Search

Reliable methods are always greatly desired for the practice of food inspection. Currently, most food inspection techniques are mainly dependent on the identification of special components, which neglect the combination effects of different components and often lead to biased results. By using Chinese liquors as an example, we developed a new food identification method based on the combination of machine learning with GC × GC/TOF-MS. The sample preparation methods SPME and LLE were compared and optimized for producing repeatable and high-quality data. Then, two machine learning algorithms were tried, and the support vector machine (SVM) algorithm was finally chosen for its better performance. It is shown that the method performs well in identifying both the geographical origins and flavor types of Chinese liquors, with high accuracies of 91.86% and 97.67%, respectively. It is also reasonable to propose that combining machine learning with advanced chromatography could be used for other foods with complex components.

This document discusses the rapid development of Artificial Intelligence (AI) and its bioinspired applications. It highlights the benefits of bioinspired AI, such as increased accuracy in image and speech processing, reduced cost and energy usage through edge devices, and enhanced bio-signal quality. However, it also acknowledges the challenges posed by improper AI utilization, such as the generation of fake news and security issues. The document calls for research papers on bioinspired AI applications to explore its potential and address these challenges. It includes examples of research papers that utilize deep reinforcement learning for robot task sequencing, propose a real-time multi-surveillance pedestrian target detection model, develop an intelligent breast mass classification approach, and introduce a bio-inspired object detection algorithm for remote sensing images. The document concludes by emphasizing the importance of biomimetic artificial intelligence in various fields and promoting further research in this area. [Extracted from the article]

The volume of residential travel with different purposes follows relatively stable patterns in a specific period and state; therefore, it can reflect the operating status of urban traffic and even indicate urban vitality. Recent research has focused on changes in the spatiotemporal characteristics of urban mobility affected by the pandemic but has rarely examined the impact of COVID-19 on the travel conditions and psychological needs of residents. To quantitatively assess travel characteristics during COVID-19, this paper proposed a method by which to determine the purpose of residential travel by combining urban functional areas (UFAs) based on machine learning. Then, the residential travel structure, which includes origin–destination (OD) points, residential travel flow, and the proportion of flows for different purposes, was established. Based on taxi trajectory data obtained during the epidemic in Nantong, China, the case study explores changes in travel flow characteristics under the framework of the residential travel structure. Through comparison of the number and spatial distribution of OD points in the residential travel structure, it is found that residential travel hotspots decreased significantly. The ratios of commuting and medical travel increased from 43.8% to 45.7% and 7.1% to 8.1%, respectively. Conversely, the ratios of other travel types all decreased sharply. Moreover, under Maslow's hierarchy of needs model, further insights into the impacts of COVID-19 on changes in residential psychological needs are discussed in this paper. This work can provide a reference for decision makers to cope with the change in urban traffic during a public health emergency, which is beneficial to the sustainable healthy development of cities. [ABSTRACT FROM AUTHOR]

Designing a product service system begins with understanding customer voices. Compared to the traditional methods such as survey, interview, customer review represents a particular kind of big data that contain rich information that is useful for the design of product service system. This paper presents a new framework that integrates a variety of artificial intelligence and machine learning techniques. All proposed operations of the framework can be realized based on the Google Cloud Platform. A case study is conducted to showcase the practical applicability of some key operations such as opinion mining. More than 40,000 customer reviews about the product Kindle White E-reader were analyzed. [ABSTRACT FROM AUTHOR]

Machine part sorting is important and monotonous in smart factory. In this paper, an auto-sorting system is proposed based on the deep learning method. In the proposed system, an industrial objection detection network combined with a robotic arm controlling system is designed to automatically and efficiently complete machine part sorting. Region-based full convolutional network (R-FCN) is applied for locating and recognizing different types of images of industrial object models. After comparison and simulation analysis, it illustrated that the R-FCN model trained with enough labeled data can efficiently and accurately recognize the object from the images captured by visual sensors. Furthermore, with enough data, the network can be robust to view angle rotation both vertically and horizontally, and a small part of overlapping of object will not mislead the judgment of the network in most situations. The case study results illustrate that the position and type of objects can be successfully detected. The code will be available publicly at https://github.com/tianwangbuaa/. [ABSTRACT FROM AUTHOR]

