IoT Applications for Honey Bee Colony Condition: What's the Buzz All About?
IoT Applications for Honey Bee Colony Condition: What's the Buzz All About?
Many countries across the world are experiencing extensive honey bee losses. In the USA alone, commercial beekeepers reported losses of 38% of their colonies in 2015-2016. Losses on this scale are dramatically reducing the profitability of beekeeping globally, and driving beekeepers out of the industry, despite the growing demand for honey, pollination, and other honey bee by-products throughout the world.
Contributing $174 billion worth of pollination to the agri-food industry annually, honey bees play an essential role in global food production. The Food and Agriculture Organisation of the United Nations estimates that 71 of the 100 most important crops, which provide 90 percent of food worldwide, are pollinated by bees.
The development of technology to more efficiently manage honey bee colonies and improve honey bee health will enable commercial beekeepers to reduce global losses and improve the quality of pollination services.
Dr. Fiona Edwards Murphy has developed a sensor platform, designed to be retrofitted into existing hives. Beekeepers tend to keep their hives in remote locations and a major challenge with instrumenting large-scale beekeeping operations is the vast geographical spread of the colonies themselves. Often located in remote rural areas, depending on Wi-Fi or cellular coverage is rarely feasible. Accumulating data from nodes spread across 10’s of square kilometers and then uploading this data to the cloud in a power efficient manner that does not interfere with the existing work practices of a farm poses a unique set of obstacles to overcome.
Working with satellite data transmission would enable instrumentation of hives at any location on the planet. However, putting a satellite transceiver in every beehive is impractical for many reasons, including cost and power implications. The solution ApisProtect has developed for this challenge is to use a combination of various long-range networks, including satellite, LTE, and LPWAN technologies to connect the various devices throughout a farm. This data stream is then analyzed and the beekeeping insights are sent to the customer in real time.
This solution uses a unique combination of sensors to monitor honey bees in the hive: temperature, humidity, CO2, sound, and acceleration. The data from these five onboard sensors provide the necessary data for machine learning and big data techniques to extract valuable information about hive condition, activities, and productivity levels.
Smart alerts, with actionable insights, are provided to the beekeeper. These insights detail hive condition, identify problems and suggest actions. Currently, this technology has been deployed to hives across the globe. Ten million honey bees across the USA, Ireland, South Africa, and the UK are now being monitored in specially selected test sites, with a variety of host beekeepers.
Data are being collected from multiple sources including thousands of examples of healthy and weak colonies; inspection reports; and aggregate, anonymized data collected from hives around the globe. These data are used by algorithms to understand each hive and send suggested actions for improved colony health and help beekeepers with the key problems they face every day.
Having access to this insight will help beekeepers identify a wide variety of problems, earlier than they can by using traditional inspections and enable beekeepers to monitor the health of their hives almost continuously, and in-between manual inspections.
A challenge in this area is that periodic manual checks can disturb the colony, are impossible during poor weather, are time-consuming, and require both specialized knowledge and equipment.
Therefore, even the most well-run commercial beekeeping operations will not be able to perform a manual check on a colony more than a couple of times per month. For operators with thousands of hives, manual spot checks can’t hope to catch all the issues. Unfortunately, this can lead to problems within hives being missed before it is too late to resolve.
The key value of this technology is the processed data – a high-level overview of each apiary with a breakdown of which hives are doing well, which ones are likely to experience problems, and which hives need immediate attention providing a 24/7 early warning system to help reduce losses.
This technology helps beekeepers identify which hives (out of thousands) need their immediate attention, and also plan their resource use (time, materials, labor) much more effectively; leading to more productive and effective colonies, and beekeeping operations even in the most remote locations.
Fiona Edwards Murphy is the CEO and co-founder of ApisProtect. She is among the most widely published authors on Internet of Things and honey bees. ApisProtect is an Irish technology company, which specializes in agricultural applications of Internet of Things technology, focusing on beekeeping. Dr. Edwards Murphy's work on the topic of hive monitoring has received many national and international awards from the Irish Research Council, The IEEE, IBM, The Irish Laboratory Awards, Google, and the Global Entrepreneurship Summit. Dr. Edwards Murphy completed her Ph.D. with the School of Engineering, and the School of Biological, Earth and Environmental Sciences at University College Cork in the area of Internet of Things applications for honey bee health. To find out more, log on to www.apisprotect.com or follow her on Twitter, Facebook, and Instagram using @ApisProtect.
