Search

Background: Cytoreductive surgery (CRS) combined with hyperthermic intraperitoneal chemotherapy (HIPEC) is a major treatment of colorectal peritoneal carcinomatosis (CPC). The aim was to determine the disease-free survival (DFS) and overall survival (OS) of patients undergoing CRS–HIPEC for CPC and factors associated with long-term survival (LTS). Methods: consecutive CPC patients who underwent CRS–HIPEC at a HIPEC center between 2007 and 2021 were included. Actual survival was calculated, and Cox proportional hazards models were used to identify factors associated with OS, DFS and LTS. Results: there were 125 patients with CPC who underwent primary CRS–HIPEC, with mean age of 54.5 years. Median follow-up was 31 months. Average intraoperative PCI was 11, and complete cytoreduction (CC-0) was achieved in 96.8%. Median OS was 41.6 months (6–196). The 2-year and 5-year OS were 68% and 24.8%, respectively, and the 2-year DFS was 28.8%. Factors associated with worse OS included pre-HIPEC systemic therapy, synchronous extraperitoneal metastasis, and PCI ≥ 20 (p < 0.05). Progression prior to CRS–HIPEC was associated with worse DFS (p < 0.05). Lower PCI, fewer complications, lower recurrence and longer DFS were associated with LTS (p < 0.05). Conclusion: CRS and HIPEC improve OS in CPC patients but they have high disease recurrence. Outcomes depend on preoperative therapy response, extraperitoneal metastasis, and peritoneal disease burden.

Ratio-scaled VO2 is the widely used method for quantifying running economy (RE). However, this method should be criticized due to its theoretical defect and curvilinear relationship indicated by the allometric scaling, although no consensus has been achieved on the generally accepted exponent b value of body weight. Therefore, this study aimed to provide a quantitative synthesis of the reported exponents used to scale VO2 to body weight. Six electronic databases were searched based on related terms. Inclusion criteria involved human cardiopulmonary testing data, derived exponents, and reported precision statistics. The random-effects model was applied to statistically analyze exponent b. Subgroup and meta-regression analyses were conducted to explore the potential factors contributing to variation in b values. The probability of the true exponent being below 1 in future studies was calculated. The estimated b values were all below 1 and aligned with the 3/4 power law, except for the 95 % prediction interval of the estimated fat-free body weight exponent b. A publication bias and a slightly greater I2 and τ statistic were also observed in the fat-free body weight study cohort. The estimated probabilities of the true body weight exponent, full body weight exponent, and fat-free body weight exponent being lower than 1 were 93.8 % (likely), 95.1 % (very likely), and 94.5 % (likely) respectively. ‘Sex difference’, ‘age category’, ‘sporting background’, and ‘testing modality’ were four potential but critical variables that impacted exponent b. Overall, allometric-scaled RE should be measured by full body weight with exponent b raised to 3/4.

Various assessments have contributed to inconsistent findings regarding the correlation between core stability and vertical jumps. Therefore, this study aimed to re-examine this correlation based on novel core stability assessments. Twenty-one recreationally active male college students (age, 21.7 ± 2.1 years; stature, 174.9 ± 6.7 cm; body mass, 67.7 ± 7.8 kg; leg length, 88.9 ± 4.8 cm; arm length, 87.8 ± 4.0 cm) participated in this experiment. Core stability was divided into static and dynamic core stabilities, with the static core stability measured using the Eight-Level Prone Bridge and Five-Level Side Bridge tests and the dynamic core stability measured using the Y Balance Test (YBT). These tests comprehensively evaluate core stability as it is defined. Kinematic and kinetic data on vertical jumps were collected to provide process information beyond the outcome performance. Subsequently, these data were correlated with core stability for a deeper insight into the relationship between core stability and the process and outcome performance of vertical jumps. The main results revealed that the Eight-Level Prone Bridge demonstrated moderate to substantial correlations with Δ Fy‾, Δ Iy, ΔDleftkneez, and ΔDleftankley (−0.62 ≤ r ≤ 0.52); the Five-Level Side Bridge exhibited moderate correlations with Δ Fx‾, Δ Fy‾, Δ Ix, Δ Iy, ΔDleftkneez, and ΔDleftankley (−0.52 ≤ r ≤ 0.59); YBT displayed moderate correlations with Fz‾, Fleftz‾, Δ Dleftankley, Δ Drightankley, Δ Dleftanklez, Δ Drightanklez, NΔ Tankley‾, and N Tleftanklez‾ (−0.54 ≤ r ≤ 0.54) during the propulsive phase of vertical jumps. However, no significant correlations were observed between static/dynamic core stability and jumping height. Therefore, individuals with greater core stability should experience improved process performance (better movement quality), although this benefit is ineffective in translating into jumping height improvement due to impaired explosive features. Coaches may consider core stability in training to trigger an improved process performance of the vertical jump when the technique is the key issue to be solved, although future studies are required to verify this further.

Industrial cyber-physical systems (ICPS) are a key element that acts as the backbone infrastructure for realizing innovative systems compliant with the fourth industrial revolution vision and requirements to realize it. Several architectures, such as the reference architectural model industry 4.0 (RAMI4.0), the industrial Internet reference architecture (IIRA), and the smart grid architecture model (SGAM), have been proposed to develop and integrate ICPS, their services, and applications for different domains. In such architectures, the digitization of assets and interconnection to relevant industrial processes and business services is of paramount importance. Different technological solutions have been developed that overwhelmingly focus on the integration of the assets with their cyber counterpart. In this context, the adoption of standards is crucial to enable the compatibility and interoperability of these network-based systems. Since industrial agents are seen as an enabler in realizing ICPS, this work aims to provide insights related to the use and alignment of the recently established IEEE 2660.1 recommended practice to support ICPS developers and engineers to integrate assets in the context of each one of the three referred reference architectures. A critical discussion also points out some noteworthy aspects that emerge when using the IEEE 2660.1 in these architectures and discusses limitations and challenges ahead.

