YOLO-Based Damage Detection with StyleGAN3 Data Augmentation for Parcel Information-Recognition System

Damage to parcels reduces customer satisfactionwith delivery services and increases return-logistics costs.This can be prevented by detecting and addressing the damage before the parcels reach the customer.Consequently,various studies have been conducted on deep learning techniques related to the detection of parcel damage.This study proposes a deep learning-based damage detectionmethod for various types of parcels.Themethod is intended to be part of a parcel information-recognition systemthat identifies the volume and shipping information of parcels,and determines whether they are damaged;this method is intended for use in the actual parcel-transportation process.For this purpose,1)the study acquired image data in an environment simulating the actual parcel-transportation process,and 2)the training dataset was expanded based on StyleGAN3 with adaptive discriminator augmentation.Additionally,3)a preliminary distinction was made between the appearance of parcels and their damage status to enhance the performance of the parcel damage detection model and analyze the causes of parcel damage.Finally,using the dataset constructed based on the proposed method,a damage type detection model was trained,and its mean average precision was confirmed.This model can improve customer satisfaction and reduce return costs for parcel delivery companies.

Shape Analysis of Agricultural Parcels for Land Consolidation Priorities in Tekirdag Province,Turkey

Shape irregularity,a sub-factor of parcel fragmentation is a problem that hinders sustainable agriculture and is solved using land consolidation projects.Determination of the parcel shape degree contributes significantly to spatial prioritization where there is also a high probability of achieving positive effects of consolidation projects.This study aims to determine the shape degree of the agricultural parcels both at singular and rural county scales in Tekirdag Province,Turkey in 2020 by combining the parcel shape index(PSI) with the minimum bounding geometry index(MBG) to improve parcel scores.Hot-spot zones of the highly irregular and near optimum parcels were also determined using Getis-Ord G_(i)^(*) statistic.The parcel degrees were classified into four categories,namely highly irregular,irregular,regular and near optimum.The obtained unweighted scores of the parameters exhibit deviations from the expected values.After weighting by pairwise comparison,the values approached ideal scores.Among 346 740 parcels,53% were highly irregular and irregular and 47% were regular and near optimum shapes after weighting whereas these were 70% and 30%,respectively before weighting.The average parcel degree of 63 rural counties was regular while the average parcel degree of the remaining 264 rural counties was irregular.The combined use of PSI and MBG index improved the correctness of the parcel shape score.It could be suggested to use as a tool in land consolidation prioritization.

高性能并行PIM系统中Parcels通信机制研究

基于Processor-in-Memory(PIM)技术的高性能并行系统具有可扩展性、自适应性、鲁棒性和低功耗等特性.借助于Parcels通信机制,并行PIM系统可以实现消息驱动的计算,重叠计算与通信,降低通信系统对细粒度并行应用的影响,可充分利用PIM的内部带宽和应用局部性.文章对并行PIM系统中采用的Parcels通信机制及其特点、Parcels通信模型,以及Parcels的典型应用系统进行了着重介绍,对存在的问题进行了分析并指出了进一步的研究方向.

On the Development of Meso-Scale Heavy Rain Parcels in China

Heavy rains occur in China frequently, which often bring us floods and serious disasters in the summer half-year. The meso-scale heavy rain parcels (MHRP) in the mid-latitude are usually developed in following cases:I.By the approaching, meeting and / or overlapping of different weather systems, when two or more different rainfall systems are getting to conjugate, some MHRPs could be developed, such as: 1) a new cold/warm front or squall line approaches an old front or squall, even when the old one is somewhat decrepit; 2) at the places where two or more synoptic systems with different characteristics are meeting together, such as the meeting of tropical cyclone with the cold airs coming from the mid- and / or high-latitudes, or the low latitude vortex meeting with the westerly trough; 3) at the intersections of some different weather systems, such as the intersection of drylines, squall lines or fronts moving from different directions; and 4) by the overlapping of rainfall parcels produced continuously from a meso-generation centre.II.Resonance Effect and Tibetan Plateau Influence are two reasons why high frequency of heavy and torrential rains arround the meiyu front is discussed also.

