International Conference on IoT for Smart Living

I’ve just returned from International Conference on IoT for Smart Living, which was held in Colombo, Sri Lanka. It was my first time attending to an IoT conference, and I was very pleasantly impressed on many levels including conference organization and breadth of the talks delivered.

In day to day life as a software engineering practitioners we tend to think in terms of solving the problem and getting results in the best possible way. In that process, we choose the best technologies we could utilize, and the most promising software stack that could help us to simplify the lives of both people and us (developers). The hardest part of this process is not implementing the solution as a product, but give a solution that simplify the problem. This is something really important thing I learned from most of the presentations we had.

The keynote speech of the conference was delivered by Mr. Wasantha Deshapriya, who is the secretary of the Ministry of Telecommunication and Digital Infrastructure. His speech was on “IoT Country Readiness in Digital Sri Lanka”. Throughout his speech, Wasantha highlighted how Sri Lankan is introducing eGovernance to improve the efficiency and impact of public sector, and the need of national level policy (or rather a roadmap) to leverage IoT to accelerate the current work being done.

Morning session had three more speeches other than the keynote speech. Dr. Rishi Bhatnagar, who is the president of Aeris Communication India, Mr. Shivananda Koteshwar (Shivu) who is the Director of Technology at Media Tech India were delivering speeches of the evolution of IoT , Global prospectives of IoT and Smart Cities. Both of them were able to share some insights of IoT in India, where most of the focus is on utilizing IoT to take good care of the senior population, mitigating the problems of urbanization, and climate change. Also, Dr. Rishi highlighted the dimensions of cost, security, right skillset, mindset and cultures readiness, regulations and some technical aspects such as interoperability of devices and long lasting batteries.

Mr. Ajit Ashok Shenvi, who is the Director of Big Data & Analytics at Philips Innovation Campus, Bangalore was also delivered a speech in the morning. He was more focused on IoT in Healthcare. In his speech one thing that I noticed is the new business models that emerging with IoT such as “charge per service, not for the product” (Philips MRI scanners are available as a service in India as I heard).

We had four speakers delivering speeches in the evening. Mr. Pradeep De Almeida, Group CTO of Dialog Axiata delivered an insightful talk on IoT Infrastructure Development in Developing Country Perspective. The speech contained details about protocols that could leverage in developing country’s context of IoT. But the most important part is a use case that he presented complex problem and solved it without any technological infrastructure (I have attached a video below on that). His point was, “If you see a problem, simplify it and solve with minimal complexity. Later move for a more sophisticate solution peacefully”.

Mr. Wellington Perera from Microsoft and Mr. M. I. Deen fro Sri Lanka Telecom also presented in the evening session. The second most important speech of the evening session was delivered by Dr. Chathura De Silva, who is the Head of the Department of Computer Science and Engineering at University of Moratuwa. Where he demonstrated how he has done home automation to wire up things at his home. This presentation was one of exciting one we had.

In sum, IoT haven’t been in a level that would motivate me to attend to a conference, but this participation was refreshing and worth the time I spent there.

Understanding Softmax Regression

This is going to be short... Very short!

Reason being this post is too short is it's Pokemon Go time :)

Logistic regression is where we simply classify a set of values into two known classes. For example predicting whether a grid of pixels intensities represent a “0” or “1” digit. Now let’s consider a situation where we have to predict which digit a grid of pixel intensities are representing. This is exactly a generalization of Logistic regression, where we have to perform a multi-class classification. Hence we could also refer this as “Multinomial Logistic Regression”, which is also referred as the “Softmax Regression”.

Given an input x, our hypothesis will estimate the probability of the class label of the K different possible values and output a K-dimensional vector resulting K estimated probabilities.

Data Flow Graphs

In data flow graphs, computation is programmed as a directed graph. This graph enables the data flow across operations, where each node in the graph represents an operation or a computation. A node may send, receive or can send a response to a message that they received.

In the above data flow graph, the left most node generates the integer values from 1 to 10 and passes them to two successor nodes. One of the successors squares each value it receives and passes the result downstream. The second successor cubes each value it received and passed the result downstream. The right most node received values from both of the middle nodes. As it receives each value, it adds it to a running sum of values. When the application is run to completion, the value of sum will be equal to the sum of the sequence of squares and cubes from 1 to 10.

Given below is a pseudocode that represents above computations. Each function in the pseudocode is equivalent to a node in the graph.