Background and Objectives: The number of lymph nodes found harboring metastasis can be impacted by the extent of harvest. Guidelines recommend 12 lymph nodes for adequate lymphadenectomy to predict long-term oncologic outcomes, yet different cut-offs remain unevaluated. The aim of this review was to determine cut-offs that may predict survival outcomes. Methods: Medline, Embase, and CENTRAL were systematically searched. Articles were included if they compared overall survival (OS) or disease-free survival (DFS) above and below a lymph node harvest cut-off. Studies solely examining rectal cancer or stage-IV disease were excluded. Pairwise meta-analyses using inverse variance random effects were performed. Results: From 2587 citations, 20 studies with 854,359 patients (51.9% female, mean age: 68.9) were included, with 19 studies included in quantitative synthesis. A lymph node harvest cut-off of 12 predicted improved five-year OS (7 studies; OR 1.11, 95% CI 1.08–1.14, p

In this study, we investigate the transferability of the process-property relationship between two Inconel alloys for laser powder bed fusion (LPBF). By developing a Bayesian learning approach, the process-property model of Inconel 625 learned from Inconel 718 demonstrates high accuracy with R of 0.95, which verifies the feasibility of this innovative concept. It is further found that the accuracy of the knowledge transfer model of Inconel 625 is increased if the data on Inconel 625 is more abundant. In this regard, the mean RMSE and MAE on relative density are decreased by about 0.45% and 0.35% when the Inconel 625 dataset size is increased from 15 to 60. In addition, both accuracy and robustness of the Inconel 625 model are increased with transferred knowledge from Inconel 718 regardless of the dataset size of Inconel 625, in which the mean RMSE and MAE are decreased by up to 0.7% and 0.5%, respectively.

To understand the process-response relations among physical forcing and biogeochemical properties of suspended particles (SPs) in the river-dominated northern South China Sea shelf, a 5-day shipboard observation was conducted at a fixed location on the dispersal pathway of the Zhujiang (Pearl) River plume (ZRP) in the summer of 2016. Instrumented moorings were deployed near the sampling site to record the flow and wave fields every 10 minutes. Hydrographic properties were measured hourly to identify different water masses. Water and SPs samples at the surface (3 m) and near the bottom (3 m above the bed) were taken every 3 h for the analyses of nutrients, chlorophyll-a (Chl-a), and particulate organic matter (POM including POC, PN, and δ13CPOC). Meanwhile, the grain-size composition of SPs and seafloor sediment were also analyzed. Results showed that monsoon winds drove cold upwelling and ZRP waters at the surface. Both the upwelling and ZRP regimes contained newly produced marine phytoplankton based on low POC/Chl-a ratio (PC ratio) and enriched δ13CPOC. However, SPs in the ZRP regime were smaller (

Electric Vehicles (EVs) have become a trending topic in recent years due to the industry’s race for competitive pricing as well as environmental awareness. These concerns have led to increased research into the development of both affordable and environmentally friendly EV technology. This paper aims to review EV-related issues beginning with the component level, through the system level, based on intelligent maintenance aspects. The paper will also clarify the existing gaps in practical applications and highlight the potential opportunities related to the current issues in EVs for the EV industry moving forward. More specifically, we will briefly start with an overview of the fast-growing EV market, showing the urgent demand for Prognostics and Health Management (PHM) applications in the EV industry. At the component level, the issues of the major components such as the motor, battery, and charging system in EVs are elaborated, and the relevant PHM research of these components is surveyed to show the development in the era of EV expansion. Moreover, the impact of an increasing number of EVs at the system level such as power distribution systems and power grid are explored to uncover possible research in the future. The combination of existing PHM techniques and robust measurement or feature extraction methods can provide better solutions to address the motor, battery, or transformer issues at the component level. A comprehensive optimization and cybersecurity strategy will help to address the issues of the whole network at a system level. Four aspects of vision in the overall charging network – battery innovation, charging optimization, infrastructure evolution, and sustainability – that cover the demands of research in new battery materials, innovative charging techniques, new architectures of the charging network, and reliable waste treatment mechanisms are outlined. A conclusion is reached in this paper by summarizing the opportunities for future EV research and development.

Tron is a simultaneous move two-player game where a wall is created along the path where two agents move and the agent that crash with the wall first is defeated. Due to the fact that the same action may result in different outcomes (non-stationarity), it is difficult to utilize the basic approach of reinforcement learning. In this paper, we present a modular reinforcement learning (MRL) approach to tackling the game of Tron by decomposing the game into two phases where the first phase is non-stationary and the second phase is stationary. We train two separate models where the first model deals with the non-stationary environments such that two models move simultaneously and affect each other while the second model deals with the stationary environment when two agents are separated by walls created and cannot affect each other. We show that the latter model can be effectively pre-trained using randomly generated stationary environments. We evaluate the performance of our algorithm by comparing with previous algorithms including the state-of-the-art algorithm for the game of Tron (called a1k0n) in different grid sizes. As a result, we demonstrate that the proposed algorithm based on MRL outperforms all previous algorithms on $6 \times 6$ and $8 \times 8$ grids. Although our algorithm shows slightly worse performance on $10 \times 10$ grid than the strongest baseline a1k0n, we show that our algorithm exhibits better scalability in terms of time complexity as the grid size increases than search-based heuristics including the a1k0n.

Sedimentary organic matter (OM) in coastal systems is inherently diverse, often with multiple particulate sources and transport histories. The Taiwan Strait (TS) is a typical shallow conduit region, linking the East and South China Seas. Strong ocean currents, coastal upwellings, distal large rivers, and proximal small mountainous rivers all influence the distribution of OM in the TS. We investigated the covarying patterns in the distribution of gain size classes of sand, silt, and clay; terrestrial-sourced biomarkers (n-C27+29+31 alkanes, n-C26+28+30 fatty acids (FAs), and n-C28+30+32 alkanols); marine-sourced biomarkers (phytoplankton-derived alkenones, brassicasterol, dinosterol, and zooplankton-derived cholesterol) in sea floor sediment; indicator satellite-derived primary production (Chl-a); and water-mass indicator (sea surface temperature, SST). We used an empirical orthogonal/eigen function (EOF) analysis to distinguish the influence of four hypothetical sources that entered the TS through the north, south, west, and east boundaries. Results show that input sources from the south-bound ZMCC (Zhejiang-Fujian Coastal Current) and north-bound SCSWC (South China Sea Warm Current) had the dominant influence on the OM distributions buried in the TS. Input sources via river plumes on lateral boundaries and upwellings in the TS were the secondary factors that affected the sedimentary OM distribution. Within this source-to-sink system of multiple sources and transport processes, silt and clay were the major carriers of the OM signals. Terrestrial biomarkers and primary production (Chl-a) were associated with the two major current systems and river plumes along the edge of TS. Marine biomarkers were associated with upwellings in the interior of the TS. Our finding points out that the physical systems of ocean currents, river plumes, and upwelling not only determine the distributions of biomarkers in the TS but also determine the diversity of OM in the TS.

