Shixiang Zhu, Alexander W. Bukharin, Liyan Xie, M. Santillana, Shihao Yang, Yao Xie
{"title":"High-Resolution Spatio-Temporal Model for County-Level COVID-19 Activity in the U.S","authors":"Shixiang Zhu, Alexander W. Bukharin, Liyan Xie, M. Santillana, Shihao Yang, Yao Xie","doi":"10.1145/3468876","DOIUrl":"https://doi.org/10.1145/3468876","url":null,"abstract":"\u0000 We present an interpretable high-resolution spatio-temporal model to estimate COVID-19 deaths together with confirmed cases 1 week ahead of the current time, at the county level and weekly aggregated, in the United States. A notable feature of our spatio-temporal model is that it considers the (1) temporal auto- and pairwise correlation of the two local time series (confirmed cases and deaths from the COVID-19), (2) correlation between locations (propagation between counties), and (3) covariates such as local within-community mobility and social demographic factors. The within-community mobility and demographic factors, such as total population and the proportion of the elderly, are included as important predictors since they are hypothesized to be important in determining the dynamics of COVID-19. To reduce the model’s high dimensionality, we impose sparsity structures as constraints and emphasize the impact of the top 10 metropolitan areas in the nation, which we refer to (and treat within our models) as\u0000 hubs\u0000 in spreading the disease. Our retrospective out-of-sample county-level predictions were able to forecast the subsequently observed COVID-19 activity accurately. The proposed multivariate predictive models were designed to be highly interpretable, with clear identification and quantification of the most important factors that determine the dynamics of COVID-19. Ongoing work involves incorporating more covariates, such as education and income, to improve prediction accuracy and model interpretability.\u0000","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132087427","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}
M. Zokaeinikoo, Pooyan Kazemian, P. Mitra, S. Kumara
{"title":"AIDCOV: An Interpretable Artificial Intelligence Model for Detection of COVID-19 from Chest Radiography Images","authors":"M. Zokaeinikoo, Pooyan Kazemian, P. Mitra, S. Kumara","doi":"10.1101/2020.05.24.20111922","DOIUrl":"https://doi.org/10.1101/2020.05.24.20111922","url":null,"abstract":"As the Coronavirus Disease 2019 (COVID-19) pandemic continues to grow globally, testing to detect COVID-19 and isolating individuals who test positive remains to be the primary strategy for preventing community spread of the disease. The current gold standard method of testing for COVID-19 is the reverse transcription polymerase chain reaction (RT-PCR) test. The RT-PCR test, however, has an imperfect sensitivity (around 70%), is time-consuming and labor-intensive, and is in short supply, particularly in resource-limited countries. Therefore, automatic and accurate detection of COVID-19 using medical imaging modalities such as chest X-ray and Computed Tomography, which are more widely available and accessible, can be beneficial. We develop a novel hierarchical attention neural network model to classify chest radiography images as belonging to a person with either COVID-19, other infections, or no pneumonia (i.e., normal). We refer to this model as Artificial Intelligence for Detection of COVID-19 (AIDCOV). The hierarchical structure in AIDCOV captures the dependency of features and improves model performance while the attention mechanism makes the model interpretable and transparent. Using a publicly available dataset of 5801 chest images, we demonstrate that our model achieves a mean cross-validation accuracy of 97.8%. AIDCOV has a sensitivity of 99.3%, a specificity of 99.98%, and a positive predictive value of 99.6% in detecting COVID-19 from chest radiography images. AIDCOV can be used in conjunction with or instead of RT-PCR testing (where RT-PCR testing is unavailable) to detect and isolate individuals with COVID-19 and prevent onward transmission to the general population and healthcare workers.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115618753","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":"Are Stakeholders the Only Source of Information for Requirements Engineers? Toward a Taxonomy of Elicitation Information Sources","authors":"C. Burnay","doi":"10.1145/2965085","DOIUrl":"https://doi.org/10.1145/2965085","url":null,"abstract":"Requirements elicitation consists in collecting and documenting information about the requirements from a system-to-be and about the environment of that system. Elicitation forms a critical step in the design of any information system, subject to many challenges like information incompleteness, variability, or ambiguity. To deal with these challenges, requirements engineers heavily rely on stakeholders, who turn out to be one of the most significant provider of information during elicitation. Sometimes, this comes at the cost of less attention being paid by engineers to other sources of information accessible in a business. In this article, we try to deal with this issue by studying the different sources of information that can be used by engineers when designing a system. We propose TELIS (a Taxonomy of Elicitation Sources), which can be used during elicitation to review more systematically the sources of information about a system-to-be. TELIS was produced through a series of empirical studies and was partially validated through a real-world case study. Our objective in this article is to increase the awareness of engineers about the other information providers within a business. Ultimately, we believe our taxonomy may help in better dealing with classical elicitation challenges and increase the chances of successful information systems design.