Why IoT Needs AI?
Why IoT Needs AI?
Businesses across the world are rapidly leveraging the Internet-of-Things (IoT) to create new products and services that are opening up new business opportunities and creating new business models. The resulting transformation is ushering in a new era of how companies run their operations and engage with customers . By 2020, the Internet of Things (IoT) is predicted to generate an additional $344B in revenues, as well as to drive $177B in cost reductions. IoT and smart devices are already increasing the performance metrics of major US-based factories. They are in the hands of employees, covering routine management issues and boosting their productivity by 40-60% .
Gartner forecasted there would be 20.8 billion connected things in use worldwide by 2020, but more recent predictions put the 2020 figure at over 50 billion devices. Various other reports have predicted huge growth in a variety of industries, such as estimating healthcare IoT to be worth $117 billion by 2020 and forecasting 250 million connected vehicles on the road by the same year. IoT developments bring exciting opportunities to make our personal lives easier as well as improving efficiency, productivity, and safety for many businesses .
However, tapping into the IoT is only part of the story. In order for companies to realize the full potential of IoT enablement, they need to combine IoT with rapidly-advancing Artificial Intelligence (AI) technologies .
AI is the engine or the “brain” that will enable analytics and decision making from the data collected by IoT. In other words, IoT collects the data and AI processes this data in order to make sense of it. You can see these systems working together at a personal level in devices like fitness trackers and Google Home, Amazon’s Alexa, and Apple’s Siri .
With more connected devices comes more data that has the potential to provide amazing insights for businesses but presents a new challenge for how to analyze it all. Collecting this data benefits no one unless there is a way to understand it all. This is where AI comes in. Making sense of huge amounts of data is a perfect application for AI .
By applying the analytic capabilities of AI to data collected by IoT, companies can identify and understand patterns and make more informed decisions. This leads to a variety of benefits for both consumers and companies such as proactive intervention, intelligent automation, and highly personalized experiences. It also enables us to find ways for connected devices to work better together and make these systems easier to use.
It’s simply impossible for humans to review and understand all of this data with traditional methods, even if they cut down the sample size, simply takes too much time. The big problem will be finding ways to analyze the deluge of performance data and information that all these devices create. Finding insights in terabytes of machine data is a real challenge.
AI and IoT Data Analytics
There are six types of IoT Data Analysis where AI can help :
- Data Preparation: defining pools of data and clean them which will take us to concepts like Dark Data, Data Lakes.
- Data Discovery: finding useful data in the defined pools of data
- Visualization of Streaming Data: on the fly dealing with streaming data by defining, discovering data, and visualizing it in smart ways to make it easy for the decision-making process to take place without delay.
- Time Series Accuracy of Data: keeping the level of confidence in data collected high with high accuracy and integrity of data
- Predictive and Advanced Analytics: a very important step where decisions can be made based on data collected, discovered and analyzed.
- Real-Time Geospatial and Location (logistical Data): maintaining the flow of data smooth and under control.
AI in IoT Applications
The following are only a few examples of Artificial Intelligence applied in the Internet of Things applications:
- Visual big data will allow computers to gain a deeper understanding of images on the screen, with new AI applications that understand the context of images.
- Cognitive systems will create new recipes that appeal to the user’s sense of taste, creating optimized menus for each individual, and automatically adapting to local ingredients.
- Newer sensors will allow computers to “hear” gathering sonic information about the user’s environment.
- Connected and Remote Operations- With smart and connected warehouse operations, workers no longer have to roam the warehouse picking goods off the shelves to fulfill an order. Instead, shelves whisk down the aisles, guided by small robotic platforms that deliver the right inventory to the right place, avoiding collisions along the way. Order fulfillment is faster, safer, and more efficient.
