Look Out Spotify, Apple Music: Tesla Considering To Launch Its Own Music Streaming Service

Spotify and Apple Music may soon find a new challenger in the music streaming service industry from an unlikely source: electric vehicle manufacturer Tesla.

According to reports, Tesla has been speaking with the music industry on the possibility of creating its own music streaming service that will be bundled with its electric vehicles.

Tesla To Enter Music Streaming Scene?

Sources in the music industry claim that Tesla has spoken with all the major music labels on licensing a music streaming service. The service will be bundled with the company’s vehicles, such as the electric sedan Model S, the electric SUV Model X, and the upcoming mass-market electric sedan Model 3.

The full scope of Tesla’s ambitions was not made clear, but sources believe that the company is looking to offer multiple tiers for the planned music streaming service. The tiers will start with a web radio service, such as the one offered by Pandora, which will be enabled by the internet connectivity already present in Tesla’s electric vehicles through their dashboards.

The whole plan is seemingly not yet fully formed, but Tesla is already doing its due diligence by asking about acquiring the rights to stream albums and songs from the top artists from all over the world.

Tesla CEO Elon Musk actually hinted that the company was exploring music products at the latest shareholder meeting of the company in June. He said that it was difficult to “find good playlists or good matching algorithms” for music that drivers want to hear while on the road, and that the company will be announcing how it will solve the problem within the year.

Why Will Tesla Challenge Spotify And Apple Music?

The big question is why Tesla is planning to go through the trouble of creating its own music streaming service, when it can instead integrate Spotify or Apple Music into its electric vehicles. Tesla already has a deal in place to include Spotify in electric vehicles sold outside the United States, so such a setup can be done if the company wants to.

The labels will not turn down Tesla’s overtures if it pushes through with creating its own music streaming service, as it will be another source of revenue. From the comment of a Tesla spokesperson, it appears that the company is indeed serious about its plans.

“We believe it’s important to have an exceptional in-car experience so our customers can listen to the music they want from whatever source they choose,” the spokesperson said, adding that Tesla’s goal is to “achieve maximum happiness” for its customers.

While Tesla is considered as the market leader in the burgeoning electric car industry, it will be jumping into a music streaming space that is currently dominated by Spotify, with 50 million premium subscribers, followed by Apple Music, with 27 million paid users and looking to pose a bigger challenge to Spotify by launching a $99 annual subscription option.

How Tesla’s music streaming service will stand up against these two remains to be seen, but it will have to offer something beyond the usual features if it wants to make a significant impression in the industry.

[Source”pcworld”]

How to use Gmail’s Google Tasks as your daily to-do list

gmail logo resized

Dedicated to-do apps abound, but one of the best may be right in your inbox. Google Tasks, integrated into Gmail, provides a simple way to create ordered task lists, complete with due dates, and even turn emails into action items. Here’s how to get started.

Create a task

add to tasks

PCWorld

With Google Tasks you can create a to-do list right in your inbox.

To start building a to-do list, click the down arrow next to “Gmail” in the upper left corner of your inbox. The Tasks window will open in the lower-right corner. To add a task, click the plus icon at the bottom of the window. A blank field will open with a checkbox and a blinking cursor. Type in your action item.

If you want to add a due date or notes, click the arrow to the right of the task and enter the details in the appropriate fields.

Turn an email message into a task

create task

PCWorld

You can type to-dos directly in your task list or add emails as action items.

You probably find that a good chunk of the emails you receive require some action from you. Google Tasks allows you to quickly turn these messages into to-do items without leaving your inbox.

To turn an email into a task, select the message either by selecting the checkbox next to it or opening it. Next, click the More button above your inbox and select Add to Tasks from the drop-down menu. The message is added to your to-do list using the subject line as the item name. A link to the original message is also included. As when you create a task, you can add a due date and other details by clicking the arrow next to the task.

Add sub-tasks

For more complex to-dos, you’ll want to break the main task into several sub-tasks. To do this, create each sub-task under the main task and hit the Tab button to indent each one.

