scholarly journals A Novel Integrated Machine & Business Intelligence Framework for Sensor Data Analysis

Author(s):  
Kalyani akiri ◽  
Venkat Rao b

Increased smart devices in various industries is creating numerous sensors in each of the equipment prompting the need for methods and models for sensor data. Current research proposes a systematic approach to analyze the data generated from sensors attached to industrial equipment. The methodology involves data cleaning, preprocessing, basics statistics, outlier, and anomaly detection. Present study presents the prediction of RUL by using various Machine Learning models like Regression, Polynomial Regression, Random Forest, Decision Tree, XG Boost. Hyper Parameter Optimization is performed to find the optimal parameters for each variable. In each of the model for RUL prediction RMSE, MAE are compared. Outcome of the RUL prediction should be useful for decision maker to drive the business decision; hence Binary classification is performed, and business case analysis is performed. Business case analysis includes the cost of maintenance and cost of non-maintaining a particular asset. Current research is aimed at integrating the machine intelligence and business intelligence so that the industrial operations optimized both in resource and profit.

2018 ◽  
Vol 28 (5) ◽  
pp. 1489-1496
Author(s):  
Branislav Stanisavljević

Research carried out in the last few years as the example of companies belonging to the category of medium-size enterprises has shown that, for example, typical enterprises, of the total number of data processed in information of importance for its business, seriously takes into consideration and process only 10% of the observed firms. It is justifiable to ask whether these 10% of the processed and analyzed business information can have an adequate potential or motive power to direct the organization to success that is measured by competitive advantages and on a sustainable basis? Or, the question can be formulated: what happens to the rest, mostly 90% of the information that the enterprise does not transform into a form suitable for business analysis and decision-making. It is precisely the task of business intelligence to find a way to utilize all the data collected and processed in the business decision-making process. In this regard, we can conclude that Business Intelligence is, in fact, the framework title for all tools and / or applications that will enable the collection, processing, analysis, distribution to decision-making bodies in the business system in order to derivate from this information valid business decisions - as the most important and / or most important task of the manager. Of course, from an economic point of view, the best decisions are management decisions that provide a lasting competitive advantage and achieve maximum financial performance. This means that business intelligence actually allows a more complete and / or comprehensive view of the overall business performance of all its parts and subsystems. But the system functions can be measured essential and positive economic and financial performance, as well as the position in the branch of the business to which it belongs, and wider, within the national economy. (Of course, today the boundaries of the national economy have become too crowded for many companies, bearing in mind globalization and competitiveness in the light of organization of work and business function). The advantage of business intelligence as a model, if accepted at the organization level, ensures that each subsystem in the organization receives precisely the information needed to make development decisions, but also decisions regarding operational activities. So, it should be born in mind that business intelligence does not imply that information is shared on some key words, on the contrary, the goal is to look at the context of the business, or in general, and that anyone in the further decision hierarchy can manage exactly the same information that is necessary for achieving excellent business performance. Because, if the insight into the information is not complete, the analysis is based on the description of individual parts, i.e. proving partial performance in the realization of individual information, which can certainly create a space for the loss of the expensive time and energy. Illustratively, if the view, or insight into the information, is not 100%, then all business decision-making is like the song of J.J. Zmaj "Elephant", about an elephant and a blindmen, where everyone feels and act only on the base of the experienced work, and brings judgment on what is what or what can be. As in this song for children, everyone thinks that he touches different animals and when they make claims about what they feel, everyone describes a completely different life. Therefore, business intelligence implies that information is fully considered and it is basically the basis or knowledge base, and therefore the basis of business excellence. In doing so, the main problem is how information is transformed into knowledge and based on it in business decision making. It is precisely in this segment that the main advantage of business intelligence is its contribution to the knowledge and business of the company based on power of knowledge. Therefore, for modern business conditions, it is characteristic that the management of the company is realized on the basis of partial knowledge about stakeholders (buyers, suppliers, competitors, shareholders, governments, institutional framework, legislation), and only a complete overview of managers at the highest level in all these partial interest groups allows managers to have a “boat” called the organization of labor leading a safe hand through the storm, Scile and Haribde threatens to endanger business, towards a calm sea and a safe harbor - called a sustainable competitive advantage based on power and knowledge.


Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4486
Author(s):  
Niall O’Mahony ◽  
Sean Campbell ◽  
Lenka Krpalkova ◽  
Anderson Carvalho ◽  
Joseph Walsh ◽  
...  

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.


Author(s):  
Osman Salem ◽  
Alexey Guerassimov ◽  
Ahmed Mehaoua ◽  
Anthony Marcus ◽  
Borko Furht

This paper details the architecture and describes the preliminary experimentation with the proposed framework for anomaly detection in medical wireless body area networks for ubiquitous patient and healthcare monitoring. The architecture integrates novel data mining and machine learning algorithms with modern sensor fusion techniques. Knowing wireless sensor networks are prone to failures resulting from their limitations (i.e. limited energy resources and computational power), using this framework, the authors can distinguish between irregular variations in the physiological parameters of the monitored patient and faulty sensor data, to ensure reliable operations and real time global monitoring from smart devices. Sensor nodes are used to measure characteristics of the patient and the sensed data is stored on the local processing unit. Authorized users may access this patient data remotely as long as they maintain connectivity with their application enabled smart device. Anomalous or faulty measurement data resulting from damaged sensor nodes or caused by malicious external parties may lead to misdiagnosis or even death for patients. The authors' application uses a Support Vector Machine to classify abnormal instances in the incoming sensor data. If found, the authors apply a periodically rebuilt, regressive prediction model to the abnormal instance and determine if the patient is entering a critical state or if a sensor is reporting faulty readings. Using real patient data in our experiments, the results validate the robustness of our proposed framework. The authors further discuss the experimental analysis with the proposed approach which shows that it is quickly able to identify sensor anomalies and compared with several other algorithms, it maintains a higher true positive and lower false negative rate.


Author(s):  
Gamze Akpolat ◽  
David Valerdi ◽  
Engin Zeydan ◽  
Ahmet Serdar Tan

Sign in / Sign up

Export Citation Format

Share Document