- Preventive/Predictive Maintenance: Saving companies millions before any breakdown or leaks by predicting and preventing locations and time of such events.
These are just a few promising applications of Artificial Intelligence in IoT. The potential for highly individualized services are endless and will dramatically change the way people lives.
Figure 1: Challenges Facing AI in IoT   (Image credit: Ahmed Banafa).
Challenges Facing AI in IoT
AI and IoT is a perfect mix if used with all the capabilities of both technologies , but challenges are real and can slowdown this magical integration , below is a list of some of the challenges:
- Compatibility: IoT is a collection of many parts and systems they are fundamentally different in time and space.
- Complexity: IoT is a complicated system with many moving parts and non –stop the stream of data making it a very complicated ecosystem
- Privacy/Security/Safety (PSS): PSS is always an issue with every new technology or concept, how far IA can help without compromising PSS? One of the new solutions for such a problem is using Blockchain technology.
- Ethical and legal issues: it is a new world for many companies with no precedents, untested territory with new laws and cases emerging rapidly.
- Artificial Stupidity: back to the very simple concept of GIGO (Garbage In Garbage Out), AI still needs “training” to understand human reactions/emotions so the decisions will make sense.
While IoT is quite impressive, it really doesn’t amount to much without a good AI system. Both technologies need to reach the same level of development in order to function as perfectly as we believe they should and would.
Integrating AI into IoT networks is becoming a prerequisite for success in today’s IoT-based digital ecosystems. So, businesses must move rapidly to identify how they’ll drive value from combining AI and IoT—or face playing catch-up in years to come.
The only way to keep up with this IoT-generated data and gain the hidden insights it holds is by using AI in IoT.
- “ AI is the Brain IoT is the Body” https://aibusiness.com/ai-brain-iot-body/
- “AI, IoT, and Business Disruption” http://www.creativevirtual.com/artificial-intelligence-the-internet-of-things-and-business-disruption/
- “What are the major components of IoT” https://www.rfpage.com/what-are-the-major-components-of-internet-of-things/
- “The last mile of IoT is AI” https://www.bbvaopenmind.com/en/the-last-mile-of-iot-artificial-intelligence-ai/
- “Data Intelligence” http://www.datawatch.com/
- “AI and IoT” https://www.pwc.es/es/publicaciones/digital/pwc-ai-and-iot.pdf
- “IoT and AI” http://www.iamwire.com/2017/01/iot-ai/148265
- “IoT trends for business in 2018 and beyond” https://mobidev.biz/blog/iot-trends-for-business-2018-and-beyond
Ahmed Banafa has extensive research work with focus on IoT, Blockchain, cybersecurity and AI. He served as an instructor at well-known universities and colleges. He is the recipient of several awards, including Distinguished Tenured Staff Award, Instructor of the year and Certificate of Honor from the City and County of San Francisco. He was named as No.1 tech voice to follow, technology fortune teller and influencer by LinkedIn in 2018, featured in Forbes, IEEE-IoT and MIT Technology Review, with frequent appearances on ABC, CBS, NBC, BBC, and Fox TV and Radio stations. He is a member of MIT Technology Review Global Panel. He studied Electrical Engineering at Lehigh University, Cybersecurity at Harvard University and Digital Transformation at Massachusetts Institute of Technology (MIT). He is the author of the book “Secure and Smart Internet of Things (IoT) using Blockchain and Artificial Intelligence (AI)”.
In-Body Internet of Things Networks Using Adipose Tissue
In-Body Internet of Things Networks Using Adipose Tissue
As people are becoming older and more patients have multiple diseases, the number of embedded medical devices humans will have in their body increases. These implanted devices will collect vital information about the health status of patients and in some cases also perform actuation such as drug delivery. Transmitting data out of the body is difficult from many places inside the body. We advocate to network implanted devices using radio frequency communication. By making use of the body’s adipose (fat) tissue we able to achieve both higher data rates than conventional approaches and make it possible to transfer data to devices in regions from where it is easier to couple out the data.