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114936997","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":"Discovering Finance Keywords via Continuous-Space Language Models","authors":"Ming-Feng Tsai, Chuan-Ju Wang, Po-Chuan Chien","doi":"10.1145/2948072","DOIUrl":"https://doi.org/10.1145/2948072","url":null,"abstract":"The growing amount of public financial data makes it increasingly important to learn how to discover valuable information for financial decision making. This article proposes an approach to discovering financial keywords from a large number of financial reports. In particular, we apply the continuous bag-of-words (CBOW) model, a well-known continuous-space language model, to the textual information in 10-K financial reports to discover new finance keywords. In order to capture word meanings to better locate financial terms, we also present a novel technique to incorporate syntactic information into the CBOW model. Experimental results on four prediction tasks using the discovered keywords demonstrate that our approach is effective for discovering predictability keywords for post-event volatility, stock volatility, abnormal trading volume, and excess return predictions. We also analyze the discovered keywords that attest to the ability of the proposed method to capture both syntactic and contextual information between words. This shows the success of this method when applied to the field of finance.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116062040","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":"Resource Management for Business Process Scheduling in the Presence of Availability Constraints","authors":"Jiajie Xu, Chengfei Liu, Xiaohui Zhao, Sira Yongchareon, Zhiming Ding","doi":"10.1145/2990197","DOIUrl":"https://doi.org/10.1145/2990197","url":null,"abstract":"In the context of business process management, the resources required by business processes, such as workshop staff, manufacturing machines, etc., tend to follow certain availability patterns, due to maintenance cycles, work shifts and other factors. Such availability patterns heavily influence the efficiency and effectiveness of enterprise resource management. Most existing process scheduling and resource management approaches tend to tune the process structure to seek better resource utilisation, yet neglect the constraints on resource availability. In this article, we investigate the scheduling of business process instances in accordance with resource availability patterns, to find out how enterprise resources can be rationally and sufficiently used. Three heuristic-based planning strategies are proposed to maximise the process instance throughput together with another strategy based on a genetic algorithm. The performance of these strategies has been evaluated by conducting experiments of different settings and analysing the strategy characteristics.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122911297","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":"Systemic Concentration in Sponsored Search Markets: The Role of Time Window in Click-Through-Rate Computation","authors":"Agam Gupta, Biswatosh Saha, U. Sarkar","doi":"10.1145/2934695","DOIUrl":"https://doi.org/10.1145/2934695","url":null,"abstract":"Keyword-based search engine advertising markets on the Internet, referred to as Sponsored Search Markets (SSMs), have reduced entry barriers to advertising for niche players. Known empirical research, though scant and emerging, suggests that while these markets provided niche firms with greater access, they do exhibit high levels of concentration—a phenomenon that warrants further study. This research, using agent-based simulation of SSM, investigates the role of “market rules” and “advertiser practices” in generating emergent click share heterogeneity among advertisers in an industry. SSMs often rank ads based on the click-through rate (CTR) that gives rise to reinforcing dynamics at an individual keyword level. In the presence of spillovers arising from advertisers’ practice of managing keyword bids with a cost cap operating on the keyword portfolio, these reinforcing dynamics can endogenously generate industry-level concentration. Analysis of counterfactual markets with different window sizes used to compute CTR reveals that industry-level concentration bears an inverted-“U” relationship with window size.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114449314","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":"A Real-Time Audit Mechanism Based on the Compression Technique","authors":"Shing-Han Li, D. Yen, Ying-Ping Chuang","doi":"10.1145/2629569","DOIUrl":"https://doi.org/10.1145/2629569","url":null,"abstract":"Log management and log auditing have become increasingly crucial for enterprises in this era of information and technology explosion. The log analysis technique is useful for discovering possible problems in business processes and preventing illegal-intrusion attempts and data-tampering attacks. Because of the complexity of the dynamically changing environment, auditing a tremendous number of data is a challenging issue. We provide a real-time audit mechanism to improve the aforementioned problems in log auditing. This mechanism was developed based on the Lempel-Ziv-Welch (LZW) compression technique to facilitate effective compression and provide reliable auditing log entries. The mechanism can be used to predict unusual activities when compressing the log data according to pre-defined auditing rules. Auditors using real-time and continuous monitoring can perceive instantly the most likely anomalies or exceptions that could cause problems. We also designed a user interface that allows auditors to define the various compression and audit parameters, using real log cases in the experiment to verify the feasibility and effectiveness of this proposed audit mechanism. In summary, this mechanism changes the log access method and improves the efficiency of log analysis. This mechanism greatly simplifies auditing so that auditors must only trace the sources and causes of the problems related to the detected anomalies. This greatly reduces the processing time of analytical audit procedures and the manual checking time, and improves the log audit efficiency.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123564414","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}