Accurate battery capacity prediction is important to ensure reliable battery operation and reduce the cost. However, the complex nature of battery degradation and the presence of capacity regeneration phenomenon render the prediction task very challenging. To address this problem, this paper proposes a novel and efficient algorithm to predict the battery capacity trajectory in a multi-cell setting. The proposed method is a new variant of Gaussian process regression (GPR) model, and it utilizes similar trajectories in the historical data to enhance the prediction of desired capacity trajectory. More importantly, the proposed method adds no extra computation cost to the standard GPR. To demonstrate the effectiveness of the proposed method, validation tests on two different battery datasets are implemented in the case studies. The prediction results and the computation cost are carefully benchmarked with cutting-edge GPR approaches for battery capacity prediction.

Abstract Fundamentally, river plume dynamics are controlled by the buoyancy due to river effluent and mixing induced by local forcing such as winds and tides. Rarely the influence of far-field internal waves on the river plume dynamics is documented. Our 5-day fix-point measurements and underway acoustic profiling identified hydrodynamic processes on the dispersal pathway of the Pearl River plume. The river plume dispersal was driven by the SW monsoon winds that induced the intrusion of cold water near the bottom. The river effluent occupied the surface water, creating strong stratification and showing on-offshore variability due to tidal fluctuations. However, intermittent disruptions weakened stratification due to wind mixing and perturbations by nonlinear internal waves (NIWs) from the northern South China Sea (NSCS). During events of NIW encounter, significant drawdowns of the river plume up to 20 m occurred. The EOF deciphers and ranks the contributions of abovementioned processes: (1) the stratification/mixing coupled by wind-driven plume water and NIWs disruptions (81.7%); (2) the variation caused by tidal modulation (6.9%); and (3) the cold water intrusion induced by summer monsoon winds (5.1%). Our findings further improve the understanding of the Pearl River plume dynamics influenced by the NIWs from the NSCS.

The declining trend of the δ13C of tropical corals over the last century was about −0.01‰ year−1, according to global coral records. The decrease was attributable to the significant input of anthropogenic CO2 (13C Suess effect) to the atmosphere. Previous studies of δ13C in corals suggested that the signal of the anthropogenic carbon in the Pacific and Indian Oceans were weaker than that in the Atlantic Ocean. However, biases relating to environments in which corals grew caused concerns. To investigate the anthropogenic carbon signal in the Western Pacific, foraminiferal records in a suite of 13 box cores with good age control were obtained from the continental slope off southwestern Taiwan between 2004 and 2006. δ18O values of planktonic foraminifera (Globigerinoides sacculifer or so-called Trilobatus sacculifer) in collected cores were relatively stable at −2.5‰ to −2‰ in the last century, but foraminiferal δ13C had a gradual secular decline after the 1900s. The decline trend of δ13C began to intensify after the 1960s, and its rate was similar to that observed in the Atlantic. Similar decline trends of δ13C were also found in coral records at regions where the human activity is high (Liuqiu) and low (Dongsha). Our findings indicate that the anthropogenic carbon signal in the Western Pacific was not weaker than that recorded in the Atlantic, and the nearshore sediment can supplement the lack of δ13C records in corals, which are deficient when the environment is not suitable to grow.

Aortoesophageal fistula (AEF) is a rare complication of esophageal interventions. We present a 49-year-old woman who underwent Roux-en-Y gastric bypass with a recurrent gastrojejunal anastomotic leak requiring covered esophageal stent placement. She presented 1 month later with abdominal pain, leukocytosis, and hematemesis. A computed tomography scan demonstrated migration of the esophageal stent with aortic erosion concerning for AEF. She underwent emergent endovascular exclusion of an AEF to the descending thoracic aorta with subsequent esophageal resection and diversion and aortic endograft explant, resection, and homograft repair on postoperative day 6 allowing for staged removal of prosthetic material and maintenance of inline flow.

The advent of the Industry 4.0 initiative has made it so that manufacturing environments are becoming more and more dynamic, connected but also inherently more complex, with additional inter-dependencies, uncertainties and large volumes of data being generated. Recent advances in Industrial Artificial Intelligence have showcased the potential of this technology to assist manufacturers in tackling the challenges associated with this digital transformation of Cyber-Physical Systems, through its data-driven predictive analytics and capacity to assist decision-making in highly complex, non-linear and often multistage environments. However, the industrial adoption of such solutions is still relatively low beyond the experimental pilot stage, as real environments provide unique and difficult challenges for which organizations are still unprepared. The aim of this paper is thus two-fold. First, a systematic review of current Industrial Artificial Intelligence literature is presented, focusing on its application in real manufacturing environments to identify the main enabling technologies and core design principles. Then, a set of key challenges and opportunities to be addressed by future research efforts are formulated along with a conceptual framework to bridge the gap between research in this field and the manufacturing industry, with the goal of promoting industrial adoption through a successful transition towards a digitized and data-driven company-wide culture. This paper is among the first to provide a clear definition and holistic view of Industrial Artificial Intelligence in the Industry 4.0 landscape, identifying and analysing its fundamental building blocks and ongoing trends. Its findings are expected to assist and empower researchers and manufacturers alike to better understand the requirements and steps necessary for a successful transition into Industry 4.0 supported by AI, as well as the challenges that may arise during this process.

Transmission of dengue virus is a complex process with interactions between virus, mosquitoes and humans, influenced by multiple factors simultaneously. Studies have examined the impact of climate or socio-ecological factors on dengue, or only analyzed the individual effects of each single factor on dengue transmission. However, little research has addressed the interactive effects by multiple factors on dengue incidence. This study uses the geographical detector method to investigate the interactive effect of climate and socio-ecological factors on dengue incidence from two perspectives: over a long-time series and during outbreak periods; and surmised on the possibility of dengue outbreaks in the future. Results suggest that the temperature plays a dominant role in the long-time series of dengue transmission, while socio-ecological factors have great explanatory power for dengue outbreaks. The interactive effect of any two factors is greater than the impact of single factor on dengue transmission, and the interactions of pairs of climate and socio-ecological factors have more significant impact on dengue. Increasing temperature and surge in travel could cause dengue outbreaks in the future. Based on these results, three recommendations are offered regarding the prevention of dengue outbreaks: mitigating the urban heat island effect, adjusting the time and frequency of vector control intervention, and providing targeted health education to travelers at the border points. This study hopes to provide meaningful clues and a scientific basis for policymakers regarding effective interventions against dengue transmission, even during outbreaks.

