Connect with us


Coping With Havoc Is A Must For AI Autonomous Cars 

By Lance Eliot, the AI Trends Insider  Havoc is a standout.    In sports, one of the more unusual and lesser-known metrics for analyzing football teams consists of their havoc rating.  To calculate a havoc rating, you count up the number of football plays that your defense was able to disrupt against the opposing team, such […]



Whether AI self-driving cars will be able to contend with the havoc created by human drivers and pedestrians remains to be seen. (Credit: Getty Images) 

By Lance Eliot, the AI Trends Insider 

Havoc is a standout.   

In sports, one of the more unusual and lesser-known metrics for analyzing football teams consists of their havoc rating.  To calculate a havoc rating, you count up the number of football plays that your defense was able to disrupt against the opposing team, such as plays when your defense was able to intercept the football or forced the opposing team to fumble the ball, or tackled the opposing side for a loss of yardage, and so on. Next, you divide that count of disrupted plays by the total number of plays undertaken by the opposing team.   

The resulting fraction is turned into a percentage, allowing you to readily see what percentage of the time that the defense was able to mess-up the opposing side’s offense.  For example, if there were 100 plays by the opposing team and your defense was able to undermine the offense on 25 of those plays, you would have a havoc rating of 25% (that’s 25 divided by 100).   

The offense wants to keep the havoc rating as low as possible; the defense is aiming to get as high a havoc rating as they can, showcasing how often they can cause the offense to slip-up. If you had a havoc rating of 100%, it would mean that on every play that was run by the opposing team, you managed to confound their efforts. That would be tremendous as a defense. Of course, if you had a havoc rating of zero, it would suggest that your defense is not doing its job and that the opposing side is making plays without being at all disturbed or undermined. 

Havoc ratings can be used in other endeavors too. Perhaps we ought to be using a havoc rating when it comes to the emergence of true AI-based autonomous self-driving cars. 

For my framework about AI autonomous cars, see the link here: 

Why this is a moonshot effort, see my explanation here: 

For more about the levels as a type of Richter scale, see my discussion here: 

For the argument about bifurcating the levels, see my explanation here: 

Understanding Havoc And Self-Driving Cars  

True self-driving cars are ones where the AI drives the car entirely on its own and there isn’t any human assistance during the driving task. These driverless cars are considered a Level 4 and Level 5, while a car that requires a human driver to co-share the driving effort is usually considered at a Level 2 or Level 3. The cars that co-share the driving task are considered semi-autonomous, and typically contain a variety of automated add-ons that are referred to as ADAS (Advanced Driver-Assistance Systems). 

There is not yet a true self-driving car at Level 5. We don’t yet know if this will be possible or how long it will take to get there.   

Meanwhile, the Level 4 efforts are gradually trying to get some traction by undergoing very narrow and selective public roadway trials, though there is controversy over whether this testing should be allowed per se (we are all life-or-death guinea pigs in an experiment taking place on our highways and byways, some point out).   

Since the semi-autonomous cars require a human driver, I’m not going to try and apply a havoc rating to the efforts of a Level 2 or Level 3 car. We could do so, but it would make the havoc aspects murky because there would be a portion attributable to the human driver and another portion caused by the automation, likely a blur of the two sources.   

Instead, let’s focus on the havoc aspects involving true self-driving cars, ones at Level 4, and Level 5. With the AI being the only driver, the havoc aspects can be assigned to the driving system per se.   

There are two ways in which havoc can arise: 

1)      By the actions of human drivers and for which the AI must contend 

2)      By the action of the AI driving system and for which other drivers need to contend   

I think that we would all agree that human drivers often create havoc in traffic. As such, the AI driving system must be able to cope with havoc instigated by nearby human drivers. 

You might be somewhat surprised at the second way in which havoc arises, namely by the actions of the AI driving system. Many pundits claim that AI driving systems will be perfect drivers, but as you’ll see in a moment, this is a false and misleading assumption.   

Before I jump into the fray, some pundits also assert that we’ll have only self-driving cars on our roadways and therefore there isn’t a need to deal with human drivers. Only someone living in a dream world would believe that we are only going to have self-driving cars and won’t also have human drivers in other nearby cars.   

