As the volume, variety, and velocity of data continue to reach unprecedented levels, big data analytics has drawn significant interest. According to a recent report, the worldwide enterprise data analytics market is forecasted to grow at a 9.4% annual growth rate through 2018, reaching $59.2B.
Many organizations are keen on adopting big data techniques to analyze huge volumes of data that conventional business intelligence solutions cannot touch, and discover insightful knowledge for better decision making.
Recently deep learning, which extracts high-level abstractions from data, has emerged, and shows great potential for solving business problems. Several many startups are using deep learning techniques in their applications because it is effective for running many tasks.
OpenGov spoke to Ju Fan, Research Fellow, National University of Singapore, and Wei Wang, PhD Student, National University of Singapore, both of which are working on developing a distributed deep learning platform, Apache SINGA.
Apache SINGA is a distributed deep learning platform that entered Apache incubator in March of this year. The project is funded by the National Research Foundation, Ministry of Education, and A*STAR. SINGA is a valuable tool for big data analytics because:
- It supports various deep learning models, and thus has the flexibility to allow users to customize the models that fit their business requirements
- It provides a scalable architecture to train deep learning models from huge volumes of data
- It provides a simple programming model, making the distributed training process transparent to users.
We talked to Ju Fan and Wei Wang about their research in deep learning, how they got into the Apache incubator, case examples, and what challenges them about their research.
The very beginnings…
“For this project, we started from a research problem on multi-model data retrieval. We were to use different data from different modalities, like image data or text data. Later, I found that deep learning was really effective for extracting features from different modalities,” said Wei Wang.
He then started developing his work with deep learning and has since published papers on algorithms and retrieval problems.
His mentor, Prof Ooi, is an expert on database distributed computing and advised that Wei Wang work on the system part. Deep Learning training is very time consuming because it takes a long time to train a complex model over a large data set.
In order to train the model, Wei Wang used a Stochastic Gradient Descent algorithm, commonly used for deep learning models. This is because it updates the model parameters based on parameter gradients.
Additionally, distributed training had to be applied because datasets can be quite large and models, quite complex. This accelerates the speed of training through the use of more computing resources, which catered to running different training frameworks in a scalable manner.
After they finished the first version of SINGA, Prof Ooi suggested that they try the Apache Incubator and get more people outside NUS to contribute to this project.
Wei Wang submitted his proposal to be included in the incubator and would receive comments from Apache mentors. Within Apache, this project was the only project of its kind, focused on deep learning.
Wei Wang told us that the team is now working on improving the system. “We are working to improve this system in terms of: scalability, efficiency, and the features to support different applications,” he said.
SINGA applied to Healthcare Data Analytics
With the data analytics power of SINGA, Ju Fan explained that they are collaborating with the National University Hospital System to work with data scientists and medical specialists in the healthcare domain.
They would look at data relating to diagnosis, medications, and lab tests results, with the greater aim to reduce the cost of healthcare and improve performance of services.
“The approach we draw knowledge from the healthcare data,” stated Ju Fan, “We are carrying out two applications of SINGA: the first is to predict risk of hospital readmission, and the second is chronic disease progression modelling.”
These two applications show how SINGA is helpful in analysing electronic medical record (EMR) data because:
- Hospital readmission contributes a significant proportion of healthcare spending, while a large proportion of readmissions are potentially avoidable. Predicting risk of readmission for potentially fatal diseases can effectively yield lower costs and better healthcare quality.
- Chronic diseases tend to evolve and progress over a long time, and if their conditions are not properly managed, more serious comorbidities as well as complications may ensue. Disease progression modelling can help with the early detection and management of chronic diseases.
“Working with healthcare analytics is quite challenging because of two things: the data is sparse and personalised medications,” Ju Fan told us, “To address these problems we apply the deep learning techniques because deep learning has a good ability to find the high level abstractions from the raw data.”
The benefits of having such a personalised system are clear, patients would have better treatment, doctors would perform more efficient, and hospitals would be able to reduce the overall cost of treatment.
Going forward, Apache SINGA will continue to develop and improve as SINGA could be useful to other data types and applications. The team is currently working with a local security company on malware detection, using deep learning techniques.