A Cyber-Physical System (CPS)-enabled rehabilitation system framework for enhanced recovery rate in gait training systems is presented in this paper. Recent advancements in sensing and data analytics have paved the way for the transformation of healthcare systems from experience-based to evidence-based. To this end, this paper introduces a CPS-enabled rehabilitation system that collects, processes, and models the data from patient and rehabilitative training machines. This proposed system consists of a set of sensors to collect various physiological data as well as machine parameters. The sensors and data acquisition systems are connected to an edge computing unit that handles the data preprocessing, analytics, and results visualization. Advanced machine learning algorithms are used to analyze data from physiological data, machine parameters, and patients’ metadata to quantify each patient’s recovery progress, devise personalized treatment strategies, adjust machine parameters for optimized performance, and provide feedback regarding patient’s adherence to instructions. Moreover, the accumulation of the knowledge gathered by patients with different conditions can provide a powerful tool for better understanding the human-machine interaction and its impact on patient recovery. Such system can eventually serve as a ‘Virtual Doctor’, providing accurate feedback and personalized treatment strategies for patients.

Understanding and detecting the intended meaning in social media is challenging because social media messages contain varieties of noise and chaos that are irrelevant to the themes of interests. For example, conventional supervised classification approaches would produce inconsistent solutions to detecting and clarifying whether any given Twitter message is really about a wildfire event. Consequently, a renovated workflow was designed and implemented. The workflow consists of four sequential procedures: (1) Apply the latent semantic analysis and cosine similarity calculation to examine the similarity between Twitter messages; (2) Apply Affinity Propagation to identify exemplars of Twitter messages; (3) Apply the cosine similarity calculation again to automatically match the exemplars to known training results, and (4) Apply accumulative exemplars to classify Twitter messages using a support vector machine approach. The overall correction ratio was over 90% when a series of ongoing and historical wildfire events were examined.

The basolateral amygdala (BLA) is critical for reward behaviors via a projection to the nucleus accumbens (NAc). Specifically, BLA-NAc projections are involved in reinforcement learning, reward-seeking, sustained instrumental responding, and risk behaviors. However, it remains unclear whether chronic stress interacts with BLA-NAc projection neurons to result in maladaptive behaviors. Here we take a chemogenetic, projection-specific approach to clarify how NAc-projecting BLA neurons affect avoidance, reward, and feeding behaviors in male mice. Then, we examine whether chemogenetic activation of NAc-projecting BLA neurons attenuates the maladaptive effects of chronic corticosterone (CORT) administration on these behaviors. CORT mimics the behavioral and neural effects of chronic stress exposure. We found a nuanced role of BLA-NAc neurons in mediating reward behaviors. Surprisingly, activation of BLA-NAc projections rescues CORT-induced deficits in the novelty suppressed feeding, a behavior typically associated with avoidance. Activation of BLA-NAc neurons also increases instrumental reward-seeking without affecting free-feeding in chronic CORT mice. Taken together, these data suggest that NAc-projecting BLA neurons are involved in chronic CORT-induced maladaptive reward and motivation behaviors.

Maximum oxygen uptake (VO2max) is a "gold standard" in aerobic capacity assessment, playing a vital role in various fields. However, ratio scaling ([Formula: see text]), the present method used to express relative VO2max, should be suspected due to its theoretical deficiencies. Therefore, the aim of the study was to revise the quantitative relationship between VO2max and body weight (bw). Dimensional analysis was utilized to deduce their theoretical relationship, while linear or nonlinear regression analysis based on four mathematical models (ratio scaling, linear function, simple allometric model and full allometric model) were utilized in statistics analysis to verify the theoretical relationship. Besides, to investigate the effect of ratio scaling on removing body weight, Pearson correlation coefficient was used to analyze the correlation between [Formula: see text] and bw. All the relevant data were collected from published references. Dimensional analysis suggested VO2max be proportional to [Formula: see text]. Statistics analysis displayed that four mathematical expressions were VO2max = 0.047bw (p

Since half a century ago, the number and area of dead zones (dissolved oxygen (DO) < 2 mg L–1 or 30% saturation) in the coastal oceans has increased dramatically. As widely recognized, the increased terrestrial nutrient and organic matter inputs are the two main factors causing the eutrophication of many coastal oceans. Here we show with decadal observed time series data from stations off the Pearl River Estuary and in the northern South China Sea (nSCS) that a strong intrusion into the nSCS of the West Philippine Sea (WPS) seawater in the form of Kuroshio branch occurred during the warm phase of the Pacific Decadal Oscillation (PDO) around 2003–2004 and 2015–2016 (also a strong El Niño event). Consequently, the DO concentration increased but NO3– and PO43– concentrations decreased in the subsurface layers of the nSCS. The WPS seawater was observed to reach the hypoxic area off the Pearl River Estuary in 2003–2004. Likely, due to the oxygen supply carried by the Kuroshio, little hypoxia developed. Yet, anoxic condition developed in the cold phase of PDO or strong La Niña years with weak Kuroshio intrusions.

Agricultural clusters play a powerful role in promoting the agricultural transformation and rejuvenation of rural areas. However, no in-depth exploration has been made on how agricultural clusters form and evolve, especially in the context of China’s long-term small-scale rural economy. The purpose of this article is to reveal the formation process and evolution mechanism of agricultural clusters by case study research. With the knowledge flow as the starting point, this article takes the Vegetable Cluster in Shouguang City of Shandong Province, China as an example to construct a theoretical framework in the three dimensions of points (spin-offs of enterprises or farmers), lines (network-spillovers of various innovation) and planes (the formation of new regional industry spaces) and put forward theoretical hypotheses. It is shown that: (1) The local spin-off of seed farmers is the main path in the transformation of traditional farmers into enterprises. (2) The network-spillover and adoption of innovative knowledge promote the derivation of specialized farmers or enterprises and realize regional agricultural specialization and spatial agglomeration. (3) The formation of the agricultural cluster resulted from the joint effects of spin-off derived from the entrepreneurial spirit of the farmers, network-spillover of various agricultural innovations and spatial integration of the agricultural landscape. The formation of local agricultural innovation systems marks the maturity of an agricultural cluster. This article contribute to the field by studying one source of Alfred Marshall’s knowledge of external economy from the perspective of spin-offs and innovative spillovers, analyzing the agricultural increasing returns to scale neglected by Krugman, and exploring the micro mechanism of farmers’ enterprise-oriented evolution and the formation of agricultural clusters in underdeveloped rural areas. The research results are of profound referential significance for the cultivation of agricultural clusters in developing countries.

