Machine learning examples are; algorithmic geospatial data analysis, self-driving technology, facial recognition-based security, automated medical diagnosis, and speech recognition/translation.
This article discusses machine learning examples, as follows;
1). Algorithmic Geospatial Data Analysis (as one of the Machine Learning Examples)
Geospatial data analysis is the act and process whereby geographic data is collected, analyzed, manipulated, modified and utilized to solve real-world problems. It is mostly applied within the context of GIS (geographic information system) operations.
Machine learning is used in GIS, where there is need to automate all or part of the process of geospatial data analysis .
A machine learning tool like Python is very useful for spatial analysis, especially with regards to automation of data handling processes.
The use of machine learning in geospatial analysis is recommendable because of the large volume of datasets that is often involved.
With machine learning, geospatial data can be collected from satellite systems, analyzed, juxtaposed, and used for functions in environmental assessment, pollution monitoring for environmental remediation, urban planning, development of circular economic schemes, and observation of humanitarian issues like flooding, overpopulation, urbanization andresource depletion.
Operations that can be performed on geospatial datasets using machine learning tools include; classification, predictive analysis, clustering, and model-building.
2). Self-driving Technology
Machine learning is used in self-driving cars to enable their software algorithms to actively collect, analyze and 'learn' from multiple layers of visual and geographic data from their surroundings .
Alongside machine learning as a core functionality, autonomous driving technology is usually equipped with general artificial intelligence, and robotic functionalities that work alongside the ML system.
AI is used in self-driving cars by the incorporation of software tools that organize data and manage neural networks in such a manner that mimics human cognizance mechanisms.
The kind of machine learning which self-driving cars use is mainly deep learning; with convolutional neural networks among other algorithmic models . This is due to the need for recurrent and continuous scrutiny of data, to correlate datasets on both spatial and temporal bases.
While it is still undergoing improvement, self-driving by machine learning is already capable of performing some advanced functions autonomously, such as map-reading and object identification. It has also formed a major innovative factor in both hybrid cars and electric cars.
3). Facial Recognition-based Security (as one of the Machine Learning Examples)
Facial recognition, is used in security as a biometric factor that can be applied to verify the authenticity of an access request or an identity claim; in the same manner that other biometric factors like fingerprints are used.
Machine learning can be used tor facial recognition as the core mechanism for storage and analysis of biometric data .
Since visual data is the main type involved here, the functionalities applied in machine learning for facial recognition are mainly data storage, classification, attribution and matching.
In cybersecurity systems, facial recognition can be used as a protocol for access to, or editing of, a database.
However, the use of facial recognition as a sole or central security feature is not always recommendable.
Security risks of facial recognition border around the possibility of providing visual data that could match with, and be accepted by, the datasets in the machine learning model. This means that for highly-classified and sensitive security operations, facial recognition should be used in combination with other tools and measures.
4). Automated Diagnosis in Healthcare
Machine learning is used in medical diagnosis, by supplying AI algorithms with multiple layers of diagnostic data on various health conditions, which the algorithms sort, match, classify, and use to identify similar health conditions using data from medical tests.
The potential of machine learning to affect medical diagnosis is enormous, and can be assessed in terms of time and cost-saving, less labor, elimination of human error and increase in energy efficiency.
Numerous algorithmic techniques can be used in medical diagnosis systems, including recurrent neural networks (RNNs), radial basis function (RBF) networks, and convolutional neural networks (CNNs), with data collection, curve-fitting, and approximation functions.
Diseases that can be diagnosed with machine learning include; breast cancer, Alzheimer's disease, pneumonia, liver disease, diabetes, lung cancer and heart disease .
5). Automated Speech Recognition and Translation (as one of the Machine Learning Examples)
Machine learning is used for speech recognition; where an algorithm compares an audio input with data stored in the system.
The use of machine learning is also common in natural language processing (NLP) operations, where data is converted between speech and text formats.
Two main methods of language and speech data handling for machine learning systems are; statistical machine translation (SMT) and neural machine translation (NMT), which differ from each other in terms of the model for data analysis.
Neural machine translation is currently the most-utilized algorithmic model or method of machine translation, due to its high efficiency . It is used with popular tools like Google Translate.
Speech recognition and machine translation functionalities are useful for simplifying data modification and input processes, which are in turn relevant for operations like file/database management, and security.
Machine learning examples are;
1. Algorithmic Geospatial Data Analysis
2. Self-driving Technology
3. Facial Recognition-based Security
4. Automated Diagnosis in Healthcare
5. Automated Speech Recognition and Translation
1). AbdELminaam, S.; Almansori, D. A. M.; Taha, M.; Badr, E. (2020). "A deep facial recognition system using computational intelligent algorithms." PLoS One. 2020 Dec 3;15(12):e0242269. Available at: https://doi.org/10.1371/journal.pone.0242269. (Accessed 6 January 2023).
2). Gupta, A.; Anpalagan, A.; Guan, L.; Khwaja, A. S. (2021). "Deep Learning for Object Detection and Scene Perception in Self-Driving Cars: Survey, Challenges, and Open Issues." Array 10(10):100057. Available at: https://doi.org/10.1016/j.array.2021.100057. (Accessed 6 January 2023).
3). Huang, X.; Jensen, J. R. (1997). "A Machine-Learning Approach to Automated Knowledge-Base Building for Remote Sensing Image Analysis with GIs Data." Photogrammetric Engineering and Remote Sensing. pp. 1185-1194. Available at: https://www.semanticscholar.org/paper/A-Machine-Learning-Approach-to-Automated-Building-Huang-Jensen/19a935d39239497ca67fc9c560302d905b85c165. (Accessed 6 January 2023).
4). Mohamed, S.; Malhat, M.; Elhady, G. (2022). "Prediction of cardiovascular disease using machine learning techniques." IJCI. International Journal of Computers and Information, 9(2), 25-44. Available at: https://doi.org/10.21608/ijci.2022.129472.1071. (Accessed 6 January 2023).
5). Simhambhatla, R.; Kuchkula, S.; Slater, R. (2019). "Self-Driving Cars: Evaluation of Deep Learning Techniques for Object Detection in Different Driving Conditions." Data Science Review, Vol. 2. Available at: https://scholar.smu.edu/datasciencereview/vol2/iss1/23/. (Accessed 6 January 2023).
6). Vashisht, V.; Pandey, A. K.; Yadav, S. P. (2021). "Speech Recognition using Machine Learning." IEIE Transactions on Smart Processing and Computing 10(3):233-239. Available at: https://doi.org/10.5573/IEIESPC.2021.10.3.233. (Accessed 2 January 2023).