The team behind Apache SINGA will release version 2 of their programming model next month, January 2016.
For more technical details and development schedule, interested readers please refer to http://www.comp.nus.edu.sg/~dbsystem/singa/
Ju Fan received his PhD in computer science from Tsinghua University, China in 2012. He is currently a research fellow in the School of Computing, National University of Singapore. His research interest includes big data analytics, crowdsourcing, and database management.
Wei Wang is a Ph.D. student in the computer science department of the National University of Singapore. Currently, he is working on an Apache incubator project (SINGA) for developing a general distributed deep learning system.
The Ohio Criminal Sentencing Commission is working with the University of Cincinnati to build the Ohio Sentencing Data Platform (OSDP). The OSDP is designed to help judges implement the Uniform Sentencing Entry and Method of Conviction entries and empower courts with accessible and reliable information. The OSDP will achieve goals that include: using data to inform decision-making; improving transparency; and, making data accessible for the public, practitioners, and research.
The collection of sentencing data in a comprehensive and searchable database will inform decision-making and give judges the tools and information needed to impose sentences in accordance with the purposes and principles of felony sentencing.
Courts, Counties, and policymakers statewide can use this data to make sensible, cost-effective decisions, promote smart, effective use of resources, and ensure measured proportional responses. Further, reliance on data creates an opportunity to monitor and evaluate the results of those changes, to determine if the desired effects are achieved, and assess unintended consequences.
The OSDP will establish standardised data formats for compiling and tracking felony sentencing in all 88 Ohio counties. Built with $800,000 in funding from the court, the database will allow users to compare sentences across the state and see the broader demographics of those who are sentenced to identify race- or income-based inconsistencies, for example.
Those of us who have been entrusted with the duty to lead and to participate in the criminal justice system have an obligation to make sure there is public trust in that system and that the system delivers. Diverse justice for all. And data collection will make that happen.
– Maureen O’Connor , Ohio Supreme Court Chief Justice
So far, 34 of the state’s 244 common pleas judges have opted into the program, which requires them to fill out detailed forms on their sentences. More judges are signing up every week. The platform is the first step to providing accessible and searchable information for judges making sentencing decisions and increasing transparency and accessibility for the public, journalists and researchers.
Giving justice-system practitioners, including judges, attorneys, and court staff the best information available for use during the sentencing process without administrative or fiscal burden, allows them to perform their public-service duties in the most impactful way.
Until recently, Ohio didn’t have a central index on sentencing, so it was difficult to find the number of people sentenced for a specific felony in a given year, the sentences imposed for each felony offender, how many of those were imposed as a result of a plea bargain or how many offenders were placed on community supervision.
The data-driven OSDP project is designed to “tell the story” of sentencing in Ohio by providing understanding and analysis of the criminal justice system by providing statewide, reliable and accessible information on sentencing outcomes.
As reported by OpenGov Asia, the justice system, banks, and private companies use algorithms to make decisions that have profound impacts on people’s lives. Unfortunately, those algorithms are sometimes biased — disproportionately impacting people of colour as well as individuals in lower-income classes when they apply for loans or jobs, or even when courts decide what bail should be set while a person awaits trial.
U.S. researchers have developed a new Artificial Intelligence (AI) programming language that can assess the fairness of algorithms more exactly, and more quickly, than available alternatives. Their Sum-Product Probabilistic Language (SPPL) is a probabilistic programming system.
SPPL shows that exact probabilistic inference is practical, not just theoretically possible, for a broad class of probabilistic programmes. The researchers have been applying SPPL to probabilistic programmes learned from real-world databases, to quantify the probability of rare events, generate synthetic proxy data given constraints, and automatically screen data for probable anomalies.
Healthcare systems around the world spend trillions of dollars each year to address growing healthcare challenges. These barriers include epidemiological shifts in death rates (from maternal, perinatal and infectious diseases to cardiovascular diseases and cancers), as well as an ageing population with longer life expectancies.
Singapore stands out among countries across the world. Its constantly stable economy, focus on social inclusivity and penchant for deploying technology have aided in hastening the achievement of the country’s healthcare milestones.