In the United States alone, there are about 250 million conventional cars. All those cars are not going to suddenly be dispatched to the scrap heap upon the introduction of self-driving cars. For a lengthy foreseeable future, there will be both human-driven cars and self-driving cars mixing together on our highways and byways. 

It stands to reason.   

Human Drivers Create Havoc   

Consider the apparent notion that human drivers can create havoc. 

You are driving along, minding your own business, when a car that’s to your left opts to dart in front of your car and make a right turn at the corner up ahead. 

We’ve all experienced that kind of panicky and curse invoking driving situation.   

The lout that shockingly performs such a dangerous driving act is creating havoc. 

They are likely to disrupt your driving, forcing you to heavily use your brakes, maybe even causing you to swerve to avoid hitting their car. A car behind you might then need to also take radical actions, trying to avoid you, while you are trying to avoid the transgressor.   

There might be pedestrians standing at the corner that see the madcap car heading toward them, forcing them to leap away and cower on the sidewalk.   

Imagine then a human driver that throughout a driving journey might undertake some number of havocs producing driving actions. Divide the number of havoc acts by the total number of overall driving actions, and you have a percentage that reveals their havoc rating. 

The higher a havoc rating for a driver, the worse a driver they are. For a driver with a low havoc rating, it tends to suggest that they are not creating untoward driving circumstances while on the public roadways. 

Are you already thinking about a friend or colleague that you are sure must have a sky-high havoc rating? 

I’m sure you know such driving Neanderthals.   

Currently, few of the self-driving cars that are being tried out on our roadways are particularly versed in dealing with high havoc-rated human drivers. 

Most of the self-driving cars generally assume that the surrounding traffic will be relatively calm and mundane. You can think of those self-driving cars as acting a bit like a timid teenage driver that is just starting to drive a car. Those novice drivers hope and pray that no other driver will do something outlandish.   

If other drivers do crazy things, the teenage driver will resort to the simplest possible retort, which might be applicable or might make the situation even worse. In the case of getting cut off by the driver to their left that is darting toward a right turn, the novice driver might jam on the brakes and come to a sudden halt. Doing so might not have been the best choice, and it could end up with the car behind them rear-ending their car. 

 True self-driving cars need to step-up their game and be able to contend with high havoc human drivers.   

This capability can either be hand programmed into the AI driving system or can be “learned” overtime via the use of Machine Learning (ML) and Deep Learning (DL). I don’t want to though suggest that the ML and DL are equivalent to human learning, which they most decidedly are not. There is no kind of common-sense reasoning involved in today’s ML and DL, nor do I expect to see such a capability anytime soon. 

For why remote piloting or operating of self-driving cars is generally eschewed, see my explanation here: 

To be wary of fake news about self-driving cars, see my tips here:  

The ethical implications of AI driving systems are significant, see my indication here: 

Be aware of the pitfalls of normalization of deviance when it comes to self-driving cars, here’s my call to arms:   

Self-Driving Cars Create Havoc 

Now that we’ve covered the obvious use case of human drivers that create havoc, let’s explore the lesser realized aspect that self-driving cars can also generate havoc.   

Suppose that a true self-driving car is coming down the street. The self-driving car is moving along at the posted speed limit and obeying all the local traffic laws.   

A pedestrian on the sidewalk is looking at their smartphone and not paying attention to the traffic, and not noticing the sidewalk activity since their nose is pointed at their phone.   

Oops, the distracted pedestrian nearly walks right into a fire hydrant. At the last moment, the pedestrian side steps around the fire hydrant, moving suddenly onto the curb.   

The AI driving system of the self-driving car is using its cameras, radar, LIDAR, ultrasonic sensors, and other detection devices to monitor the traffic and nearby pedestrians.   

Upon detecting the pedestrian that seems to be bent on entering into the street, and not realizing that the pedestrian was merely avoiding conking into a fire hydrant, the AI calculates that the pedestrian might get into harm’s way and end up in front of the car.   

Wanting to be as safe as possible, the AI instructs the car to come to an immediate halt. 

