one-shot-based NAS baselines., Comment: arXiv admin note: text overlap with arXiv:2307.04131

Published
2024

4. Multi-Objective Neural Architecture Search by Learning Search Space Partitions

Author

Zhao, Yiyang, Wang, Linnan, and Guo, Tian

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Deploying deep learning models requires taking into consideration neural network metrics such as model size, inference latency, and #FLOPs, aside from inference accuracy. This results in deep learning model designers leveraging multi-objective optimization to design effective deep neural networks in multiple criteria. However, applying multi-objective optimizations to neural architecture search (NAS) is nontrivial because NAS tasks usually have a huge search space, along with a non-negligible searching cost. This requires effective multi-objective search algorithms to alleviate the GPU costs. In this work, we implement a novel multi-objectives optimizer based on a recently proposed meta-algorithm called LaMOO on NAS tasks. In a nutshell, LaMOO speedups the search process by learning a model from observed samples to partition the search space and then focusing on promising regions likely to contain a subset of the Pareto frontier. Using LaMOO, we observe an improvement of more than 200% sample efficiency compared to Bayesian optimization and evolutionary-based multi-objective optimizers on different NAS datasets. For example, when combined with LaMOO, qEHVI achieves a 225% improvement in sample efficiency compared to using qEHVI alone in NasBench201. For real-world tasks, LaMOO achieves 97.36% accuracy with only 1.62M #Params on CIFAR10 in only 600 search samples. On ImageNet, our large model reaches 80.4% top-1 accuracy with only 522M #FLOPs.

Published
2024

9. Mobile AR Depth Estimation: Challenges & Prospects -- Extended Version

Author

Ganj, Ashkan, Zhao, Yiqin, Su, Hang, and Guo, Tian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Metric depth estimation plays an important role in mobile augmented reality (AR). With accurate metric depth, we can achieve more realistic user interactions such as object placement and occlusion detection. While specialized hardware like LiDAR demonstrates its promise, its restricted availability, i.e., only on selected high-end mobile devices, and performance limitations such as range and sensitivity to the environment, make it less ideal. Monocular depth estimation, on the other hand, relies solely on mobile cameras, which are ubiquitous, making it a promising alternative for mobile AR. In this paper, we investigate the challenges and opportunities of achieving accurate metric depth estimation in mobile AR. We tested four different state-of-the-art monocular depth estimation models on a newly introduced dataset (ARKitScenes) and identified three types of challenges: hard-ware, data, and model related challenges. Furthermore, our research provides promising future directions to explore and solve those challenges. These directions include (i) using more hardware-related information from the mobile device's camera and other available sensors, (ii) capturing high-quality data to reflect real-world AR scenarios, and (iii) designing a model architecture to utilize the new information.

Published
2023

10. Get-A-Sense: Designing Spatial Context Awareness for Mobile AR Environment Understanding

Author

Zhao, Yiqin, Ganj, Ashkan, and Guo, Tian

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

Physical environment understanding is vital in delivering immersive and interactive mobile augmented reality (AR) user experiences. Recently, we have witnessed a transition in the design of environment understanding systems, from visual data focused to centering on the concept of spatial context, including user, device, and environment information. Even though spatial context can benefit the environment understanding tasks, e.g., we demonstrate in a case study that lighting estimation performance can be improved by as much as 59%, not all environment understanding systems support spatial context. Furthermore, even for the environment understanding systems that support spatial context, not all useful spatial context has been leveraged; and the design and implementation can differ vastly. In this paper, we advocate for the design of a spatial context-aware and shared environment understanding system that can effectively support multiple tasks simultaneously. Fundamentally, there are many practical challenges in designing such a unified environment understanding system. We discuss the challenges in the context of three open questions, (i) how to fully leverage user mobility, (ii) how to design a unified data model, and (iii) finally how to build a shared system for multiple tasks.

Published
2023

12. Toward Scalable and Controllable AR Experimentation

Author

Ganj, Ashkan, Zhao, Yiqin, Galbiati, Federico, and Guo, Tian

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Human-Computer Interaction
Abstract

To understand how well a proposed augmented reality (AR) solution works, existing papers often conducted tailored and isolated evaluations for specific AR tasks, e.g., depth or lighting estimation, and compared them to easy-to-setup baselines, either using datasets or resorting to time-consuming data capturing. Conceptually simple, it can be extremely difficult to evaluate an AR system fairly and in scale to understand its real-world performance. The difficulties arise for three key reasons: lack of control of the physical environment, the time-consuming data capturing, and the difficulties to reproduce baseline results. This paper presents our design of an AR experimentation platform, ExpAR, aiming to provide scalable and controllable AR experimentation. ExpAR is envisioned to operate as a standalone deployment or a federated platform; in the latter case, AR researchers can contribute physical resources, including scene setup and capturing devices, and allow others to time share these resources. Our design centers around the generic sensing-understanding-rendering pipeline and is driven by the evaluation limitations observed in recent AR systems papers. We demonstrate the feasibility of this vision with a preliminary prototype and our preliminary evaluations suggest the importance of further investigating different device capabilities to stream in 30 FPS. The ExpAR project site can be found at https://cake.wpi.edu/expar.

Published
2023

13. Carbon-Efficient Neural Architecture Search

Author

Zhao, Yiyang and Guo, Tian

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

This work presents a novel approach to neural architecture search (NAS) that aims to reduce energy costs and increase carbon efficiency during the model design process. The proposed framework, called carbon-efficient NAS (CE-NAS), consists of NAS evaluation algorithms with different energy requirements, a multi-objective optimizer, and a heuristic GPU allocation strategy. CE-NAS dynamically balances energy-efficient sampling and energy-consuming evaluation tasks based on current carbon emissions. Using a recent NAS benchmark dataset and two carbon traces, our trace-driven simulations demonstrate that CE-NAS achieves better carbon and search efficiency than the three baselines.