Over the past few years, a few experimental failure data of composites have been collected. It would be of interest to leverage the existing data to improve the prediction of failure criteria. In this paper, we developed a framework that combines sparse regression with compressed sensing to discover failure criteria of composites from experimental data, which leveraging advances in sparsity techniques and machine learning. This framework does not need Bigdata to train the model and is remarkably robust to the noised data, which satisfies the constraints of the current failure data. To test the performance of the proposed method, we collected the experimental data from the first Worldwide Failure Exercise (WWFE I) and fed it to the proposed method. To satisfy the engineering design needs, we proposed an optimization approach to enforce a constraint to the discovered failure criterion to yield a conservative model. Three examples were presented to demonstrate the proposed framework. The result shows that the proposed framework can identify the most important features and the discovered failure criterion match the experiment result well. Besides, with the enforced constraint, the proposed method can yield a conservative failure criterion. [ABSTRACT FROM AUTHOR]

Due to the country's rapid economic growth, the problem of air pollution in China is becoming increasingly serious. In order to achieve a win-win situation for the environment and urban development, the government has issued many policies to strengthen environmental protection. PM2.5 is the primary particulate matter in air pollution, so an accurate estimation of PM2.5 distribution is of great significance. Although previous studies have attempted to retrieve PM2.5 using geostatistical or aerosol remote sensing retrieval methods, the current rough resolution and accuracy remain as limitations of such methods. This paper proposes a fine-grained spatiotemporal PM2.5 retrieval method that comprehensively considers various datasets, such as Landsat 8 satellite images, ground monitoring station data, and socio-economic data, to explore the applicability of different machine learning algorithms in PM2.5 retrieval. Six typical algorithms were used to train the multi-dimensional elements in a series of experiments. The characteristics of retrieval accuracy in different scenarios were clarified mainly according to the validation index, R2. The random forest algorithm was shown to have the best numerical and PM2.5-based air-quality-category accuracy, with a cross-validated R2 of 0.86 and a category retrieval accuracy of 0.83, while both maintained excellent retrieval accuracy and achieved a high spatiotemporal resolution. Based on this retrieval model, we evaluated the PM2.5 distribution characteristics and hourly variation in the sample area, as well as the functions of different input variables in the model. The PM2.5 retrieval method proposed in this paper provides a new model for fine-grained PM2.5 concentration estimation to determine the distribution laws of air pollutants and thereby specify more effective measures to realize the high-quality development of the city. [ABSTRACT FROM AUTHOR]

The rapid growth of urbanization and population has aggravated the urban heat island (UHI) effect in urban agglomerations. However, because scholars have so far focused mainly on the magnitude of the UHI effect, there is still a lack of research on the quantitative evaluation of the relationship between urban expansion and the degree of the UHI effect from the urban agglomeration perspective. This paper analyzed the spatiotemporal characteristics and the interactive mechanism of the surface urban heat island footprint (SUHI FP) in the Yangtze River Delta urban agglomeration (YRDUA). The summer footprints (FPs) of 27 cities were extracted using a logistics model, and the temporal trend was estimated by a standard deviation ellipse (SDE). Furthermore, the authors used the classical machine-learning k-means algorithm to cluster the temperature attenuation curves to reveal development patterns in different cities. The results showed that the degree of FP expansion during the daytime was more apparent than at night, the area of urban growth positively correlated with a city's population level, and from 2005 to 2018 (the period of the study), the spatial evolution for all cities showed an overall trend from east to west. These cities were divided roughly into three development patterns by clustering their 2018 temperature attenuation curves. These findings can provide a scientific basis for formulating effective land-use policies by giving a deeper understanding of the spatiotemporal changes in the SUHI FPs and their relationship with land cover in the YRDUA. [ABSTRACT FROM AUTHOR]