Well, it turns out that the sudden stop of the self-driving car then leads to a human-driven car that is behind the driverless car to rear-end the self-driving car. 

The point is that the actions of the AI driving system can be well-intended (though don’t ascribe human intention to the AI system, please, at least until someday the “singularity” happens), and yet the efforts produce havoc. 

Similar in some respects to the earlier description of a novice teenage driver, the AI system is going to be performing driving acts that have as an adverse consequence the generation of havoc.   

Thus, perhaps we ought to be measuring the havoc ratings of self-driving cars.  


A driverless car that has a high havoc rating should either be prevented from driving around or at least shunted into specific driving areas whereby the havoc producing actions won’t have serious consequences (such as when moving at very low speeds or driving in lanes devoted exclusively to self-driving cars). 

I realize that some of you might be exclaiming that the havoc producing self-driving car can readily be updated with better software by undertaking an OTA (Over-The-Air) electronic communications and downloading improved driving AI. 

Yes, that’s true, but you are also mistakenly assuming that somehow those changes are going to be immediately ready and usable.   

Not so.   

Gradually, over time, presumably, the AI driving systems will be improved.   

Meanwhile, we are going to be somewhat at the mercy of whatever havoc producing AI driving systems are on our roadways. 

For more details about ODDs, see my indication at this link here:  

On the topic of off-road self-driving cars, here’s my details elicitation: 

I’ve urged that there must be a Chief Safety Officer at self-driving car makers, here’s the scoop:  

Expect that lawsuits are going to gradually become a significant part of the self-driving car industry, see my explanatory details here: 


Allow me to quote from Shakespeare (Act 3, Scene 1): “Cry ‘Havoc!,’ and let slip the dogs of war.”   

This famous line from the play Julius Caesar is spoken by Mark Antony and indicates that he wanted to go after the assassins that murdered Caesar. 

The dogs of war are most likely actual dogs that were trained for warfare, and he was saying that the killer dogs should be let loose to attack the assassins, though the expression might also mean to let loose the military forces overall. 

For the self-driving cars that are currently being let loose on our roadways, and once they no longer have back-up human drivers attending to the driving of the AI system, will we be potentially incurring havoc and will those AI systems be able to also contend with the havoc created by human drivers?   

Nobody knows, and especially nobody knows if we aren’t measuring the havoc producing and havoc handling capabilities of self-driving cars.   

Automakers and tech firms might be well-intended in their spirited efforts to get self-driving cars onto our roads, but let’s not also allow ourselves to fall into the trap of unleashing havoc.   

I think Shakespeare if he were alive today, would likely have something to say about that.   

Copyright 2020 Dr. Lance Eliot  

This content is originally posted on AI Trends. 

[Ed. Note: For reader’s interested in Dr. Eliot’s ongoing business analyses about the advent of self-driving cars, see his online Forbes column: and] 



Are Chatbots Vulnerable? Best Practices to Ensure Chatbots Security



Rebecca James
credit IT Security Guru

A simple answer is a Yes! Chatbots are vulnerable. Some specific threats and vulnerabilities risk chatbots security and prove them a wrong choice for usage. With the advancement in technology, hackers can now easily target the hidden infrastructure of a chatbot.

The chatbot’s framework has an opportunity for the attackers ready to inject the malicious codes or commands that might unlock the secured data of the customers and your business. However, the extent of the attack’s complexity and success might depend on the messaging platform’s security.

Are you thinking about how chatbots are being exposed to attacks? Well! Hackers are now highly advanced. They attack the chatbots in two ways, i.e., either by social engineering attack or by technical attacks.

  • An evil bot can impersonate a legal user by using backup data of the possibly targeted victims by social engineering attack. All such data is collected from various sources like the dark web and social media platforms. Sometimes they use both sources to gain access to some other user’s data by a bot providing such services.
  • The second attack is technical. Here also attackers can turn themself into evil bots who exchange messages with the other bots. The purpose is to look for some vulnerabilities in the target’s profile that can be later exploited. It can eventually lead to the compromise of the entire framework that protects the data and can ultimately lead to data theft.