Published
2023
Full Text
View/download PDF

15. Identification of key biomarkers for early warning of diabetic retinopathy using BP neural network algorithm and hierarchical clustering analysis

Author

Peiyu Li, Hui Wang, Guo Tian, and Zhihui Fan

Subjects
Diabetic retinopathy, Early warning of disease, Key markers, BP neural network, Hierarchical cluster analysis, Medicine, Science
Abstract

Abstract Diabetic retinopathy is one of the most common microangiopathy in diabetes, essentially caused by abnormal blood glucose metabolism resulting from insufficient insulin secretion or reduced insulin activity. Epidemiological survey results show that about one third of diabetes patients have signs of diabetic retinopathy, and another third may suffer from serious retinopathy that threatens vision. However, the pathogenesis of diabetic retinopathy is still unclear, and there is no systematic method to detect the onset of the disease and effectively predict its occurrence. In this study, we used medical detection data from diabetic retinopathy patients to determine key biomarkers that induce disease onset through back propagation neural network algorithm and hierarchical clustering analysis, ultimately obtaining early warning signals of the disease. The key markers that induce diabetic retinopathy have been detected, which can also be used to explore the induction mechanism of disease occurrence and deliver strong warning signal before disease occurrence. We found that multiple clinical indicators that form key markers, such as glycated hemoglobin, serum uric acid, alanine aminotransferase are closely related to the occurrence of the disease. They respectively induced disease from the aspects of the individual lipid metabolism, cell oxidation reduction, bone metabolism and bone resorption and cell function of blood coagulation. The key markers that induce diabetic retinopathy complications do not act independently, but form a complete module to coordinate and work together before the onset of the disease, and transmit a strong warning signal. The key markers detected by this algorithm are more sensitive and effective in the early warning of disease. Hence, a new method related to key markers is proposed for the study of diabetic microvascular lesions. In clinical prediction and diagnosis, doctors can use key markers to give early warning of individual diseases and make early intervention.

Published
2024
Full Text
View/download PDF

16. Opportunities of Renewable Energy Powered DNN Inference

Author

Nabavinejad, Seyed Morteza and Guo, Tian

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

With the proliferation of the adoption of renewable energy in powering data centers, addressing the challenges of such energy sources has attracted researchers from academia and industry. One of the challenging characteristics of data centers with renewable energy is the intrinsic power fluctuation. Fluctuation in renewable power supply inevitably requires adjusting applications' power consumption, which can lead to undesirable performance degradation. This paper investigates the possible control knobs to manage the power and performance of a popular cloud workload, i.e., deep neural network inference, under the fluctuating power supply. Through empirical profiling and trace-driven simulations, we observe the different impact levels associated with inference control knobs on throughput, under varying power supplies. Based on our observations, we provide a list of future research directions to leverage the control knobs to achieve high throughput.

Published
2023

21. Simulation Analysis of the Electrical and Thermal Characteristics of Water Ingress Defects Within High-Voltage Direct Current Cable Terminals

Author

Zhao, Yang, Guo, Tian, Ma, Boxiang, Shang, Yingqiang, Wang, Yaogang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Yang, Qingxin, editor, Li, Zewen, editor, and Luo, An, editor

Published
2024
Full Text
View/download PDF

26. Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting

Author

Guo, Tian

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

In many data-driven applications, collecting data from different sources is increasingly desirable for enhancing performance. In this paper, we are interested in the problem of probabilistic forecasting with multi-source time series. We propose a neural mixture structure-based probability model for learning different predictive relations and their adaptive combinations from multi-source time series. We present the prediction and uncertainty quantification methods that apply to different distributions of target variables. Additionally, given the imbalanced and unstable behaviors observed during the direct training of the proposed mixture model, we develop a phased learning method and provide a theoretical analysis. In experimental evaluations, the mixture model trained by the phased learning exhibits competitive performance on both point and probabilistic prediction metrics. Meanwhile, the proposed uncertainty conditioned error suggests the potential of the mixture model's uncertainty score as a reliability indicator of predictions., Comment: A causal view on dynamical systems workshop at the 36th Conference on Neural Information Processing Sys- tems (NeurIPS 2022)

Published
2023

27. LitAR: Visually Coherent Lighting for Mobile Augmented Reality

Author

Zhao, Yiqin, Ma, Chongyang, Huang, Haibin, and Guo, Tian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

An accurate understanding of omnidirectional environment lighting is crucial for high-quality virtual object rendering in mobile augmented reality (AR). In particular, to support reflective rendering, existing methods have leveraged deep learning models to estimate or have used physical light probes to capture physical lighting, typically represented in the form of an environment map. However, these methods often fail to provide visually coherent details or require additional setups. For example, the commercial framework ARKit uses a convolutional neural network that can generate realistic environment maps; however the corresponding reflective rendering might not match the physical environments. In this work, we present the design and implementation of a lighting reconstruction framework called LitAR that enables realistic and visually-coherent rendering. LitAR addresses several challenges of supporting lighting information for mobile AR. First, to address the spatial variance problem, LitAR uses two-field lighting reconstruction to divide the lighting reconstruction task into the spatial variance-aware near-field reconstruction and the directional-aware far-field reconstruction. The corresponding environment map allows reflective rendering with correct color tones. Second, LitAR uses two noise-tolerant data capturing policies to ensure data quality, namely guided bootstrapped movement and motion-based automatic capturing. Third, to handle the mismatch between the mobile computation capability and the high computation requirement of lighting reconstruction, LitAR employs two novel real-time environment map rendering techniques called multi-resolution projection and anchor extrapolation. These two techniques effectively remove the need of time-consuming mesh reconstruction while maintaining visual quality.