Make multiple task lists

task notes

PCWorld

You can add a due date and notes to any task by clicking the arrow next to it.

In addition to your daily task list, you may want to create separate lists dedicated to specific projects. To do this, click the Switch List icon (it looks like three bullets, each followed by a line) at the bottom of your main task list and select New list from the pop-up menu. Enter the name of your new list, then click OK and add your tasks. When you want to switch between lists, just click the Switch List icon and choose the one you want.

Print or email lists and other actions

To print or email a task list click the Actions button and select the appropriate option. From here you can also rearrange your tasks either by sorting them by due date or manually moving them up and down using the displayed key combos.

To comment on this article and other PCWorld content, visit our Facebook page or our Twitter feed.
[Source”pcworld”]

New national statistics report shows over 5m fraud and computer misuse offences in 2016

UK statistics cyber crime

New figures from the Office of National Statistic’s ‘Crime in England and Wales: year ending Sept 2016’ report, showed an estimated 6.2 million incidents of crime in 2016.

In addition to covering a wide variety of crimes, such as burglary and theft of vehicles, new for the 2016 results is the inclusion of statistics on fraud and computer misuse.

There were 3.6 million fraud and 2.0 million computer misuse offences for the first full year in which such questions have been included in the CSEW.

“The inclusion of these new offences yields a new headline estimate of 11.8 million incidents of crime covered by the survey, but it will be another year before a comparable time series is available,” the report stated.

“The new fraud and computer misuse estimation of 5.6 million offences highlights the challenge forces face to be better equipped to fight cyber enabled crime and the need for all of us to better protect ourselves,” said Andy Lea, Head of Policing at KPMG. “These figures also show the difficult decisions forces will need to make when prioritising their use of resources.”

Fraud and computer misuse details

The survey results show that adults aged 16 and over experienced an estimated 3.6 million incidents of fraud, with just over half of these (53%; 1.9 million incidents) being cyber-related.

The CSEW classifies a crime as being ‘cyber-related’ when the internet or any type of online activity was related to any aspect of the offence.

Key findings include:

  • The most common types of fraud experienced were “Bank and credit account” fraud (2.5 million incidents; 68% of the total).
  • “Non-investment” fraud – such as fraud related to online shopping or fraudulent computer service calls (0.9 million incidents; 26% of the total) was the second highest.
  • There were an estimated 2.0 million computer misuse incidents reported.
  • Around two-thirds (66%; 1.3 million incidents) of the computer misuse incidents were computer virus-related and around one-third (34%; 0.7 million incidents) were related to unauthorised access to personal information (including hacking).
cybercrime statistics
CSEW fraud and computer misuse – numbers of incidents for year ending September 2016 (Experimental Statistics).

Financial losses to victims

The report shows that, although a high number of cyber crimes were reported, in just under two-thirds of incidents resulting in financial loss, the victim lost less than £250 (61%).

Two-thirds of fraud incidents involved initial loss of money or goods to the victim (66%), independent of any reimbursement received. This equates to an estimated 2.4 million offences, compared with 1.2 million incidents of fraud involving no loss.

Incidents of bank and credit account fraud were more likely to result in initial loss to the victim (73%, equivalent to 1.8 million) than other types of fraud.

In the majority of these incidents, the victim received a full reimbursement, typically from their financial services provider (83%).

Traditional crime blurs into virtual crime

“We see a blurring between traditional, real world crime and virtual crime; criminals are happy to blend their techniques across the two and so ‘cyber’ can no longer be seen as a separate compartment of crime,” said David Emm, Principal Security Researcher at Kaspersky Lab.

“It is important to note that an accurate year-on-year comparison from the ONS, to demonstrate the growth of fraudulent cybercrime, will not be possible until January 2018. However, we agree that bank and credit account fraud is one of the most problematic areas with the continuing rise of e-commerce,” Emm continued.

