Skip to main content

Tag: Engineering

TAU makes schizophrenia diagnosis easier with AI

TAU Computer Science master’s student Vered Zilberstein applies machine learning to identify schizophrenics

Tel Aviv University student, Vered Zilberstein, pursuing an MSc in Computer Science at the Blavatnik School of Computer Science, has co-led a study that will help detect schizophrenia patients using artificial intelligence.

She and her research partners applied a machine learning algorithm that identified which study participants were afflicted by schizophrenia and which were not.

 “We used participant scores in a language experiment to train a machine learning classifier to differentiate between schizophrenia patients and a control group of the same sex and age. It managed to do it at an 81.5% accuracy rate,” says Zilberstein, “This procedure is done through a sub-area called natural language processing.”

Collaborating with Beer Yaacov Mental Health Center, Zilberstein set out to explore how AI and computing can assist in the world of mental health – specifically in dealing with schizophrenia.

The disorder is very tricky to diagnose and is characterized by abnormal behavior, speech impairments and a diminished ability to understand reality.

Examples of thought and language disorders characterizing people with schizophrenia include jumping between unrelated issues, called “derailment,” while engaging in conversation. “Tangentiality” occurs when a sufferer replies to a question in an oblique and irrelevant manner. Grammatical mistakes and incoherent, illogical speech are also among the symptoms.

“However,” says Zilberstein, “you need to be very skilled to succeed in identifying speech difficulties affecting schizophrenia sufferers as well as those affecting other groups, such as people on the autistic spectrum.”

Zilberstein’s study included two experiments which examined two types of thought disorders. One focused on derailment, which is dissociative weakness. “It means that one is jumping from one subject to another during a conversation,” explains Zilberstein, “for example, someone can say: ‘I’ve always liked geography. My last teacher in that subject was Prof. August A. He was a man with black eyes. I also like black eyes. There are blue and grey eyes and other sorts too…’ and so on. You can clearly see that they jump very quickly between subjects and by the end of the sentence they have completely derailed from the initial topic, which was geography.”

The other experiment focused on incoherence caused by peculiar vocabulary and incorrect grammar. It is hard to understand what is meant. For example: “Oh, it was superb, you know, the trains broke, and the pond fell in the front doorway.”

Both experiments utilized interviews, questionnaires and photo descriptions. They involved 24 male patients affected by schizophrenia aged 30-40 and 27 mentally healthy males, serving as a control group.

The test results showed that, predictably, the control group tended to maintain focus on the conversation topics whereas the patients were more inclined to changing the subject. More important, it was the machine learning algorithm that could analyze and identify who was whom.

As a computer science master’s student, who comes from the world of exact sciences, what draws you to the world of mental health?

“I wanted to be involved in a combination of disciplines, and not only computer science. I wanted to write a thesis based on real data.”

How widespread, if at all, is the intertwining of artificial intelligence and mental health?

“While artificial intelligence gathers pace in the academic, industrial, educational and social media worlds, combining computer science and mental health is still very much in its infancy. However, artificial intelligence is inevitably going to affect almost all aspects of our lives.

“My study examined the way patients and healthy people talk but further studies may explore and compare between the way patients and healthy people write, for example on social media, which is what I intend on looking into in my research going forward.”

The spirit Behind Engineering

The Faculty of Engineering is trying to be the bridge between sciences and humanities

Prof. Yossi Rosenwaks, dean of the Faculty of Engineering at Tel Aviv University, told The Jerusalem Post about the BSc in Engineering with a program in the Humanities and how the high-tech industry benefit with such a program. Also introducing the “High Tech Plus” program, enabling undergraduate students to combine engineering studies with all dual-disciplinary courses, including from the humanities and social sciences.

Click for the full article

TAU’s race car is headed to Italy

Team of engineering students who constructed the car entirely by themselves will compete internationally

The students of the Formula project designed and built a race car as part of their final project in Mechanical Engineering. Now, after a year of hard and challenging work, they are preparing for the cherry on the cake – participating in the Formula ATA competition, where they will compete with students from all over the world for the honor, glory and of course, the trophy, of coming first.

 

Getting your hands dirty

Fifteen students and instructors from the Faculty of Engineering of the Iby and Aladar Fleischmann Faculty of Engineering at Tel Aviv University will travel to Italy at the end of July – the country is one of the world’s leading manufacturers of rare sports cars. In the belly of the plane will rest their race car, which they spent an entire year building, as part of their final project for their Bachelor’s degree. This is the only project at the faculty that requires a manufacturing process (not just planning and design) and is one of the university’s flagship projects as a result. It’s the result of collaboration between all the schools of engineering that comprise the faculty – Electric/Software, Materials, and of course Mechanical. The project is led by the School of Mechanical Engineering, and headed by by Prof. Yoram Reich.

