Mechanical Engineering eJournal最新文献

{"title":"Anomaly Detection in Market Data Structures via Machine Learning Algorithms","authors":"D. Röder, Henning Mueller","doi":"10.2139/ssrn.3516028","DOIUrl":"https://doi.org/10.2139/ssrn.3516028","url":null,"abstract":"We made use of a stacked autoencoder machine learning algorithm to detect injected anomalies in swaption volatility offset cubes, a financial market data entity. These consist of 240 datapoints each. Injected cubes contained a modification at one single point, five modi-fied cubes with modifications of different severity had been constructed as our test cases. We investigated the detection results of four slightly different autoencoder architectures with SELU activation, ADAM optimizer and five symmetric hidden layers, differing in number of nodes in the bottleneck layer and whether input noise was applied or not. Implementation was established using the tensorflow library.<br><br>Unsupervised training was performed on 638 historical swaption volatility offset cubes, ten percent of which had been randomly selected and set aside to constitute the test dataset. The trained algorithms detected the three largest injections reliably and marked a total of 25 da-tasets out of 638 historical and 5 injected ones as ‘spurious’, including all five cubes containing an injection. Using this technology in quality assurance to pre-select for conspicuous data, we could – in our case – reduce the data requiring human attention by 96%, making it a useful tool for the market data quality manager which can easily be applied to other problems. <br><br>Code and example data can be found on our GitHub repo (Roeder Dirk, Mueller Henning, 2019).","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134280002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"JD.com: Transaction Level Data for the 2020 MSOM Data Driven Research Challenge","authors":"Zuo‐Jun Max Shen, Christopher S. Tang, Di Wu, Rong Yuan, Wei Zhou","doi":"10.2139/ssrn.3511861","DOIUrl":"https://doi.org/10.2139/ssrn.3511861","url":null,"abstract":"To support the 2020 MSOM Data Driven Research Challenge, JD.com, China’s largest retailer, offers transaction level data to MSOM members for conducting data-driven research. This article describes the transactional data associated with over 2.5 million customers (457,298 made purchases) and 31,868 SKUs over the month of March in 2018. We also present potential research questions suggested by JD.com. Researchers are welcome to develop econometric models or data-driven models using this database to address some of the suggested questions or examine their own research questions.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124250769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanism of Fracture in Friction Stir Processed Aluminium Alloy","authors":"P. K. Mandal, Mebin T Kuruvila, Jithin Devasia","doi":"10.31033/ijemr.9.6.12","DOIUrl":"https://doi.org/10.31033/ijemr.9.6.12","url":null,"abstract":"Aluminium alloys are used for important applications in reducing the weight of the component and structure particularly associated with transport, marine, and aerospace fields. Grain refinement by scandium (Sc) addition can eliminate the casting defects and increase the resistance to hot tearing for high strength aluminium alloys. FSP for cast aluminium alloys have been focused and it has great advantages including solid state microstructural evolution, altering mechanical properties by optimizing process parameters. These parameters are tool rotational speeds (720, and 1000 rpm), traverse speeds (80, and 70 mm/min), and axial compressive force  at 15 kN, etc. The mechanical properties had been evaluated on FSPed aluminium alloy with different microstructural conditions. Fracture properties of aluminium alloys are very important for industrial applications. Tensile and fracture toughness properties were correlated to microstructural and fractographic features of the aluminium alloys need to explore their essential failure mechanisms.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122855383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IBEECP: Improved Biogeography Optimization Based Energy Efficient Clustering Protocol for Wireless Sensor Networks","authors":"V. Subba Rao, K. Srinivas, R. Pavithra","doi":"10.2139/ssrn.3511042","DOIUrl":"https://doi.org/10.2139/ssrn.3511042","url":null,"abstract":"Biogeography-based Optimization (BBO) is a new nature inspired computing algorithm for solving optimization problems. Cluster head selection is a well-known optimization problem in wireless sensor networks (WSN). The life of network is depends on selecting the cluster head (CH) for transferring the data to the base station in Wireless Sensor Network. This paper proposes Improved Biogeography Optimization Based Energy Efficient Clustering Protocol (IBEECP) for Wireless sensor networks for cluster head selection. The concept of IBCEEP is by using efficient CH selection inspired by biogeography-based optimization for efficient energy utilization of WSNs. The performance of simulation results through MATLAB shows IBEECP enhance the network lifetime, quality of network, network stability period and throughput compared with heterogeneous protocols in WSN are stable election protocol (SEP), evolutionary routing protocol (ERP), intelligent hierarchical clustering routing protocol (IHCR) and biogeography based energy efficient cluster protocol (BEECP).","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132966646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Information