OpenGov Asia had the opportunity to speak with Associate Professor Thomas Lew, Group Chief Data & Strategy Officer, National Healthcare Group to gain further insights on the future of healthcare in the nation as well as the key pillars and catalysts that drive the sector.
Technology has accelerated transformation in the health sector
COVID-19 has introduced unprecedented challenges for healthcare across the board but at the same time inspired and driven innovations at unprecedented speed. Beyond a doubt, the use of technology in healthcare has resulted in better patient diagnosis and treatment and has improved the quality of life and saved lives.
In the current context, it is likely the most important sector to benefit from technological adoption. Telehealth, for example, has proven to be fairly successful as people seek to manage their care in new and different ways during the pandemic, which has surprised some physicians.
Singapore is a densely connected city-state where the complexities of an internet-enabled telehealth consultation compete with the standard physical visit to the doctor. According to Associate Professor Lew, telehealth must be contextualised for value, grounded on trust-based relationships, in areas such as real-time biological monitoring, and round-the-clock trusted advice and alerts.
“For the healthy population, the potential of health coaching for individuals and organisations has yet to be fully realised. In order to envision telehealth beyond transactional efficiency, much remains to be done,” he explains.
Artificial intelligence and automation services and systems also significantly benefit healthcare. Yet, Associate Professor Lew believes, while AI is not in the consciousness of mainstream healthcare workers, it is ubiquitous without their realisation.
The lower hanging fruits for AI inclusion in direct care interventions continue to be mundane and predictable tasks, as well as assistive robots in ancillary or health facility production systems. AI and machine learning are probably most valuable as augmented intelligence for narrowly defined use-cases with adequate digital guardrails so that the basis for interpretation is understood and trusted. In this context, experts have recommended that, in addition to deep learning, more traditional hierarchical models of reasoning be used.
When asked about the decision-making process through data analytics, Associate Professor Lew firmly believes that “decision-making is a complex cognitive science.” He says, “NHG has always been a data-driven organisation and has made many major shifts in its strategic directions, from attention to acute care, to the ageing population, to a pre-emptive model for augmenting today’s medical model for tomorrow’s preventive health of the population.”
Data scientists, such as those at the Institute of Mental Health, Tan Tock Seng Hospital’s Office of Clinical Epidemiology, Analytics, and Knowledge (OCEAN) and NHG’s Health Services and Outcomes Research (HSOR), enable NHG to apply data for insights and translation into policy and investments in new services. By creating a shared data model, NHG can implement near real-time health-intelligence tools across the organisation.
NHG’s River of Life population health strategy comprising the Living Well, Living With Illness, Crisis and Complex Care, Living with Frailty, and Leaving Well segments of care, seeks to provide holistic, integrated care from cradle to grave, and ensures that no one is left behind for his or her health needs.
NHG is focused on implementing its digital master plan in tandem with the Ministry of Health’s digital ecosystem and the national Smart Nation Digital strategy. This entails strengthening NHG’s digital front-door services to the population. In addition, NHG intends to improve its data analytics infrastructure for ingesting unstructured data, analytics workbenches and business intelligence tools to advise policy decisions and improve outcomes.
“When we collaborate with our partners through portals on shared care plans, our residents can access digital services seamlessly to augment their experience with our physical healthcare system,” Associate Professor Lew elaborates.
When asked about his current role in upskilling the workforce and bolstering the talent pipeline, Associate Professor Thomas believes in the synergy of dual-domain expertise. Many of NHG’s skilled healthcare professionals, he noted, have solid foundations for expanding their roles over and above their core experiences into health technology-related areas such as informatics, data science, data systems management, and biomedical engineering.
Arguably, the COVID-19 pandemic has revealed stress points in societies’ coping mechanisms, as well as the limits to which individual needs are balanced with the collective interest. The way forward, he emphasises, is a return to basics, based on the values and ethical systems that govern healthcare delivery. With NHG’s vision of “Adding Years of Healthy Life,” the organisation is driven to be foresighted, proactive, and responsive to changing needs.
