Dear Author, you have a very good research. In many Engineering work it's hard to address issues all at the same time. Somehow to address some issues you need to trade or give up some advantages. In your work, what specific aspect(s) was/were sacrificed or ignored to achieve your goal. Like for example, the more complex encryption becomes the more hardware becomes expensive and complex too.
Thank you for your beautiful words and for taking an interest in our study. I agree that it is difficult to include all of the characteristics that affect the IoT device resources. Those characteristics can be within the encryption algorithm, as you mentioned, such as key size, number of rounds, and algorithm complexity, or within the IoT device itself, such as the number of processors, frequency, or even the type of operating system, or they can be in the environment surrounding the IoT device, such as temperature since our research experiment operates in multidimensional problems, which is why we addressed Machine Learning as a perfect solution for such issues. However, because the dataset was not available to us, it wasn't easy to evaluate all of the characteristics during our test, so we excluded several aspects in each of the sectors listed above. Some examples of ignored attributes are power consumption, the surrounding temperature, operating system impact (lightweight vs full version), limited number of key size and message size, and limited number of IoT devices. We hope that by making our framework open-source, the research community will be able to engage in incorporating all of the characteristics we have ignored.