To ensure chatbots security, the bot creators must ensure that all the security processes are in place and are responsible for restoring the architecture. The data flow via the chatbot system should also be encrypted both in transit and rest.

To further aid you in chatbot security, this article discusses five best practices to ensure chatbots security. So, let’s read on.

The following mentioned below are some of the best practices to ensure the security of chatbots.

It’s always feared that data in transit can be spoofed or tampered with the sophistication of cybercriminals’ technology and smartness. It’s essential to implement end-to-end encryption to ensure that your entire conversation remains secured. It means that by encryption, you can prevent any third person other than the sender and the receiver from peeping into your messages.

Encryption importance can’t be neglected in the cyber world, and undoubtedly the chatbot designers are adapting this method to make sure that their chatbot security is right on the point. For more robust encryption, consider using business VPNs that encrypt your internet traffic and messages. With a VPN, you can also prevent the threats and vulnerabilities associated with chatbots.

1. 8 Proven Ways to Use Chatbots for Marketing (with Real Examples)

2. How to Use Texthero to Prepare a Text-based Dataset for Your NLP Project

3. 5 Top Tips For Human-Centred Chatbot Design

4. Chatbot Conference Online

Moreover, it’s a crucial feature of other chat services like WhatsApp and other giant tech developers. They are anxious to guarantee security via encryption even when there’s strict surveillance by the government. Such encryption is to fulfill the legal principles of the GDPR that says that companies should adopt measures to encrypt the users’ data.

User identity authentication is a process that verifies if the user is having secure and valid credentials like the username and password. The login credentials are exchanged for having a secure authentication token used during the complete user session. If you haven’t, then you should try out this method for boosting user security.

Authentication timeouts are another way to ensure your chatbots security. This method is more common in banks as the token can be used for the predetermined time.

Moreover, two-factor authentication is yet another method to prove user identity. Users are asked to verify identity either by a text message or email, depending on the way they’ve chosen. It also helps in the authorization process as it permits access to the right person and ensures that information isn’t mishandled or breached.

The self-destructive message features open another way for enhancing chatbot security. This option comes in handy when the user provides their personally identifiable information. Such information can pose a serious threat to user privacy and should be destroyed or deleted within a set period. This method is handier when you’re associated with backing or any other financial chatbots.

By using secure protocols, you can also ensure chatbots security. Every security system, by default, has the HTTPS protocol installed in it. If you aren’t an IT specialist, you can also identify it when you view the search bar’s URL. As long as your data is being transferred via HTTPS protocol and encrypted connections, TLS and SSL, your data is secured from vulnerabilities and different types of cyber-attacks.

Thus, make sure to use secure protocols for enhanced security. Remember that when Chatbots are new, the coding and system used to protect it is the same as the existing HIMs. They interconnect with their security systems and have more than one encryption layer to protect their users’ security.

Do you know what the most significant security vulnerability that’s challenging to combat is? Wondering? Well! It’s none other than human error. User behavior must be resolved using commercial applications because they might continue to believe that the systems are flawed.

No doubt that an unprecedented number of users label the significance of digital security, but still, humans are the most vulnerable in the system. Chatbot security continues to be a real big problem until the problem of user errors comes to an end. And this needs education on various forms of digital technology, including chatbots.

Here the customers aren’t the ones who are to be blamed. Like customers, employees can make a mistake, and they do make most of the time. To prevent this, the chatbot developers should form a defined strategy, including the IT experts, and train them on the system’s safe use. Doing so enhances the team’s skillset and allows them to engage with the chatbot system confidently.

However, clients can’t be educated like the employees. But at least you can provide them a detailed road map of securely interacting with the system. It might involve other professionals who can successfully engage customers and educate them on the right way to interact with the chatbots.

Several emerging technologies are keen to play a vital role in protecting the chatbots against threats and vulnerabilities in the upcoming time, among all the most potent method behavior analytics and Artificial Intelligence developments.

  • User Behavioral Analytics: It’s a process that uses applications to study the patterns of user behavior. It enables them to implement complex algorithms and statistical analysis to detect any abnormal behavior that possibly represents a security threat. Analytical tools are quite common and powerful; thus, this methodology can become a fundamental component of the chatbot system.
  • Developments in AI: Artificial technology is a two-end sword that offers benefits and threats simultaneously. But, as AI is predicted to fulfill its potential, it will provide an extra security level to the systems. It is mainly because of its ability to wipe a large amount of data for abnormalities that recognizes security breaches and threats.