Singapore is not lacking in potentially disruptive technologies such as 5G for remote care or real-time supervision; machine learning for augmented intelligence, drug discoveries, and biomarkers; health insights through digital phenotyping; assistive robots for preventive care of the isolated; or using blockchain for improving the data security.
“What is important is being true to the values treasured by person and community, to ensure we deliver care to those we serve with good judgement, ethos, and empathy.”
About Associate Professor Thomas Lew
Associate Professor Thomas Lew graduated from the National University of Singapore (NUS)’s Faculty of Medicine in 1985, specialising in anaesthesia and intensive care medicine, with special interests in neurological intensive care and neuro-anaesthesia. He is Group Chief Data and Strategy Officer at the National Healthcare Group (NHG), one of three public healthcare clusters in Singapore, which serves 2.2 million residents in Central Singapore. He is currently an anaesthesiologist at TTSH, where he was Chairman of the Medical Board between 2011 and 2019.
Associate Professor Lew is also Clinical Director of NHG’s Centre for Medical Technology and Innovation (CMTi), an integrated agency that supports clinician innovators in collaborating with industry and academic partners to bring new technologies to market. On practising medicine, Associate Professor Lew says, “The practice of medicine builds purpose and meaning through service to individuals and community. It is very satisfying to help patients to recover and heal, and undeservedly receive their gratitude for a new lease on life. Through these encounters, tinged with their suffering, courage, and grief, we realise the fragility of life and the limits of medicine. However, this also inspires personal growth and maturity through learned experiences, in particular the power of communications, receiving and offering empathy.”
To foster healthy and orderly development of the industry, Chinese regulators will strengthen the management of algorithms related to internet information services. According to new guidelines issued by nine ministries or departments including the Cyberspace Administration of China, a three-year campaign will seek to put in place a sound management mechanism and supervision system, and a standardised algorithm ecosystem.
The guidelines urged enterprises to strengthen their sense of responsibility and set up responsibility systems for algorithm security and sci-tech ethical review systems. Algorithm recommendation service providers should also allow users to select or modify their individual tags used for recommending services.
Legal violations and malpractices related to algorithms will be severely punished, the guidelines stipulated. The guidelines also demanded efforts to prevent the abuse of algorithms, prohibiting activities that use them to tamper with public opinion, attack competitors and infringe upon the rights and interests of internet users.
China also passed the Personal Information Protection Law to further regulate cyberspace. The law will come into force on November 1, serving as the first on the Chinese mainland solely dedicated to personal data protection.
The new law on personal data protection is the first in the Chinese mainland solely dedicated to the issue. The Personal Information Protection Law stipulates that the processing of personal information shall be carried out legally and with due process. Buying, selling, and revealing other people’s personal information without their consent are now illegal.
The hundreds of millions of people in China who enjoy the benefits of digitisation may be unaware that their personal information may have been compromised in the course of using online and offline services. But with the Chinese mainland’s first Personal Information Protection Law coming into force in November, along with the existing regulations, ordinary citizens can now ensure that their data remains private.
The new law is expected to help consumers raise awareness of their rights to the security of their personal data. It will also help them say no to the illegal processing of their information. Even people without legal expertise can report their cases or file complaints through dedicated channels to reach authorities for further inspections. With tougher and clearer regulations coming into effect, companies in this sector will likely exercise more caution and restraint when gathering customer information.
As reported by OpenGov Asia, China has also passed regulations on cybersecurity. Measures including monitoring, defence, and proper handling of cybersecurity risks and threats from both home and overseas will be carried out to ensure that relevant facilities are protected from attacks, intrusions, interference and sabotage. The regulation came as the country’s major IT infrastructure faces severe security challenges including frequent cyberattacks.
Measures including monitoring, defence, and proper handling of cybersecurity risks and threats from both home and overseas will be carried out to ensure that relevant facilities are protected from attacks, intrusions, interference and sabotage. The regulation came as the country’s major IT infrastructure faces severe security challenges including frequent cyberattacks.z
The regulation also called on operators of major IT infrastructure projects to bear their primary responsibility of maintaining the integrity, confidentiality and availability of relevant data. Requirements for these operators include conducting security checks and risk assessments every year and prioritising safe and creditable internet products and services in procurement.
