Home Tags Forest

Tag: Forest

Paying people to preserve forests really seems to work

It's a cost-effective option for carbon management.

Understanding large-scale plant health, Rezatec analyses satellite data to map tree...

Harwell, Oxfordshire, 5th July, 2017.

By developing pioneering data analysis techniques and machine learning algorithms, Rezatec is now able to produce powerful analytical insights for owners and managers of the worldrsquo;s forests.Rezatec analyses earth observation data and imagery to provide scalable, accurate and regularly updated forest landscape intelligence. Rezatec provides a level of insight into forest assets that is not achievable or cost effective using other land surveying techniques such as Lidar and ground-based data... Source: RealWire

iPhone at 10: How Apple changed gaming for the better and...

For gaming, the iPhone sparked a gold rush and burst of creativity still felt today.

New trailer for Blade Runner 2049 is pretty dang alluring

This film looks like a genuinely novel approach to the world established by Ridley Scott.

On the heels of Zika comes its deadlier relative, yellow fever,...

Outbreaks in Brazil are raging close to urban areas that could spark another big issue.

The Amazon forest is the result of an 8,000-year experiment

Ancient peoples discovered agriculture by cultivating trees in the Amazon.

In the US, added wildfires due to carelessness, not climate change

Humans start fire when lightning wouldn't, making for a much longer risk season.

Op-ed: Mark Zuckerberg’s manifesto is a political trainwreck

He says that Facebook is developing AI to create a global democracy—kind of.

Big props to Bigfoot—new bill would name it “official cryptid” of...

"Sasquatch has made immeasurable contributions..."

Guiding ecosystem conservation using airborne lasers

It’s possible to get a sense of how forest species interact from aircraft.

Machine learning versus spam

Machine learning methods are often presented by developers of security solutions as a silver bullet, or a magic catch-all technology that will protect users from a huge range of threats.

But just how justified are these claims? Unless explanations are provided as to where and how exactly these technologies are used, these assertions appear to be little more than a marketing ploy. For many years, machine learning technology has been a working component of Kaspersky Lab’s security products, and our firm belief is that they must not be seen as a super technology capable of combating all threats. Yes, they are a highly effective protection tool, but just one tool among many. My colleague Alexey Malanov even made the point of writing an article on the Myths about machine learning in cybersecurity. At Kaspersky Lab, machine learning can be found in a number of different areas, especially when dealing with the interesting task of spam detection.

This particular task is in fact much more challenging than it appears to be at first glance.

A spam filter’s job is not only to detect and filter out all messages with undesired content but, more importantly, it has to ensure all legitimate messages are delivered to the recipient.
In other words, type I errors, or so-called false positives, need to be kept to a minimum. Another aspect that should not be forgotten is that the spam detection system needs to respond quickly.
It must work pretty much instantaneously; otherwise, it will hinder the normal exchange of email traffic. A graphic representation can be provided in a project management triangle, only in our case the three corners represent speed, absence of false positives, and the quality of spam detection; no compromise is possible on any of these three.
If we were to go to extremes, for example, spam could be filtered manually – this would provide 100% effectiveness, but minimal speed.
In another extreme case, very rigid rules could be imposed, so no email messages whatsoever would pass – the recipient would receive no spam and no legitimate messages. Yet another approach would be to filter out only known spam; in that case, some spam messages would still reach the recipient.

To find the right balance inside the triangle, we use machine learning technologies, part of which is an algorithm enabling the classifier to pass prompt and error-free verdicts for every email message. How is this algorithm built? Obviously, it requires data as input. However, before data is fed into the classifier, is must be cleansed of any ‘noise’, which is yet another problem that needs to be solved.

The greatest challenge about spam filtration is that different people may have different criteria for deciding which messages are valid, and which are spam. One user may see sales promotion messages as outright spam, while another may consider them potentially useful.

A message of this kind creates noise and thus complicates the process of building a quality machine learning algorithm. Using the language of statistics, there may be so-called outlier values in the dataset, i.e., values that are dramatically different from the rest of the data.

To address this problem, we implemented automatic outlier filtration, based on the Isolation Forest algorithm customized for this purpose. Naturally, this removes only some of the noise data, but has already made life much easier for our algorithms. After this, we obtain data that is practically ‘clean’.

The next task is to convert the data into a format that the classifier can understand, i.e., into a set of identifiers, or features.

Three of the main types of features used in our classifier are: Text features – fragments of text that often occur in spam messages.

After preprocessing, these can be used as fairly stable features. Expert features – features based on expert knowledge accumulated over many years in our databases.

They may be related to domains, the frequency of headers, etc. Raw features. Perhaps the most difficult to understand. We use parts of the message in their raw form to identify features that we have not yet factored in.

The message text is either transformed using word embedding or reduced to the Bag-of-Words model (i.e., formed into a multiset of words which does not account for grammar and word order), and then passed to the classifier, which autonomously identifies features. All these features and their combinations will help us in the final stage – the launch of the classifier. What we eventually want to see is a system that produces a minimum of false positives, works fast and achieves its principal aim – filtering out spam.