Published
2023
Full Text
View/download PDF

28. Multi-Camera Lighting Estimation for Photorealistic Front-Facing Mobile Augmented Reality

Author

Zhao, Yiqin, Fanello, Sean, and Guo, Tian

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Lighting understanding plays an important role in virtual object composition, including mobile augmented reality (AR) applications. Prior work often targets recovering lighting from the physical environment to support photorealistic AR rendering. Because the common workflow is to use a back-facing camera to capture the physical world for overlaying virtual objects, we refer to this usage pattern as back-facing AR. However, existing methods often fall short in supporting emerging front-facing mobile AR applications, e.g., virtual try-on where a user leverages a front-facing camera to explore the effect of various products (e.g., glasses or hats) of different styles. This lack of support can be attributed to the unique challenges of obtaining 360$^\circ$ HDR environment maps, an ideal format of lighting representation, from the front-facing camera and existing techniques. In this paper, we propose to leverage dual-camera streaming to generate a high-quality environment map by combining multi-view lighting reconstruction and parametric directional lighting estimation. Our preliminary results show improved rendering quality using a dual-camera setup for front-facing AR compared to a commercial solution.

Published
2023
Full Text
View/download PDF

29. The effect of hyperlipidemia on overall survival in patients with cancer was differentiated by BMI and hyperlipidemia type

Author

Hai-Ying Tian, Ming Yang, Hai-Lun Xie, Guo-Tian Ruan, Yi-Zhong Ge, Xiao-Wei Zhang, He-Yang Zhang, Chen-An Liu, Tong Liu, and Han-Ping Shi

Subjects
Hyperlipidemia, Body mass index, Overall survival, Cancer, Nutrition. Foods and food supply, TX341-641, Nutritional diseases. Deficiency diseases, RC620-627
Abstract

Abstract Background and aims The impact of lipids on the overall survival (OS) of patients with malignancy has not yet been clarified. This study aimed to evaluate the effect of hyperlipidemia on the OS among Chinese patients based on Body Mass Index (BMI) stratifications and hyperlipidemia types. Method The patients in this study were derived from the Investigation of the Nutrition Status and Clinical Outcome of Common Cancers (INSCOC) trial. Kaplan–Meier was used to draw the survival curve, and the log-rank test was used to estimate the survival rates between each group. Cox proportional hazards regression models were used to estimate the hazard ratios (HR) and 95% confidence intervals (CI). Results A total of 9054 patients were included in the final study, with a median age of 59 years, and 55.3% (5004) of them were males. Regarding types of hyperlipidemia, only low high-density lipoprotein was an independent risk factor for the prognosis of all patients (HR = 1.35, 95% CI: 1.25–1.45, P

Published
2024
Full Text
View/download PDF

30. Upgrading CO2 to sustainable aromatics via perovskite-mediated tandem catalysis

Author

Guo Tian, Zhengwen Li, Chenxi Zhang, Xinyan Liu, Xiaoyu Fan, Kui Shen, Haibin Meng, Ning Wang, Hao Xiong, Mingyu Zhao, Xiaoyu Liang, Liqiang Luo, Lan Zhang, Binhang Yan, Xiao Chen, Hong-Jie Peng, and Fei Wei

Subjects
Science
Abstract

Abstract The directional transformation of carbon dioxide (CO2) with renewable hydrogen into specific carbon-heavy products (C6+) of high value presents a sustainable route for net-zero chemical manufacture. However, it is still challenging to simultaneously achieve high activity and selectivity due to the unbalanced CO2 hydrogenation and C–C coupling rates on complementary active sites in a bifunctional catalyst, thus causing unexpected secondary reaction. Here we report LaFeO3 perovskite-mediated directional tandem conversion of CO2 towards heavy aromatics with high CO2 conversion (> 60%), exceptional aromatics selectivity among hydrocarbons (> 85%), and no obvious deactivation for 1000 hours. This is enabled by disentangling the CO2 hydrogenation domain from the C-C coupling domain in the tandem system for Iron-based catalyst. Unlike other active Fe oxides showing wide hydrocarbon product distribution due to carbide formation, LaFeO3 by design is endowed with superior resistance to carburization, therefore inhibiting uncontrolled C–C coupling on oxide and isolating aromatics formation in the zeolite. In-situ spectroscopic evidence and theoretical calculations reveal an oxygenate-rich surface chemistry of LaFeO3, that easily escape from the oxide surface for further precise C–C coupling inside zeolites, thus steering CO2-HCOOH/H2CO-Aromatics reaction pathway to enable a high yield of aromatics.