Already in 2005, 25 million US citizens were relying on implanted medical devices (IMDs) such as pacemakers for life-critical functions . This number is expected to increase tremendously in the future, as new application areas for implanted medical devices such as drug delivery systems, intracranial pressure monitoring devices and artificial kidneys are emerging.
A further trend is to network these implanted devices which is necessary since more and more (elderly) people have multiple diseases that can benefit from implanted devices. This trend brings the Internet of Things into the human body. Nevertheless, some applications cannot be realized today due to a lack of bandwidth inside the body since current in-body communication methods such as capacitive and galvanic coupling do not offer high data rates.
Figure 1: In the future, we may have several IoT devices inside our body.
In this article, we present a novel approach that addresses exactly these issues. We show that the human body’s adipose (fat) tissue can be used as a communication channel for radio frequency (RF)-based communication. One major advantage of this approach is that it can support high data rates . This allows for supporting multiple sensors and in the long run more data-intensive applications such as electronic arms and brain-to-machine interfaces. Furthermore, coupling out signals at low power from inside the human body is impossible from many locations. Therefore, a communication channel within the human body will allow transferring in-body data to a location from where it is easy to couple out the signal.
Adipose Tissue As Communication Channel
Materials in human tissues can be divided into two main categories: those with high and those with low water contents. Muscle and skin have high water content with 73-78 % and 60-76 %, respectively, while fat and bone have low water content: 5-10 %, and 8-16 %, respectively . As adipose tissues retain less water, they have a low dielectric constant which means that radio waves travel better through adipose than muscle and skin.
In order to evaluate the applicability of using adipose tissue for communication between implanted IoT devices, we have been experimenting with different modalities. We have performed simulations with the CST simulator as well as experiments with ex-vivo material, i.e., porcine tissue. Furthermore, we have designed phantoms, i.e., artifacts that exhibit similar behaviour (e.g., in terms of dielectric properties) as adipose tissue.
Figure 2: The model used to characterize adipose communication.
Figure 2 shows an illustration of the model we used to characterize the adipose tissue. It consists of three layers with the adipose tissue situated between skin and muscle.
We have performed our experiments on 2.4 GHz, the same frequency WiFi, Bluetooth, ZigBee and other wireless technologies use. Our results show that fat tissue offers low transmission loss for intra-body communication. For a fat layer with a sickness of 20 mm or above (the human fat tissue sickness is on average between 20 and 30 mm), there is a good signal coupling between transmitter and receiver. Another finding from our experiments is that the skin and muscle layers act as a waveguide for the fat layer. This allows for energy-efficient communication meaning that even with low transmit output power, communication is possible. In more detail, our results suggest the following losses for a distance of 20 mm: 2 dB for the phantom and 4 dB for the ex-vivo setup. Based on these numbers we expect a loss of 3 dB for human adipose tissue.
Reliability and Potential Disturbances
The experiments above are performed using a straight fat channel without any disturbances. In a human body, however, the fat channel is in many cases not straight, the thickness is not homogeneous and has disturbances in form of blood vessels. Our results have shown that also in such cases, communication using low-power communication is possible.
Adipose Tissue As Sensing Channel
Networking implanted IoT devices also enables new sensing applications within the human body because the fat channel can also be used for sensing: for example, a tumor relapse changes the communication properties . In particular, the strength of the received signal decreases with hinders such as tumors. This enables us to identify, e.g., the relapse of a breast cancer tumor.
Figure 3: Model and results for pertubants such as tumors. The adipose tissue can be used as a sensing channel to identify, e.g., tumor relapse.
Figure 3 shows the simulation setup used for studying the impact of pertubants such as tumors on the communication. The simulation model is informed by parameters measured with an ex-vivo setup. The results clearly show that with the size of the tumor, the coupling between the transmitter and receiver probes decreases. Hence, measurements of the coupling between the probes over time can be used to identify tumor relapse.
Safety, Privacy, and Security
While we propose to use RF inside the body which may have harmful expect as humans, we note that we use low-power waves with 1000 times lower power than cell phones and hence this type of in-body communication would still be SAR (specific absorption rate)-compliant.