The Bottom Line

Security concerns have always been there with new technologies and bring new threats and vulnerabilities with them. Although chatbots are an emerging technology, the security practices that stand behind them are present for a long time and are effective. Chatbots are the innovative development of the current era, and emerging technologies like AI will transform the way businesses might interact with the customers and ensure their security.


Continue Reading


Best Technology Stacks For Mobile App Development



What’s the Best Tech Stack for Mobile App Development? Read To Know

Which is the Best Tech Stack for Mobile Application Development? Kotlin, React Native, Ionic, Xamarin, Objective-C, Swift, JAVA… Which One?

Image Source: Google

Technology Stack for smartphones is like what blood is for the human body. Without a technology stack, it is hard even to imagine smartphones. Having a smartphone in uncountable hands is rising exponentially. For tech pundits, this is one unmissable aspect of our digital experience wherein tech stack is as critical as ROI.

The riveting experience for a successful mobile app predominantly depends on technology stacks.

The unbiased selection of mobile apps development language facilitates developers to build smooth, functional, efficient apps. They help businesses tone down the costs, focus on revenue-generation opportunities. Most importantly, it provides customers with jaw-dropping amazement, giving a reason to have it installed on the indispensable gadget in present times.

In today’s time, when there are over 5 million apps globally, and by all conscience, these are whopping no.s and going to push the smartphone industry further. But now you could see mobile app development every ‘nook and corner.’ But the fact is not who provides what but understanding the behavioural pattern of users.

So the pertinent question is, which is the ideal tech stack to use for mobile app development?

In native mobile app development, all toolkits, mobile apps development language, and the SDK are supported and provided by operating system vendors. Native app development thus allows developers to build apps compatible with specific OS environments; it is suitable for device-specific hardware and software. Hence it renders optimized performance using the latest technology. However, since Android & iOS imparts — — a unique platform for development, businesses have to develop multiple mobile apps for each platform.

1. Waz

2. Pokemon Go

3. Lyft

1.Java: The popularity of JAVA still makes it one of the official programming languages for android app development until the introduction of Kotlin. Java itself is at the core of the Android OS. Many of us even see the logo of Java when the device reboots. However, contradictions with Oracle (which owns the license to Java) made Google shift to open-source Java SDK for versions starting from Android 7.0 Nougat

2.Kotlin: According to Google I/O conference in 2019- Kotlin is the officially supported language for Android app development. It is entirely based on Java but has a few additions which make it simpler and easier to work.

1. 8 Proven Ways to Use Chatbots for Marketing (with Real Examples)

2. How to Use Texthero to Prepare a Text-based Dataset for Your NLP Project

3. 5 Top Tips For Human-Centred Chatbot Design

4. Chatbot Conference Online

It’s my gut feeling like other developers to say that Kotlin is simply better. It has a leaner, more straightforward and concise code than open-cell Java, and several other advantages about handling null-pointer exceptions and more productive coding.

HERE’S A Programming Illustration Defining the CONCISENESS OF KOTLIN CODE

public class Address {

private String street;

private int streetNumber;

private String postCode;

private String city;

private Country country;

public Address(String street, int streetNumber, String postCode, String city, Country country) {

this.street = street;

this.streetNumber = streetNumber;

this.postCode = postCode; = city; = country;



public boolean equals(Object o) {

if (this == o) return true;

if (o == null || getClass() != o.getClass()) return false;