Published
2024
Full Text
View/download PDF

31. Application of λ esophagojejunostomy in total gastrectomy under laparoscopy: a modified technique for post-gastrectomy reconstruction

Author

Lang-Biao Liu, Guo-Tian Ruan, Ya-Dong Wu, Lei Niu, and Jun Cai

Subjects
laparoscopy, total gastrectomy, lambda anastomosis, Roux-en-Y anastomosis, non-dismembered Roux-en-Y anastomosis, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

ObjectiveCommon gastrectomy methods can significantly affect patients’ postoperative quality of life. This study investigated the safety, feasibility, and short-term efficacy of λ-type esophagojejunostomy in total gastrectomy under total laparoscopy.MethodsWe retrospectively analyzed the clinical and follow-up data of 50 patients with adenocarcinoma of the gastric/gastroesophageal junction who underwent total laparoscopic radical gastrectomy with λ-type esophagojejunostomy at the Beijing Friendship Hospital from January 2021 to July 2022. Data are reported as mean ± standard deviation.ResultsPatients comprised 27 males and 23 females, aged 42 to 76 (60.9 ± 5.6) years. There were 26 cases of gastroesophageal junction adenocarcinoma (16 Siewert type II and 10 Siewert type III) and 24 cases of adenocarcinoma of the proximal gastric body. All patients underwent radical total gastrectomy and D2 lymph node dissection with λ-type esophagojejunostomy for digestive tract reconstruction under total laparoscopy. The total operation time was 235–295 (249.4 ± 48.5) min, digestive tract reconstruction time was (48.2 ± 23.2) min, intraoperative blood loss was (63.4 ± 48.4) mL, recovery time of exhaust was (3.1 ± 2.2) d, first drinking or eating time was (4.1 ± 2.1) d, and hospital stay was (9.3 ± 4.4) d. Three patients had postoperative complications, including one with duodenal remnant leakage combined with abdominal infection. Anastomotic bleeding and postoperative inflammatory intestinal obstruction occurred in one patient each, all of whom were cured by conservative treatment. The Nutritional Risk Index of the whole group was 53.5 ± 8.4 preoperatively, 47.3 ± 5.6 one week postoperatively, 50.3 ± 5.6 six months postoperatively, and 52.4 ± 4.2 at 12 months postoperatively. Roux-en-Y stasis syndrome and bile reflux esophagitis occurred in one patient each (2.0%). There were no occurrences of recanalization of the closed end of the afferent loop of the esophagojejunostomy anastomosis, anastomotic stricture or obstruction, or tumor recurrence.Conclusionλ-type esophagojejunostomy is safe and feasible for digestive tract reconstruction after total laparoscopic radical gastrectomy. This digestive tract reconstruction method not only maintains intestinal continuity but also simplifies surgical procedures, allowing patients to recover quickly with an excellent short-term effect.

Published
2024
Full Text
View/download PDF

32. cng-term variations and trends of tropospheric and ground-level NO2 over typical coastal areas

Author

Xin-Peng Tian, De Wang, Yue-Qi Wang, Zhi-Qiang Gao, Chong-Guo Tian, Xiao-Li Bi, and Ji-Cai Ning

Subjects
Ground-level, Tropospheric, Nitrogen dioxide, Coastal regions, OMI, Patterns and trends, Ecology, QH540-549.5
Abstract

Tropospheric and ground-level levels of nitrogen dioxide (NO2) may have changed due to environmental policies and technological changes. Here, multiyear ground-based measurement (2014–2022) and satellite-derived retrieval (October 2004 to May 2023) datasets of NO2 concentrations are used to study the long-term ground-level and tropospheric NO2 patterns and trends at four time scales (interannual, quarterly, monthly, and hourly) over the three regions with the highest global NO2 concentrations. Several tropospheric NO2 hotspots are observed over industrialized and highly populated coastal zone areas. Over the past 18 years, these hotpots have generally decreased due to the implementation of strong and effective environmental protection policies. A significant trend reversal was observed in 2011 in East-central China. The maximum values of tropospheric NO2 occurred in winter over East-central China, Western Europe and East-central USA, with concentrations of 13.010, 4.243 and 4.149 × 1015 molecules cm−2, respectively. The Bohai Sea exhibited disproportionately high tropospheric NO2 levels, suggesting it as a significant contributor to regional nitrogen pollution. Ground-level NO2 shows similar temporal patterns to tropospheric concentrations, with over 82.8 % of sites in East-central China exceeding 30 μg m−3, compared to 12.8 % in Western Europe and 3.8 % in East-central USA. The analysis of diurnal variations in ground-level NO2 concentrations shows a significantly decrease during the daytime compared to nighttime, reflecting that the peak occurs at approximately 08:00 and 20:00 LT, while the lowest concentrations at around 12:00 LT. These insights clarify the impacts of environmental policies on NO2 levels and identify critical areas for targeted pollution control, enhancing our understanding of NO2 dynamics in high-pollution regions globally.

Published
2024
Full Text
View/download PDF

33. Privacy-preserving Reflection Rendering for Augmented Reality

Author

Zhao, Yiqin, Wei, Sheng, and Guo, Tian

Subjects
Computer Science - Multimedia
Abstract

Many augmented reality (AR) applications rely on omnidirectional environment lighting to render photorealistic virtual objects. When the virtual objects consist of reflective materials, such as a metallic sphere, the required lighting information to render such objects can consist of privacy-sensitive information that is outside the current camera view. In this paper, we show, for the first time, that accuracy-driven multi-view environment lighting can reveal out-of-camera scene information and compromise privacy. We present a simple yet effective privacy attack that extracts sensitive scene information such as human face and text information from the rendered objects, under a number of application scenarios. To defend against such attacks, we develop a novel $IPC^{2}S$ defense and a conditional $R^2$ defense. Our $IPC^{2}S$ defense, used in conjunction with a generic lighting reconstruction method, preserves the scene geometry while obfuscating the privacy-sensitive information. As a proof-of-concept, we leverage existing OCR and face detection models to identify text and human faces from past camera observations and blur the color pixels associated with detected regions. We evaluate the visual quality impact of our defense by comparing rendered virtual objects to ones rendered with a generic multi-lighting reconstruction technique, ARKit, and $R^2$ defense. Our visual and quantitative results demonstrate that our defense leads to structurally similar reflections with up to 0.98 SSIM score across a variety of rendering scenarios while preserving sensitive information by reducing the automatic extraction success rate to at most 8.8%., Comment: Accepted to ACM Multimedia 2022