An academician with the Chinese Academy of Engineering believes that the latest moves highlight strengthened governance in cyberspace. He, however, stressed that regulation does not mean discarding the development. It is about attaching equal importance to both sides. Strengthened governance will provide a healthier environment for the development of the internet sector, calling for greater emphasis on national security and protection of users’ rights in the process.
Kerala Rail Development Corporation (KRDC) is collaborating with a start-up incubated at the Indian Institute for Science (IISc) to use sensing technology to make its railways safer, especially on vulnerable terrains. The IISc-incubated start-up, L2MRail, the Society for Innovation and Development (SID), and IISc signed a memorandum of understanding (MoU) with KRDC. The technology is based on optical light and works on the principle of wavelength shifts.
The organisations have pioneered a sensing technology to develop a structural health monitoring system (SHMS) that will monitor civil engineering structures of the Kerala Rail’s Silverline project, under which the two ends of the state will be connected by a semi high-speed rail corridor from Kasaragod to Thiruvananthapuram. It is a 530-kilometre (km) double-track stretch and the project will reduce travel time from the current ten or so hours to less than four hours. Trains are expected to run at 200 kilometres per hour (kmph), which is more than four times the current average speed of 45 kmph.
Using the Fibre Bragg Grating (FBG)-sensor-driven monitoring system, rail corporations can embed or attach sensors in rail structures, enabling both on-demand and continuous data, as well as 24/7 warning alerts for damage detection. The technology can also be customised for each structure and location. According to a news report, KRDC stated that addressing the need for accurate, real-time data of rail conditions like railway tracks and train wheels will ensure the stability and integrity of structures even in vulnerable areas.
Ensuring rail safety in settlement-prone locations, flood-prone areas, earth slip locations, weak soil, and heavy rainfall areas, necessitates a shift from conventional manual inspection. Constant, technology-driven monitoring of both running trains and rail structures offers the ideal solution, authorities have explained. There is a gap between the critical need for rail safety and the lack of systems that constantly monitor both trains and railway structures in real-time.
Structural defects are generally identified only when an accident occurs, and the preventative identification of weak links can help avoid mass casualties. The potential of FBG sensor technology is immense. Its applications are not just restricted to railways but can be used in any field that necessitates constant real-time monitoring and timely warning alerts to identify damages, an official noted.
The state has been working to digitise public service delivery and boost investment in technology start-ups. Recently, OpenGov Asia reported that the Kerala Chief Minister, Pinarayi Vijayan, inaugurated a Digital Hub at the Technology Innovation Zone in Kochi. It occupies 200,000 square feet of built-up space, set up by the Kerala Startup Mission (KSUM). The hub has the capacity to support 200 start-ups, apart from the 165 start-ups hosted in the adjoining Integrated Startup Complex.
The Digital Hub is expected to emerge as one of South Asia’s largest centres for technology start-ups. The hub houses a design incubator, healthcare incubator, centre of excellence (CoE) for mouser electronics, co-working spaces, design studios, investors hive, and an innovation centre. The digital hub is the latest addition to the Startup Mission’s Technology Innovation Zone (TIZ) as a global innovation hub for several technology sectors.
The CoE at the hub aims to groom shelter-related ideas and innovations and will function as a one-stop centre for all product design and development activities for software and hardware components. These include all sectors and emerging technologies such as artificial intelligence (AI), robotics, augmented reality/virtual reality, the Internet of things (IoT), and natural language processing.
The Indian Institute of Technology in Roorkee (IIT-Roorkee), in collaboration with a private player, has announced that they will be setting up a new school that focuses on education in emerging technologies such as artificial intelligence (AI) and data science to meet the rising global demand for data analysts and AI experts.
According to a news report, the school will accept admissions from September 2022 and will offer bachelor’s, master’s, and doctoral degrees. The objective of the school is to develop new and skilled manpower in the areas of data science and AI. It also intends to empower existing manpower by offering focused training and certifications in these fields.