Technology for Heat Losses Management of Construction Structures","authors":"A. Yerokhin, H. Zatserklyanyi","doi":"10.15587/2312-8372.2020.198265","DOIUrl":"https://doi.org/10.15587/2312-8372.2020.198265","url":null,"abstract":"The object of research in this work is unproductive heat loss in buildings and construction structures; due to the nature of the heat and mass transfer process; which operates in a complex architectural and structural scheme. One of the ways to reduce unproductive heat losses in buildings and construction is the use of information and control technologies and systems for managing such objects. These technologies and systems based on information processing on the state of buildings and construction facilities should ensure the formation of effective managerial decisions aimed at reducing unproductive heat losses and optimizing the structure of consumption of fuel and energy resources in the housing and communal sector. Today; both in the energy efficiency control systems of buildings and outside of their heat and mass transfer processes; they are analyzed either in a simple statement or in separate elements of the architectural design of a building structure. Such an approach to modeling the heat and mass transfer process does not provide a sufficiently complete assessment of unproductive heat loss. This is due to the fact that the process of heat and mass transfer is a complex interconnected and interdependent system and operates in a complex architectural and structural system of a building structure. In this paper; a component-oriented information technology is proposed that relies on a mathematical model of an interconnected and interdependent heat and mass transfer process that operates in any complex architectural and structural scheme of a house or building structure. This model; in comparison with other models used; covers all the basic properties of heat and mass transfer both in building envelopes and in vapor-air spaces. It takes into account the heat input to the house from heating and lighting systems; solar radiation and people in the building. So; it allows to more fully evaluate the heat loss in a house or building.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123997580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fintech: Research Directions to Explore the Digital Transformation of Financial Service Systems","authors":"Christoph F. Breidbach, B. Keating, Chiehyeon Lim","doi":"10.2139/ssrn.3649758","DOIUrl":"https://doi.org/10.2139/ssrn.3649758","url":null,"abstract":"PurposeThe purpose of this paper is to delineate a research agenda to guide future service research investigating the digital transformation of financial service systems through Fintech – disruptive innovations by new market entrants that challenge the position of mainstream financial institutions.Design/methodology/approachRooted in the philosophical foundations of “use-inspired research,” this paper addresses the managerially and societally relevant phenomenon of Fintech by identifying, and responding to, the individual challenges and problems associated with the digital transformation of financial services. This is accomplished through a computational text-mining approach to analyze the corpus of 1,545 published practitioner articles associated with Fintech, identification of managerial challenges therein and subsequent delineation of a novel research agenda.FindingsBy connecting managerial challenges relating to Fintech with the service literature, this paper develops a use-inspired research agenda that provides scholarly and managerially relevant research directions (RDs). These pertain to the complexity of digital financial service systems (micro level), orchestration of value co-creation with Fintech (meso level), and the development of elastic infrastructures, models and markets (macro level).Research limitations/implicationsFintech is an emerging phenomenon associated with the digital transformation of financial services. However, actual guidelines on how service research related to Fintech could be advanced from a theoretically as well as managerially relevant angle are unavailable to date. Here, the authors address this challenge and provide the field with 18 tangible RDs to advance service theory and practice.Practical implicationsThe purpose of this paper is to guide future academic research addressing managerial challenges associated with Fintech and the digital transformation of financial service. Due to the explicit use-inspired nature of the work, the future research stemming from the agenda that the authors put forward here will be of benefit to decision makers and society more broadly.Originality/valueThis empirical research contributes to the discourse regarding the role of information and communication technologies in service in general, and the digital transformation on financial services in particular. The in-depth computational text-mining analysis is unbiased, replicable and provides the foundation for a use-inspired research agenda that is subsequently delineated.