IoT networks and devices inside human bodies may put human privacy and safety at risk and hence security and privacy are of utmost importance. We are currently addressing these issues in a long-term project funded by the Swedish Foundation for Strategic Research.
- D. Halperin, T. S. Heydt-Benjamin, K. Fu, T. Kohno, and W. H. Maisel, “Security and privacy for implantable medical devices,” IEEE pervasive computing, vol. 7, no. 1, 2008.
- N. B. Asan, C. P. Penichet, S. Redzwan, D. Noreland, E. Hassan, A. Rydberg, T. J. Blokhuis, T. Voigt, and R. Augustine, “Data packet transmission through fat tissue,” IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology, 1(2), 43-51, 2017.
- V. Komarov, S. Wang, and J. Tang, J., “Permittivity and measurements”. In K. Chang (Ed.), Encyclopedia of RF and microwave engineering (3693e3711). New York: John Wiley and Sons, Inc., 2015.
- N. B. Asan, J. Velander, Y. Redzwan, R. Augustine, E. Hassan, D. Noreland, T. Voigt, T. Blokhuis and R. Augustine. "Reliability of the fat tissue channel for intra-body microwave communication." In 2017 IEEE Conference on Antenna Measurements & Applications (CAMA), pp. 310-313. IEEE, 2017.
Noor Badariah Asan is currently a Ph.D. student in Microwave Technology in the Department of Engineering Sciences, Uppsala University, since 2015. She is working on characterizing and developing fat intra-body microwave communication. She received the B.E. degree in Electronic Engineering (Telecommunication Electronics) from Universiti Teknikal Malaysia Melaka, Malaysia, in 2008, and the M.E. degree in communication and computer from National University of Malaysia, Selangor, Malaysia, in 2012. In 2010, she joined the Department of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka, as a Lecturer. Her current research interests include wireless sensor network, designing, optimizing and characterizing biomedical sensor for intra-body area network. She is a student member of IEEE.
Robin Augustine received his Ph.D. in electronics from Université de Paris Est Marne La Vallée, France, in July 2009. He was post-doc at the University of Rennes 1, from 2009 to 2011. Since 2011, he has been working as a senior researcher at Uppsala University, Sweden. In February 2016, he was appointed as Associate Professor. He is the PI of Indo-Swedish Vinnova-DST funded project BDAS. He received Swedish Research Council (VR) funding for his project Osteodiagnosis. He is currently leading the Microwaves in Medical Engineering Group (MMG) at the Solid State Electronics Division, Uppsala University. He is author or co-author of more than 110 publications and IEEE member.
Thiemo Voigt received the Ph.D. degree from Uppsala University, Sweden, in 2002. He is a Professor of computer science at the Department of Information Technology, Uppsala University. He also leads the Networked Embedded Systems group at RISE SICS. His current research focuses on system software for embedded networked devices and the Internet of Things. He is author or co-author of more than 170 reviewed publications and his work has been cited more than 12400 times and received awards at multiple conferences.
Setting a New Pace for the Future of Farming
Setting a New Pace for the Future of Farming
In the last 50 years, the world’s population has rapidly increased and continues to expand faster than at any other time in human history. To meet the needs of the world’s growing population, food production must increase by 70% by 2050 . For small farmers, herders, and fishermen who currently produce about 70 percent of the global food supply, this presents a grave task. With their current farming systems not up to the challenge, the need for a solution which can overcome modern challenges in fast-paced farming environments has never been greater – and the answer lies with precision farming.
In today’s modern world, farmers are tasked with overcoming challenges such as limited farmland, waning natural resources, strict sustainability regulations and water shortages. These hurdles have major implications for farmers and prevent them from feeding the growing population. Enter the solution for farmers to partner with technology. Farming equipment that is automated can increase efficiency, while remaining sustainable, producing higher yield from 24/7 operation that manpower alone cannot provide.