 

[Source:- softwaretestingnews]

 

Software innovation in healthcare round up

software healthcare

The healthcare sector is benefitting immensely from going digital. Recent eHealth announcements show how cloud-based solutions and collaborative platforms are pushing future medical discoveries, cross-border healthcare, and patient care into the
21st century.

Cloud-based open source platform inspires genetics research collaboration

Writing in Wired, Commis­sioner of the US Food and Drug Administration, Robert M. Califf, MD, discusses a new open source R&D portal called precisionFDA, where “nearly
2100 individual members from 568 organi­sations are sharing and comparing data, software tools, and testing methodologies on the site.”

Designed to spur collaboration among next-generation sequencing (NGS), an advanced DNA testing process, researchers, the cloud-based portal will accelerate NGS technology development, increase collaboration, and ensure the medical community can develop data collectively rather than indi­vidually, reducing the need for duplicative clinical studies.

Another benefit “besides helping to accelerate the development of NGS technology, [is] it puts the agency at the centre of ongoing discussions, allowing us to stay up to date on issues and breakthroughs in the field,” Califf wrote.

NGS tech­nology will be able to chart almost all of a person’s genome in a single run, much quicker and more economical than current methods. Genetic markers for diseases can help inform prevention efforts and improve diagnoses.

Common IT platform connects rare diseases specialists across the EU

In similar news of online collaboration, Dublin-based software company OpenApp has announced its software will aid 24 European Reference Networks to connect over
370 hospitals and nearly 1000 specialist rare disease centres across 25 EU Member States.

The Irish eHealth firm will develop and manage a common IT platform to support the ERNs.

The platform will allow teams of multi-disciplinary medical specialists to meet as a virtual clinical board. Some 30 million patients across the EU suffer from rare diseases, and will now be able to benefit from specialist diagnostics and suggest treatments wherever they are in Europe.

“Seeing this embedded in a pan-European effort to address rare diseases is exciting and will revolutionise equity of access to high-quality care.” commented Professor Alan Irvine, Crumlin Children’s Hospital Ireland.

Investments in diabetes management software

Atlanta’s Grady Health System, operator of Atlanta’s Grady Memorial Hospital and numerous health centres, has begun implementing Glytec’s eGlycemic Management System® (eGMS), a personalised diabetes therapy management solution.

The diabetes management software system is made up of a set of modules that helps healthcare professionals better regulate insulin dosing for the care of patients with acute diabetes, hypoglycemia and hyperglycemia.

eGMS is integrated with Grady’s Epic electronic medical record (EMR), allowing users direct access from a patient’s chart without the need for a separate login.

Also included in the software systems is a surveillance solution, which the hospital relies on for rapid identification of patients in need of insulin therapy. GlucoSurveillance® interfaces with Grady’s laboratory information system to perform continuous real-time surveillance of blood glucose values, flagging patients who meet
pre-defined criteria for persistent hyperglycemia.

“Our rate of hypoglycemia among critically ill patients was not at a level we were comfortable with,” said Dr. Robert Jansen, Grady’s Chief Medical Officer and Chief of Staff. “As we worked to improve our care model, the clinical research conducted by
Dr. Umpierrez using the Glytec system showed that the system has real merit. We were unanimous in our decision to use eGMS.”

 

 

[Source:- softwaretestingnews]

 

Big data applications

Richard J Self, Research Fellow – Big Data Lab, University of Derby, examines the role of software testing in the achievement of effective information and corporate governance.

As a reminder, software testing is about both verifying that software meets the specification and also validating that the software system meets the business requirements. Most of the activity of the software testing teams attempts to verify that the code meets the specification. A small amount of validation occurs during user acceptance testing, at which point it is normal to discover many issues where the system does not do what the user needs or wants.

It is only too clear that current approaches to software testing do not, so far, guarantee successful systems development and implementation.

IT project success

The Standish Group have been reporting annually on the success and failure of IT related projects since the original CHAOS report of 1994, using major surveys of projects of all sizes. They use three simple definitions of project successful, failed and challenged projects, as follows:

Project successful:

The project is completed on time and on budget, with all features and functions as initially specified.

