Tag: machine learning

Customs House
Digital Supply Chain

Making Waves in International Trade: The Benefits of AI in Simplifying Customs Processes

Hello everyone! As the host of the Digital Supply Chain podcast, I’ve been exploring the latest trends and innovations in the world of supply chain management and logistics. Recently, I had the pleasure of speaking with Oscar Morales, the CEO of Sifty, a company that is leading the charge in the use of AI and ML to simplify customs processes for customs brokers and improve efficiency in international trade.

In our conversation, Oscar highlighted the importance of data and the role it plays in the logistics industry. He explained that the more data that is shared about the various variables involved in an import/export transaction, the better the AI systems can become. This is because the more information that is fed into these systems, the better the outcome will be. This is why Sifty is dedicated to curating data automatically to extract the relevant information and provide its customers with actionable insights.

One of the major pain points that customs brokers face is the time-consuming and often complicated process of clearing goods through customs. Sifty is changing this by using AI and ML to automate many of the tasks that were once performed manually. This not only saves time, but it also reduces the risk of errors, making the entire process more efficient and streamlined.

Oscar also discussed the potential of the “digital ecosystem” in the logistics industry and how Sifty is working towards becoming the “operating system of the logistics industry”. By connecting with other participants in the industry and sharing data, Sifty is able to create better products and offer its customers a set of interconnected AI solutions to increase their efficiency.

One of the key takeaways from my conversation with Oscar is that Sifty is all about efficiency. The company produces software to decrease the time spent on certain bottlenecks in the customs process and make it easier for customs brokers. Sifty uses a lot of machine learning and advanced technologies, but it also works with humans, as the human element is critical for the efficiency of the technology to be effective.

Another important point that Oscar made was that there is often a fear surrounding AI and how it may replace jobs in various industries. However, he believes that this is not the case with Sifty. In fact, Sifty needs humans to be successful, as they play a crucial role in ensuring that the technology is used effectively.

In conclusion, the use of AI and ML in the customs process is a game-changer for customs brokers and those involved in international trade. By simplifying the process and reducing the risk of errors, companies can save time and increase efficiency, leading to increased revenue. If you’re a supply chain professional, I highly recommend checking out Sifty and learning more about the incredible work they’re doing in this space. And of course, be sure to listen to the podcast episode with Oscar Morales to hear more about this exciting topic!

If you enjoy this episode, please consider following the podcast and sharing it with others who may be interested. And as always, if you find the podcast of value, and you’d like to help me continue to make episodes like this one, you can go to the podcast’s Support page and become a Digital Supply Chain podcast Supporter for less than the cost of a cup of coffee!

And if you’re interested in having your brand associated with the leading Supply Chain podcast, don’t hesitate to check out these sponsorship packages and how I can help your company gain exposure and establish yourself as a thought leader in the supply chain industry, please don’t hesitate to get in touch.

Thank you!

Photo credit Shawn Harquail on Flickr

Mogens Maersk container ship
Digital Supply Chain

The Role of AI in Making Shipping Safer, Smarter, and More Sustainable

I’m excited to share the latest episode of the Digital Supply Chain podcast with you. This week, I had the pleasure of chatting with Ami Daniel, the co-founder and CEO of Windward, a company that provides maritime data and analytics to the supply chain industry.

During the episode, Ami shared some fascinating insights into how the company’s technology is being used to help various stakeholders in the supply chain ecosystem, from regulators to shippers to freight forwarders. We discussed Windward’s journey as a company, their plans for the future, and the challenges they’ve faced along the way.

One of the main topics we explored was the importance of data in the supply chain industry. Ami explained how Windward’s data is being used to increase transparency, reduce friction, and drive efficiency in the shipping industry. We also talked about the challenges of working with data at such a large scale and how Windward is using AI and machine learning to make sense of the vast amounts of information they collect.

Another interesting area we delved into was the impact of the COVID-19 pandemic on the supply chain industry. Ami shared his perspective on how the pandemic has accelerated the adoption of technology in the industry, as well as the challenges it has posed to various stakeholders in the ecosystem.

Ami also shared how data can be used to tackle illegal fishing and labor abuse in the global shipping industry, as well as with compliance with the Jones Act.

If you’re interested in the supply chain industry or the role of data in driving efficiency and transparency, I highly recommend you check out this episode of the Digital Supply Chain podcast. You can listen to it here or click the player above.

If you enjoy this episode, please consider following the podcast and sharing it with others who may be interested. And as always, if you find the podcast of value, and you’d like to help me continue to make episodes like this one, you can go to the podcast’s Support page and become a Digital Supply Chain podcast Supporter for less than the cost of a cup of coffee!

And if you’re interested in having your brand associated with the leading Supply Chain podcast, don’t hesitate to check out these sponsorship packages and how I can help your company gain exposure and establish yourself as a thought leader in the supply chain industry, please don’t hesitate to get in touch.

Thank you!

Photo credit – Torsten Sobanski on Flickr

Hospital monitor control panel
Digital Supply Chain

Simplifying Real-Time Location Tracking with Cloud-Delivered AI for Supply Chain

In this episode of the Digital Supply Chain podcast, I sat down with Adrian Jennings, the Chief Product Officer of Cognosos.

Cognosos provides real-time location intelligence solutions for the logistics and healthcare industries. Their aim is to bring the location intelligence technology that is now common in our personal lives to the enterprise level of logistics.