Abandoned land identification in karst mountain area based on time series SAR characteristics at geo-parcels scale

Mapping abandoned land is very important for accurate agricultural management.However,in karst mountainous areas,continuous high-resolution optical images are difficult to obtain in rainy weather,and the land is fragmented,which poses a great challenge for remote sensing monitoring of agriculture activities.In this study,a new method for identifying abandoned land is proposed:firstly,a few Google Earth images are used to transform arable land into accurate vectorized geo-parcels;secondly,a time-series data set was constructed using Sentinel-1A Alpha parameters for 2020 on each farmland geoparcel;thirdly,the semi-variation function(SVF)was used to analyze the spatial-temporal characteristics,then identify abandoned land.The results show:(1)On the basis of accurate spatial information and boundary of farmland land,the SAR time-series dataset reflects the structure and time-series response.abandoned land with an accuracy of 80.25%.The problem of remote sensing monitoring in rainy regions and complex surface areas is well-resolved.(2)The spatial heterogeneity of abandoned land is more obvious than that of cultivated land within geoparcels.The step size for significant changes in the SVF of abandoned land is shorter than that of cultivated land.(3)The SVF time sequence curve presented a strong peak feature when farmland was abandoned.This reveals that the internal spatial structure of abandoned land is more disordered and complex.It showed that time-series variations of spatial structure within cultivated land have broader applications in remote sensing monitoring of agriculture in complex imaging environments.

Building a Geodatabase for Parcel and Cadaster Mapping and Add-Ins Development: A Case Study for Defense Housing Authority (DHA), Lahore, Pakistan

This paper presents a systematic view of most up-to-date tools, technologies and techniques which is appropriate not only for effective decision making, but also helpful for competent administration to provide efficient resolution for spatial troubles of Khasra and Parcel management. Different Data collection techniques have been applied on different data sources. Worldview II of 0.5 resolution image, scanned Master Plan and Cadastral/Khasra Maps was used for development of geodatabase for spatial and non-spatial entities using ArcGIS 10.2. Multiple processing on Satellite Imagery using ERDAS Imagine was performed like Image enhancement, Mosaicking and Color Balancing, Image Geo-referencing and Raster Cataloging. Development of Customize Graphical User Interface (GUI) for DHA’s officials and administrator makes efficient decision in society matters. This is the first spatial GUI, for DHA to plan and maintain society’s activities efficiently, in the form of ArcMap Add-Ins. These Add-Ins are written in C#.Net using ArcObjects APIs within MSVS 2012.

An Analysis of the Air Parcel Trajectories of Long-Range Transport at Shanghai

1.INTRODUCTION Acid rain observations show that acid cloud water in Shanghai region appears not only

Parcels Delivered in 2019 to Reach 60 Billion

The State Post Bureau(SPB)predicts that the volume of parcels delivered this year will reach 60 billion,a 20 percent year-onyear growth.

Alarm on Invasion of Harmful Organisms Via Postal Parcels

In recent years,with the rapid development of cross-border e-commerce,international postal parcels have been increasing sharply,thus giving rise to a new way for alien biological invasion.According to the"animal and plant quarantine information platform"of the General Adminis-tration of Customs,postal inspection system intercepted a total of 4975 harmful organisms nationwide.There were 219 quarantine organisms,including 142 insects,27 weeds,12 nematodes,29 fungi,1 bacterium and 8 viruses.Insects accounted for 64.84%of the quarantine organisms,among which Hypothenemus hampei had the highest interception frequency.Up to 71.36%of those harmful organisms were from seedlings,yet47.31%organisms came from products exported from India.These analyses indicate the direction of future portal quarantine work and lay a theoret-ical foundation for better guarding the biological security.

A Uniform Parcel Delivery System Based on IoT

Nowadays, many different kinds of delivery companies transport their own kinds of parcels and offer their own services, which have caused a lot waste of resources. In addition, the volume of parcels in all cities that need to be delivered has been grown dramatically. To cope with these problems, a uniform parcel delivery system in a smart city which can offer service to all kinds of customers in the city including manufactures, department stores, restaurants, individual people and so forth was designed. This system uses IoT (Internet of Things) and RFID technology, combining computer network technology, wireless communication and cloud computing. With this system, the whole package delivery process including classification of packages, vehicle scheduling, path planning, transportation monitoring can be intellectualized as well as managed automatically, and the use of both material resources and manpower resources can be reduced accordingly.

