Friday, June 28, 2024

Installing Koalas, the latest version of Android Studio

 


The latest version of Android Studio is called Koalas(2024.1.1)

Please visit this site for details: https://bit.ly/4eAwThe

For Windows download go here: https://bit.ly/3VToH4h

I had problems installing an older version named Arctic Fox here;

https://hodentekmobile.blogspot.com/2021/09/installing-android-studio-arctic-fox.html#google_vignette

Instructions:

If you downloaded an .exe file (recommended), double-click to launch it.

If you downloaded a .zip file:

Unpack the .zip.

Copy the android-studio folder into your Program Files folder.

Open the android-studio > bin folder.

Launch studio64.exe (for 64-bit machines) or studio.exe (for 32-bit machines).

Follow the Setup Wizard in Android Studio and install any recommended SDK packages.

Herein I describe the installation of Android Studio Koalas on a Windows x64 laptop Surface Pro 5. I downloaded this file:  android-studio-2024.1.1.11-windows.exe

The installation screens are shown here:










Although all the screens have successfully traversed, you do not see the Finish button enabled. The trick is go to each item in the list and accept the license terms. If all of them are accepted the Finish button gets enabled.


It will start downloading all the components and the program successfully ends.


This problem has been faced by any and even made it to the StackOverflow forum.


https://stackoverflow.com/questions/67062999/unable-to-install-the-sdk-tools-finish-button-is-disabled

Wednesday, June 26, 2024

Gemini puts Android App development on turbo-charge

Gemini is integrated with Android Studio (the latest version) as a plugin. There are very many plugins. Scroll down to see Gemini.


How does Gemini help Android Studio?:

In its present embodiment, it can do the following with some exceptions:

Code Generation: Analyze your code and suggest code completion like most other programming software IDEs. Code refactoring suggestions. It can suggest alternative approaches to achieve end result.

Error Analysis: Spotting errors related to code both in scripts and UI. UI integration being very important, this may be an extremely useful help.

Search and Navigation: They are strong points of Gemini and it will wade through the code and take you t specific part of your code. You should find it useful troubleshooting code not of your own but you got ownership. UI/Code interaction will get a great benefit from this feature. 

As can be seen, Gemini can greatly assist in App development. Some of these are also parts of what Android Studio do. We will come to the overlap later.

Do you have to do anything to get the Gemini to work with your code.?

This is a great question. You do not have to do anything special. Gemini works in the background and unless you look for it carefully you may not even notice it. Looking at suggestions you may infer it is coming form Gemini.

Take your suggestions from Gemini:

The previous paragraphs emphasizes the fact that Gemini can only suggest and it is up to the developer to implement or take action. This is very important presently because Gemini is still in the 'Learning' mode and it could make mistakes. However, as its suggestions are based on studied analysis, it can add to the repertoire of the developer. As Gemini goes through analysis, it can point to deficiencies in the project that can greatly improve the quality.

Gemini is your friend working in the background and no need to import anything extra. It only offers contextual help based on what you are doing.

There is an overlap between what Gemini brings to the project and what Android Studio already has but Code analysis for code improvement and refactoring are in the realm of Gemini.

I am indebted to Gemini for some of the above.


Friday, June 21, 2024

AI and diabetes

 It will be nice to bind together, food intake, CGM measurements and AI models to optimize intake for better glucose profiles for diabetes type I and II.

There are pretrained AI models for diabetes.

GlucoNet Model: Deep learning model that can predict Glucose levels based on carbohydrate intake.

Deep Gluco Model: Not only takes carbo intake into consideration but also insulin dosage, physical activity, etc.

GlucoNet is adequate for diabetes type II. I will be homing in on type II.

These are used to improve the MIT control loop for adjusting optimal carbo intake.

There is company (Alertgy) in Melbourne, Australia involved in the development of diabetes monitored by a wearable device.

Right now, I have one with questionable activity, but qualitatively measuring (Zero, when not connected and 3 peaks to coincide in time with break fast, lunch and dinner).

Tuesday, June 18, 2024

CoPilot loses to Gemini in a simple question

 Certainly! Let’s compare the carbohydrate content in 100 grams of rice, coconut powder, and soya powder:

CoPilot Reply:

White Rice:

  1. Coconut Powder:

  2. Soya Powder (Soybeans):

In summary:

  • Soya powder has the highest carbohydrate content, followed by rice and then coc

Gemini Reply:

Here's a comparison of carbohydrates in 100 grams of each food item:

  • Rice: Brown rice has about 70 grams of carbohydrates per 100 grams, while white rice has around 80 grams.
  • Coconut Powder: Unsweetened coconut powder typically contains around 60 grams of carbohydrates per 100 grams, with most of it being fiber.
  • Soybean Powder (Soy Powder): Defatted soy powder generally has around 50 grams of carbohydrates per 100 grams, with a significant portion being complex carbohydrates and fiber.

Therefore, based on this information:

  • Rice generally has the highest amount of carbohydrates among the three.
  • Coconut Powder comes in second with a moderate amount of carbohydrates, most of which is fiber.
  • Soybean Powder has the lowest amount of carbohydrates, with a good portion being complex carbohydrates and fiber.
How much of factual data can we depend upon using these AI's? Should we be afraid of them?