Project challenged:

The project is completed and operational but over‑budget, over the time estimate, and offers fewer features and functions than originally specified.

Project failed:

The project is cancelled at some point during the development cycle.

Due to significant disquiet amongst CIOs about the definition of success requiring meeting the contracted functionality in a globalised and rapidly changing world, Standish Group changed the definition in 2013 to:

Project successful:

The project is completed on time and on budget, with a satisfactory result; which is, in some ways, a lower bar.

As the graph in Figure 1 shows, the levels of project success, challenge and failure have remained remarkably stable over time.

It is clear that, as an industry, IT is remarkably unsuccessful in delivering satisfactory products. There is a range of estimates of the resultant costs of challenged and failed projects which range from approximately US$500 billion to US$6 trillion, which compares to the annual ICT spend of US$3 trillion in a world GDP of approximately US$65 trillion.

Clearly something needs to be done.

The list of types of systems and software failures is too long to include here but a few examples include the recent announcements by YAHOO of the loss of between 500 and 700 million sets of personal data in 2012 and 2014, the loss of 75 million sets of personal and financial data by Target in 2012 and regular failures of operating system updates for iOS and Windows etc.

Common themes, verification and validation

Evaluating some of the primary causes of the long list of failures suggests some common themes and causes ranging from incomplete requirements capture, unit testing failures, volume test failures due to using too small an environment and too small sets of data, inappropriate HCI factors and the inability to effectively understand what machine learning is doing.

Using the waterfall process as a way of understanding the fundamentals of what is happening, even in agile and DevOps approaches, we can see that software verification is happening close to the end of the process just before implementation.

As professionals we recognise that there is little effective verification and validation activity happening earlier in the process.

The fundamental question for systems developers is, therefore, whether there is any way that the skills and processes of software testing can be brought forward to earlier stages of the systems development cycle in order to more effectively ensure fully verified and validated requirements specifications, architectures and designs, software, data structures, interfaces, APIs etc.

Impact of big data

As we move into the world of big data and the internet of things, the problems become ever more complex and important. We have the three traditional Vs of big data: velocity, volume and variety which stress the infrastructures, cause problems with ensuring data dictionaries are consistent between the various siloes of databases, the ability to guarantee valid and correct connections between corporate master data and data being found in other databases and social media.

Improved project governance

If the IT industry is to become more successful, stronger information and project governance is required that is based on a holistic approach to the overall project, ensures a more effectively validated requirement specification, far more effectively verified and validated non‑functional requirements, especially in the areas of security by design and the human‑to‑computer interfaces.

It is also vital to ensure that adequate contingencies are added to the project estimates. The 2001 Extreme Chaos report observed that for many of the successful projects, the IT executives took the best estimates multiplied by 2 and added another 50%. This is in direct contrast to most modern projects where the best and most informed estimates are reduced by some large percentage and a ‘challenging target’ is presented to the project team. Inevitably, the result is a challenged or failed project.

If we can achieve more effective project governance, with effective verification and validation of all aspects from the beginning of the project, the rewards are very large in terms of much more successful software that truly meets the needs of all the involved stakeholders.

12 Vs of project governance and big data

One effective approach is to develop a set of questions that can be asked of the various stakeholders, the requirements, the designs, the data, the technologies and the processing logic.

In the field of information security, ISO 27002 provides a very wide range of questions that can help an organisation of any size to identify the most important aspects that need to be solved. By analogy, a set of 12 Vs have been developed at the University of Derby which pose 12 critical questions which can be used both with big data and IoT projects and also for more traditional projects as the ‘12 Vs of IT Project Governance’.

The 12 Vs are:

Volume (size).

Velocity (speed).

Variety (sources/format/type).

Variability (temporal).

Value (what/whom/when?).

Veracity (truth).

Validity (applicable).

Volatility (temporal).

Verbosity (text).

Vulnerability (security/reputation).

Verification (trust/accuracy).

Visualisation (presentation).