Published
2022

34. The age‐related obesity paradigm: results from two large prospective cohort studies

Author

Yi‐Zhong Ge, Tong Liu, Li Deng, Qi Zhang, Chen‐An Liu, Guo‐Tian Ruan, Hai‐Lun Xie, Meng‐Meng Song, Shi‐Qi Lin, Qin‐Hua Yao, Xian Shen, Han‐Ping Shi, and Investigation on the Nutrition Status and Clinical Outcome of Common Cancers (INSCOC) Group

Subjects
Aging, Cancer, Inflammation, Obesity paradigm, Diseases of the musculoskeletal system, RC925-935, Human anatomy, QM1-695
Abstract

Abstract Background The obesity paradigm has been a health concern globally for many years, its meaning is controversial. In this study, we assess the characteristics and causes of obesity paradigm and detail the mediation of obesity and inflammation on survival. Methods The original cohort included participants from the US National Health and Nutrition Examination Survey (NHANES) from 1999 to 2018, a prospective cohort of a nationally representative sample of adult participants; the oncology validation cohort included patients from the Investigation on Nutrition Status and Clinical Outcome of Common Cancers (INSCOC) from 2013 to 2021, a prospective cohort of Chinese patients with cancer. Survival analysis was performed using weighted (NHANES) or unweighted (INSCOC) Cox survival analyses. The normal BMI group was used as a reference for all comparisons. Systemic inflammation was defined as neutrophil‐to‐lymphocyte ratio (NLR) > 3. Model‐based causal mediation analysis was used to identify the mediators. Results A total of 52 270 (weighted population: 528506229) participants of the NHANES [mean follow‐up times: 10.2 years; mean age (SD): 47 (19.16) years] were included in the original cohort; and a total of 17 418 patients with cancer of INSCOC [mean follow‐up times: 2.9 years; mean age (SD): 57.37 (11.66) years] were included in the validation cohort. In the subgroups of all the participants, the obesity paradigm was more apparent in older participants and participants with disease [HR (95% CI): age ≥ 65 years, 0.84 (0.76, 0.93); with cancer, 0.84 (0.71, 0.99); with CVD, 0.74 (0.65, 0.85)]. As aged, the protective effect of a high BMI on survival gradually increased and a high BMI showed the effect of a protective factor on older participants [for obese II, HR (95% CI): young adults, 1.91 (1.40, 2.62); middle age, 1.56 (1.28, 1.91); old adults, 0.85 (0.76, 0.96]). The aged‐related obesity paradigm in patients with cancer from the NHANES was verified in the INSCOC cohorts [for obese, HR (95%CI): 0.65 (0.52, 0.81)]. The NLR is an important mediator of the effect of BMI on survival (proportion of mediation = 15.4%). Conclusions The obesity paradigm has a strong correlation with age. Relative to normal weight, obese in young people was association with higher all‐cause mortality, and obese in elderly people was not association with higher mortality. The protection of obesity is association with systemic inflammation.

Published
2024
Full Text
View/download PDF

35. Systemic inflammation and insulin resistance-related indicator predicts poor outcome in patients with cancer cachexia

Author

Guo-Tian Ruan, Li Deng, Hai-Lun Xie, Jin-Yu Shi, Xiao-Yue Liu, Xin Zheng, Yue Chen, Shi-Qi Lin, He-Yang Zhang, Chen-An Liu, Yi-Zhong Ge, Meng-Meng Song, Chun-Lei Hu, Xiao-Wei Zhang, Ming Yang, Wen Hu, Ming-Hua Cong, Li-Chen Zhu, Kun-Hua Wang, and Han-Ping Shi

Subjects
Systemic inflammation, Insulin resistance, CTI, Overall survival, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Abstract Background The C-reactive protein (CRP)-triglyceride-glucose (TyG) index (CTI), which is a measure representing the level of inflammation and insulin resistance (IR), is related to poor cancer prognosis; however, the CTI has not been validated in patients with cancer cachexia. Thus, this study aimed to explore the potential clinical value of the CTI in patients with cancer cachexia. Methods In this study, our prospective multicenter cohort included 1411 patients with cancer cachexia (mean age 59.45 ± 11.38, 63.3% male), which was a combined analysis of multiple cancer types. We randomly selected 30% of the patients for the internal test cohort (mean age 58.90 ± 11.22% 61.4% male). Additionally, we included 307 patients with cancer cachexia in the external validation cohort (mean age 61.16 ± 11, 58.5% male). Receiver operating characteristic (ROC) and calibration curves were performed to investigate the prognostic value of CTI. The prognostic value of the CTI was also investigated performing univariate and multivariate survival analyses. Results The survival curve indicated that the CTI showed a significant prognostic value in the total, internal, and external validation cohorts. Prognostic ROC curves and calibration curves revealed that the CTI showed good consistency in predicting the survival of patients with cancer cachexia. Multivariate survival analysis showed that an elevated CTI increased the risk of death by 22% (total cohort, 95% confidence interval [CI] = 1.13–1.33), 34% (internal test cohort, 95%CI = 1.11–1.62), and 35% (external validation cohort, 95%CI = 1.14–1.59) for each increase in the standard deviation of CTI. High CTI reliably predicted shorter survival (total cohort, hazard ratio [HR] = 1.45, 95%CI = 1.22–1.71; internal test cohort, HR = 1.62, 95%CI = 1.12–2.36; external validation cohort, HR = 1.61, 95%CI = 1.15–2.26). High CTI significantly predicted shorter survival in different tumor subgroups, such as esophageal [HR = 2.11, 95%CI = 1.05–4.21] and colorectal cancer [HR = 2.29, 95%CI = 1.42–3.71]. The mediating effects analysis found that the mediating proportions of PGSGA, ECOG PS, and EORTC QLQ-C30 on the direct effects of CTI were 21.72%, 19.63%, and 11.61%, respectively We found that there was a significant positive correlation between the CTI and 90-day [HR = 2.48, 95%CI = 1.52–4.14] and 180-day mortality [HR = 1.77,95%CI = 1.24–2.55] in patients with cancer cachexia. Conclusion The CTI can predict the short- and long-term survival of patients with cancer cachexia and provide a useful prognostic tool for clinical practice.

