BI Analytics, IoT, EmIoT, And Introduction To Database Queries For Data Analysis

Notable Uses of Different Types of Mining including Data, Text, Web and Social Mining

Data Mining

The process of identifying patterns from large sets of data is commonly known as data mining. Data mining can be conducted with all methods at the interaction of database systems, machine learning and statistics (Witten, 2016).  Some of the most notable uses of data mining techniques are as follows:

• Business-market analysis: This is widely used in the e-commerce applications to analyse customer purchase trends (Lee & Lee, 2016).
• Bio Informatics: The mining of biological data helps to extract crucial knowledge in the field of biology, which can be applied in the fields of neuroscience, genetic research and medicine.
• Customer-Relationship Management: CRM uses data mining facilities to collect and analyse customer information. Data mining helps to analyse the gathered information and concentrate on the appropriate factors that will help the concerned organization to retain customers.

This is the process where massive chunks of unstructured text data is is explored and analysed. Software are used to identify recognizable topics, patterns and concepts or attributes in the respective collectives. This is commonly used in the following fields:

• Customer Care service: Text analysis techniques in text mining helps in the rapid and automated response generation to customers, by gathering and reading through the patterns of past customer-operator text chat responses. Automated text-message-support curbs off the burden from the call-center operators, in providing hassle-free solutions to the client.
• Spam Filtering: Spamming has been quite a crucial issue in the modern days. Text mining methods are applied to improve the effectiveness of various types of statistical-based email or message filtering methods. This technique is widely used by of the greatest names in the business like Google, Facebook and so on (Aggarwal & Zhai, 2012).

Web Mining

Web mining allows the pattern recognition techniques with the help of content and structure mining abilities. This data mining application aids in the process of discovering necessary data patterns from the WWW or World Wide Web. Some of its renowned use cases are as follows:

• Search Engine analytics: Google Analytics is one of the most important examples of the usage of the web mining technology. It uses this technology to gather visitor response information of various websites and provides analytical reports. This also allow them to meaningfully extract the best outputs on search queries.
• Advertising performance analysis: Web mining allows to collect data about the user or web-visitor interaction on the ads that are displayed on various websites. This method helps to create meaningful statistical reports on the reach and popularity of such e-adverts.

Social Mining

Social mining or social media mining is one of the most common mining trends of the modern era. The process of analysing, representing, and retrieving meaningful patterns from data that is collected from social media that is a product of several user interactions of posts and information of the respective platforms. This involves the collection and analysis of data collected from the perspective of user’s emotional attachment. This is in turn used in the process of content management. Highlighting likewise content and adverts is an important use case of this process.

Internet of Technology, which is most commonly known as IoT can be defined as a network of several devices or appliances that are connected to a control system. This allows them to be remotely operated or work on their own, based on AI or Artificial Intelligence aids. These IoT devices can be so operated to work on their own, interact with each other and exchange data as necessary. Some of the major analytics techniques that are applied in IoT are as follows:

• Application Analytics: This helps to gain fair knowledge about the usage of the IoT devices based on the data collected from the applications that are used by the users to operate these devices.
• Social Analytics: This helps to gather data about the user interaction with the various IoT devices. Artificial Intelligence means are availed to make the devices to work based on the data analysed. This helps to make the devices work according user’s preferences.
• Real-Time visualization analytics: Data collected is often required to be analysed and prompt solutions are to be delivered. Such types of analytic techniques help in this process. Smart cars are the best example in this field. They collect data based on sensor inputs and the device needs to make accurate decisions based on the real time updates in the data or environment.
• Data mining: Big data helps to collect and focus on the most important portion of data that are collected. Data analytic techniques allow these devices to formulate appropriate reports for solutions to long-term or real-time problems.

The advantages of IoT are as follows:

• It is highly cost and effort effective. The transferring of data from one device to another is easy. They are internally shared over the networks, hence saving up lots of charges and time of the user.
• Ease of information access is another crucial addition to the list of advantages that comes with the implementation of IoT devices. Also, massive chunks of data can be collected and retrieved as and when necessary. This helps in the proper management of these devices (Formisano et al., 2015).
• Automation is the key aspect. The reduction of human interaction or involvement in data collection techniques is another positive point that can be noted in the favour of IoT. This allows the devices to collect and produce flawless data outputs.

There arises various complexities with IoT. Some commonly mentioned disadvantages are as follows:

• Privacy and security is the most effective concern in the usage of IoT. These being few of the major devices in a household, if compromised, will lead to a massive breakout. This leads to the leakage of crucial and sensitive information. In addition, the control of these devices into the hands of anti-socials will lead to a vital unsecured situation (Zhang et al., 2014).
• With the increase of automation, there will be less works for humans to do. All crucial data collection and or analysis can be done by these devices and human value will decrease.
• Incorrect ethical analysis is a huge drawback in this technology. However smart a device can be designed to get, they can never match the intuition level of human beings. Hence, in crucial ethical situations, the smart device may fail to make a proper decision. An example of this can be the ethical consideration of a smart car. In case the car is faced with a situation where it has a pedestrian appearing suddenly in front of it and it cannot turn as it will else hit a tree, hence harm its own passengers. The car faces an ethical dilemma and will generally jeopardise the life of its passengers to save the pedestrians (He, Yan & Da Xu, 2014). A human driver could have handled such situations in a more matured way.