Address address = (Address) o;

if (streetNumber != address.streetNumber) return false;

if (!street.equals(address.street)) return false;

if (!postCode.equals(address.postCode)) return false;

if (!city.equals( return false;

return country ==;



public int hashCode() {

int result = street.hashCode();

result = 31 * result + streetNumber;

result = 31 * result + postCode.hashCode();

result = 31 * result + city.hashCode();

result = 31 * result + (country != null ? country.hashCode() : 0);

return result;



public String toString() {

return “Address{“ +

“street=’” + street + ‘\’’ +

“, streetNumber=” + streetNumber +

“, postCode=’” + postCode + ‘\’’ +

“, city=’” + city + ‘\’’ +

“, country=” + country +



public String getStreet() {

return street;


public void setStreet(String street) {

this.street = street;


public int getStreetNumber() {

return streetNumber;


public void setStreetNumber(int streetNumber) {

this.streetNumber = streetNumber;


public String getPostCode() {

return postCode;


public void setPostCode(String postCode) {

this.postCode = postCode;


public String getCity() {

return city;


public void setCity(String city) { = city;


public Country getCountry() {

return country;


public void setCountry(Country country) { = country;



class Address(street:String, streetNumber:Int, postCode:String, city:String, country:Country) {

var street: String

var streetNumber:Int = 0

var postCode:String

var city: String

var country:Country


this.street = street

this.streetNumber = streetNumber

this.postCode = postCode = city = country


public override fun equals(o:Any):Boolean {

if (this === o) return true

if (o == null || javaClass != o.javaClass) return false

Val address = o as Address

if (streetNumber != address.streetNumber) return false

if (street != address.street) return false

if (postCode != address.postCode) return false

if (city != return false

return country ===


public override fun hashCode():Int {

val result = street.hashCode()

result = 31 * result + streetNumber

result = 31 * result + postCode.hashCode()

result = 31 * result + city.hashCode()

result = 31 * result + (if (country != null) country.hashCode() else 0)

return result


public override fun toString():String {

return (“Address{“ +

“street=’” + street + ‘\’’.toString() +

“, streetNumber=” + streetNumber +

“, postCode=’” + postCode + ‘\’’.toString() +

“, city=’” + city + ‘\’’.toString() +

“, country=” + country +




I’d say KOTLIN IS THE BEST FIND FOR ANDROID APP DEVELOPMENT.Google has dug deeper with some plans ahead since announcing it as an official language. Moreover, it signals Google’s first steps in moving away from the Java ecosystem, which is imminent, considering its recent adventures with Flutter and the upcoming Fuchsia OS.

Objective C is the same for iOS what Java is for Android. Objective-C, a superset of the C programming language( with objective -oriented capabilities and dynamic run time) initially used to build the core of iOS operating system across the Apple devices. However, Apple soon started using swift, which diminishes the importance of Objective -C in comparison to previous compilations.

Apple introduced Swift as an alternative to Objective-C in late 2015, and it has since been continued to be the primary language for iOS app development.Swift is more functional than Objective-C, less prone to errors, dynamic libraries help reduce the size and app without ever compromising performance.

Now, you would remember the comparison we’ve done with Java and kotlin. In iOS, objective-C is much older than swift with much more complicated syntax. Giving cringeworthy feel to beginners to get started with Objective-C.

Image Source: Google


NSMutableArray * array =[[NSMutableArray alloc] init];


var array =[Int]()


In cross-platform app development, developers build a single mobile app that can be used on multiple OS platforms. It is made possible by creating an app with a shared common codebase, adapted to various platforms.

Image Source: Google

Popular Cross-platform apps:

  1. Instagram
  2. Skype
  3. LinkedIN

React Native is a mobile app development framework based on JavaScript. It is used and supported by one of the biggest social media platforms- Facebook. In cross-platform apps built using React Native, the application logic is coded in JavaScript, whereas its UI is entirely native. This blog about building a React Native app is worth reading if you want to know why its stakes are higher.

Xamarin is a Microsoft-supported cross-platform mobile app development tool that uses the C# programming language. Using Xamarin, developers can build mobile apps for multiple platforms, sharing over 90% of the same code.

TypeScript is a superset of JavaScript, and is a statically-typed programming language supported by Microsoft. TypeScript can be used along with the React Native framework to make full use of its error detection features when writing code for react components.

In Hybrid mobile app development, developers build web apps using HTML, CSS & JavaScript and then wrap the code in a native shell. It allows the app to be deployed as a regular app, with functionality at a level between a fully native app and a website rendered(web browser).

