Analysis of Lab Reports Exploring Artificial Intelligence

Artificial intelligence has revolutionized the worlds of science and technology, and its applications have been widespread in various fields. These three AI lab reports demonstrate the potential of AI in advancing the field of computer science and engineering, specifically in the areas of machine learning, natural language processing, and computer vision. The first lab report, “Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques” by Senthilkumar Mohan et al., about machine learning in predicting heart diseases proved to be the strongest lab report because it provided many experiments and the results of the data, which were expressed in an organized table and were very concise and straightforward; the second report, “Effects of sentence structure and word complexity on intelligibility in machine-to-human communications” by Justine Hui et al., was also a strong lab report about the effects of sentence structure in machine-to-human communications, but provided far less data and repetitive visualization, which makes it hard for the reader to imagine how useful AI processing is; the last lab report, “Sequential three-way decisions in multi-category image recognition with deep features based on distance factor” by A.V. Savchenko, on computer vision and image recognition, was the weakest because it used very confusing language and used formulas that I wasn’t able to understand or comprehend.

In the lab report “Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques”, the authors demonstrate the power of AI in identifying patterns and making predictions based on data. The report explores the use of a deep learning algorithm to predict the likelihood of heart disease in patients based on their medical records. The results showed that the algorithm was able to predict the risk of heart disease with an accuracy of 90%, which is a significant improvement compared to traditional methods. This lab report has the best structure because there are headings before every new topic, such as “Overview of Method and Results”, “Proposed Method HRFLM”, “Experimentational Environment”, “Evaluation Results”, and “Conclusion”, which makes it a lot easier for the reader to understand what they will find in each section. The wording was surprisingly a lot easier to understand given that this lab report is about such a complicated topic as machine learning. The introduction was very clear and specific about the problem of identifying heart disease and how this new algorithm will improve current standards. To prove their claim, the authors provided a very clear description of their methods and experiments, as well as their findings and the data they collected based on this new algorithm that was converted into tables and graphs, which clearly showed the results of this new technology and how this new algorithm is a lot more accurate than anything we have tried before. The analysis of this data converted these graphical findings into mathematical equations used to create this algorithm, which ties together the entire study to the conclusion and proves that this new method in predicting heart disease will “save human lives”. The results and findings of this lab report were very clearly shown, and the entire report was very detailed and organized.

The lab report “Effects of sentence structure and word complexity on intelligibility in machine-to-human communications” on natural language processing highlights the potential of AI in improving communication between humans and machines. The report investigates the use of a natural language processing algorithm to generate human-like responses to text input. The results demonstrated that the algorithm was able to generate responses that were indistinguishable from those generated by a human, which could have significant implications for the development of chatbots and virtual assistants. This lab report had a very detailed introduction which did a very good job of illustrating the potential of such technology and how important it is to improve communication between humans and machines. The headings that followed the introduction such as, “Methodology”, “Participants”, and “Semantically unpredictable sentences (SUS)”, made this lab report very organized and provided a nice flow between each subject matter and how each topic affected the overall results of the experiments. The participants and experiment themselves were very clearly demonstrated and the authors did a good job in conveying why they specifically chose participants from New Zealand in order to control possible variances in their language dispositions and why the experiment was conducted on a select number of people from one country rather than people from different places in the world. However, the overall results of this report failed to illustrate the data in a comprehensive way, which makes it unclear to the reader about the accuracy of new language processing algorithms. All of the graphical data in this lab report were expressed in box and whisker diagrams which made the overall results for each experiment seem very mundanely similar to the previous one since that was the only way the data from each experiment was expressed. This repetition made this experiment a lot more dull and tedious to understand because the plots only did a good job in showing the medians of the experiments but not the actual distributions of the given data. The wording that explained these diagrams was also more complex and difficult to follow, but the headings of the report outlined the purpose of each experiment which was able to help me understand the main point of this report. Overall, this lab report was well structured and very concise, but it offered its results in a very repetitive manner that failed to provide the clarity of the data and illustrations that the previous report had.

Lastly, the lab report “Sequential three-way decisions in multi-category image recognition with deep features based on distance factor” on computer vision showcases the capabilities of AI in interpreting and understanding visual data. The report explores the use of a convolutional neural network to classify images of various objects. The results of this lab report showed in the introduction and conclusion informed the readers that the algorithm in this new image recognition technology was able to classify objects with an accuracy of over 95%, which is a significant improvement compared to traditional image recognition techniques. However, this lab report had the worst structure because the headings after the introduction all had confusing terminology that isn’t apparent to readers who are not educated in artificial intelligence and algorithms, such as “Sequential Three-way Decisions”, and “Transform Matrix”. The overall language in this report was too difficult to follow, and most of the data provided was presented in very confusing mathematical equations. The data provided by these equations showed little to no illustrations, and there were no definitions for these equations that showed the relevance of these complicated mathematical formulas. All the complex words and equations made the report the worst out of all three lab reports since it was very hard to understand all the jargon that comes with facial recognition software.

Overall, these three lab reports demonstrate the potential of AI to advance various fields of science and technology. These reports did a good job of demonstrating their point and using data and formulas to support their claims. The overall structure for these labs was good, but I struggled reading some parts of each report. The first lab report was structured the best because the headings provided a clear subject matter, and even if the language was confusing at some points, the headings and illustrations provided an overall summary of the findings of this new algorithm, which made this report a lot easier to understand than the rest. The other two were a lot more difficult to understand, with some unclear headings and sometimes undefined data and mathematical equations, which is what makes them so poorly structured since a good lab report consists of consistency and the ability to convey your message to a larger audience so that more people could understand the message in the reports. Overall, all three reports were very interesting and had fascinating results that tied up the flow of each lab report, which will prove to change how we use and understand artificial intelligence. The ability of AI to identify patterns, improve communication, and interpret visual data has enormous implications for the future of computer science and engineering. As AI continues to evolve and become more advanced, it is likely that we will see even more impressive applications of this technology in the future.

References

Mohan, S. (2019, June 19). Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques. Ieeexplore.Ieee.org. Retrieved March 14, 2023, from https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8740989

Hui, J., Jain, S., & Watson, C. I. (2019, September 20). Effects of sentence structure and word complexity on intelligibility in machine-to-human communications. Sciencedirect.com. Retrieved March 14, 2023, from https://www.sciencedirect.com/science/article/pii/S0885230817302243?ref=pdf_download&fr=RR-2&rr=7a8052931f5b335a

Savchenko, A. V. (2019, July 5). Sequential three-way decisions in multi-category image recognition with deep features based on distance factor. Sciencedirect.com. Retrieved March 14, 2023, from https://doi.org/10.1016/j.ins.2019.03.030