Friday, 21 September 2018

Kanpur Air Quality Analysis using Yuktix Monitor and ankiDB ™ Software

Access to clean water and air should be our right as citizens. You can buy bottled water but you cannot buy pure air. Bad air is a health tax the society is forced to pay. (There was a Canadian company selling mountain air during Beijing crisis though!). The green activism around air quality suffers on two counts
  • The problem that we have no data
  • The problem that raw data is not action plan.

We touched upon the first problem in a separate blog where we talked about the density of stations, improving coverage for a city and developing hybrid network models where sensors can be deployed in large numbers. Here we want to talk about the second problem, namely what to do with the air quality data.

Kanpur is a city in North India that is synonymous with pollution. It used to be an industrial town and is famous for  leather tanneries.  Unfortunately there are few checks and balances in government and society re. the pollution. One drive along the stretch of Ganges near Unnao can convince you of that fact.  A current survey put Kanpur as the most polluted city in India.  This study was based on readings collected by Air quality stations like the one located in Nehru Nagar which is about 9 Km from Panki Power plant.

The link for accessing real time data from Nehru Nagar CPCB air Quality station is here.

We decided to do our own investigation and put an air pollution meter in Kanpur to capture PM 2.5 and PM 10 data for 3 months. We wanted to reach our own conclusions. We also wanted to see what kind of air quality analysis can be useful.

What is important to understand is that instead of poring over large data sets, most people want
    - visual clues
    - relationships in data set
    - quick comparisons

Now armed with 3 months worth of data , we set out to make ourselves a wish list for analysis. The same data is available as an excel file on request, just drop us a line on support email.

Question is, what can be done to make conclusions jump out of the data? Here, we have few suggestions.

1. The sensor locations on a map can be turned red or green in real time based on a pre defined threshold. This provides a visual clue about the areas needing more action.

2. Pollution time series data can be plotted to identify peaks hours.
3. Pollution data can be sliced by day of week and hours. This will tell us if some days or hours can better be avoided.

We capture PM2.5 and PM10 data every 5 minutes. Here is how it looks on Yuktix Air Quality dashboard. You can see the trends by hours, days and weeks. We took the same data in an excel sheet and went looking for day of week correlation with pollution peaks.

Here is the  excel plot with data bucketed on day of the week.  Here one interesting find is that pollution counter is going off on Thursdays! Do we really have more pollution on Thursdays?

We fire up the python SDK that comes as part of Yuktix ankiDB. Yuktix python SDK allows us to pull data from cache for a range of dates and devices and then we can run them through computation routines with ease.

Suppose if I want to download data for a group of devices between certain dates for my analysis, all I have to do is,

$python cron/cache/ --name dump:aq:raw:1 --serial devaq01 --start 20082018 --end 29082018
and viola I have all the data in a file. I can also instruct Yuktix Python SDK to run a series of computations on the data during download.  For example, to get differences between subsequent readings, we can use numpy epdiff1d on data and to filter outliers, we can use numpy to deal with a multi dimensional array. Plugging a new computation routine is as simple as writing a method and registering it with the SDK. for example, here is one computation routine that  runs on air quality devices.

We have code to update the serial routine mappings via the SDK. The SDK stores the map in database tables and our python lookup code can dynamically plug it when data for a device is downloaded. The results of computations are stored for further processing.  One neat analysis that we do is to detect peak hours of pollution. We are using peakutils and numpy to detect the changes and then use plotly to show the peak data on our web GUI.

We saw how can we go from merely collecting data to actually analyzing it and show useful actionable items.  Like, 

- Maps to show where to focus attention
- Peak detection in time can help us locate the source of pollution 
- Comparison of aggregates over time can show the effectiveness of strategies used to deal with pollution

Here is a screencast of Yuktix Air Quality dashboard. We value your feedback. If you have ideas on what can be done to improve data analysis, please drop us a line on

Tuesday, 11 September 2018

From Sensors to cloud - Digitizing Agriculture Research

"How do you get data for experiments"? I asked this question to one of the scientist working in an Agriculture institute. We do measurements twice a day, morning 8'0 clock and afternoon 2 pm, pat came the reply. Two data points for temperature and humidity. Wind speed is a counter and wind direction is inspected manually. This same data is used by researchers developing predictive models at their center. Then I made a suggestion. what if we automate the data collection process for not just above 4 variables but 10 and increase the data points to 300 per day? Now it was his turn to get excited. "It would be awesome! I can then focus more on developing models. I can as well do better modeling."