 

“Our goal was to design and manufacture a vehicle the way a real engineering company does it, with all that that entails,” says Nadav Gvaram, a fourth year student who is taking part in the project. “The entire project is divided into sub-projects according to the different systems in the vehicle, such as the chassis design, the wheel assembly, the cab, the steering system and more, and is executed according to the competition rules (about 120 pages that specify the requirements and nature of the competition), which we can now quote even in the middle of the night,” he adds with a smile.

 

I’m very excited about the trip,” says team leader Dima Medvednik, a Bachelor’s degree student in Mechanical Engineering, who has been part of the project for five years. “Two years of very intensive work have all led to the past two weeks and to this competition.” The rest of the group attests to him being the most extensive source of knowledge in the project.

 

Is there a screw loose? The Formula Team tightens and examines each element of the race car

Is there a screw loose? The Formula Team tightens and examines each element of the race car

 

The unique project gives students practical experience in planning and assembling a product. “There’s a real a win-win situation here both for our graduates and for the industry,” explains the project manager, Baruch Meirovich. “Most of the students come to us without hands-on knowledge, and this work gives them practical tools for real life, where they get their hands dirty and can go into the industry with more experience. And beyond the pride we feel at the School of Mechanical Engineering, we also feel like we’re representing our country internationally.”

 

#tau_racer: Nadav Gvaram’s debut story about the car on Instagram

 

International standards

Tel Aviv University is one of three universities in Israel (alongside the Technion and Ben-Gurion University), which traditionally participates in annual international competitions of this kind. This year, TAU’s race car will be the only Israeli representative at the competition in Italy, along with 46 cars from universities all over the world, including India, Egypt, Spain, Ukraine, Thailand and more. The requirements for admission to the competition are very strict, and currently the waiting list, two weeks before the event starts, stands at 32.

 

The cars are tested according to many parameters. Even the business plan and production costs are scored. With a low budget, comprised mostly of sponsorships from companies like Xenom, HP and others, students acquiring the spare parts and build the entire car themselves, from the chassis to the engine.

 

“There are static tests, that examine mainly the design of the main systems and the quality of the assembly, and then there are of course the dynamic stages in which the cars get on the track,” explains Gvaram. The car’s driver, who must meet stringent height and weight criteria, drives the vehicle first on the acceleration track, which the ability to accelerate the vehicle along a straight path is tested. He then competes in another track called “skidpad”, where the car is tested on its maneuvering abilities. The race culminates on the last day, as cars compete on the “autocross” race track, that examines the overall dynamic abilities of the vehicle, and then on an endurance track that is 22 kilometers long and identical to the autocross.

 

As befits a competition of this calibre, the car with the highest score earns its team a cup and of course, enormous respect. “I don’t know if there’s another major prize like this, but I can say that this will certainly be enough for us,” says Gavram.

Featured image: Part of the team who spent a year building the race car from scratch

 

What will life look like in 2030?

From surgery to household tasks, humanity is about to see its daily life transformed. Prof. Irad Ben-Gal is planning for the biggest unknowns of our future.

Only twenty years ago, connecting to the internet meant sitting next to a desk and sorting through various cables, when downloading a photo could take ten minutes or more. Today, it seems like everything happens online – it’s where we find our friends and where elections and revolutions are won and lost.

But as we spend more and more of our lives in cyberspace, the question is: what’s next? The rate of change and growth is so rapid, even ten years can make a huge difference. Humanity’s biggest “unknown” is the immediate future: what can we do to foresee and cope with the next set of changes and challenges?

To answer these questions, Tel Aviv University partnered with Stanford University to create the Digital Living 2030 program. It will connect engineering students from Israel and the U.S. to lead the development of infrastructures, processes, methods and algorithms, hardware and software components, to create and support this new world. 

When our digital self goes grocery shopping

According to Prof. Irad Ben-Gal, from the Department of Industrial Engineering, a founder of the Digital Living 2030 project, we’ll see many changes over the next ten years. Some for the better, some, potentially, for the worst.

What are the biggest changes waiting around the corner?

“In general,” Prof. Irad Ben-Gal said. “A lot of sectors will see accelerated progress in the coming decade, such as autonomous transportation, personal digital medicine, smart cities, industry (robots and artificial intelligence), virtual environments and applications that affect our personal lives.

 

“On a personal level, we will witness a more complete integration between our digital world and our physical world. People will live simultaneously in both worlds when their digital self will perform different tasks for them – it will learn, make decisions (in collaboration with other digital agents), perform social interactions, and more.”