Cross-domain fault diagnosis methods have been successfully and widely developed in the past years, which focus on practical industrial scenarios with training and testing data from numerous machinery working regimes. Due to the remarkable effectiveness in such problems, deep learning-based domain adaptation approaches have been attracting increasing attention. However, the existing methods in the literature are generally lower compared to environmental noise and data availability, and it is difficult to achieve promising performance under harsh practical conditions. This paper proposes a new cross-domain fault diagnosis method with enhanced robustness. Noisy labels are introduced to significantly increase the generalization ability of the data-driven model. Promising diagnosis performance can be obtained with strong noise interference in testing, as well as in practical cases with low-quality data. Experiments on two rotating machinery datasets are carried out for validation. The results indicate that the proposed algorithm is well suited to be applied in real industrial environments to achieve promising performance with variations of working conditions.

With the rapid development of urbanization, various urban problems such as air pollution, urban heat islands, poor ventilation, and so on have followed. Ventilation corridors can improve the internal ventilation conditions of a city and can effectively alleviate these urban problems. Taking Kaifeng as an example of a medium-sized city, this study used meteorological analysis and remote sensing (RS) technology and a geographical information system (GIS) to plan ventilation corridors. Through analysis of the thermal environment, the influential factors of the underlying surface (building density, road length, water length, vegetation coverage) and wind environment in Kaifeng, the compensation space and action space, and the comprehensive values of the ventilation potential in each region were determined. The results show that with the use of the single-window algorithm and Landsat8 data, high-resolution ground temperature can be retrieved. Moreover, although the ventilation potential value of Kaifeng in the northern part is better than that in the southern part, the temperature in the north is higher than that in the south. Through comparison and analysis of the location of the low-temperature zone, the air duct opening of the ventilation corridor can be determined and the source areas of three ecological ventilation corridors identified. According to the ventilation corridor air duct opening, the urban underlying surface and the dominant wind direction of Kaifeng city, two ventilation corridors located on the eastern and western sides of Kaifeng city were planned. This urban ventilation corridor planning method, which is based on temperature difference analysis and determination of the source area of the ventilation corridor, can provide a reference for the construction of an ecologically livable city.

Continuous intracranial pressure (ICP) monitoring is a cornerstone of neurocritical care after severe brain injuries such as traumatic brain injury and acts as a biomarker of secondary brain injury. With the rapid development of artificial intelligent (AI) approaches to data analysis, the acquisition, storage, real-time analysis, and interpretation of physiological signal data can bring insights to the field of neurocritical care bioinformatics. We review the existing literature on the quantification and analysis of the ICP waveform and present an integrated framework to incorporate signal processing tools, advanced statistical methods, and machine learning techniques in order to comprehensively understand the ICP signal and its clinical importance. Our goals were to identify the strengths and pitfalls of existing methods for data cleaning, information extraction, and application. In particular, we describe the use of ICP signal analytics to detect intracranial hypertension and to predict both short-term intracranial hypertension and long-term clinical outcome. We provide a well-organized roadmap for future researchers based on existing literature and a computational approach to clinically-relevant biomedical signal data.

With social changes and economic development, human activities inevitably lead to significant changes in land use types. Land use and land cover change (LUCC) leads to a series of changes in energy balance and surface temperature, which has an impact on the regional climate. In this study, MODIS remote sensing data were used to quantify the results of the biological and geophysical effects caused by LUCC in four typical cities in the Yellow River Basin of China: Jinan, Zhengzhou, Lanzhou and Xining. The results showed the following: (1) The latent heat flux and the net radiation of the four cities were both increasing on the whole. The latent heat flux of water and forest was higher, which played a key role in energy consumption on the ground. The net radiation value of the old urban and urban expansion areas was higher, while that of the forest was lower, which indicated that human activities increased the input of surface energy. (2) The differences between latent heat flux and net radiation in areas greatly affected by human activities were much smaller than those in natural areas such as forest and grassland. This indicted that human activities increased the warming trend. In addition, most of the differences between latent heat flux and net radiation in the four cities showed a downward trend. (3) Different cities have different regulating factors for land surface temperature (LST). In Jinan and Zhengzhou, the regulation of LST by net radiation was more obvious, while in Lanzhou and Xining, the regulation of LST by latent heat flux was more pronounced. By comparing LUCC and the forced balance between energy intake and consumption in four typical cities along the Yellow River Basin, this study emphasizes the difference of energy budgets under different land use types, which has important reference value for judging the spatial difference of urban thermal environments.

Convolutional neural network (CNN) has shown excellent performance in hyperspectral image (HSI) classification. However, the structure of the CNN models is complex, requiring many training parameters and floating-point operations (FLOPs). This is often inefficient and results in longer training and testing time. In addition, the label samples of hyperspectral data are limited, and a deep network often causes the over-fitting phenomenon. Hence, a dual-path small convolution (DPSC) module is proposed. It is composed of two 1 × 1 small convolutions with a residual path and a density path. It can effectively extract abstract features from HSI. A dual-path small convolution network (DPSCN) is constructed by stacking DPSC modules. Specifically, the proposed model uses a DPSC module to complete the extraction of spectral and spectral–spatial features successively. It then uses a global average pooling layer at the end of the model to replace the conventional fully connected layer to complete the final classification. In the implemented study, all convolutional layers of the proposed network, except the middle layer, use 1 × 1 small convolution, effectively reduced model parameters and increased the speed of feature extraction processes. DPSCN was compared with several current state-of-the-art models. The results on three benchmark HSI data sets demonstrated that the proposed model is of lower complexity, has stronger generalization ability, and has higher classification efficiency.

The Yellow River is the second largest river in China, and the provinces and cities affected by the Yellow River are called the Yellow River Basin influence area. The relationship between land use and surface thermal effects in the influence area of the Yellow River Basin from 2000 to 2015 was analyzed using MODIS remote sensing data and an energy balance algorithm. The results showed that: (1) net radiation and latent heat flux both increased, and the high value areas were located in the urban expansion areas and natural and seminatural areas, respectively; (2) net surface energy intake showed a upward trend, and increased as the intensity of human influence increased, indicating that human activities had strengthed the positive trend of net surface energy intake and increased the warming effect; (3) net radiation had a greater impact on surface energy intake than latent heat flux, and this relationship was more obvious in land use types that were greatly affected by human activities. This study emphasizes the difference in energy budgets of different land use types under the influence of human activities. It provides a theoretical basis for judging the climate change trend and urban heat island effect in the influence area of the Yellow River Basin from the perspective of biogeophysics.

