“I’ve seen a lot of people go blind, including my grandmother, and there are a lot of direct and indirect costs that patients suffer from,” said Serpa, a data science student in the Graduate School of Arts and Sciences. “I want to make sure that people can see as long as possible.” 

The idea for the project originally came from Amin, an assistant professor of computer and information sciences, and Alauddin Bhuiyan, Ph.D., the founder of iHealthScreen and an associate professor at Mount Sinai’s Icahn School of Medicine. While searching for thesis ideas, Serpa reached out to Amin, who then introduced her to his research with Bhuiyan. 

“Many middle-aged people have diabetes, including myself,” said Amin. “They often develop eye problems, especially age-related macular degeneration (AMD) and diabetic retinopathy. These diseases spread slowly until they reach a stage where it’s difficult to recover, but if you diagnose them early, they’re easier to manage.” 

Together, the three researchers are trying to build an app that uses artificial intelligence to detect these eye diseases at an early stage. 

Training Software to Recognize Disease Symptoms

Serpa began her thesis last fall with initial research and interviews with neurologists and ophthalmologists, who shared what they thought was needed in their field. Then she visited health care facilities in the Bronx, where she recorded images of patients’ retinas with professional equipment, focusing on patients at least 55 years old and/or diabetic. The images were then uploaded to AI software that is being trained to identify signs of AMD or diabetic retinopathy and also sent to an ophthalmologist for diagnosis. Later, Serpa compared the results from the software and the ophthalmologist to see if they both agreed on a diagnosis. 

“The software uses machine-learning and deep learning to scan images, pixel by pixel, and search for specific spots that indicate a person is at risk and should be seen by a professional for further referral,” said Serpa. “Basically, we’re training the software to know what to look for in the data and to accurately diagnose patients.”

So far, Serpa has recorded and uploaded about 100 images. Her goal is to collect more than 500 images by the end of the study, but she says that most of the time, the ophthalmologist and the software agree on a diagnosis. And the more images processed by the software, the smarter it becomes. 

“It’s like if you were to study for an exam and take 10 practice exams. If someone else takes 20, then that person might do better because they’ve practiced more,” said Serpa.  

Finally, Serpa’s team will incorporate the software into a smartphone application in which anyone can take a photo of their eye and screen themselves for eye diseases at little to no cost. 

“In the past, most researchers have used a separate camera or a removable smartphone lens instead of an actual iPhone camera, but those can cost a lot of money. We’re trying to see how accurate we can get with an iPhone camera,” said Serpa. “If people can’t afford to visit a doctor, this could be a good way to first let them know that they should see a doctor and get real imaging done because we see something that may be dangerous.” 

A Cost-Effective Form of Diagnosis

After graduating from Fordham next spring, Serpa said she hopes to work full time in the medical technology field. 

“A lot of people find databases boring, but I think it’s fascinating to find patterns in the data that can be important to a business or health care system,” said Serpa, who is originally from Monroe, New York. 

She said she not only enjoys working with data, but also interacting with patients, many of whom she can personally relate to. 

“As someone who has had a lot of chronic illnesses since I was young, I feel like I understand where they’re coming from,” said Serpa, who has asthma and has suffered from migraines and fibromyalgia since childhood.

Although her thesis will be completed by May 2023, she said she plans to continue her research post-graduation. 

“In the long run, our goal is to create a cost-effective and accurate way to know that a patient is going to lose their sight, but also help them to retain some of it,” Serpa said. “Nothing’s going to reverse the damage; we can only slow down the process. But hopefully we can find a better way to detect these diseases earlier.”  

Mohammad S. Obaidat, PhD, who this fall joined Fordham’s Department of Computer and Information Science as department chair and professor, is working to make that happen.

Obaidat, a world-renowned cybersecurity expert, recently finalized the book Smart Cities and Homes: Key Enabling Technologies (Elsevier, 2015).

It’s a burgeoning topic, thanks to several emerging trends. Expanding countries like India and China are undergoing unprecedented urbanization, as citizens migrate from the countryside to megacities that are so large they make New York seem quaint. In areas such as transportation and pollution control, information and communication technologies (ICT) will be key to making these cities livable.

Contracting countries such as Japan and Spain, meanwhile, must figure out how to meet the growing medical needs of their aging populations, perhaps through “smart health homes” outfitted with equipment that delivers insulin injections and monitors vitals signs.

Smart Cities shows the many ways ICT can play a role in such metropolises. On security matters, it delves into Obaidat’s own work in pioneering keystroke biometrics, a field that can identify persons by the rhythm of their typing or scrolling style with a mouse. (Mimicking these is much harder than mimicking someone’s voice or stealing his or her password.)

There are potential uses for ICT when it comes to weather too, said Obaidat, who has published 38 books and more than 600 articles in scholarly international journals and as conference proceedings. He is working with the University of Seville to predict fires in the forests in Andalusia, Spain, through computational intelligence, “fuzzy logic” techniques, wireless sensor networks, and computer networks.

“If you could predict forest fires, you’d have the means to prepare for and hopefully avoid them. You could monitor them when they occur and try to put them down as fast as possible, to reduce losses of property and human lives,” he said.

One foreseeable challenge, according to the book, is that the amount of data being generated in today’s digital world is vastly greater than our capacity to understand it, he said.