Image Source: Google
  1. Untappd
  2. Amazon App Store
  3. Evernote

Apache Cordova is an open-source hybrid mobile app development framework that uses JavaScript for logic operations and while HTML5 & CSS3 for rendering. PhoneGap is a commercialized, free, and open-source distribution of Apache Cordova owned by Adobe. The PhoneGap platform was developed to deliver non-proprietary, free, and open-source app development solutions powered by the web.

Ionic is a hybrid app development framework based on AngularJS. Similar to other hybrid platforms, it uses HTML, CSS & JavaScript to build mobile apps. Ionic is primarily focused on the front-end UI experience and integrates well with frameworks such as Angular, Vue, and ReactJS.

To summarize, there are 3 types of mobile apps- Native mobile apps, Cross-platform mobile apps, and Hybrid mobile apps; each offers unique technologies, frameworks, and tools of their own. I have enlisted here the best mobile app technology stacks you could use for mobile app development.

The technologies, tools, and frameworks mentioned here are used in some of the most successful apps. With support from an expert, a well-established mobile app development company, that may give much-needed impetus in the dynamic mobile app development world.


Continue Reading


Arcanum makes Hungarian heritage accessible with Amazon Rekognition

Arcanum specializes in digitizing Hungarian language content, including newspapers, books, maps, and art. With over 30 years of experience, Arcanum serves more than 30,000 global subscribers with access to Hungarian culture, history, and heritage. Amazon Rekognition Solutions Architects worked with Arcanum to add highly scalable image analysis to Hungaricana, a free service provided by Arcanum, […]



Arcanum specializes in digitizing Hungarian language content, including newspapers, books, maps, and art. With over 30 years of experience, Arcanum serves more than 30,000 global subscribers with access to Hungarian culture, history, and heritage.

Amazon Rekognition Solutions Architects worked with Arcanum to add highly scalable image analysis to Hungaricana, a free service provided by Arcanum, which enables you to search and explore Hungarian cultural heritage, including 600,000 faces over 500,000 images. For example, you can find historical works by author Mór Jókai or photos on topics like weddings. The Arcanum team chose Amazon Rekognition to free valuable staff from time and cost-intensive manual labeling, and improved label accuracy to make 200,000 previously unsearchable images (approximately 40% of image inventory), available to users.

Amazon Rekognition makes it easy to add image and video analysis to your applications using highly scalable machine learning (ML) technology that requires no previous ML expertise to use. Amazon Rekognition also provides highly accurate facial recognition and facial search capabilities to detect, analyze, and compare faces.

Arcanum uses this facial recognition feature in their image database services to help you find particular people in Arcanum’s articles. This post discusses their challenges and why they chose Amazon Rekognition as their solution.

Automated image labeling challenges

Arcanum dedicated a team of three people to start tagging and labeling content for Hungaricana. The team quickly learned that they would need to invest more than 3 months of time-consuming and repetitive human labor to provide accurate search capabilities to their customers. Considering the size of the team and scope of the existing project, Arcanum needed a better solution that would automate image and object labelling at scale.

Automated image labeling solutions

To speed up and automate image labeling, Arcanum turned to Amazon Rekognition to enable users to search photos by keywords (for example, type of historic event, place name, or a person relevant to Hungarian history).

For the Hungaricana project, preprocessing all the images was challenging. Arcanum ran a TensorFlow face search across all 28 million pages on a machine with 8 GPUs in their own offices to extract only faces from images.

The following screenshot shows what an extract looks like (image provided by Arcanum Database Ltd).

The images containing only faces are sent to Amazon Rekognition, invoking the IndexFaces operation to add a face to the collection. For each face that is detected in the specified face collection, Amazon Rekognition extracts facial features into a feature vector and stores it in an Amazon Aurora database. Amazon Rekognition uses feature vectors when it performs face match and search operations using the SearchFaces and SearchFacesByImage operations.

The image preprocessing helped create a very efficient and cost-effective way to index faces. The following diagram summarizes the preprocessing workflow.

As for the web application, the workflow starts with a Hungaricana user making a face search request. The following diagram illustrates the application workflow.