Friday, June 14, 2024

Scammer impersonating Elon Musk

 Beware!


Dall-E3 created image

I recently received a private message from Elon Musk in my twitter (X) account. I confess, I felt good. However, I was skeptical because why would a multi-billionaire send a message. Has he no one else to correspond with?


Here are some screenshots on that day (about 2 days ago).




I humored him along to see where that would take me. Then he spoke about the enormous amount of money that he has made and going to make with a new Mining company of his. "Have you looked into investing in Bitcoin", etc. It did not smell good. I terminated the conversation.

It even got better. Then he sent a 0.06Sec voice mail. I ignored.

Today, another Musk (I don't know how many of them are walking around) became my follower and sent another message. This is getting comical and silly.

Well, I may not be the only person on the Internet who is subjected to this nonsense. Take care! I don't believe, he will be sending any message, especially now that he has to think about another $56 billion.

Friday, June 07, 2024

What is an identity of a person? A question and answer from Gemini

 Who am I? What is my Identity? How am I defined? These are deep questions that has bothered us and still bothering us. 

The following question was posed to Bard, an earlier implementation of CoPilot. It is interesting to note that Bard and Gemini differ. Gemini thinks, it is the head that matters. Ok. What if the consciousness is distributed at the cell or even finer level? Also, Bard missed the initial assertion that the wife in confusion made the choices and nt after thinking. Note that Gemini tries to give a definite answer.

A man and his son are walking in a forest. Some bad elements cut-off their heads. The man's wife prays to the goddess. Goddess says, no problem. Just attach their heads and I will give them back life. The wife in confusion attaches the head of her son to her husband's body and husband's head to her son's body. They come alive. Now who is the husband and who is the son? 

This riddle hinges on the fact that after reattaching the heads, the bodies come alive but their identities are switched.

Here's the answer:

  • The husband's consciousness is now in the son's body. The head contains the memories and personality, so even though it's attached to the son's body, it's still the husband.
  • The son's consciousness is now in the father's body. Similarly, the son's head with his memories and personality is now on the father's body.

So, physically, their bodies are swapped, but their identities are determined by their heads (containing their consciousness).




SQL Server Versatile and Admirably well suited to AI

 The world is datacentric and everything moves based on data. SQL Server is a database management system and takes care of every aspect of data, from second to second management by online transaction processing (OLTP) to mining stored, archived data that includes data that streams (OLAP).

Data and Data Science:

Raw data can be enormous and the only way to give meaning and take out value out is the role of analytics. The advanced analytics handlers are the data science professionals. They go through the mountain of data and distil out the most useful, and the most relevant information. The success of a company, or organization is dependent on these professionals. All of these example following use cases and many more not mentioned here may be cited: credit risk assessments; managing customer/employee churn; hospitalization metrices; targeted sales & campaigns, etc.

Data Science using SQL Server:

SQL Server is a very comprehensive, database management system well suited for everything related to data present anywhere from OLTP data to OLAP data. It can be present both on site and in the cloud and integrated with the AZURE cloud which in turn is integrated with a myriad of other data related applications not only from Microsoft but from many other applications. Doing data science with SQL Server results in high value and high returns.

Data scientists can connect to a myriad of databases that can be used to train data and test the machine learning tool at their hands.

Where does AI come in or fit in?

The data scientists access the data from the client's database and combine with data from other sources to develop models using R software for joining the data and filtering based on criteria. They may begin shaping the data by creating extra informational features like new columns, or useful data partitioned or transformed, etc. This data shaping lays the foundation for predictive analytics. Going a step further they can put into operation a plan for the model that applications can use for producing useful outputs in the form of a predictive model.

This just one scenario where data is taken out of database and worked upon to get at the useful information by creating models. How easy is it? Moving large amounts of data in and out of database comes at a cost. Thinking about cost and other contingent aspects like the location of data, the security of data (that was not mentioned so far), the latency involved if geographically separated sites are involved, and not having features of DBMS like indexing, column stores, high availability, etc. one can conclude that it may be prudent to do as much of the filtering and shaping done on the database using all the tools the DBMS can provide instead of working on raw data from a database.

As a result of considerations discussed previously it will be indeed beneficial if data science and AI on the existing database can be carried out prior to moving out data. This allows you to leverage all the inbuilt features of the DBMS previously discussed. If the data involves geographical data these can be handled inside SQL Server's inbuilt data types. If on the other hand data has to be accessed from other data sources outside of Microsoft, the linked source feature of the DBMS can be used. 

The following picture copied from a Microsoft site shows the two ways discussed so far.


Another important consideration is after doing predictive analytics the operationalization of what has been achieved with data science, namely the predictive model. The deployment of this to a production environment can be accomplished by using programming using SQL Server R services in the form of a stored procedure. The predictive model will be stored as varbinary (max) in a database table.

Look forward to more discussions related to SQL Server and AI.
DMCA.com Protection Status