Adrian has over 23 years of experience in the real-time location industry and has worked on tracking various objects, from cars and airplanes to people and even monkeys. He explained that Cognosos’ solution is different from other real-time location solutions because it addresses the need for manual, spatially distributed processes, which occur in various industries but tend to be invisible. Cognosos’ solution offers a more flexible and efficient approach to real-time location tracking than the solutions available in the market.

Cognosos was founded in the era of cloud and AI, which allows the company to take a ground-up approach to tracking. Instead of using traditional on-premise processing, they use low energy Bluetooth beacons that are low-cost and easy to deploy. These beacons emit a low-frequency signal that is picked up by the tags and sent to the cloud for processing. This approach allows for a more cost-effective solution with improved performance.

Adrian explained how Cognosos solves the issue of location through machine learning. Instead of figuring out the X, Y, and Z coordinates of an object, which is a difficult task, they treat it as a classification problem. AI algorithms are excellent at recognizing patterns and making inferences based on sparse input data, like a sparse network of beacons. Cognosos leverages this technology to create a lightweight network of beacons that can determine a high-quality, high granularity location without the need for a heavy infrastructure.

Adrian shared two use cases for their solution, one outdoor and one indoor. In the outdoor example, in a logistics yard, cars are moved multiple times from the assembly line to the logistics organization, where they undergo various processing steps. By tracking the car, Cognosos provides visibility into the process, allowing the operator to see where the inefficiencies are and optimize the process. In the indoor example, in hospitals, Cognosos goes beyond just finding lost assets, it helps improve the utilization of equipment by reducing overstocking and making the process more efficient.

Cognosos is a rapidly growing company that is currently focused on vehicle manufacturing logistics and asset management in healthcare, mostly in hospitals. However, they are now starting to extend into smaller facilities as well. Their next frontier is workflow management in healthcare, where they aim to minimize inefficiencies by better managing and understanding the flow of patients and caregivers. In logistics, they are moving beyond automotive manufacturing and are now being pulled into other areas such as food and beverage, garment, and pharmaceuticals.

In conclusion, Adrian explained that the traditional approach to RTLS has been to focus on creating value through granularity, but this often leads to expensive and difficult-to-implement solutions. Cognosos, on the other hand, focuses on creating value through simplicity and ease of use, which has led to their rapid growth and expansion in various industries.

I hope you found this episode as informative and engaging as I did. If you want to learn more about Cognosos and their real-time location intelligence solutions, be sure to listen to the full podcast episode. And don’t forget to follow and support the Digital Supply Chain podcast.

If you enjoy this episode, please consider following the podcast and sharing it with others who may be interested. And as always, if you find the podcast of value, and you’d like to help me continue to make episodes like this one, you can go to the podcast’s Support page and become a Digital Supply Chain podcast Supporter for less than the cost of a cup of coffee!

And if you’re interested in having your brand associated with the leading Supply Chain podcast, learning more about these sponsorship packages and how I can help your company gain exposure and establish yourself as a thought leader in the supply chain industry, please don’t hesitate to get in touch.

Thank you!

Photo credit Quinn Dombrowski on Flickr

Technology / Software

Here comes the sun… IBM and solar forecasting


Concentrating solar power array

For decades now electricity grids have been architected in the same way with large centralised generation facilities pumping out electricity to large numbers of distributed consumers. Generation has been controlled, and predictable. This model is breaking down fast.

In the last decade we have seen a massive upsurge in the amount of renewable generation making its way onto the grid. Most of this new renewable generation is coming from wind and solar. Just last year (2013), almost a third of all newly added electricity generation in the US came from solar. That’s an unprecedented number which points to a rapid move away from the old order.

This raises big challenges for the grid operators and utilities. Now they are moving to a situation where generation is variable and not very predictable. And demand is also variable and only somewhat predictable. In a situation where supply and demand are both variable, grid stability can be an issue.

To counter this, a number of strategies are being looked at including demand response (managing the demand so it more closely mirrors the supply), storage (where excess generation is stored as heat, or potential energy, and released once generation drops and/or demand increases), and better forecasting of the generation from variable suppliers.

Some of the more successful work being done on forecasting generation from renewables is being undertaken by Dr Hendrik Hamann at IBM’s TJ Watson Research Center, in New York. Specifically Dr Hamann is looking at improving the accuracy of forecasting solar power generation. Solar is extremely complex to forecast because factors such as cloud cover, cloud opacity and wind have to be taken into account.
IBM Solar Forecaster
Dr Hamann uses a deep machine learning approach to tackle the many petabytes of big data generated by satellite images, ground observations, and solar databases. The results have been enviable apparently. According to Dr. Hamann, solar forecast accuracy using this approach is 50% more accurate than the next best forecasting model. And the same approach can be used to predict rainfall, surface temperature, and wind. In the case of wind, the forecast accuracy is 35% better than the next best model.

This is still very much a research project so there is no timeline yet on when (or even if) this will become a product, but if it does, I can see it being an extremely valuable tool for solar farm operators (to avoid fines for over-production, for example), for utilities to plan power purchases, and for grid management companies for grid stability purposes.

The fact that it is a cloud delivered (pun intended, sorry) solution would mean that if IBM brings it to market it will have a reduced cost and time to delivery, bringing it potentially within reach of smaller operators. And with the increase in the number of solar operators (140,000 individual solar installations in the U.S. in 2013) on the grid, highly accurate forecasting is becoming more important by the day.

(Cross-posted @ GreenMonk: the blog)

(Cross-posted @ GreenMonk: the blog)