Connectivity-based Cortical Parcellation via Contrastive Learning on Spatial-Graph Convolution

Objective.Objective of this work is the development and evaluation of a cortical parcellation framework based on tractography-derived brain structural connectivity.Impact Statement.The proposed framework utilizes novel spatial-graph representation learning methods for solving the task of cortical parcellation,an important medical image analysis and neuroscientific problem.Introduction.The concept of“connectional fingerprint”has motivated many investigations on the connectivity-based cortical parcellation,especially with the technical advancement of diffusion imaging.Previous studies on multiple brain regions have been conducted with promising results.However,performance and applicability of these models are limited by the relatively simple computational scheme and the lack of effective representation of brain imaging data.Methods.We propose the Spatial-graph Convolution Parcellation(SGCP)framework,a two-stage deep learning-based modeling for the graph representation brain imaging.In the first stage,SGCP learns an effective embedding of the input data through a self-supervised contrastive learning scheme with the backbone encoder of a spatial-graph convolution network.In the second stage,SGCP learns a supervised classifier to perform voxel-wise classification for parcellating the desired brain region.Results.SGCP is evaluated on the parcellation task for 5 brain regions in a 15-subject DWI dataset.Performance comparisons between SGCP,traditional parcellation methods,and other deep learning-based methods show that SGCP can achieve superior performance in all the cases.Conclusion.Consistent good performance of the proposed SGCP framework indicates its potential to be used as a general solution for investigating the regional/subregional composition of human brain based on one or more connectivity measurements.

Summary of Animal and Plant Quarantine Objects in the Imported Parcels and X-ray Pattern Identification

The quantity of the imported parcels in China has increased rapidly,becoming an important means for criminals to hide the prohibited animal and plant quarantine objects.The x-ray applied to the port of post inspection can speed up inspection and better protect the ecological safety of China by mastering its method of judging animal and plant quarantine objects.

An end‐to‐end infant brain parcellation pipeline

Objective Accurate infant brain parcellation is crucial for understanding early brain development;however,it is challenging due to the inherent low tissue contrast,high noise,and severe partial volume effects in infant magnetic resonance images(MRIs).The aim of this study was to develop an end-to-end pipeline that enabled accurate parcellation of infant brain MRIs.Methods We proposed an end-to-end pipeline that employs a two-stage global-to-local approach for accurate parcellation of infant brain MRIs.Specifically,in the global regions of interest(ROIs)localization stage,a combination of transformer and convolution operations was employed to capture both global spatial features and fine texture features,enabling an approximate localization of the ROIs across the whole brain.In the local ROIs refinement stage,leveraging the position priors from the first stage along with the raw MRIs,the boundaries of the ROIs are refined for a more accurate parcellation.Results We utilized the Dice ratio to evaluate the accuracy of parcellation results.Results on 263 subjects from National Database for Autism Research(NDAR),Baby Connectome Project(BCP)and Cross-site datasets demonstrated the better accuracy and robustness of our method than other competing methods.Conclusion Our end-to-end pipeline may be capable of accurately parcellating 6-month-old infant brain MRIs.

A Study of the Development of the World Postal Parcel Service

The paper makes an analysis of the market demands, market competition,collaboration and the current development of the postal parcel service, and discusses some factorscounteracting the development of the postal parcel service. Furthermore, this paper gives anorientation to the future development of the postal parcel service through a comprehensive researchon the developing trend of the postal parcel service in some countries.

Joint Multi-modal Parcellation of the Human Striatum:Functions and Clinical Relevance

The human striatum is essential for both lowand high-level functions and has been implicated in the pathophysiology of various prevalent disorders,including Parkinson's disease(PD)and schizophrenia(SCZ).It is known to consist of structurally and functionally divergent subdivisions.However,previous parcellations are based on a single neuroimaging modality,leaving the extent of the multi-modal organization of the striatum unknown.Here,we investigated the organization of the striatum across three modalities—resting-state functional connectivity,probabilistic diffusion tractography,and structural covariance—to provide a holistic convergent view of its structure and function.We found convergent clusters in the dorsal,dorsolateral,rostral,ventral,and caudal striatum.Functional characterization revealed the anterior striatum to be mainly associated with cognitive and emotional functions,while the caudal striatum was related to action execution.Interestingly,significant structural atrophy in the rostral and ventral striatum was common to both PD and SCZ,but atrophy in the dorsolateral striatum was specifically attributable to PD.Our study revealed a cross-modal convergent organization of the striatum,representing a fundamental topographical model that can be useful for investigating structural and functional variability in aging and in clinical conditions.