This conversation fits the same pattern whenever I talk to researchers. The reasons can be easy to see. Recently, we came in touch with one of the scientists working in the environmental science field at Kerala University, Trivandrum. After our discussions, the requirements were similar. Can we automate the process of data collection and analysis?

I have just come back from installing a Yuktix solar powered research grade weather station in their department premises with following sensors.
1. Temperature 2. Humidity 3. Pressure 4. Rainfall 5. Wind speed 6. Wind direction 7. Soil Moisture (VWC) 8. Soil temperature 9. Solar Radiation 10.Leaf Wetness 11. Digital Pan Evaporation meter

As part of our Yuktix software bundle they get 1. Access to real time data from anywhere, anytime 2. Downloading raw data between two dates 3. Downloading aggregate data between 2 dates (minimum, maximum and average etc.) 4. Daily, weekly and monthly reports on email with attached .csv file 5. Alert rules for variables and notification via SMS and Email. 6. Sunshine hours calculation, ETO reports, Peak detection analysis. 7. Add custom reports (on-demand feature). 8. Outliers filtering

A LCD TV was also installed in the reception area to show data and reports from the weather station. Below is the screencast.

Yuktix Solar Powered Automatic Weather station

Yuktix Weather station is powered by Yuktix wireless sensing platform. Data collected by Yuktix Weather Station is pushed to Yuktix cloud. The cloud makes this data available for real time access and monitoring. Then Yuktix ankidb can access the same data via API and run statistical and other calculations to prepare reports for your subscriber base. Yuktix AnkiDB can (1) Receive data using Yuktix cloud API, (2) Run outlier filtering to remove the sensor errors, (3) Store the data in a time series data store, (4) Run computation modules for devices, (5) Generate reports for subscribers, (6) Send notifications to the users (7) Display the data on our web GUI (8) Make the data available for further integration using REST API.
In case if you want a research grade weather station installed in your institute, please contact team Yuktix at +91-8884315300 or drop us a line on

Thursday, 28 December 2017

Yuktix is winner of India Israel Innovation Challenge

Results of Government of India StartupIndia innitiative India-Isreal Innovation challenege are out. Read more at this link. Yuktix Smart Sensing solution for post harvest i.e. ColdSense was selected as one of the innovative and affordable solution for reducing post harvest losses.  

In our previous blog, we talked about Yuktix Warehouse and Coldchain monitoring solution . As per GOI of the harvest and post harvest losses run to tune of loss of INR 92,651 crore (> 14 Billion dollars) and most of the post harvest loss happen due to lack of monitoring infrastructure.  

Yuktix is creating an affordable ICT system for 24x7 monitoring of environment conditions that together with computation models for different crops can provide actionable data to reduce waste, improve quality and resource utilization, cut losses thereby boosting the income.

The affordable next generation sensing systems we are creating can impact millions of lives who are dependent on agriculture. The idea of battery powered wireless sensing is applicable throughout the agriculture value chain. Right now, most of the agriculturist take decisions based on guesswork. As data is the new oil, we want to remove guesswork from equation and provide actionable intelligence.

Yuktix ColdSense

Thursday, 12 October 2017

Yuktix Technologies - Blockchain Technologies - One of the first member of DataBrokerDAO.

Yuktix Technologies is working with DataBroker DAO that is using Blockchain Technologies to record and maintain usage of sensor data. The current discussions of smart cities assume an array of sensors deployed at a granular level. To do the smart things and derive the benefits of data driven decisions, we need a large number of sensors. It is heartening to see then an attempt to invent a unique ownership model for sensors deployment.

There has to be a revenue model in place to power the sensor deployments. That is especially needed for use cases that today are not readily identifiable but incur a huge social cost. Air pollution is one such example. One way is to assume that municipalities and local government would do it. However what if we can create an ownership model where the society can participate and benefit as well?

What if we paid people owning the sensors every time their data was used? That should encourage the people to install and own sensors. However the biggest issue with such a model is question of trust. How can I trust my aggregator to pay me the right amount? How do I know that right usage data is recorded and is not tampered with? How can we ensure that for all the micro payments that are due to a sensor owner? Enter block chain. The technology is most familiar from crypto currency use case but it can also be applied to maintain tampering proof ledgers.