EmIoT or Emotional Internet of Things is the technology that allows the IoT devices to interact on a greater aspect with the users’ emotional factors to create a better data set for analytics. The data that are collected from this technology helps in the emotional analysis process. It records data that are related to the deepest personal factors of the inheritants. This includes data like how a user reacts to certain situations or how the user interacts with the IoT devices. They gather information that consist of user’s voice pitch level or sensor data about the user’s catabolism, depending on various familiar situations that the device can simulate or note. IoT on the other hand, is designed to only collect, share and analyse the data that they are meant to handle. It is the EmIoT that aids the integrated IoT devices with data feedbacks.

Important examples of EmIoT devices are the EmoSPARK and the Feel Wristband. The EmoSPARK is a smart home device that creates an emotional profile of the inhabitants based on their vocal characteristics, choice of words and also facial recognition. This device can alter the IoT devices’’ operation based on the real-time collected emotional data. This includes changing the music or video playlist based on the user’s mood or general daily habits.

Types of Analytics Applicable to IoT

The Feel Wristband uses sensors to read pulse, body temperature and skin responses. These are useful in health assistance purposes (Mano et al., 2016). The collection of these data helps the device to create a real-time emotional profile of the user and hence instruct the connected IoT devices to operate properly. For example, if the band reads that the user has a hot skin temperature and a pounding heart, it may advice the mobile application that it is connected to, to call the doctor or it may even bring down the temperature of the AC if connected (Kelly, Suryadevara & Mukhopadhyay, 2013).

EmIoT is developed and designed to frame the feelings of the users in a special manner so as to add a deeper layer understanding of the data that they gather. While, IoT devices only face the threat of security and excess human dependence, EmIoT creates a fine line of competition between humans and the robots. Cui (2016), says that robots are getting smarter with time and a time will come when these will take over almost every network accessible device usage duties from the control human beings.

References

Aggarwal, C. C., & Zhai, C. (Eds.). (2012). Mining text data. Springer Science & Business Media.

Barbosa, R., Nunes, D., Figueira, A., Aguiar, H., Silva, J. S., Gonzalez, F., … & Sinche, S. (2016, October). An architecture for emotional smartphones in Internet of Things. In Ecuador Technical Chapters Meeting (ETCM), IEEE (pp. 1-5). IEEE.

Bhayani, M., Patel, M., & Bhatt, C. (2016). Internet of Things (IoT): In a way of smart world. In Proceedings of the international congress on information and communication technology (pp. 343-350). Springer, Singapore.

Cui, X. (2016). The internet of things. In Ethical Ripples of Creativity and Innovation (pp. 61-68). Palgrave Macmillan, London.

Formisano, C., Pavia, D., Gurgen, L., Yonezawa, T., Galache, J. A., Doguchi, K., & Matranga, I. (2015, August). The advantages of IoT and cloud applied to smart cities. In Future Internet of Things and Cloud (FiCloud), 2015 3rd International Conference on (pp. 325-332). IEEE.

He, W., Yan, G., & Da Xu, L. (2014). Developing vehicular data cloud services in the IoT environment. IEEE Transactions on Industrial Informatics, 10(2), 1587-1595.

Kelly, S. D. T., Suryadevara, N. K., & Mukhopadhyay, S. C. (2013). Towards the implementation of IoT for environmental condition monitoring in homes. IEEE Sensors Journal, 13(10), 3846-3853.

Khattab, A., Abdelgawad, A., & Yelmarthi, K. (2016, December). Design and implementation of a cloud-based IoT scheme for precision agriculture. In Microelectronics (ICM), 2016 28th International Conference on (pp. 201-204). IEEE.

Lee, I., & Lee, K. (2015). The Internet of Things (IoT): Applications, investments, and challenges for enterprises. Business Horizons, 58(4), 431-440.

Mano, L. Y., Faiçal, B. S., Nakamura, L. H., Gomes, P. H., Libralon, G. L., Meneguete, R. I., … & Ueyama, J. (2016). Exploiting IoT technologies for enhancing Health Smart Homes through patient identification and emotion recognition. Computer Communications, 89, 178-190.

Sanchez, L., Muñoz, L., Galache, J. A., Sotres, P., Santana, J. R., Gutierrez, V., … & Pfisterer, D. (2014). SmartSantander: IoT experimentation over a smart city testbed. Computer Networks, 61, 217-238.

Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.

Zhang, Z. K., Cho, M. C. Y., Wang, C. W., Hsu, C. W., Chen, C. K., & Shieh, S. (2014, November). IoT security: ongoing challenges and research opportunities. In Service-Oriented Computing and Applications (SOCA), 2014 IEEE 7th International Conference on (pp. 230-234). IEEE.