As an example, the Value question leads towards topics such as:

Is the project really business focused? What are the questions that can be answered by the project and will they really add value to the organisation and who will get the benefit and what is the benefit? Is it monetary? Is it usability? Is it tangible or intangible?

What is the value that can be found in the data? Is the data of good enough quality?

The Vulnerability question leads towards: Is security designed into the system, or added as an afterthought? Major consequences could result in significant reputation damage.

Incorrect processing leads to reputation damage.

The Veracity question is developed from the observation by J Easton2 that 80% of all data is of uncertain veracity, we cannot be certain which data are correct or incorrect, nor by how much the incorrect data are incorrect (the magnitude of the errors).

Data sourced from social media is of highly uncertain veracity, it is difficult to detect irony, humans lie, change their likes and dislikes, etc. Data from sensor networks suffer from sensor calibration drift of random levels over time, smart device location services using assisted GPS have very variable levels of accuracy. A fundamental question that needs to be asked of all these data, is how can our ETL processes detect the anomalies? A second question is to what extend do undetected errors affect the Value of the analyses and decisions being made?

Formal testing of BI and analytics

One further fundamental issue (identified by the attendees at The Software Testing Conference North 2016)3 was that the formal software testing teams are very infrequently involved in any of the big data analytics projects. The data scientists, apparently, ‘do their own thing’ and the business makes many business critical decisions based on their ‘untested’ work. In one comment, the models developed by the data scientists produced different results depending on the order in which the data were presented, when the result should have been independent of the sequence.

In conclusion, the fundamental challenge to the testing profession is to determine how their skills, knowledge, experience, processes and procedures and be applied earlier in the development lifecycle in order to deliver better validated and verified projects which can be delivered as a ‘successful project’ (in Standish Group terms)? Are there opportunities to ensure more comprehensive and correct requirements specifications?

This article is based on the presentation delivered on the 28th September 2016 at The Software Testing Conference North 2016. Video can be found here. 

This article first appeared in the November 2016 issue of TEST Magazine. Edited for web by Jordan Platt.

 

 

[Source:- softwaretestingnews]

Microsoft is bringing the full Windows 10 experience to mobile chipsets

Chip manufacturer Qualcomm and Microsoft have teamed up to support Windows 10 on mobile computing devices powered by Snapdragon processors.

The first PCs running Windows 10 based on Snapdragon processors are expected to be available as early as next year.

“With compatibility with the Windows 10 ecosystem, the Qualcomm Snapdragon platform is expected to support mobility to Cloud computing and redefine how people will use their compute devices,” said Cristiano Amon, Executive Vice President, Qualcomm Technologies, Inc., in a statement.

New Windows 10 PCs powered by Snapdragon processors can be designed to support x86 Win32 and universal Windows apps, including Adobe Photoshop, Microsoft Office and Windows 10 gaming titles.

“Bringing Windows 10 to life with a range of thin, light, power-efficient and always-connected devices, powered by the Qualcomm Snapdragon platform, is the next step in delivering the innovations our customers love,” added Terry Myerson, Executive Vice President, Windows and Devices Group, Microsoft.

 

 

[Source:- Techrader]

Apple sending out iOS 10.2 for the iPhone, iPad and the iPod Touch

iOS 10.2 is finally here, much to the rejoice of iPhone and iPad owners. The update introduces support for the all-new TV app (U.S. only), and also brings 100 new emoji to the table. The company has now included the previously reported emergency SOS button on the device which will automatically contact your predefined contacts in times of danger. This is an excellent feature to have an enhances the security of the iPhone users. The regular bunch of security patches and bug fixes are on board as well.

One of my favorite additions, however, is the inclusion of new wallpapers for the iPhone 7 and the 7 Plus. While the current collection isn’t too bad, it seems like Apple wanted to spice things up a bit and offer users a lot more out of their shiny new iPhones. There are only three new wallpapers, though.