Yuktix Technologies is working with DataBrokerDAO alliance to power this use case. We provide REST API for Yuktix sensor devices (Yuktix SensorDB allows you to create public and private devices with few clicks) and Web Hooks to push data to any customized end point. This was used by DataBrokerDAO to provide a block chain ready implementation

Yuktix SensorDB is a IoT device management software that lets you manage IoT devices, store device data, run different computations algorithms, set alerts and notifications using Email or SMS.

Sunday, 23 July 2017

Digitising Indian Agriculture - ICT / IOT role in Agriculture - Part 2

ICT / IOT role in Indian Agriculture - Part 2
Some more applications

We talked about how data alone is not going to help and we need analytics on top of the data to get actionable intelligence in our previous blog. We saw two applications of IOT / ICT , namely micro weather station and Greenhouse monitoring.

We are going to talk more applications of IOT / ICT in agriculture. So continuing from where we left

3. Warehouse and Cold chain monitoring
The definition of a cold-chain is "A cold chain is uninterrupted series of storage,
production, logistic and transport while maintaining a desired low temperature range which is necessary to preserve and maintain the shelf life of products like agriculture produce, sea food, frozen food, pharmaceutical products and medicine, chemicals and other products which if not preserved using cooling will get deteriorate from their quality standards".

A large part of agriculture produce is stored to meet future demand and to keep it safe from changing weather patterns and diseases. The table below shows temperature and humidity ranges for  products which are stored in cold storage.

ProduceMin temperatureMax temperatureHumidity
Onion0 and 254 and 3155 - 65%
Banana131485 - 90%
Mango111885 - 90%
Grape-1185 -90%

There are products that don't require cold chain to storage but they also need to be protected from the elements and kept under a controlled climate, e.g. rice and wheat. There is definitely an impact of environmental conditions on every produce.

As per Government of India (GOI) , The harvest and post harvest losses run to the tune of Loss of INR 92, 651 Crores (more than 14 Billion US dollars). Most of post harvest losses happen due to lack of monitoring infrastructure. There is no easy and cost effective way to monitor what is happening inside cold storage. We do not have enough cold storage with climate control facilities. Problem is that losses at post harvest and storage stage are much sever than at the production stage.

You can read more at this link to know the percentage breakup of crops in the post-harvest losses.
Yuktix coldsense device 

Yuktix provides an efficient and reliable cold storage and warehouse monitoring solution under the “COLDSENSE” brand. Yuktix provides wireless sensor nodes (Temperature, humidity and gases), Solar powered and grid powered gateway with edge software and Yuktix sensorDB product to store and analyse the data. You can easily monitor warehouse internal environment data from anywhere using our wireless sensors and gateway. You can download and analyse the data using sensorDB. You can do continuous 24x7 monitoring of product storage conditions.

For example red chili should be stored between 6 degree - 8 degree Celsius. Few days deviation might not effect the quality but if deviation continues for few weeks or a month, it can result in quality reduction and hence export worthiness of the chili. Yuktix COLDSENSE allow you to set alerts using SensorDB and alerts are send to you on SMS or email as soon as a sensor reports deviation from the prescribed range .

SMS based Alert
The cold sense data can be used for thermodynamic modelling of the warehouse which can then help improve the cooling efficiency and reduce the power bill of the cooling tower. That saving of power on cooling towers leads to direct savings (ROI) for the warehouse operators.

We will discuss the Yuktix Cold sense product in a different blog. How cold sense is helping agriculture companies in monitoring their produce in warehouses in order to assure quality checks as well as improve the efficiency of the operations.

4. Farm and livestock monitoring :

About 20.5 million people depend upon livestock for their livelihood which contribute to 16% of the income of small farms household income. It provides employment to 8.8%  of the population in India. IOT/ ICT can play an important role in two ways when it comes to farm and livestock Monitoring.

  • You can monitor health, track real time location, monitor reproductive cycles and calving, maximise milking using IOT.  IOT can be used in after produce of livestock e.g. dairy monitoring. Stellapps, one of the India startup provide solution for livestock monitoring and diary monitoring.
  • You can use ICT to produce organic fodder in a environment controlled hydroponics chamber. You can easily monitor the internal environment, tweak it to come in the range that is most suitable for fast growth of the fodder. ICAR Goa is conducting such experiment. There are some other companies like Hydroponics Kenya , HITECH , FodderTech, Soybean-sprouter

5. Remote Irrigation Control - Without sensor and with Sensor based feedback

Irrigation is one of the most important aspect of agriculture and with climate changes and shrinking water tables, it is going to play a very important role in the future. The irrigation is directly related to the water conservation. If we can do smart irrigation then we can save water.