For farming operations, autonomous equipment consists largely of tractors, weeding machines, and planters that must traverse large areas to plant, harvest, and manage expansive crop fields. Reliable mobile connectivity is a must-have to keep this equipment running. If there is latency or delay in data transmission to an autonomous piece of equipment, the machine will stop. However, until now, wired, cellular, LTE and traditional Wi-Fi mesh networks have not been able to deliver this level of connectivity on their own. These technologies were simply not built to meet the bandwidth demands and mobility needs that these applications require from a network.
In a scenario such as this, consistently high throughput connectivity is critical. If farmers are to achieve peak productivity, while also keeping costs low, they must find the right type of network to power its Internet of Things (IoT)/ automated applications. A farm’s network is ultimately the asset that powers agricultural automation, delivering the connectivity required to run digitally-driven precision farming equipment.
The right network technology can open doors to a new age of efficient, automated and sustainable farming. The network will empower the use of precision farming technologies, which utilize automated agriculture robots to produce a resilient, productive system that works around the clock to perform typical farming tasks with far greater speed, accuracy, and productivity than traditional manual means.
In addition to this, precision farming enables real-time data to be gathered and analyzed to help farmers make better decisions. For example, soil hydration and PH/nutrient levels in soil can be monitored to increase the yield of crops, while eliminating the need for constant surveying and testing of the ground by staff. This also opens doors for the use of drones in agricultural environments, allowing crops to be autonomously fertilized and sprayed to aid a more productive, balanced and regimented process of crop management.
Creating a Living Network
For this to be achieved, farmers require a network which can move with their operations to drive Industrial Internet of Things (IIoT) capabilities. To meet the demands of precision farming practices for any level of automation, a highly-mobile and secure network is critical. A network such as this is able to rise to the challenges of autonomous equipment, providing a way to dynamically load balance traffic, mitigate interference by routing around detected congestion, and react to topology changes to provide continuous connectivity without fail.
This is critical to farmers’ operations, as downtime can critically impede production, so connectivity must be 100% reliable regardless of mobility demands as equipment travels over farmland. It also means that farmers can keep a constant line of remote communication that is resilient to adverse weather conditions, pesticide sprays, rough conditions and mobility’s unpredictability.
Ease of set up is another factor as the network may require shifting based on varied harvest schedules. All networks are not created equal and farmers need to shop with these success factors in mind. However, thanks to advancements in wireless access nodes technology, tractors, drones, soil sensors and more can be easily connected to a peer-to-peer network, seamlessly creating an autonomous IIoT environment. Within this, every connected asset has the ability to be on the move and are always able to communicate with a remote operator, even at the network edge. By interconnecting crops, tools and vehicles to smart devices and sensors, farmers will not only be able to produce more, but they will also be able to do so while saving money and conserving natural resources.
An example of the profound abilities of wireless access nodes can be found in eucalyptus farming. By powering forest-wide remote monitoring applications to optimize yields, farmers have benefitted from sensor-based monitoring of tree growth pace, identification of disease via computer vision and AI, and fire and disaster management.
Achieving Autonomous Farming
The growth of advanced and autonomous equipment in the agricultural industry is empowering farmers globally to feed the growing population while using less farmland; using fewer natural resources while increasing yields; reducing pests and diseases without stripping the soil of its nutrients.
While the realization of a fully automated farm will not happen overnight, the key to success will be starting with a network that can easily grow to support more and new IIoT enabled assets, with increasingly autonomous demands, over time – which will, in turn, empower the fast-paced and relentless environment of agriculture.
- Global agriculture towards 2050, FAO, 2009, http://www.fao.org/fileadmin/templates/wsfs/docs/Issues_papers/HLEF2050_Global_Agriculture.pdf
Chris Mason is the Director of Business Development for the EMEA Market at Rajant Corporation. Prior to Rajant, Mason worked with British Telecom (BT) in a variety of sales, business development and management roles to help worldwide organizations identify IT solutions for common business challenges. Mason has experience with the United Kingdom’s Terrestrial Trunked Radio (TETRA) network for the Emergency Services and the Ministry of Defence. Mr Mason also earned a Bachelor of Arts and a Master of Science in Telecommunications Business from University College London and is an active member of the Institute of Directors.