What about our lives will be better by 2030?

“In principle, a large section of society will benefit from having a better life: personalized services such as autonomous transportation, personalized medicine, a longer and healthier life, increased leisure time, more efficient handling of information overload, and a variety of new and interesting professions.”

What are the biggest problems we’ll have to deal with?

“First and foremost, there is a danger of widening economic and social gaps between different people – experts and laymen in the digital world, between the rich and the poor, between developed and developing countries, between technologically advanced and non-technological sectors…

But we’ll have to cope with all of this just like previous generations had to cope with their own technological leaps forward. Every innovation introduces new risks, from the discovery of fire and stone tools, to dynamite, to artificial intelligence.”

What about 2130? On the basis of what you know today, what will life look like in a century?

“Nothing is truly certain, of course, but there’s one thing I’m sure of: the integration of the digital world with the physical world will be complete.

 

 

“The individual will not only be a physical entity represented in digital worlds (as we are today represented in social networks) but a perfect dual entity. The digital entity will be aware, make independent decisions, learn on its own, work in parallel with the physical entity and be rewarded accordingly, and will contain elements of emotions and awareness that don’t exist today.”

So, what are you most looking forward to in the coming decade, or the coming century? And how will you prepare? Are you looking forward to outsourcing your grocery shopping to your digital avatar or dreading having to be even more involved in cyberspace than you already are?

One thing’s for sure: the engineers taking part in Digital Living 2030 will do their best to make sure we’re as ready as it’s possible to be.

Better maps for better self-driving cars?

New research on object detection breaks with long-held principles of radar technologies

Radar technologies were originally designed to identify and track airborne military targets. Today they’re more often used to detect motor vehicles, weather formations and geological terrain.

Until now, scientists have believed that radar accuracy and resolution are related to the range of frequencies or radio bandwidth used by the devices. But a new Tel Aviv University study finds that an approach inspired by optical coherence tomography (OCT) requires little to no bandwidth to accurately create a high-resolution map of a radar’s surrounding environment.

“We’ve demonstrated a different type of ranging system that possesses superior range resolution and is almost completely free of bandwidth limitations,” says Prof. Pavel Ginzburg of TAU’s School of Electrical Engineering, one of the principal authors of the study. “The new technology has numerous applications, especially with respect to the automotive industry. It’s worth noting that existing facilities support our new approach, which means that it can be launched almost immediately.”

The new study was conducted jointly by Prof. Ginzburg, Vitali Kozlov, Rony Komissarov and Dmitry Filonov, all of TAU’s School of Electrical Engineering. 

Preventing the traffic jams of the future

It was commonly believed that radar resolution was proportional to the bandwidth used. Meaning, a good, accurate radar, required a lot of bandwidth, something that could become a limited resource in the future.

“Our concept offers solutions in situations that require high-range resolution and accuracy but in which the available bandwidth is limited, such as the self-driving car industry, optical imaging and astronomy,” Kozlov explains. “Not many cars on the road today use radars, so there’s almost no competition for allocated frequencies. But what will happen in the future, when every car will be equipped with a radar and every radar will demand the entire bandwidth?

“We’ll find ourselves in a sort of radio traffic jam. Our solutions permit drivers to share the available bandwidth without any conflict,” Kozlov says.

The TAU researchers have now demonstrated that low-bandwidth radars can achieve similar performance at a lower cost and without broadband signals by exploiting the coherence property of electromagnetic waves. The new “partially coherent” radar, which uses significantly less bandwidth, is as effective as a standard “coherent” radars in experimental situations.

Using radar for rescue

“Our demonstration is just the first step in a series of new approaches to radiofrequency detectors that explore the impact of low-bandwidth radars on traditional fields,” Prof. Ginzburg concludes. “We intend to apply this technology to previously unexplored areas, like rescue operations — sensing if an individual is buried in a collapsed building — or street mapping — sensing if a child is about to cross the street behind a bus that conceals him.”

Research for the study was supported by an ERC grant and Kamin, and it was conducted at TAU’s Radio Physics Laboratory’s anechoic chamber.

Victoria

Tok Corporate Centre, Level 1,
459 Toorak Road, Toorak VIC 3142
Phone: +61 3 9296 2065
Email: [email protected]

New South Wales

Level 22, Westfield Tower 2, 101 Grafton Street, Bondi Junction NSW 2022
Phone: +61 418 465 556
Email: [email protected]

Western Australia

P O Box 36, Claremont,
WA  6010
Phone: :+61 411 223 550
Email: [email protected]