In terms of marketshare, Apple is leaps and bounds ahead of its industry rival. Over 63% of all iOS devices are running iOS 10 right now, speaking volumes about the company’s streamlined update strategy. It will be interesting to see how many of these users will update to iOS 10.2, but given that the update is already seeding to the users, we don’t think the customers will want to wait much longer.

There are some minor cosmetic tweaks with iOS 10.2 as well. Observant users will be able to see minor design changes with the shuffle and repeat buttons on the Music app.

 

 

[Source:- Techrader]

Google ditches location-sharing feature in map apps

Google on Wednesday released an upgraded version of its popular maps app for Android-powered smartphones and tablets

Google on Wednesday released an upgraded version of its popular maps app for Android-powered smartphones and tablets that ditches a Latitude feature that let people share locations with family or friends.

Google on Wednesday released an upgraded version of its popular maps app for Android-powered smartphones and tablets that ditches a Latitude feature that let people share locations with family or friends.

The new software began rolling out at the online Google Play shop, and a version tailored for iPhones and iPads will soon be available at the Apple App Store, according to Google Maps director Daniel Graf.

“The new Google Maps for mobile builds on the design we released for iPhone last December and improves on it with a few useful search and navigation features,” Graf said in a blog post.

“It’s a new mapping experience that makes exploring the world and getting to the places that matter to you a lot faster and easier.”

A Latitude feature that let people automatically share their locations with friends using GPS capabilities in smartphones will be “retired” by August 9 along with the ability to “check-in” at spots being visited, according to Graf.

“We understand some of you still want to see your friends and family on a map, which is why we’ve added location sharing and check-ins to Google+ for Android,” Graf said, noting that it would soon be added to gadgets powered by Apple’s mobile operating system.

Google+ is the California-based Internet titan’s online social network, which it has been gradually weaving into its array of online services.

Enhancements to the new version of Google Maps include being able to see reports of trouble on selected routes and being automatically offered better ways to get to selected destinations.

Google also customized a version of Maps specifically for tablets.

“As more of us use mobile phones and tablets in our daily lives, information that’s useful to you isn’t just about what you need, but also where you might find it,” Graf said.

Google is tops in online maps and navigation, but Apple has been refining its own mapping software for iPhones and iPads, and Facebook is keen to follow members increasingly accessing the social network from mobile devices.

[Source:- Phys.org]

Google Maps guides travellers offline

Turn-by-turn directions and precise business information are available offline in the latest iteration of Google Maps for Androi

Google on Tuesday updated its free map service to guide users of Android-powered smartphones to destinations without relying on Internet connections.

An offline navigation feature previewed at a Google developers conference early this year began rolling out in an updated version of Google Maps application tailored for Android-powered mobile devices.

A version crafted for Apple smartphones or tablets is coming soon, according to Google product manager Amanda Bishop.

“Google Maps is taking steps to help people across the globe find directions and get where they’re going, even when they don’t have an Internet connection,” Bishop said in a blog post.

“Now you can download an area of the world to your phone, and the next time you find there’s no connectivity – whether it’s a country road or an underground parking garage – Google Maps will continue to work seamlessly.”

Earlier versions of the application let people download digital maps for viewing offline but did not provide turn-by-turn directions; allow searches for precise locations, or display information such as the hours businesses are open.

The new version of the application builds capabilities once limited to online maps into maps downloaded to smartphones while visiting Wi-Fi hotspots to avoid telecommunication service data charges.

Approximately 60 percent of the world still lacks Internet coverage, making it unrealistic to use online smartphone mapping services for finding one’s way, according to Bishop.
[Source:- Phys.org]

Spoken-language app makes meal logging easier, could aid weight loss

Spoken-language app makes meal logging easier, could aid weight loss

For people struggling with obesity, logging calorie counts and other nutritional information at every meal is a proven way to lose weight. The technique does require consistency and accuracy, however, and when it fails, it’s usually because people don’t have the time to find and record all the information they need.