Mathematical analysis of urban land use change in Xi'an city wall area by using parcel-level data

Nowadays, more and more interdisciplinary approaches have been applied in urban planning, such as computer, mathematics and geography. However, the sophisticated mathematical methods such as transition matrix, joint-count, Bayes rules and Markov chain have not been deeply utilized in urban land use analysis. Furthermore, the newborn parcel-level urban land use data method has just been tested in a few cases and has not yet been adopted in ancient city area. Based on the above, this paper uses a series of mathematical methods and parcel-level urban land use data for quantification study in the Xi'an city wall area. Digitizing the maps compiled in 1935, 1963, 1995, 2007 and 2017 of the study area leads to the acquisition of the parcel-level urban land use data concerning the following four categories: Residential(R), Service(S), Culture(C) and Other(O). Then five parcel maps of different times will be built up. Through a series of mathematical analysis, the result shows that urban land use change in this area has three kinds of characteristics. For urban land use change speed, the period between 1995 and 2007 is the fastest while the period from 1963 to 1995 is the slowest. For the transition of urban land use, R and S are the main categories, and transition from R to S is the dominant change. Besides, dominated neighbors have positive effects on their transition. C is consistently increasing and has a clustering distribution. For the influence of other factors such as environment and policy, C is a special category that has the highest sensitivity to policies. The result clearly explains the data from the research into the evolution of urban land use in the study area work as a powerful support for land use planning and policy. The mathematical methods would provide a new perspective for the study in ancient Chinese cities.

Feature-reduction and semi-simulated data in functional connectivity-based cortical parcellation

Recently, restingstate functional magnetic resonance imaging has been used to parcellate the brain into functionally distinct regions based on the information available in functional connectivity maps. However, brain voxels are not independent units and adjacent voxels are always highly correlated, so functional connectivity maps contain redundant information, which not only impairs the computational efficiency during clustering, but also reduces the accuracy of clustering results. The aim of this study was to propose featurereduction approaches to reduce the redundancy and to develop semisimulated data with defined ground truth to evaluate these approaches. We proposed a featurereduction approach based on the Affinity Propagation Algorithm （APA） and compared it with the classic feature reduction approach based on Principal Component Analysis （PCA）. We tested the two approaches to the parcellation of both semisimulated and real seed regions using the Kmeans algorithm and designed two experiments to evaluate their noise resistance. We found that all functional connectivitymaps （with/without feature reduction） provided correct information for the parcellation of the semi simulated seed region and the computational efficiency was greatly improved by both feature reduction approaches. Meanwhile, the APAbased featurereduction approach outperformed the PCA based approach in noiseresistance. The results suggested that functional connectivity maps can provide correct information for cortical parcellation, and featurereduction does not significantly change the information. Considering the improvement in computational efficiency and the noiseresistance, featurereduction of functional connectivity maps before cortical parcellation is both feasible and necessary.

Automating land parcel classification for neighborhood-scale urban analysis

Homeowners’Associations(HOAs)dictate landscape structure and management through legally enforceable land covenants at the neighborhood scale in the USA.Determining the location and spatial extent of HOAs is critical for examining its influence.However,such analysis is confounded by the lack of spatial data at the appropriate unit for such analysis.The purpose of this paper is to develop and realize an open source implementation to automate land parcel classification,which is an initial step towards the goal of determining the impact of HOAs on urban land management.Using Maricopa County,Arizona as a testbed,we found that parcel merging processes reduce the number of subdivisions from 26,042 to 17,269,such that boundaries better align with neighborhood units to which rule sets like land covenants apply.Moreover,after an initial training period,this process was completed in just over 7 hours.This research is an important first step in enabling a number of analysis including determining the location and spatial extent of HOAs regionally and,eventually,nationally and determining proposed links between HOAs and land management outcomes.

微观地块服务设施可达性评价及路网优化影响分析

针对现有的服务设施可达性评价方法分析尺度大、数据精度低且无法依赖网络地图应用程序编程接口(Application Programming Interface,API)评价路网规划方案等问题,提出一种可用于规划方案评价的微观地块综合服务设施可达性评价方法.依据土地利用性质将研究区域划分为565个微观地块,利用实际居住建筑物空间分布测算各地块的人口分布;基于实际路网构建地铁-公交加权复合网络模型和小汽车网络模型,并设计通行时间的计算方法;利用改进潜力模型精确地计算各地块的医疗、教育、就业、商业和文化休闲5类设施的可达性,加权得到综合可达性.此外,考虑路网规划方案对交通网络的更新,以评价规划方案对可达性的具体影响.研究结果表明:可达性与服务设施及交通网络的空间分布呈现强相关性,公共交通网络的合理布局可有效缓解由服务设施和路网差异引起可达性分布差异;优化路网能有效提高可达性水平,但这种改善效果在不同区域间存在差异,设施密度较高的区域提高幅度较大.此评价方法可以为城市各类公共服务设施的合理配置、交通网络的规划与优化,以及社会公平性的增强提供新的视角和工具.