To do this, we build a complex of classifiers, and it is unique for each set of features.

For example, the best results for expert features were demonstrated by gradient boosting – the sequential building up of a composition of machine learning algorithms, in which each subsequent algorithm aims to compensate for the shortcomings of all previous algorithms. Unsurprisingly, boosting has demonstrated good results in solving a broad range of problems involving numerical and category features.

As a result, the verdicts of all classifiers are integrated, and the system produces a final verdict. Our technologies also take into account potential problems such as over-training, i.e., a situation when an algorithm works well with a training data sample, but is ineffective with a test sample.

To preclude this sort of problem from occurring, the parameters of classification algorithms are selected automatically, with the help of a Random Search algorithm. This is a general overview of how we use machine learning to combat spam.

To see how effective this method is, it is best to view the results of independent testing.

Feds say Chicago e-recycler faked tear-downs, then sent CRTs to Hong...

Enlarge / EnviroGreen's homepage. Just because a website has pictures of a lush forest doesn't mean it represents a company that does good things for the environment.EnviroGreen reader comments 23 Share this story According to an indictment filed in Chicago federal court (PDF) late last week, 45-year-old Brian Brundage cut some serious corners while running his e-recycling businesses. He was arrested on Monday on charges of income tax evasion, mail fraud, and wire fraud. Brundage is the former owner of Chicago-based Intercon Solutions and the current owner of EnviroGreen Processing, based in Gary, Indiana.

Both recycling companies purported to sell e-recycling services to companies and government organizations that needed to get rid of old electronics.

Brundage promised his clients that their old computers, TV monitors, and various other devices would be broken down into their component parts and recycled in keeping with federal guidelines. Instead, feds allege that Brundage shipped some of those electronics for illegal disposal in landfills overseas.

Those electronics included Cathode Ray Tubes (CRTs) from old computer and TV monitors, which contained “hazardous amounts of lead,” as well as batteries.

The electronics that weren't shipped to Asia were destroyed inappropriately on the premises of his businesses or stockpiled indefinitely in warehouses, which is forbidden by federal guidelines. According to the indictment, Brundage also improperly resold many of the electronics he acquired.

Between 2009 and 2015, Brundage received shipments of calculators from an unnamed technology company in Texas with instructions to disassemble the calculators and recycle them accordingly.

But Brundage apparently resold the calculators to another company based in Tampa, Florida, which purchased and sold used electronics. (The Chicago Tribune notes that one of Brundage’s clients was Texas Instruments, but the company didn't respond to Ars' request for comment on the matter.) In exchange for the shipments of calculators, Brundage allegedly had the company in Tampa directly pay some of Brundage’s personal expenses.

Those expense include between $31,000 and $39,000 per year for a nanny and $26,000 to $42,000 per year for a housekeeper, as well as tens of thousands of dollars for jewelry expenses and payments to an Indiana-based casino. Among the more colorful accusations in the US government’s indictment of Brundage: the businessman allegedly went to lengths to fool third-party auditors into giving his companies the certifications necessary to keep doing business as an e-recycler.

Brundage allegedly invited unknowing customers on sham tours of Intercon’s facility. Once there, he "directed Intercon's warehouse staff to set up a staged disassembly line to make it falsely appear as though Intercon regularly processed e-waste in a manner that was consistent with its public representations." The Chicago Tribune published a feature on Intercon in 2007.
In it, Brundage is quoted saying, “We put old products on a disassembly line. We break each item down to raw materials and send them off to be smelted and reused.” He added, “nothing that leaves here goes to a landfill.” The indictment against Brundage only reaches back as far as 2009, so it’s unclear whether Brundage’s statements in 2007 were actually the case or whether the Tribune had been duped.

Brundage has operated as an e-recycler since 2000 when he purchased Intercon Solutions from its previous owner. In fact, Brundage has faced accusations of improperly disposing of e-waste materials since 2011, when he applied for an e-Stewards Certification, a certification that says the recycler is held to high standards, through the Seattle-based Basel Action Network (BAN).

BAN is an environmental organization that fights toxic and electronic dumping.
Instead of simply certifying Intercon Solutions, BAN alleged that it found evidence that Intercon was shipping CRT monitors and batteries to Hong Kong.

Brundage denied the allegations.
In response, he sued BAN for defamation.

The case wound its way through the court and was dismissed by a Chicago federal judge in October 2015 (PDF). Last week’s indictment also accuses Brundage of shipping “large quantities of e-waste” to Hong Kong, adding that in May 2011, the Hong Kong Environmental Protection Department discovered a shipping container full of waste and sent the container back to the US.

The indictment alleges that after the May 2011 incident, Brundage destroyed business records pertaining to previous shipping agreements but continued to ship e-waste overseas, with fraudulent labels and shipping reports. Brundage allegedly took destruction of e-waste into his own hands, too. He allegedly smashed CRT glass “in outdoor areas, without taking measures to prevent the release of potentially hazardous material into the environment.” The US government says that Brundage earned “millions of dollars” from his illegal schemes.

The government is asking for a judgment requiring that he forfeit all property obtained “directly and indirectly” from the alleged dealings.