A Survey of Traffic Data Visualization Chen, Wei; Guo, Fangzhou; Wang, Fei-Yue
IEEE transactions on intelligent transportation systems,
12/2015, Letnik:
16, Številka:
6
Journal Article
Recenzirano
Data-driven intelligent transportation systems utilize data resources generated within intelligent systems to improve the performance of transportation systems and provide convenient and reliable ...services. Traffic data refer to datasets generated and collected on moving vehicles and objects. Data visualization is an efficient means to represent distributions and structures of datasets and reveal hidden patterns in the data. This paper introduces the basic concept and pipeline of traffic data visualization, provides an overview of related data processing techniques, and summarizes existing methods for depicting the temporal, spatial, numerical, and categorical properties of traffic data.
Machine learning has been widely adopted for improving building energy efficiency and flexibility in the past decade owing to the ever-increasing availability of massive building operational data. ...However, it is challenging for end-users to understand and trust machine learning models because of their black-box nature. To this end, the interpretability of machine learning models has attracted increasing attention in recent studies because it helps users understand the decisions made by these models. This article reviews previous studies that adopted interpretable machine learning techniques for building energy management to analyze how model interpretability is improved. First, the studies are categorized according to the application stages of interpretable machine learning techniques: ante-hoc and post-hoc approaches. Then, the studies are analyzed in detail according to specific techniques with critical comparisons. Through the review, we find that the broad application of interpretable machine learning in building energy management faces the following significant challenges: (1) different terminologies are used to describe model interpretability which could cause confusion, (2) performance of interpretable ML in different tasks is difficult to compare, and (3) current prevalent techniques such as SHAP and LIME can only provide limited interpretability. Finally, we discuss the future R&D needs for improving the interpretability of black-box models that could be significant to accelerate the application of machine learning for building energy management.
Aim: H-type hypertension is connected with carotid atherosclerotic plaques and stroke, whereas neovascularization is a dominant contributor to plaque vulnerability. However, the correlation between ...H-type hypertension and plaque vulnerability remains unclear. This study aims to explore the influence of H-type hypertension on intraplaque neovascularization (IPN). Methods: We enrolled 235 patients with carotid plaques into the investigation and classified them into four groups: H-type hypertension group, simple hypertension group, isolated hyperhomocysteinemia group, and control group. Contrast-enhanced ultrasound (CEUS) was performed on them and IPN was evaluated using semi-quantitative visual grading: grade 1 (no microbubbles or microbubbles limited to the adventitial side and/or shoulder of plaque) and, grade 2 (diffused microbubbles within plaque or microbubbles enter plaque core). To analyze the correlation between H-type hypertension and the degree of plaque enhancement, logistic regression was used. Results: Compared with those with CEUS grade 1 plaques, those with CEUS grade 2 plaques had higher frequency of ischemic stroke (29.0% vs. 45.1%, P<0.05), hypertension (41.0% vs. 56.3%, P<0.05), and H-type hypertension (18.0% vs. 29.6%, P<0.05). No significant differences existed in plaque morphology, plaque echogenicity, and the severity of carotid artery stenosis between the degree of plaque enhancement (all P>0.05). H-type hypertension (multivariate-adjusted OR: 3.036, 95% CI: 1.258–7.329) was independently connected with the degree of plaque enhancement even after adjusting for other covariates. Conclusion: H-type hypertension is expressly connected with the degree of plaque enhancement and may facilitate plaque vulnerability. Our findings may offer a new insight for treating vulnerable plaque, lowering blood pressure, and lowering homocysteine equally crucial.
Bladder cancer is known to be the most common malignant tumor in the urinary system and has a poor prognosis; thus, new targets for drug treatment are urgently needed. Pyroptosis is defined as ...programmed cell death in the inflammatory form mediated by the gasdermin protein. It has therapeutic potential due to the synergistic effect of radiotherapy and chemotherapy, can reverse chemotherapy resistance, is able to regulate the body environment to alter tumor metabolism, and may enhance the response rate of the immune checkpoint inhibitor. Accordingly, this study attempted to explore the role of pyroptosis in bladder cancer. A prognostic model based on five pyroptosis-related genes was constructed by conducting univariate Cox survival and LASSO regression analyses using The Cancer Genome Atlas (TCGA) cohort. Patients were divided into high- and low-risk groups according to the median risk score, with all five PRGs having downregulated expression in the high-risk group. The high-risk group was shown to have a worse prognosis than the low-risk group, and survival differences between the two groups were then validated in the Gene Expression Omnibus (GEO) cohort. Moreover, the ROC curves demonstrated the model’s moderate predictive ability. The univariate and multivariate Cox regression analyses indicated that risk scores were found to serve as an independent prognosis factor for OS in bladder cancer patients. In addition, the high-risk group was observed to be associated with advanced N and TNM stages. A nomogram combining risk scores and clinical features was then established, with the ROC curve indicating that the AUC of TCGA training cohort in 3 and 5 years was 0.789 and 0.775, respectively. The calibration curve exhibited a high consistency between the actual survival rate and the predicted rate. Furthermore, the GO and KEGG analyses found that antigen processing and presentation of exogenous antigen, exogenous peptide antigen, and peptide antigen were enriched in the low-risk group. A higher abundance of tumor-infiltrating immune cells and additional active immune pathways were also noted in the low-risk group. In addition, immunotherapy biomarkers, including TMB, PD1, PD-L1, CTLA4, and LAG3, were shown to have higher levels in the low-risk group. Therefore, patients in the low-risk group may be potential responders to immune checkpoint inhibitors.