Urban functional area (UFA) recognition is one of the most important strategies for achieving sustainable city development. As remote-sensing and social-sensing data sources have increasingly become available, UFA recognition has received a significant amount of attention. Research on UFA recognition that uses a single dataset suffers from a low update frequency or low spatial resolution, while data fusion-based methods are limited in efficiency and accuracy. This paper proposes an integrated model to identify UFA using satellite images and taxi global positioning system (GPS) trajectories in four steps. First, blocks were generated as spatial units in the study area, and the spatiotemporal information entropy of the taxi GPS trajectory (STET) for each block was calculated. Second, a 24-hour time-frequency series was formed based on the pick-up and drop-off points extracted from taxi trajectories and used as the interpretation indicator of the blocks. The K-Means++ and k-Nearest Neighbor (kNN) algorithm were used to identify their social functions. Third, a multilabel classification method based on the residual neural network (MLC-ResNets) and "You Only Look Once" (YOLO) target detection algorithms were used to identify the features of the typical and atypical spatial textures, respectively, of the satellite images in the blocks. The confidence scores of the features of the blocks were categorized by the decision tree algorithm. Fourth, to find the best way to integrate the two sub-models for UFA identification, the 10-fold cross-validation method based on stratified random sampling was applied to determine the most optimal STET thresholds. The results showed that the average accuracy reached 82.0%, with an average kappa of 73.5%—significant improvements over most existing studies. This paper provides new insights into how the advantages of satellite images and taxi trajectories in UFA identification can be fully exploited to support sustainable city management. [ABSTRACT FROM AUTHOR]

The social function of areas of interest (AOIs) is crucial to the identification of urban functional zoning and land use classification, which has been a hot topic in various fields such as urban planning and smart city fields. Most existing studies on urban functional zoning and land use classification either largely rely on low-frequency remote sensing images, which are constrained to the block level due to their spatial scale limitation, or suffer from low accuracy and high uncertainty when using dynamic data, such as social media and traffic data. This paper proposes an hour-day-spectrum (HDS) approach for generating six types of distribution waveforms of taxi pick-up and drop-off points which serve as interpretation indicators of the social functions of AOIs. To achieve this goal, we first performed fine-grained cleaning of the drop-off points to eliminate the spatial errors caused by taxi drivers. Next, buffer and spatial clustering were integrated to explore the associations between travel behavior and AOIs. Third, the identification of AOI types was made by using the standard HDS method combined with the k-nearest neighbor (KNN) algorithm. Finally, some matching tests were carried out by similarity indexes of a standard HDS and sample HDS, i.e., the Gaussian kernel function and Pearson coefficient, to ensure matching accuracy. The experiment was conducted in the Chongchuan and Gangzha Districts, Nantong, Jiangsu Province, China. By training 50 AOI samples, six types of standard HDS of residential districts, schools, hospitals, and shopping malls were obtained. Then, 108 AOI samples were tested, and the overall accuracy was found to be 90.74%. This approach generates value-added services of the taxi trajectory and provides a continuous update and fine-grained supplementary method for the identification of land use types. In addition, the approach is object-oriented and based on AOIs, and can be combined with image interpretation and other methods to improve the identification effect. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method for dynamically extracting and monitoring the entrances of areas of interest (AOIs). Most AOIs in China, such as buildings and communities, are enclosed by walls and are only accessible via one or more entrances. The entrances are not marked on most maps for route planning and navigation in an accurate way. In this work, the extraction scheme of the entrances is based on taxi trajectory data with a 30 s sampling time interval. After fine-grained data cleaning, the position accuracy of the drop-off points extracted from taxi trajectory data is guaranteed. Next, the location of the entrances is extracted, combining the density-based spatial clustering of applications with noise (DBSCAN) with the boundary of the AOI under the constraint of the road network. Based on the above processing, the dynamic update scheme of the entrance is designed. First, a time series analysis is conducted using the clusters of drop-off points within the adjacent AOI, and then, a relative heat index ( R H I ) is applied to detect the recent access status (closed or open) of the entrances. The results show the average accuracy of the current extraction algorithm is improved by 24.3% over the K-means algorithm, and the R H I can reduce the limitation of map symbols in describing the access status. The proposed scheme can, therefore, help optimize the dynamic visualization of the entry symbols in mobile navigation maps, and facilitate human travel behavior and way-finding, which is of great help to sustainable urban development. [ABSTRACT FROM AUTHOR]