Published
2024
Full Text
View/download PDF

36. Ultrasmall single-layered NbSe2 nanotubes flattened within a chemical-driven self-pressurized carbon nanotube

Author

Yaxin Jiang, Hao Xiong, Tianping Ying, Guo Tian, Xiao Chen, and Fei Wei

Subjects
Science
Abstract

Abstract Pressure can alter interatomic distances and its electrostatic interactions, exerting a profound modifying effect on electron orbitals and bonding patterns. Conventional pressure engineering relies on compressions from external sources, which raises significant challenge in precisely applying pressure on individual molecules and also consume substantial mechanical energy. Here we report ultrasmall single-layered NbSe2 flat tubes (

Published
2024
Full Text
View/download PDF

37. 'Effect of magnesium methacrylate on properties of hydrogenated nitrile rubber '

Author

SUN Xiao-liang, ZHANG Guo-tian, ZHAO Yu-jun, LUO Xi-chao, SONG Jian, GUO Tian-ming, LIU Xin-xin

Subjects
hydrogenated nitrile rubber, magnesium methacrylate, thermal-oxydative aging resistance, high temperature drilling fluid resistance, mechanical property, Organic chemistry, QD241-441, Chemical engineering, TP155-156, Chemicals: Manufacture, use, etc., TP200-248
Abstract

Magnesium methacrylate (MgMA)/ hydrogenated nitrile rubber (HNBR) composites were prepared by blending MgMA with HNBR, and the effects of MgMA amount on mechanical properties of HNBR at high temperature and after immersion in drilling fluid were investigated. The results showed that under the combined action of high temperature and drilling fluid, the comprehensive performance of MgMA/HNBR composite was improved most significantly with higher tensile strength, elongation at break and tear strength, and the best thermal-oxydative aging resistance, when the amount of MgMA was 8 phr (mass).

Published
2023
Full Text
View/download PDF

38. FuncPipe: A Pipelined Serverless Framework for Fast and Cost-efficient Training of Deep Learning Models

Author

Liu, Yunzhuo, Jiang, Bo, Guo, Tian, Huang, Zimeng, Ma, Wenhao, Wang, Xinbing, and Zhou, Chenghu

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

Training deep learning (DL) models in the cloud has become a norm. With the emergence of serverless computing and its benefits of true pay-as-you-go pricing and scalability, systems researchers have recently started to provide support for serverless-based training. However, the ability to train DL models on serverless platforms is hindered by the resource limitations of today's serverless infrastructure and DL models' explosive requirement for memory and bandwidth. This paper describes FuncPipe, a novel pipelined training framework specifically designed for serverless platforms that enable fast and low-cost training of DL models. FuncPipe is designed with the key insight that model partitioning can be leveraged to bridge both memory and bandwidth gaps between the capacity of serverless functions and the requirement of DL training. Conceptually simple, we have to answer several design questions, including how to partition the model, configure each serverless function, and exploit each function's uplink/downlink bandwidth. In particular, we tailor a micro-batch scheduling policy for the serverless environment, which serves as the basis for the subsequent optimization. Our Mixed-Integer Quadratic Programming formulation automatically and simultaneously configures serverless resources and partitions models to fit within the resource constraints. Lastly, we improve the bandwidth efficiency of storage-based synchronization with a novel pipelined scatter-reduce algorithm. We implement FuncPipe on two popular cloud serverless platforms and show that it achieves 7%-77% cost savings and 1.3X-2.2X speedup compared to state-of-the-art serverless-based frameworks., Comment: Accepted by ACM SIGMETRICS 2023

Published
2022
Full Text
View/download PDF

39. High selectivity and abundant active sites in atomically dispersed TM2C12 monolayer for CO2 reduction

Author

Shu-Long Li, Yu Song, Guo Tian, Qiaoling Liu, Liang Qiao, Yong Zhao, and Li-Yong Gan

Subjects
High active site density, Intrinsic catalytic activity, Single-atom catalysts (SACs), CO2 reduction reaction, Electrocatalysis, Fuel, TP315-360, Renewable energy sources, TJ807-830
Abstract