The high-speed railway (HSR) transportation system in China has been growing rapidly during the past decade. In 2016, the total length of HSR in China has reached to 22,000 kilometers, and there are over 2,000 pairs of high speed trains operating daily. With the advancement of design and manufacturing technologies, the reliability and construction costs have been improved significantly. However, there is still great need for reduction of their operation and maintenance costs. With such incentive, a pilot project has been launched to develop a prognostics and health management system for rolling stock to transform the maintenance paradigm from preventive to predictive maintenance. Considering the high task variety and big data environment in HSR real-time monitoring system, a cyberphysical system (CPS) architecture is proposed as the framework for its PHM system. This paper reviews the needs of predictive maintenance for the HSR system, and then present a concept design of the CPS-enabled smart operation and maintenance system.

The neural network-based hyperspectral images (HSI) classification model has a deep structure, which leads to the increase of training parameters, long training time, and excessive computational cost. The deepened network models are likely to cause the problem of gradient disappearance, which limits further improvement for its classification accuracy. To this end, a residual unit with fewer training parameters were constructed by combining the residual connection with the depth-wise separable convolution. With the increased depth of the network, the number of output channels of each residual unit increases linearly with a small amplitude. The deepened network can continuously extract the spectral and spatial features while building a cone network structure by stacking the residual units. At the end of executing the model, a 1 × 1 convolution layer combined with a global average pooling layer can be used to replace the traditional fully connected layer to complete the classification with reduced parameters needed in the network. Experiments were conducted on three benchmark HSI datasets: Indian Pines, Pavia University, and Kennedy Space Center. The overall classification accuracy was 98.85%, 99.58%, and 99.96% respectively. Compared with other classification methods, the proposed network model guarantees a higher classification accuracy while spending less time on training and testing sample sites.

Human activity events are often recorded with their geographic locations and temporal stamps, which form spatial patterns of the events during individual time periods. Temporal attributes of these events help us understand the evolution of spatial processes over time. A challenge that researchers still face is that existing methods tend to treat all events as the same when evaluating the spatiotemporal pattern of events that have different properties. This article suggests a method for assessing the level of spatiotemporal clustering or spatiotemporal autocorrelation that may exist in a set of human activity events when they are associated with different categorical attributes. This method extends the Voronoi structure from 2D to 3D and integrates a sliding-window model as an approach to spatiotemporal tessellations of a space-time volume defined by a study area and time period. Furthermore, an index was developed to evaluate the partial spatiotemporal clustering level of one of the two event categories against the other category. The proposed method was applied to simulated data and a real-world dataset as a case study. Experimental results show that the method effectively measures the level of spatiotemporal clustering patterns among human activity events of multiple categories. The method can be applied to the analysis of large volumes of human activity events because of its computational efficiency.

Cyber physical systems (CPS) in a manufacturing and automation context can be referred to different manufacturing process, including design, simulation, control, and verification. However, for data analytics, the concept of CPS is relatively new, and a standard methodology is lacking on how to incorporate this type of interface for automation applications. This study discusses a modeling methodology for a cyber physical interface and presents the five levels of information for a cyber physical system, that range from the data connection level to the system configuration level. In order to achieve this awareness and health state of the machine and system, a technical approach that uses adaptive health monitoring algorithms is presented. Lastly, an experimental study on a machine tool ball screw is highlighted, in which a predictive model and a cyber physical interface is developed for this application. The outcomes from this study demonstrate that machine health state awareness is feasible, and the core technologies can aim mechanical systems systematically develop its CPS. This can lead to additional product revenue for the manufacturers, and also a potential competitive edge in the market place.

The prevalence of obesity has increased dramatically in recent decades. It is an important public health issue as it causes many other chronic health conditions, such as hypertension, cardiovascular diseases, and type II diabetics. Obesity affects life expectancy and even the quality of lives. Eventually, it increases social costs in many ways due to increasing costs of health care and workplace absenteeism. Using the spatial patterns of obesity prevalence as an example; we show how different geographic units can reveal different degrees of detail in results of analysis. We used both census tracts and census block groups as units of geographic analysis. In addition; to reveal how different geographic scales may impact on the analytic results; we applied geographically weighted regression to model the relationships between obesity rates (dependent variable) and three independent variables; including education attainment; unemployment rates; and median family income. Though not including an exhaustive list of explanatory variables; this regression model provides an example for revealing the impacts of geographic scales on analysis of health data. With obesity data based on reported heights and weights on driver’s licenses in Summit County, Ohio, we demonstrated that geographically weighted regression reveals varying spatial trends between dependent and independent variables that conventional regression models such as ordinary least squares regression cannot. Most importantly, analyses carried out with different geographic scales do show very different results. With these findings, we suggest that, while possible, smaller geographic units be used to allow better understanding of the studies phenomena.

As an essential process in semiconductor manufacturing, Chemical Mechanical Planarization has been studied in recent decades and the material removal rate has been proved to be a critical performance indicator. Comparing with after-process metrology, virtual metrology shows advantages in production time saving and quick response to the process control. This paper presents an enhanced material removal rate prediction algorithm based on an integrated model and data-driven method. The proposed approach combines the physical mechanism and the influence of nearest neighbors, and extracts relevant features. The features are then input to construct multiple regression models, which are integrated to obtain the final prognosis. This method was evaluated by the PHM 2016 Data Challenge data sets and the result obtained the best mean squared error score among competitors.

Data-driven modeling and fault detection of multi-stage manufacturing processes remain challenging due to the increasing complexity of the manufacturing process, the lack of structural data, data multi-dimensionality, and the additional difficulty when dealing with large data sets. The implementation of add-on sensors and establishing data acquisition, transfer, storage and analysis has the potential to facilitate advanced data modeling techniques. However, besides the associated costs, dealing with high-volume multi-dimensional data sets can be a major challenge. This paper presents a novel methodology for early fault identification of multi-stage manufacturing processes using a statistical approach. The major advantage of the proposed methodology is its reliance on only the product quality measurements and basic product manufacturing records, given the presence of peer sets. This leads to a feasible fault identification solution in a sensor-less environment without investing costly data collection systems. The developed methodology transforms the end-of-process quality measurements to a process performance metric based on a density-based statistical approach and a peer-to-peer comparison of the machines at one stage of the process. This approach allows one to be more proactive and identify the problematic machines that could be affecting product quality. A case study in an actual multi-stage manufacturing process is used to demonstrate the effectiveness of the developed methodology.