•FDD is performed by comparing features among peer electric bus air conditioners.•Gaussian process regression is adopted to quantify the uncertainty of predictions.•Domain expertise is used for ...feature selection and performing fault diagnosis.•The method can label faulty systems efficiently with low false positives/negatives.•Even 1/3 of bus systems are faulty, accuracy of the method can still be guaranteed.
The air conditioning systems in electric city buses usually operate in rapidly changing ambient conditions and are more likely to suffer from mechanical faults. Although many fault detection and diagnosis (FDD) methods have been developed for building air conditioning systems, they are difficult to be applied to bus air conditioners since its operation is highly dynamic and fault-free data are usually unavailable. Therefore, this paper proposes an FDD method for electric bus air conditioners to tackle the above issues. First, the method identifies faults in an unsupervised manner by comparing selected features among a group of peer systems. Then, considering the features are influenced by the operating conditions, Gaussian process regression (GPR) models are established to find the relationships between each feature and its influential parameters. The probabilistic nature of the GPR is used to differentiate predictions with large uncertainty, which are then excluded from FDD. In this way, robustness of the method is evidently improved. Finally, fault indexes are defined to detect and diagnose mechanical faults. We applied the method to a group of air conditioners in a city bus fleet. Results showed that it can effectively identify refrigerant undercharge and indoor and outdoor fan problems with low false positive/genitive rates. Also, the method is highly robust and not sensitive to the faulty systems in the bus fleet.
Display omitted
Intracerebral hemorrhage (ICH) is the second-largest stroke subtype and has a high mortality and disability rate. Secondary brain injury (SBI) is delayed after ICH. The main contributors to SBI are ...inflammation, oxidative stress, and excitotoxicity. Harmful substances from blood and hemolysis, such as hemoglobin, thrombin, and iron, induce SBI. When cells suffer stress, a critical protective mechanism called "autophagy" help to maintain the homeostasis of damaged cells, remove harmful substances or damaged organelles, and recycle them. Autophagy plays a critical role in the pathology of ICH, and its function remains controversial. Several lines of evidence demonstrate a pro-survival role for autophagy in ICH by facilitating the removal of damaged proteins and organelles. However, many studies have found that heme and iron can aggravate SBI by enhancing autophagy. Autophagy and inflammation are essential culprits in the progression of brain injury. It is a fascinating hypothesis that autophagy regulates inflammation in ICH-induced SBI. Autophagy could degrade and clear pro-IL-1β and apoptosis-associated speck-like protein containing a CARD (ASC) to antagonize NLRP3-mediated inflammation. In addition, mitophagy can remove endogenous activators of inflammasomes, such as reactive oxygen species (ROS), inflammatory components, and cytokines, in damaged mitochondria. However, many studies support the idea that autophagy activates microglia and aggravates microglial inflammation
the toll-like receptor 4 (TLR4) pathway. In addition, autophagy can promote ICH-induced SBI through inflammasome-dependent NLRP6-mediated inflammation. Moreover, some resident cells in the brain are involved in autophagy in regulating inflammation after ICH. Some compounds or therapeutic targets that regulate inflammation by autophagy may represent promising candidates for the treatment of ICH-induced SBI. In conclusion, the mutual regulation of autophagy and inflammation in ICH is worth exploring. The control of inflammation by autophagy will hopefully prove to be an essential treatment target for ICH.
To address the problems of mutual interference between shaped steel and reinforcement bars and the difficulty of concrete pouring in the construction of steel-reinforced concrete (SRC) composite ...structure, the steel and steel fiber-reinforced concrete (SSFRC) composite structure without rebars was proposed. Bond behavior between the shaped steel and steel fiber reinforced concrete is the basis to ensure two kinds of materials work together. 20 square specimens were designed and tested by push-out test to study the bond performance and shear modulus of the interface between the shaped steel and steel fiber reinforced concrete. The effects of steel fiber ratio (ρsf), embedded length (Le), and concrete cover thickness (Css) on the interfacial shear modulus (G) were analyzed quantitatively. The degradation law of G was studied by defining the degradation variable of interfacial shear modulus (Da). The results show that the increase of ρsf contributes to the ascent in G, and the loading end displacement (D) at the end of degradation related to G also increase. With the rise of Le, the value of G decreases gradually and the D becomes larger when G starts to deteriorate. In addition, there is a positive correlation between G and Css. Besides, the higher Css leads to a slower degradation process of G.