Developing highly efficient single-atom catalysts (SACs) for electrocatalytic carbon dioxide reduction reaction (CO2RR) is a promising approach to promoting carbon neutrality. However, challenges such as low activity, selectivity and high costs hinder industrial scaling, attributed to the lack of innate activity or insufficient transition metal (TM) active site density in current catalysts. Therefore, the focus of CO2RR research remains on developing SACs with intrinsic catalytic activity, high TM coverage and cost-effectiveness. This study presents the design of carbon-based materials with ultra-high TM coverage (TM2C12) (TM = Mo, Ru, Rh, W, Re, Os and Ir) as electrocatalyst SACs for CO2RR using density functional theory calculations. Among these materials, W2C12 (W represents tungsten) demonstrates superior selectivity and catalytic activity for CO2RR to carbon monoxide (CO) products with overpotentials of 0.45 V and a W coverage of up to 71.84 wt%. To further enhance its catalytic activity, non-metallic (NM) coordination modification (NM = B, N, O, P doping and C vacancy) was explored on W2C12. The results indicate that N-doped W2C12 (N-W2C12) can significantly improve selectivity and catalytic activity, achieving an extremely low overpotential of 0.34 V. This research offers valuable insights into designing SACs with high activity, selectivity and stability for CO2RR and other catalytic reactions.

Published
2024
Full Text
View/download PDF

40. Relationship between educational level and survival of patients with cancer: A multicentre cohort study

Author

Xiao‐Yue Liu, Xi Zhang, Guo‐Tian Ruan, Xin Zheng, Yue Chen, Xiao‐Wei Zhang, Tong Liu, Yi‐Zhong Ge, Han‐Ping Shi, and INSCOC Group

Subjects
educational status, neoplasms, nutritional status, prognosis, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Abstract Background Although socioeconomic factors are important determinants of population mortality, the effect of educational level on the survival of patients with cancer in China is unclear. This study aimed to assess whether educational level is associated with the prognosis of patients with cancer and to explore the mediators of this association. Methods This multicentre cohort study included 18,251 patients diagnosed with cancer between May 2013 and December 2018. The main parameters measured were overall survival (OS) and all‐cause mortality. The relationship between educational level and all‐cause mortality was assessed using multifactor‐corrected Cox survival analysis. Logistic regression was used to analyze the association between educational level and patient‐generated subjective global assessment (PG‐SGA). Results The mean age of the 18,251 participants (men, 9939 [54.4%]) was 57.37 ± 11.66 years. Multifactorial survival analysis showed that patients survived longer with increasing education (university and above vs. elementary school and below; p = p =

Published
2024
Full Text
View/download PDF

45. AIWW: a new nutrition-screening tool for the oncologic population

Author

Ge, Yi-Zhong, Fu, Zhen-Ming, Zhang, Qi, Song, Meng-Meng, Ruan, Guo-Tian, Zhang, Xi, Zhang, Xiao-Wei, Li, Xiang-Rui, Zhang, Kang-Ping, Tang, Meng, Liu, Xiao-Yue, Yang, Ming, Liu, Tong, Xie, Hai-Lun, Zhang, He-Yang, Wang, Zi-Wen, Hu, Chun-Lei, Lin, Shi-Qi, Zhang, Rui, Xu, Hong-Xia, Li, Wei, Song, Chun-Hua, Liu, Ming, Chen, Jun-Qiang, Wang, Kun-Hua, Bo, Li, Cong, Ming-Hua, Li, Zeng-Ning, Guo, Zeng-Qin, Wang, Xiao-Bin, Wang, Bin-Yan, Xu, Benjamin, Qin, Xian-Hui, Xu, Xi-Ping, Barazzoni, Rocco, Yao, Qing-Hua, Weng, Min, Shen, Xian, and Shi, Han-Ping

Published
2023
Full Text
View/download PDF

46. Prognostic value of systemic inflammation and for patients with colorectal cancer cachexia

Author

Guo‐Tian Ruan, Hai‐Lun Xie, Kai‐Tao Yuan, Shi‐Qi Lin, He‐Yang Zhang, Chen‐An Liu, Jin‐Yu Shi, Yi‐Zhong Ge, Meng‐Meng Song, Chun‐Lei Hu, Xiao‐Wei Zhang, Xiao‐Yue Liu, Ming Yang, Kun‐Hua Wang, Xin Zheng, Yue Chen, Wen Hu, Ming‐Hua Cong, Li‐Chen Zhu, Li Deng, and Han‐Ping Shi

Subjects
Cachexia, CRC, ECOG‐PS, Systemic inflammation, Diseases of the musculoskeletal system, RC925-935, Human anatomy, QM1-695
Abstract