Yet another example is remote control of irrigation pumps. . Most of the farmers live quite far away from the field and they have to reach the field to turn ON/OFF the motors at odd hours i.e. late in the night and early in the morning. This difficult chore can be automated using ICT/IoT using a mobile phone or sensor feedback based system.

  • Mobile phone based control -Mobile phone based control -– You can call the number and press a button and , your pump would turn ON / OFF depending on the settings. You can control one motor or multiple motor with the same device. One of the well know India company working in this area is KISAN RAJA. Some others are Flybirdinnovation , Avanijal.
  • Sensor based automatic control of the irrigation line -   An automatic version of the previous solution  can be done by measuring the soil moisture with the help of conductance based soil moisture sensors. You then start the irrigation pumps depending on the actual soil moisture conditions. Some companies which are active in this are Corpx, FarmX, Farmobile, Edyn, Hortau, tevatronic, Aquaspy.

    You can irrigate a wide area with just using a single pump and drip irrigation. Such solutions are very effective where there is a water shortage for the crops that need very accurate irrigation like Banana or cotton plants. Using latest communication technologies like LORA or Sigfox , a big and large network of wireless soil moisture sensors can be deployed over a wide area and water supply can be made to specific areas depending on the real time irrigation requirements, thus optimising the usage of precious resource.

    In Gulf countries like Qatar or Saudi Arabia where there is an acute shortage of water, such solutions can prove to be very useful. Here is demonstration of how Yuktix Sensor based irrigation solution can be deployed over a large area using our different IP blocks like Yuktix LORA based soil moisture sensors, Yuktix Weather Station, Yuktix Solar powered gateway and Yuktix SensorDB  

That's all for now folks. Stay tuned for next instalment in our agriculture series. Next we will discuss  

6. NDVI imaging using Drones AgribotixTatransense 
7. Weather based Agriculture disease predictionYuktix Technologies 
8. Plantation Dashboard - Yuktix Plantation dashboard that combines many of above Yuktix solutions together in a one single product.

Happy Farming.

Saturday, 8 July 2017

Digitising Indian Agriculture - ICT / IOT role in Agriculture - Part 1

 ICT / IOT role in Indian Agriculture

In our past blogs, we shared information on how Yuktix is playing its role in Digitisation of Indian Agriculture institutes (Here is the link to the blog). We in Yuktix come across lot of enquiries about how IOT / ICT can  play a important role in India Agriculture keeping in mind the harsh economics realities ( 80% of rural house hold have marginal landholdings of 1 hectare and just 7% hold more than 2 hectare which lead to low quarterly revenue and thus low investment in technology - Source). 

I thought, it will be nice to write a blog on different applications of IOT / ICT in Agriculture and how it can make a difference. The rural-urban split of population in India is 68.84% and 31.16% and the level of urbanisation has increased from 27.81% (2001) to 31.16% (2011) which is further expected to increase in incoming years (interesting to note that the growth rate from 2001 to 2011 is less than 1991 to 2001 - Source). 

This incoming urbanisation and population growth will lead to more demand for food and away from the current production centres. More demand for food will require more production from different sectors of agriculture. Now weather is becoming more and more unpredictable due to global warming. It is no more like the earlier days when farmers were confident of looking up at the sky and predicting the rainfall (Source). The increased vagaries of weather are a major cause of concern for agriculture and in turn asking us to use more climate controlled technologies to bring predictable production.

Before start explaining the application of IOT(Internet of things) and ICT (Information and communication technology) in Agriculture, we need to clear a point. The raw data alone is not going to help any farmer. What farmers (and almost everyone else) would want are actionable and easy to follow outcomes on top of data that helps quality and yield. Below is a illustration of how IOT can really be a asset to India Agriculture.

Application of technology to agriculture is a big topic. It can cover areas like micro biology, tissue culture, farm mechanisation, Farm ERP systems, better seeds, better fertilisers, Hydroponics systems, better preservatives, market discovery mechanisms, supply chain improvements, better credit schemes, solar powered farm tools and a host of other things. Here we will focus mainly on application of electronics and computer in agriculture.