“If you analyze information in the classical way, it may take days to reach a decision, so we need smart algorithms and technologies that will allow you to take that large volume of traffic data, analyze it, data mine it, search it, compress it, and transport it fast, in order to be able to make timely and accurate decisions,” Obaidat said.

“Worldwide, we still don’t have efficient algorithms to do that.”

There are also goals that are hard to reconcile. The “Internet of Things,” or the array of smart objects wirelessly connected to computer networks, relies on processors with little memory and minimal computing power.

“Because of the object’s limitations, you really cannot have efficient algorithms to protect privacy and security of the data, because an efficient security algorithm requires high computational power with larger memory—a more sophisticated processor,” he said.

Devising algorithms to overcome these limitations is a major part of Obaidat’s plans for the computer and information science department. In addition to the master’s in cyber security and master’s in computer science currently offered, in the fall of 2016 the department will add a master’s in data analytics, which was just approved by the State of New York. Obaidat said a proposal for a doctoral program is under review.

The department is also overhauling the undergraduate curriculum so it meets the standards of the Accreditation Board for Engineering and Technology (ABET). Accreditation is key to employment at many global corporations, and opens doors to many federal and state loans as well as private scholarships, he said.

That global perspective applies to recruitment as well. Obaidat hopes to attract more international students and secure partnerships with universities abroad.

New teaching labs for cybersecurity and data analytics are planned at the Lincoln Center campus. At Rose Hill, a new Wireless Information Networks and Cyber Security (WINCS) research lab will debut in spring 2016.

Despite the real threats of cyberhacking, data theft, and espionage, Obaidat is optimistic about the future of cybersecurity in the United States.

“If you ask me, ‘Can we have a 100 percent secure network,’ the answer is no. The Internet was not designed to carry the traffic it is carrying now. Its protocols are not actually meant to be used with the services that are provided nowadays,” he said.

“We may reach 98, or even 99 percent. But … 100 percent security in all cases, I say no. There will always be challenges and security holes. But if we adopt best practices and implement the most up-to-date cybersecurity protocols and policies, then we can significantly reduce the threat.”

So, why not send in a team of robots first to map out the area?

That concept recently inspired three Fordham undergraduates to develop a computer program that enhances autonomous exploration of disaster sites by robots. The students, Rose Hill senior Alina Kenealy and Lincoln Center juniors Nicholas Primiano and Alex Keyes, presented their findings in February at SPIE, the international society for optics and photonics conference.

Damian Lyons, Ph.D., associate professor of computer and information sciences, mentors the students.

The team worked on writing algorithms that would enable computerized robots to quickly disburse throughout a site and work independently, while still coordinating as a team.

“First responders have an extremely dangerous job,” said Lyons. “They are going into a disaster area and they don’t know what is out there. Our objective is to have this team of robots very quickly go out and map this area to see where’s the unstable masonry, where are the holes in the floor, where are the potential victims, where are the clear paths—and do it all within a matter of minutes.”

As the SPIE conference attracts many graduate students, faculty researchers, and members of the defense industry, Lyons said it was a significant accomplishment for undergraduate research to be accepted.

“But it is a commitment we have made here, to enable undergraduates to see the excitement of the field rather than just sitting in a classroom. They took the ball and ran with it, and produced some tremendous results.”

The students, who were called “blue cells,” were assigned to defend computer systems from cyber attacks made by other teams, which were known as “red cells.”

Blue cells received points based on their ability to keep attackers from gaining access to protected databases, obtaining vital information and shutting down defense systems.

Fordham, the only student team at the competition, finished in third place.

Joseph R. Concannon, president and chief executive officer of InfraGard, which sponsored the event, described the blue cells’ defense system in medieval terms.

“It’s like a castle with a moat around it,” Concannon said. “There are soldiers in front of that moat, with a horseback team in front of the soldiers. On the castle itself, there are cannons as well as men equipped with bows and arrows.”

In the world of cyber security, firewalls and access points take the place of moats and horseback teams.

During the competition, the Fordham team faced constant attacks and forced intrusions into their systems. Lunchtime rolled by and stacks of pizza lay untouched on round tables while empty sugar packets and coffee pots littered the coffee counter.

Team public affairs officer Raymond Kram, a student in the Graduate School of Arts and Science, conducted a forensic analysis to identify a key attack and report it to a simulated FBI representative. This analysis helped contribute to the team’s third-place finish.

“What I find inspiring is how a diverse group of Fordham students came together through a common interest—cyber security,” Kram said.

The Fordham team consisted of seven undergraduate and graduate students from Fordham’s Cyber Security Research Group. Other blue cell teams included professional cyber security experts from Citigroup and the City of New York, among others.

The students trained vigorously for the event, making a trip in April to the United States Military Academy at West Point to observe cyber defense exercises. They also attended weekly seminars held by Frank Hsu, Ph.D., Clavius Distinguished Professor of Science,  and Anthony Ferrante, adjunct professor, Department of Computer and Information Science.

Fordham is planning to strengthen its cyber security offerings and curriculum at the undergraduate and graduate level, Hsu said, before adding that a certificate program may be forthcoming.

InfraGard, a collaboration between the FBI and the private sector, staged the event at the offices of Cisco Systems at 1 Penn Plaza.