Summary: Limited number of labeled data of surveillance video causes the training of supervised model for pedestrian re‐identification to be a difficult task. Besides, applications of pedestrian re‐identification in pedestrian retrieving and criminal tracking are limited because of the lack of semantic representation. In this paper, a data‐driven pedestrian re‐identification model based on hierarchical semantic representation is proposed, extracting essential features with unsupervised deep learning model and enhancing the semantic representation of features with hierarchical mid‐level 'attributes'. Firstly, CNNs, well‐trained with the training process of CAEs, is used to extract features of horizontal blocks segmented from unlabeled pedestrian images. Then, these features are input into corresponding attribute classifiers to judge whether the pedestrian has the attributes. Lastly, with a table of 'attributes‐classes mapping relations', final result can be calculated. Under the premise of improving the accuracy of attribute classifier, our qualitative results show its clear advantages over the CHUK02, VIPeR, and i‐LIDS data set. Our proposed method is proved to effectively solve the problem of dependency on labeled data and lack of semantic expression, and it also significantly outperforms the state‐of‐the‐art in terms of accuracy and semanteme. [ABSTRACT FROM AUTHOR]

Machine learning models are increasingly used in many engineering fields thanks to the widespread digital data, growing computing power, and advanced algorithms. The most popular machine learning model in recent years is artificial neural networks (ANN). Although many ANN models are used in the constitutive modeling of composite materials, there are still some unsolved issues that hinder the acceptance of ANN models in the practical design and analysis of composite materials and structures. Moreover, the emerging machine learning techniques are posing new opportunities and challenges in the data-based design paradigm. This paper aims to give a state-of-the-art literature review of ANN models in the constitutive modeling of composite materials, focusing on discovering unknown constitutive laws and accelerating multiscale modeling. This review focuses on the general frameworks, benefits, and challenges and opportunities of ANN models to the constitutive modeling of composite materials. Moreover, potential applications of ANN-based constitutive models in composite materials and structures are also discussed. This review is intended to initiate discussion of future research scope and new directions to enable efficient, robust, and accurate data-driven design and analysis of composite materials and structures. • Applications of ANN models in composites constitutive modeling are reviewed. • Challenges of discovering constitutive laws are discussed. • Challenges of accelerating multiscale modeling are summarized. • Potential solutions to the challenges of ANN constitutive models are proposed. • Future opportunities for ANN-based constitutive models are discussed. [ABSTRACT FROM AUTHOR]

• A practical and effective method is presented for energy prediction of machine tool. • Energy consumption features are extracted by using unsupervised deep learning. • Supervised deep learning is used to develop energy prediction model of machine tool. • This method is a generalized way for identifying energy of different machine tools. • The results show that the method could improve the energy prediction performance. Energy prediction of machine tools plays an irreplaceable role in energy planning, management, and conservation in the manufacturing industry. In the era of big machinery data, data-driven energy prediction models of machine tools have achieved remarkable results in the identification of energy consumption patterns and prediction of energy consumption conditions. However, existing data-driven studies towards the energy consumption of machine tools focus on the utilization of handcrafted-feature learning methods, which are inefficient and exhibit poor generalization. Moreover, considering variations in energy consumption characteristics among different machine tools, it is impractical to identify energy consumption features manually for energy model development. Therefore, this paper proposes a novel data-driven energy prediction approach using deep learning algorithms. Here, deep learning is used in an unsupervised manner to extract sensitive energy consumption features from raw machinery data, and in a supervised manner to develop the prediction model between the extracted features and the energy consumption of machine tools. The experiments conducted on a milling machine and a grinding machine are exploited and compared with those conducted in conventional studies. The results show that the proposed method can improve the energy prediction performance from 19.14% to 74.13% for the grinding machine and from 64.89% to 85.61% for the milling machine, and it achieves a better performance than the conventional methods in terms of effectiveness and generalization. [ABSTRACT FROM AUTHOR]