This study aims to evaluate the impacts of climate change and technical progress on the wheat yield per unit area from 1970 to 2014 in Henan, the largest agricultural province in China, using an autoregressive distributed lag approach. The bounded F-test for cointegration among the model variables yielded evidence of a long-run relationship among climate change, technical progress, and the wheat yield per unit area. In the long run, agricultural machinery and fertilizer use both had significantly positive impacts on the per unit area wheat yield. A 1% increase in the aggregate quantity of fertilizer use increased the wheat yield by 0.19%. Additionally, a 1% increase in machine use increased the wheat yield by 0.21%. In contrast, precipitation during the wheat growth period (from emergence to maturity, consisting of the period from last October to June) led to a decrease in the wheat yield per unit area. In the short run, the coefficient of the aggregate quantity of fertilizer used was negative. Land size had a significantly positive impact on the per unit area wheat yield in the short run. There was no significant short-run or long-run impact of temperature on the wheat yield per unit area in Henan Province. The results of our analysis suggest that climate change had a weak impact on the wheat yield, while technical progress played an important role in increasing the wheat yield per unit area. The results of this study have implications for national and local agriculture policies under climate change. To design well-targeted agriculture adaptation policies for the future and to reduce the adverse effects of climate change on the wheat yield, climate change and technical progress factors should be considered simultaneously. In addition, adaptive measures associated with technical progress should be given more attention.

The goals of this paper are to 1) examine the current practices of diagnostics, prognostics, and maintenance employed by United States (U.S.) manufacturers to achieve productivity and quality targets and 2) to understand the present level of maintenance technologies and strategies that are being incorporated into these practices. A study is performed to contrast the impact of various industry-specific factors on the effectiveness and profitability of the implementation of prognostics and health management technologies, and maintenance strategies using both surveys and case studies on a sample of U.S. manufacturing firms ranging from small to mid-sized enterprises (SMEs) to large-sized manufacturing enterprises in various industries. The results obtained provide important insights on the different impacts of specific factors on the successful adoption of these technologies between SMEs and large manufacturing enterprises. The varying degrees of success with respect to current maintenance programs highlight the opportunity for larger manufacturers to improve maintenance practices and consider the use of advanced prognostics and health management (PHM) technology. This paper also provides the existing gaps, barriers, future trends, and roadmaps for manufacturing PHM technology and maintenance strategy.

The age of Smart Manufacturing has arrived where more and more organizations are embracing it to innovate and maintain their competitiveness. Smart Manufacturing blends information technology (IT) with operations technology (OT) to enable greater productivity, efficiency, quality, and customization within factory operations. More specifically, emerging and existing factory-floor level technologies (including robotics, machine tools, additive processes, automation, and sensors) are being fused with networking (both wired and wireless) and analysis technologies to generate more timely, accurate, and appropriate communication. This communication directly enables more intelligent sensing, monitoring, and control of the overall manufacturing system, including its constituent processes and sub-systems. Organizations that are adopting a smart manufacturing approach have become more flexible and adaptive to address changing customer demands, integrate new technologies, mitigate supply chain disruptions, and better utilize their human workforce. Prognostics and Health Management (PHM), in the context of Smart Manufacturing, focuses on the technologies and capabilities that enable health monitoring, diagnostics, and prognostics to promote greater intelligence in maintenance and control activities.

As wind energy proliferates in onshore and offshore applications, it has become significantly important to predict wind turbine downtime and maintain operation uptime to ensure maximal yield. Two types of data systems have been widely adopted for monitoring turbine health condition: supervisory control and data acquisition (SCADA) and condition monitoring system (CMS). Provided that research and development have focused on advancing analytical techniques based on these systems independently, an intelligent model that associates information from both systems is necessary and beneficial. In this paper, a systematic framework is designed to integrate CMS and SCADA data and assess drivetrain degradation over its lifecycle. Information reference and advanced feature extraction techniques are employed to procure heterogeneous health indicators. A pattern recognition algorithm is used to model baseline behavior and measure deviation of current behavior, where a Self-organizing Map (SOM) and minimum quantization error (MQE) method is selected to achieve degradation assessment. Eventually, the computation and ranking of component contribution to the detected degradation offers component-level fault localization. When validated and automated by various applications, the approach is able to incorporate diverse data resources and output actionable information to advise predictive maintenance with precise fault information. The approach is validated on a 3 MW offshore turbine, where an incipient fault is detected well before existing system shuts down the unit. A radar chart is used to illustrate the fault localization result.

This paper deals with mobility prediction of LiFeMnPO_4 batteries for an emission-free Electric Vehicle. The data-driven model has been developed based on empirical data from two different road types –highway and local streets –and two different driving modes – aggressive and moderate. Battery State of Charge (SoC) can be predicted on any new roads based on the trained model by selecting the drving mode. In this paper, the performance of Adaptive Recurrent Neural Network (ARNN) and regression is evaluated using two benchmark data sets. The ARNN model at first estimates the speed profile of the new road based on slope and then both slope and speed is going to be used as the input to estimate battery current and SoC. Through comparison it is found that if ARNN system is appropriately trained, it performs with better accuracy than Regression in both two road types and driving modes. The results show that prediction SoC model follows the Columb-counting SoC according to the road slope.

Gearbox is a very complex mechanical system that can generate vibrations from its various elements such as gears, shafts, and bearings. Transmission path effect, signal coupling, and noise contamination can further induce difficulties to the development of a prognostics and health management (PHM) system for a gearbox. This paper introduces a novel information reconstruction approach to clustering and diagnosis of gearbox signals in varying operating conditions. First, vibration signal is transformed from time domain to frequency domain with Fast Fourier Transform (FFT). Then, reconstruction filters are employed to sift the frequency components in FFT spectrum to retain the information of interest. Features are further extracted to calculate the coefficients of the reconstructed energy expression. Then, correlation analysis (CA) and distance measurement (DM) techniques are utilized to cluster signals under diverse shaft speeds and loads. Finally, energy coefficients are used as health indicators for the purpose of fault diagnosis of the rotating elements in the gearbox. The proposed method was used to solve the gearbox problem of the 2009 PHM Conference Data Analysis Competition and won with the best score in both professional and student categories.