The school will also be a leader in seeding entrepreneurship and start-ups related to data science and AI and creating resource centres for information and knowledge sharing. The course will invite renowned experts in the field of AI to participate in designing relevant curricula as well as faculties and mentors who will encourage innovative research ideas to the students. These experts will also facilitate student scholarships and faculty exchange programmes. An industry expert noted that AI-driven technologies are rapidly transforming the world. Academic collaborations between international faculty and institutes can produce individuals poised to address such ongoing global challenges as climate change, resource sustainability, and security.
Earlier this month, the Indian Institute of Science in Bangalore (IISc) announced it would establish a state-of-the-art AI and machine learning (AI/ML) centre at the IISc campus. Spread across approximately 140,000 square feet, the centre will offer bachelor’s, master’s, and short-term courses in areas AI/ML, deep learning, fintech, reinforcement learning, image processing, and computer vision.
The centre will also promote research and innovation in AI/ML and develop the talent pool from across the country to provide cutting-edge solutions to meet the industry’s emerging and future requirements. According to a statement, as IISc continues to deliver on its mandate to provide advanced scientific and technological research and education, its partnerships with forward-thinking institutions will help it scale up substantially and position India as a deep tech innovation hub.
The global AI market size is expected to gain momentum and reach US$360.36 billion by 2028 while exhibiting a CAGR of 33.6% between 2021 to 2028. AI has become immensely popular, and industries across the globe are rapidly incorporating it into their processes to improve business operations and customer experience. The Indian government is developing and implementing several AI-driven initiatives in education, healthcare, agriculture, and finance. Educational institutes and government agencies are launching centres and offering courses in emerging technology to help build a skilled workforce.
For instance, earlier this year, India’s Ministry of Finance entered a strategic partnership with a tech giant to build a Centre of Excellence in AI and emerging technologies at the Arun Jaitley National Institute of Financial Management (AJNIFM). The centre will serve as a central body for research, AI scenario envisioning, and technology-led innovation. The two sides would jointly explore use cases of emerging technologies in finance and related areas, across central and state ministries and public sector enterprises. Public sector officials would be trained on the application of emerging technologies in finance management to address potential risks like money laundering, the use of machine learning models for decision making, and the role of responsible tech in finance, among others.
The Office of National Intelligence and the Department of Defence National Security Science and Technology Centre is funding the National Intelligence and Security Discovery Research Grants (NISDRG) program, which was awarded to Associate Professor Vallipuram Muthukkumarasamy from the School of Information and Communication Technology and his project partners Professor Ryan Ko from the University of Queensland and Professor Marimuthu Palaniswami from the University of Melbourne.
Associate Professor Muthukkumarasamy said that cryptocurrency comes with anonymity or pseudo-anonymity, so law enforcement authorities find it very difficult to link certain payments with illegal activity.
As it is not a central bank-issued currency, it is not controlled by any organisation or any country. This project will create new tools based on artificial intelligence to analyse anonymised transactions and link them with financial crime patterns to effectively identify perpetrators. It will develop a novel investigative toolkit to facilitate attribution – such as source identification and legal evidence – of criminals linked to digital payments to crime in almost real-time.
Associate Professor Muthukkumarasmy said there were no algorithms or techniques to unravel the hidden connections from a massive network of digital payments, which is being misused by criminals. Therefore, the proposed big data analytics will exploit the hidden connections and reveal the linkages to automatically reconstruct the provenance – information flows and payment histories of criminal activities – in near real-time.
There are more than 2000 unregulated cryptocurrencies worldwide. These massive digital networks and the frequency with which anonymous transactions occur pose numerous challenges to the existing financial systems’ stability and the ability of Law Enforcement Agencies (LEAs) to intelligently identify and link these transactions to crimes.
With the advent of cryptocurrencies, criminals can hide their identities and launder money by transferring their illicit collection into digital wallets.
These transactions can be tracked as they are based on public ledgers and there is a traceable link for each transaction. However, criminals can then use services such as ‘mixing’ or ‘tumbling’ to convert ‘dirty money’ into ‘clean money’.
The services also break a transaction into smaller amounts, which are then sent to clusters of new addresses in the network repeatedly, and finally arriving at the ‘clean wallet’. This process removes the link from ‘dirty wallet’ to the ‘clean wallet’ and therefore, cannot establish the link to the ‘root wallet’.