The workflow includes the following steps:

  1. The user requests a facial match by uploading the image. The web request is automatically distributed by the Elastic Load Balancer to the webserver fleet.
  2. Amazon Elastic Compute Cloud (Amazon EC2) powers application servers that handle the user request.
  3. The uploaded image is stored in Amazon Simple Storage Service (Amazon S3).
  4. Amazon Rekognition indexes the face and runs SearchFaces to look for a face similar to the new face ID.
  5. The output of the search face by image operation is stored in Amazon ElastiCache, a fully managed in-memory data store.
  6. The metadata of the indexed faces are stored in an Aurora relational database built for the cloud.
  7. The resulting face thumbnails are served to the customer via the fast content-delivery network (CDN) service Amazon CloudFront.

Experimenting and live testing Hungaricana

During our test of Hungaricana, the application performed extremely well. The searches not only correctly identified people, but also provided links to all publications and sources in Arcanum’s privately owned database where found faces are present. For example, the following screenshot shows the result of the famous composer and pianist Franz Liszt.

The application provided 42 pages of 6×4 results. The results are capped to 1,000. The 100% scores are the confidence scores returned by Amazon Rekognition and are rounded up to whole numbers.

The application of Hungaricana has always promptly, and with a high degree of certainty, presented results and links to all corresponding publications.

Business results

By introducing Amazon Rekognition into their workflow, Arcanum enabled a better customer experience, including building family trees, searching for historical figures, and researching historical places and events.

The concept of face searching using artificial intelligence certainly isn’t new. But Hungaricana uses it in a very creative, unique way.

Amazon Rekognition allowed Arcanum to realize three distinct advantages:

  • Time savings – The time to market speed increased dramatically. Now, instead of spending several months of intense manual labor to label all the images, the company can do this job in a few days. Before, basic labeling on 150,000 images took months for three people to complete.
  • Cost savings – Arcanum saved around $15,000 on the Hungaricana project. Before using Amazon Rekognition, there was no automation, so a human workforce had to scan all the images. Now, employees can shift their focus to other high-value tasks.
  • Improved accuracy – Users now have a much better experience regarding hit rates. Since Arcanum started using Amazon Rekognition, the number of hits has doubled. Before, out of 500,000 images, about 200,000 weren’t searchable. But with Amazon Rekognition, search is now possible for all 500,000 images.

 “Amazon Rekognition made Hungarian culture, history, and heritage more accessible to the world,” says Előd Biszak, Arcanum CEO. “It has made research a lot easier for customers building family trees, searching for historical figures, and researching historical places and events. We cannot wait to see what the future of artificial intelligence has to offer to enrich our content further.”


In this post, you learned how to add highly scalable face and image analysis to an enterprise-level image gallery to improve label accuracy, reduce costs, and save time.

You can test Amazon Rekognition features such as facial analysis, face comparison, or celebrity recognition on images specific to your use case on the Amazon Rekognition console.

For video presentations and tutorials, see Getting Started with Amazon Rekognition. For more information about Amazon Rekognition, see Amazon Rekognition Documentation.

About the Authors

Siniša Mikašinović is a Senior Solutions Architect at AWS Luxembourg, covering Central and Eastern Europe—a region full of opportunities, talented and innovative developers, ISVs, and startups. He helps customers adopt AWS services as well as acquire new skills, learn best practices, and succeed globally with the power of AWS. His areas of expertise are Game Tech and Microsoft on AWS. Siniša is a PowerShell enthusiast, a gamer, and a father of a small and very loud boy. He flies under the flags of Croatia and Serbia.

Cameron Peron is Senior Marketing Manager for AWS Amazon Rekognition and the AWS AI/ML community. He evangelizes how AI/ML innovation solves complex challenges facing community, enterprise, and startups alike. Out of the office, he enjoys staying active with kettlebell-sport, spending time with his family and friends, and is an avid fan of Euro-league basketball.


Continue Reading
AI3 hours ago

Are Chatbots Vulnerable? Best Practices to Ensure Chatbots Security

AI3 hours ago

Best Technology Stacks For Mobile App Development

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition

AI23 hours ago

Arcanum makes Hungarian heritage accessible with Amazon Rekognition