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128545856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fabrication of 316 Ss–B4c Composite by Powder Metallurgical Route","authors":"T. S., U. M, P. P, S. Skoczypiec, T. Ko, T. Varol","doi":"10.2139/ssrn.3653948","DOIUrl":"https://doi.org/10.2139/ssrn.3653948","url":null,"abstract":"The control rod consists of 316 stainless steel filled with boron carbide (B4C) pellets. This novel method is to prepare the specimen as a composite bar using powder metallurgical route. The optimum compaction pressure of 450 MPa is used to fabricate with a dimension of 10x30 mm. The prepared composite ensured the uniform dispersion of the reinforcements. The X-Ray elemental mapping shows the presence of mud-pot cracking which is due to oxidation effects. Further, the spectrum analysis explicit the various components present in 316 SS–B4C composite. The quality of the specimen can further be improved when sintering in vacuum chamber or processing by spark plasma.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130421266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Practical Machine Learning Approach for Stock Trading Strategies using Alternative Dataset","authors":"Yunzhe Fang, Xiao-Yang Liu, Hongyang Yang","doi":"10.2139/ssrn.3501239","DOIUrl":"https://doi.org/10.2139/ssrn.3501239","url":null,"abstract":"AI technologies are helping more and more companies leverage their resources to expand business, reach higher financial performance and become more valuable for investors. However, it is difficult to capture and predict the impacts of AI technologies on companies’ stock prices through traditional financial factors. Moreover, common information sources such as company’s earnings calls and news are not enough to quantify and predict the actual AI premium for a certain company. In this paper, we utilize scholar data as alternative data for trading strategy development and propose a practical machine learning approach to quantify the AI premium of a company and capture the scholar data driven alpha in the AI industry. First, we collect the scholar data from the Microsoft Academic Graph database, and conduct feature engineering based on AI publication and patent data, such as conference/journal publication counts, patent counts, fields of studies and paper citations. Second, we apply machine learning algorithms to weight and re-balance stocks using the scholar data and traditional financial factors every month, and construct portfolios using the “buy-and-hold-long only” strategy. Finally, we evaluate our factor and portfolio in terms of factor performance and portfolio’s cumulative return. The proposed scholar data driven approach achieves a cumulative return of 1029.1% during our backtesting period, which significantly outperforms the Nasdaq 100 index’s 529.5% and S&P 500’s 222.6%. The traditional financial factors approach only leads to 776.7%, which indicates that our scholar data driven approach is better at capturing investment alpha in AI industry than traditional financial factors.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115917949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scheduling Queues with Customer Transfers","authors":"Xu Sun","doi":"10.2139/ssrn.3542352","DOIUrl":"https://doi.org/10.2139/ssrn.3542352","url":null,"abstract":"We consider a multiclass single-server system wherein customers of each class form their own queue and can either abandon the system or transfer to other queues while waiting. A system manager makes dynamic scheduling decisions to minimize system-wide waiting cost. We solve the stochastic control problem under both infinite-horizon discounted and average cost criteria. By studying a Brownian control problem that arises in the conventional heavy traffic regime, we identify (under each cost criterion) an asymptotically optimal policy that prioritizes across different classes according to a workload-dependent dynamic index rule. The proposed policies acknowledge the impact of customer transfers on the optimal allocation of service resources and generate rich managerial insights. One of the technical difficulties in the proof of the asymptotic optimality result is to identify a natural stability condition and formally show that the sequence of diffusion-scaled processes is uniformly stable under that condition.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124710405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamics of Content Contributors’ Performance: Evidence from a Social Question-and-Answer Community","authors":"Yue Jin, Yong Tan, Jinghua Huang","doi":"10.2139/ssrn.3502109","DOIUrl":"https://doi.org/10.2139/ssrn.3502109","url":null,"abstract":"This paper concerns the dynamics of contributor performance in a social content-sharing community. Based on ability-motivation-opportunity theory, we propose a hidden Markov model to characterize the change in a contributor’s latent state, which then determines performance in terms of quantity and quality. The proposed model is calibrated using data from a social question-and-answer community. Three latent states are identified: unmotivated, motivated but incompetent, and motivated and competent. Several factors influence the state-transition process. Specifically, the increase in followers encourages contributors in the unmotivated state to transition to the motivated states. When the contributors are motivated but incompetent, observing the behavior of their followings increases the probability of their transitioning to the motivated and competent state. In addition, direct experience boosts all contributors to higher states. The modeling framework and findings of this study have implications for contributor performance management in a variety of settings.","PeriodicalId":404477,"journal":{"name":"Mechanical Engineering eJournal","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124632999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}