A few years ago, a team of nutritionists from Tufts University who had been experimenting with mobile-phone apps for recording caloric intake approached members of the Spoken Language Systems Group at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), with the idea of a spoken-language application that would make meal logging even easier.

This week, at the International Conference on Acoustics, Speech, and Signal Processing in Shanghai, the MIT researchers are presenting a Web-based prototype of their speech-controlled nutrition-logging system.

With it, the user verbally describes the contents of a meal, and the system parses the description and automatically retrieves the pertinent nutritional data from an online database maintained by the U.S. Department of Agriculture (USDA).

The data is displayed together with images of the corresponding foods and pull-down menus that allow the user to refine their descriptions—selecting, for instance, precise quantities of food. But those refinements can also be made verbally. A user who begins by saying, “For breakfast, I had a bowl of oatmeal, bananas, and a glass of orange juice” can then make the amendment, “I had half a banana,” and the system will update the data it displays about bananas while leaving the rest unchanged.

“What [the Tufts nutritionists] have experienced is that the apps that were out there to help people try to log meals tended to be a little tedious, and therefore people didn’t keep up with them,” says James Glass, a senior research scientist at CSAIL, who leads the Spoken Language Systems Group. “So they were looking for ways that were accurate and easy to input information.”

The first author on the new paper is Mandy Korpusik, an MIT graduate student in electrical engineering and computer science. She’s joined by Glass, who’s her thesis advisor; her fellow graduate student Michael Price; and by Calvin Huang, an undergraduate researcher in Glass’s group.

Context sensitivity

In the paper, the researchers report the results of experiments with a speech-recognition system that they developed specifically to handle food-related terminology. But that wasn’t the main focus of their work; indeed, an online demo of their meal-logging system instead uses Google’s free speech-recognition app.

Their research concentrated on two other problems. One is identifying words’ functional role: The system needs to recognize that if the user records the phrase “bowl of oatmeal,” nutritional information on oatmeal is pertinent, but if the phrase is “oatmeal cookie,” it’s not.

The other problem is reconciling the user’s phrasing with the entries in the USDA database. For instance, the USDA data on oatmeal is recorded under the heading “oats”; the word “oatmeal” shows up nowhere in the entry.

To address the first problem, the researchers used machine learning. Through the Amazon Mechanical Turk crowdsourcing platform, they recruited workers who simply described what they’d eaten at recent meals, then labeled the pertinent words in the description as names of foods, quantities, brand names, or modifiers of the food names. In “bowl of oatmeal,” “bowl” is a quantity and “oatmeal” is a food, but in “oatmeal cookie,” oatmeal is a modifier.

Once they had roughly 10,000 labeled meal descriptions, the researchers used machine-learning algorithms to find patterns in the syntactic relationships between words that would identify their functional roles.

Semantic matching

To translate between users’ descriptions and the labels in the USDA database, the researchers used an open-source database called Freebase, which has entries on more than 8,000 common food items, many of which include synonyms. Where synonyms were lacking, they again recruited Mechanical Turk workers to supply them.

The version of the system presented at the conference is intended chiefly to demonstrate the viability of its approach to natural-language processing; it reports calorie counts but doesn’t yet total them automatically. A version that does is in the works, however, and when it’s complete, the Tufts researchers plan to conduct a user study to determine whether it indeed makes nutrition logging easier.

“I think logging is enormously helpful for many people,” says Susan Roberts, director of the Energy Metabolism Lab at Tufts’ USDA-sponsored Jean Mayer Human Nutrition Research Center on Aging. “It makes people more self-aware about the junk they are eating and how little they actually enjoy it, and the shock of huge portions, et cetera. But currently, it is really tedious to log your food. There are any number of programs like MyFitnessPal where you can manually enter it by hand, but even with shortcuts it is tedious and not as user friendly as it needs to be for millions of people to use it really regularly.”

“A spoken-language system that you can use with your phone would allow people to log food wherever they are eating it, with less work,” she adds. “As I see it, we need to come up with something that really isn’t much work, so it isn’t an extra burden in life.”

[Source:- Phys.org]