A systematic methodology for gearbox health assessment and fault classification is developed and evaluated for 560 data sets of gearbox vibration data provided by the Prognostics and Health Management Society for the 2009 data challenge competition. A comprehensive set of signal processing and feature extraction methods are used to extract over 200 features, including features extracted from the raw time signal, time synchronous signal, wavelet decomposition signal, frequency domain spectrum, envelope spectrum, among others. A regime segmentation approach using the tachometer signal, a spectrum similarity metric, and gear mesh frequency peak information are used to segment the data by gear type, input shaft speed, and braking torque load. A health assessment method that finds the minimum feature vector sum in each regime is used to classify and find the 80 baseline healthy data sets. A fault diagnosis method based on a distance calculation from normal along with specific features correlated to different fault signatures is used to diagnosis specific faults. The fault diagnosis method is evaluated for the diagnosis of a gear tooth breakage, input shaft imbalance, bent shaft, bearing inner race defect, and bad key, and the method could be further extended for other faults as long as a set of features can be correlated with a known fault signature. Future work looks to further refine the distance calculation algorithm for fault diagnosis, as well as further evaluate other signal processing method such as the empirical mode decomposition to see if an improved set of features can be used to improve the fault diagnosis accuracy.

This paper presents a health assessment methodology, as well as specific residual processing and figure of merit algorithms for anemometers in two different configurations. The methodology and algorithms are applied to data sets provided by the Prognostics and Health Management Society 2011 Data Challenge. The two configurations consist of the “paired” data set in which two anemometers are positioned at the same height, and the “shear” data set which includes an array of anemometers at different heights. Various wind speed statistics, wind direction, and ambient temperature information are provided, in which the objective is to classify the anemometer health status during a set of samples from a 5 day period. The proposed health assessment methodology consists of a set of data processing steps that include: data filtering and pre-processing, a residual or difference calculation, and a k-means clustering based figure of merit calculation. The residual processing for the paired data set was performed using a straightforward difference calculation, while the shear data set utilized an additional set of algorithm processing steps to calculate a weighted residual value for each anemometer. The residual processing algorithm for the shear data set used a set of auto-associative neural network models to learn the underlying correlation relationship between the anemometer sensors and to calculate a weighted residual value for each of the anemometer wind speed measurements. A figure of merit value based on the mean value of the smaller of the two clusters for the wind speed residual is used to determine the health status of each anemometer. Overall, the proposed methodology and algorithms show promise, in that the results from this approach resulted in the top score for the PHM 2011 Data Challenge Competition. Using different clustering algorithms or density estimation methods for the figure of merit calculation is being considered for future work.

For implementing data analytic tools in real-world applications, researchers face major challenges such as the complexity of machines or processes, their dynamic operating regimes and the limitations on the availability, sufficiency and quality of the data measured by sensors. The limits on using sensors are often related to the costs associated with them and the inaccessibility of critical locations within machines or processes. Manufacturing processes, as a large group of applications in which data analytics can bring significant value to, are the focus of this study. As the cost of instrumenting the machines in a manufacturing process is significant, an alternative solution which relies solely on product quality measurements is greatly desirable in the manufacturing industry. In this paper, a minimal-sensing framework for machine anomaly detection in multistage manufacturing processes based on product quality measurements is introduced. This framework, which relies on product quality data along with products’ manufacturing routes, allows the detection of variations in the quality of the products and is able to pinpoint the machine which is the cause of anomaly. A moving window is applied to the data, and a statistical metric is extracted by comparing the performance of a machine to its peers. This approach is expanded to work for multistage processes. The proposed method is validated using a dataset from a real-world manufacturing process and additional simulated datasets. Moreover, an alternative approach based on Bayesian Networks is provided and the performance of the two proposed methods is evaluated from an industrial implementation perspective. The results showed that the proposed similarity-based approach was able to successfully identify the root cause of the quality variations and pinpoint the machine that adversely impacted the product quality.

This paper brings up a novel method for detecting induction motor stator winding faults at an early stage. The contribution of the work comes from the delicate handling of motor vibration by applying envelope analysis, which makes it possible to capture electrical short-circuit signature in mechanical signals, even if the magnitude of the fault is fairly incipient. Conventional induction motor condition-based maintenance methods usually involve current and voltage measurements, which could be expensive to collect, and vibration-based analysis is often only capable of detecting the fault when it is already quite significant. In contrast, the solution presented in this study provides a refreshing perspective by applying time synchronous averaging to remove the discrete frequency component, and amplitude demodulation to further enhance the signal with the help of kurtogram. Experimental results on a three-phase induction motor show that the method is also able to distinguish different fault severity levels.

This paper presents an effective health assessment and predictive maintenance technique for industrial assets. The technique and algorithms applied to data sets provided by the Prognostics and Health Management Society 2014 Data Challenge. The data contains usage and part consumption for three years. In short, the usage data contains a parameter that roughly measures asset usage, and the part consumption data includes information regarding part replacement and maintenance actions. The first two years of data are considered as "Training" data and the third year is considered as "Testing" data. The proposed method built on the probability of the failure risk during training dataset. The main objective is to develop a model based on first two years data set (training) and determine the high risk and low risk times of failure for each individual asset for the third year. Training data shows many maintenance activities with 14 different codes. The principle difficulty is to detect the Preventive Maintenance (PM) in the training data. The paper presents the method in three main steps: the first step is to recognize the PM pattern based on time and type of maintenance activity via the training data. The second step is to determine the high-risk time intervals based on PM times by checking the frequency of the failures at specific times between each PM. The third step is to predict the high risk time intervals in the testing data using the information acquired from the training data. The score predicted by this probabilistic risk assessment method won the first place in the PHM Data Challenge Competition.

This paper proposes a combined method of ant-based clustering and cerebellar model articulation controller for performance assessment for a fleet of machines. A novel ant-based clustering algorithm with kernel method is used to cluster machines in a fleet. The algorithm has two features. First, a projection based on kernel principal component analysis replaces random projection to improve the efficiency. Second, the clustering is performed on the feature space after kernel mapping to improve the clustering accuracy. The algorithm can cluster machines in a self-organizing way to achieve the horizontal assessment. The vertical assessment for the single machine based on CMAC is presented. Then, how to combine the vertical and horizontal assessment results is discussed. The outlier mining method to detect abnormal machines based on the clustering results is also proposed. Cluster-based global outlying factor is suggested to measure the outlying degree of abnormal machine. Finally, the case study on axial fans shows that the combined method can give a more comprehensive assessment for fans' performance monitoring.