The talk of IOT and ICT in Agriculture today is interesting because of many inflection points. The semiconductor and wireless technology is easily available and at price points that would make sense from an ROI perspective of even a small-time farmer when manufacturing is done at production scale. We are going to talk about some of the useful applications of IOT and ICT in Agriculture for Indian Scenario.

1. Research Grade weather Station / Citizen Weather station 
Network of Weather station's run by IMD and some private organisation provide useful weather data to both research institutes and Weather enthusiastic. However with the availability of low cost and high precision semiconductor sensors, there is ample opportunity for research institutes and private parties to move away from a high cost instrument model to off-the-shelf sensor models. The communication options are cheaper, the micro controllers are power optimized and sensors are available off the shelf. It no longer makes sense to continue with the old model unless requirements are of a specific nature.

One of the hallmarks of next generation solutions are instant availability of data and deep analytic integration. The weather data is made available to the researchers instantly with Yuktix SensorDB and thus researchers can focus more on their core area of research rather than trying to collect data from the field.

There are weather prediction and disease prediction models available in public domain (link1 , link2) that researchers can use to analyse occurrence of crop specific diseases. Researcher can use Yuktix API to fetch data and run any computation model on that data to quantify risks of a disease outbreak. More information about research grade weather station can be found at this link

With respect to Citizen grade weather station, we are running one of its type, Bangalore open weather network funded by Citizen's of Bangalore. The data from these weather stations is open to public. We have also release Public API's and many people have used to make their own visualisations (one of the sample is this) . This kind of network prove out to be useful when scaled on a large area like City or state. Then the data can be used by government organisation for various purposes like weather prediction, agri-disease prediction, making a city as a more reliant city (here is a link for one of the interesting analysis we did using Bangalore open weather data)

2. Greenhouse remote  monitoring -  We raised the issue of working with raw data earlier. Most of the people do not have the training, inclination and resources to interpret raw data. What people would like instead is clear set of actionable outcomes that comes from mining the raw data. The question then is, what kind of outcomes can be powered by observing environment data from a greenhouse?

Yuktix battery and solar powered wireless sensor nodes enables greenhouse owners to remotely monitor climate conditions inside a greenhouse.
  • The drift of average temperature in a greenhouse is useful to time the plantation of seeds (Temperature drift play a major role in Rose greenhouses).
  • Disease prediction algorithm like Fire Blight Disease prediction model and Downy Mildew (another link) can be run by feeding the collected data in real time and precautionary measures can be taken before the onset of disease.  
  • Mums (small seedlings for Chrysanthemum) need humidity range between 90-95%. Anything above 95% will cause seedlings to die and anything less then 90% will cause slow growth. 
    The availability of continuous humidity data combined an automated sprinkler system can help owners get more out of their investments.
  • Disease prediction model for Capsicum 
  • Humidity management is a valuable tool to prevent diseases in greenhouses as part of overall Integrated Pest Management. Effective environmental control not only reduces disease pressure and reduces pesticide use, the reentry intervals from pesticide applications are no longer an issue.

The remote-control solutions for greenhouse would allow ideal conditions to be maintained with taking the human error factors out of the equation. You can monitor the conditions on an app and flick a switch on the app to control sprinklers or exhaust fans.
 Here are our earlier blogs about Smart Greenhouses

Stay tuned to know more about other area's where IOT/ICT can be helpful in the filed of Agriculture. 

3. Warehouse / Cold Chain monitoring
4. Farm Monitoring  / Livestock Monitoring
5. Remote Irrigation Control - Without sensor and with Sensor based feedback like Cropx, Farmx, KisanRaja
6. NDVI imaging using Drones - Agribotix, Tatransense 
7. Weather based Agriculture disease prediction - Yuktix Technologies 
8. Plantation Dashboard - Yuktix Plantation dashboard that combines many of above Yuktix solutions together in a one single product.

Happy Farming.

Friday, 22 April 2016

Yuktix python library to get Bangalore weather network data

Here we are releasing our python library for accessing Yuktix public API. This release is limited to weather network and public API only.

You can access the public API doc from here . Yuktix public API are REST API and of course you can write a client in your favourite language. All you need is your public API access key that you can see on your account | profile page.

This is a wrapper built using Request library ( and tested with Python 2.7.11. The full code is available as Gist right now. I will do better packaging and check it in a Github repo as well. I know all about API abuse. we are a small team and the only time I get to work on such stuff is between 12:00-3 AM so please play nice!

The Library

The script