The population of Texas has increased rapidly in the past decade. The San Antonio Field Study (SAFS) was designed to investigate ozone (O3) production and precursors in this rapidly changing, ...sprawling metropolitan area. There are still many questions regarding the sources and chemistry of volatile organic compounds (VOCs) in urban areas like San Antonio which are affected by a complex mixture of industry, traffic, biogenic sources and transported pollutants. The goal of the SAFS campaign in May 2017 was to measure inorganic trace gases, VOCs, methane (CH4), and ethane (C2H6). The SAFS field design included two sites to better assess air quality across the metro area: an urban site (Traveler's World; TW) and a downwind/suburban site (University of Texas at San Antonio; UTSA). The results indicated that acetone (2.52 ± 1.17 and 2.39 ± 1.27 ppbv), acetaldehyde (1.45 ± 1.02 and 0.93 ± 0.45 ppbv) and isoprene (0.64 ± 0.49 and 1.21 ± 0.85 ppbv; TW and UTSA, respectively) were the VOCs with the highest concentrations. Additionally, positive matrix factorization showed three dominant factors of VOC emissions: biogenic, aged urban mixed source, and acetone. Methyl vinyl ketone and methacrolein (MVK + MACR) exhibited contributions from both secondary photooxidation of isoprene and direct emissions from traffic. The C2H6:CH4 demonstrated potential influence of oil and gas activities in San Antonio. Moreover, the high O3 days during the campaign were in the NOx-limited O3 formation regime and were preceded by evening peaks in select VOCs, NOx and CO. Overall, quantification of the concentration and trends of VOCs and trace gases in a major city in Texas offers vital information for general air quality management and supports strategies for reducing O3 pollution. The SAFS campaign VOC results will also add to the growing body of literature on urban sources and concentrations of VOCs in major urban areas.
Display omitted
•PMF revealed three VOC factors for San Antonio: biogenic, aged urban mixed source and acetone.•High concentrations of acetone and acetaldehyde at both sites indicate high contribution of regional, oxidized VOCs.•Methane to ethane ratios reveal periods of oil and natural gas influence on San Antonio.•High O3 episode occurs from the combination of northern continental airmass, high actinic flux and high nighttime O3 precursors (VOCs and NOx) on the preceding day.
•Smart thermostat data are used to perform FDD for residential air conditioners.•The FDD method is based on two modified Mann-Kendall tests for trend detection.•Historical trend detection and ...real-time monitoring are adopted as FDD strategies.•The hourly and daily analysis can both detect gradual capacity degradation faults.•The method is verified by systems with refrigerant leaks in actual, occupied homes.
Predictive maintenance through fault detection and diagnosis (FDD) is an effective approach to correct soft faults in residential air conditioners before complete failure. In particular, gradual degradation of heating or cooling capacity is the most common soft fault often caused by refrigerant leakage and goes largely unnoticed by occupants. Traditional FDD methods rely on extracting features from sensor measurements of the refrigeration cycle and need labeled fault-free or faulty data to establish models and rules. These methods are commonly used for large commercial systems. For residential systems, however, installing additional sensors in the refrigeration cycle and collecting labeled data from lab experiments are cost-prohibitive for manufactures. In contrast, smart thermostats are widely adopted by residential homeowners with data streamed to the cloud, enabling powerful FDD methods with limited sensor information. This paper presents two methods, namely the hourly and daily analysis, for extracting key data features from unlabeled smart thermostat data and then applying modified Mann-Kendall statistical tests to identify significant trends in cooling capacity. The effectiveness of these two methods are first evaluated by simulated data. After that, they are applied to approximately 10,000 residential air conditioners for historical trend detection and real-time condition monitoring, with case studies selected from a few verified faulty systems to validate the approach. The methods would allow technicians to identify and prioritize residential systems with gradual degradation for repair prior to catastrophic failure.
Abstract
We present the discovery and studies of the helium-rich, fast-evolving supernova (SN) 2021agco at a distance of ∼40 Mpc. Its early-time flux is found to rise from half peak to the peak of ...−16.06 ± 0.42 mag in the
r
band within
2.4
−
1.0
+
1.5
days, and the post-peak light curves also decline at a much faster pace relative to normal stripped-envelope supernovae (SNe) of Type Ib/Ic. The early-time spectrum of SN 2021agco (
t
≈ 1.0 days after the peak) is characterized by a featureless blue continuum superimposed with a weak emission line of ionized C
iii
, and the subsequent spectra show prominent He
i
lines. Both the photometric and spectroscopic evolution show close resemblances to SN 2019dge, which is believed to have an extremely stripped progenitor. We reproduce the multicolor light curves of SN 2021agco with a model combining shock-cooling emission with
56
Ni decay. The best-fit results give an ejecta mass of ≈0.3
M
⊙
and a synthesized nickel mass of ≈2.2 × 10
−2
M
⊙
. The progenitor is estimated to have an envelope radius of
R
env
≈ 80
R
⊙
and a mass of
M
env
≈ 0.10
M
⊙
. All these suggest that SN 2021agco can be categorized as an ultra-stripped SN Ib, representing the closest object of this rare subtype. This SN is found to explode in the disk of a Sab-type galaxy with an age of ∼10.0 Gyr and low star-forming activity. Compared to normal SNe Ib/c, the host galaxies of SN 2021agco and other ultra-stripped SNe tend to have relatively lower metallicity, which complicates the properties of their progenitor populations.