Abstract Background The development and progression of cancer cachexia are connected to systemic inflammation and physical performance. However, few relevant studies have reported the survival outcomes prediction of systemic inflammation and physical performance in patients with colorectal cancer (CRC) cachexia. This study investigated the prognostic prediction value of systemic inflammation and performance status in patients with CRC cachexia. Methods This multicentre cohort study prospectively collected 905 patients with CRC (58.3% males, 59.3 ± 11.5 years old). Cancer cachexia was diagnosed according to the 2011 Fearon Cachexia Diagnostic Consensus. The prognostic value of systematic inflammatory indicators was determined using the area under the curve, concordance index, and multivariate survival analysis. Performance status was evaluated with Eastern Coopertive Oncology Group performance score (ECOG‐PS). Survival data were analysed using univariate and multivariate Cox regression analyses. Results The area under the curve, concordance index and survival analysis showed that C‐reactive protein (CRP), lymphocyte to CRP ratio (LCR) and CRP to albumin ratio (CAR) were more stable and consistent with the survival of patients with CRC, both in non‐cachexia and cachexia populations. Among patients with CRC cachexia, high inflammation [low LCR, hazard ratio (HR) 95% confidence interval (95% CI) = 3.33 (2.08–5.32); high CAR, HR (95% CI) = 2.92 (1.88–4.55); high CRP, HR (95% CI) = 3.12 (2.08–4.67)] indicated a worse prognosis, compared with non‐cachexia patients [low LCR, HR (95% CI) = 2.28 (1.65–3.16); high CAR, HR (95% CI) = 2.36 (1.71–3.25); high CRP, HR (95% CI) = 2.58 (1.85–3.60)]. Similarly, among patients with CRC cachexia, high PS [ECOG‐PS 2, HR (95% CI) = 1.61 (1.04–2.50); ECOG‐PS 3/4, HR (95% CI) = 2.91 (1.69–5.00]) indicated a worse prognosis, compared with patients with CRC without cachexia [ECOG‐PS 2, HR (95% CI) = 1.28 (0.90–1.81); ECOG‐PS 3/4, HR (95% CI) = 2.41 (1.32–4.39]). Patients with CRC cachexia with an ECOG‐PS score of 2 or 3–4 and a high inflammation had a shorter median survival time, compared with patients with an ECOG‐PS score of 0/1 and a low inflammation. Conclusions The systemic inflammatory markers LCR, CAR and CRP have stable prognostic values in patients with CRC. The ECOG‐PS may be an independent risk factor for CRC. Combined evaluation of systemic inflammation and ECOG‐PS in patients with CRC cachexia could provide a simple survival prediction.

Published
2023
Full Text
View/download PDF

47. Development and application of KASP marker for high throughput detection of the seedless trait in grapevine

Author

Fu-qiang WANG, Lu BIAN, Peng-peng QIU, Shuo GUO, Jing-han GUO, Chen-shuo GUO, Jian-fu JIANG, Chong-huai LIU, Yong WANG, Guo-tian LIU, Yue-jin WANG, and Yan XU

Subjects
seedless grape, MAS, KASP, SSR, Agriculture (General), S1-972
Abstract

Molecular marker-assisted selection (MAS) can significantly accelerate and improve the efficiency of the breeding process in seedless grape cultivars. In this study, we developed the KASP_VviAGL11 and VviAGL11_410 markers based on a single nucleotide polymorphism (SNP) site (Chr18: 26889437 (A/C)) of the VviAGL11 gene, and compared them with previously reported SSR markers p3_VvAGL11 and 5U_VviAGL11 by testing 101 cultivars and 81 F1 hybrid progenies. The results showed that both of the proposed markers obtained 100% accuracy rates in detecting allele A, which was closely associated with the seedless trait in grapes, while p3_VvAGL11 and 5U_VviAGL11 had lower accuracy rates due to their tendency to produce false positives. After careful evaluation of the technical advantages and disadvantages associated with these markers, we concluded that KASP_VviAGL11 was superior in terms of simplicity, cost-effectiveness, efficiency, and accuracy. Thus, we optimized the process of molecular MAS for seedless grapes, focusing on the KASP_VviAGL11 marker as a central component, to provide key technical support for the development of new seedless grape cultivars.

Published
2023
Full Text
View/download PDF

48. Multi-objective Optimization by Learning Space Partitions

Author

Zhao, Yiyang, Wang, Linnan, Yang, Kevin, Zhang, Tianjun, Guo, Tian, and Tian, Yuandong

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier. The partitioning is based on the dominance number, which measures "how close" a data point is to the Pareto frontier among existing samples. To account for possible partition errors due to limited samples and model mismatch, we leverage Monte Carlo Tree Search (MCTS) to exploit promising regions while exploring suboptimal regions that may turn out to contain good solutions later. Theoretically, we prove the efficacy of learning space partitioning via LaMOO under certain assumptions. Empirically, on the HyperVolume (HV) benchmark, a popular MOO metric, LaMOO substantially outperforms strong baselines on multiple real-world MOO tasks, by up to 225% in sample efficiency for neural architecture search on Nasbench201, and up to 10% for molecular design.

Published
2021

49. A Cooperative Intrusion Detection System for the Internet of Things Using Convolutional Neural Networks and Black Hole Optimization

Author

Peiyu Li, Hui Wang, Guo Tian, and Zhihui Fan

Subjects
cooperative intrusion detection system (CIDS), internet of things (IoT), convolutional neural network (CNN), black hole optimization (BHO), Chemical technology, TP1-1185
Abstract

Maintaining security in communication networks has long been a major concern. This issue has become increasingly crucial due to the emergence of new communication architectures like the Internet of Things (IoT) and the advancement and complexity of infiltration techniques. For usage in networks based on the Internet of Things, previous intrusion detection systems (IDSs), which often use a centralized design to identify threats, are now ineffective. For the resolution of these issues, this study presents a novel and cooperative approach to IoT intrusion detection that may be useful in resolving certain current security issues. The suggested approach chooses the most important attributes that best describe the communication between objects by using Black Hole Optimization (BHO). Additionally, a novel method for describing the network’s matrix-based communication properties is put forward. The inputs of the suggested intrusion detection model consist of these two feature sets. The suggested technique splits the network into a number of subnets using the software-defined network (SDN). Monitoring of each subnet is done by a controller node, which uses a parallel combination of convolutional neural networks (PCNN) to determine the presence of security threats in the traffic passing through its subnet. The proposed method also uses the majority voting approach for the cooperation of controller nodes in order to more accurately detect attacks. The findings demonstrate that, in comparison to the prior approaches, the suggested cooperative strategy can detect assaults in the NSLKDD and NSW-NB15 datasets with an accuracy of 99.89 and 97.72 percent, respectively. This is a minimum 0.6 percent improvement.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results