Khayyam Hashmi, Zaki Malik, Erfan Najmi, Amal Alhosban, B. Medjahed
{"title":"A Web Service Negotiation Management and QoS Dependency Modeling Framework","authors":"Khayyam Hashmi, Zaki Malik, Erfan Najmi, Amal Alhosban, B. Medjahed","doi":"10.1145/2893187","DOIUrl":"https://doi.org/10.1145/2893187","url":null,"abstract":"Information Management Systems that outsource part of the functionality to other (likely unknown) services need an effective way to communicate with these services, so that a mutually beneficial solution can be generated. This includes bargaining for their optimal customizations and the discovery of overlooked potential solutions. In this article, we present an automated negotiation framework for information systems (denoted as WebNeg) that can be used by both the parties for conducting negotiations. WebNeg uses a Genetic Algorithm (GA)-based approach for finding acceptable solutions in multiparty and multiobjective scenarios. The GA is enhanced using a new operator called Norm, which represents the cumulative knowledge of all the parties involved in the negotiation process. Norm incorporates the dependencies of different quality attributes of independently developed component services for the system composition. This enables WebNeg to find a better solution in the context of the current requirements. Experiment results indicate the applicability and improved performance of WebNeg (in comparison with existing similar works) in facilitating the negotiation management involved in a web service-based information composition process.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"216 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120854591","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":"Universal Artifacts: A New Approach to Business Process Management (BPM) Systems","authors":"Yutian Sun, Jianwen Su, Jian Yang","doi":"10.1145/2886104","DOIUrl":"https://doi.org/10.1145/2886104","url":null,"abstract":"In most BPM systems (a.k.a. workflow systems), the data for process execution is scattered across databases for enterprise, auxiliary local data stores within the BPM systems, and even file systems (e.g., specification of process models). The interleaving nature of data management and BP execution and the lack of a coherent conceptual data model for all data needed for execution make it hard for (1) providing Business-Process-as-a-Service (BPaaS) and (2) effective support for collaboration between business processes. The primary reason is that an enormous effort is required for maintaining both the engines and the data for the client applications. In particular, different modeling languages and different BPM systems make process interoperation one of the toughest challenges. In this article, we formulate a concept of a “universal artifact,” which extends artifact-centric models by capturing all needed data for a process instance throughout its execution. A framework called SeGA based on universal artifacts is developed to support separation of data and BP execution, a key principle for BPM systems. We demonstrate in this article that SeGA is versatile enough to fully facilitate not only executions of individual processes (to support BPaaS) but also various collaboration models. Moreover, SeGA reduces the complexity in runtime management including runtime querying, constraints enforcement, and dynamic modification upon collaboration across possibly different BPM systems.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115119640","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":"The Effect of a Multichannel Customer Service System on Customer Service and Financial Performance","authors":"T. Lui, G. Piccoli","doi":"10.1145/2875444","DOIUrl":"https://doi.org/10.1145/2875444","url":null,"abstract":"Customer service is an important competitive lever for the modern firm. At the same time, the continuous evolution and performance improvements in information technology (IT) capabilities have enabled the utilization of multichannel service delivery strategies. Our research focuses on IT-enabled customer service systems (CSS) and their effect on firm performance. Previous studies have failed to find a consensus on the effect of a new self-service channel on the firm's performance. We argue that the embedded assumptions underpinning the previous research are responsible for these mixed findings. Consequently, using archival data from 169 hotels affiliated with a hotel chain, we designed a longitudinal multichannel study to resolve some of these inconsistencies. Our results illustrate that when firms implement an IT-enabled self-service channel to complement their existing customer service infrastructure, they experience an early negative effect on financial performance due to the disruption of the service processes. Thus, the multichannel CSS generates a positive effect only when the new process becomes a stable part of the organizational procedures. Our findings suggest that researchers evaluate the effect of a technological initiative after the new business process has been stabilized and consider that an additional IT-enabled self-service channel rarely operates in isolation.","PeriodicalId":178565,"journal":{"name":"ACM Trans. Manag. Inf. Syst.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124262168","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}