The money that is now in the ‘clean wallet’ can be used for legitimate purposes.
Associate Professor Muthukkumarasamy pioneered the Network Security teaching and research at Griffith University and is leading the Networking & Security and Blockchain Research Group at the Institute for Integrated and Intelligent Systems. He also led the development of the first Master of Cyber Security program in Queensland.
The aims of the project include:
- Design and develop an efficient multi-source feature extraction mechanism to facilitate gathering intelligent information and security alerts about suspicious cryptocurrency payments;
- Design and build a high usability automated provenance reconstruction tool to facilitate forensic investigators for real-time attribution of payments to crime.
The Minister for Defence announced Griffith as among the eight Australian universities to receive funding for projects in the first round of the NISDRG program. He noted that the targeted funding for Australia’s higher education sector will enhance our ability to deal with threats to our national interests through the development of cutting-edge technology. The three-year project ‘Linking Digital Payments to Crime Using Big Data Machine Learning Tools’ received $590,843 in funding.
A research team of the Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong (CUHK) has recently developed a self-powered wireless sensing e-sticker (SWISE).
SWISE can convert the energy of the finger touch on the e-sticker into electromagnetic wave signals for wireless transmission without batteries or wires. Taking advantage of flexible, ultra-thin, and long effective transmission distance, SWISE can further the development of smart sensing and remote-control technologies. The findings have been published in the internationally renowned journal Science Advances, and the research team will cooperate with tech companies to bring related smart products to market.
In addition, the team has invented a novel triboelectric nanogenerator (TENG) the power output of which is far beyond that of the existing TENG. This invention may pave the way for using TENG to power home electrical appliances and offer an alternative renewable energy option.
Wireless sensing e-sticker
The development of the Internet of Things (IoT) is the key to building a smart city, in which sensors act as eyes and ears of the IoT system. These sensors are responsible for collecting physical variables such as temperature, pressure, speed, and convert them into electronic signals for analysis. Some researchers predicted that there will be billions of sensor nodes connected to the IoT in the next few years forming a physical information sensing network.
However, traditional wireless sensing and transmission technology still require multiple independent modules for sensing, signal modulation, transmission, and power source and management, which make the whole system bulky and rigid, with high power consumption and pricy too. This undoubtedly limits the application scenarios of wireless sensing technology and increases maintenance costs and difficulties.
The research team led by Professor Zi Yunlong, Assistant Professor of the Department of Mechanical and Automation Engineering at CUHK, has designed a smart material-based e-sticker SWISE, combining the four functional modules of traditional wireless sensing systems into a single unit.
SWISE is a soft and flexible electronic film (the thinnest is only 95 μm, which is less than the width of two human hairs), which generates displacement current during the discharge process to achieve self-powered wireless sensing based on the triboelectric nanogenerator (TENG) technology.
SWISE has three layers, where the middle one is a metal film with two electrodes, and the outside is composed of a tribo-charge layer and a substrate layer. When the finger slides on the tribo-charge layers of SWISE to generate tribo-charges, a discharge effect will be generated, which converts the kinetic energy of the finger movement into electromagnetic signals. The research team has proved that the signal can travel long distances (up to 30 metres) without an external power supply.
Multi-point sensing ability, which can be achieved by distinguishing the signals generated from different design parameters, allows sensors to be widely applied in different scenarios in a smart city. Thus, the research team has designed devices with varied parameters, for instance, by changing the inductance of the device, so that SWISE can generate signals with different characteristics and spectrums, which expands its application fields.
The wireless soft keyboard and wristband shown in videos 1 and 2 can transmit four different signals 1, 2, 3, and 4, respectively. SWISE is also expected to be used in smart clothes, robotics, medical treatment, human-machine interfaces, body area sensor networks, and virtual reality in the future.
In addition, the research team is exploring the potential of SWISE for gas detection. They found that spectrums of the electromagnetic signal generated by the displacement current will be slightly varied when the gas composition between the two electrodes of the metal film is changed.
Through artificial intelligence (AI) and deep learning technologies, they successfully distinguished the signal characteristics of ten different gas composition and concentration combinations (including argon, carbon dioxide, helium, nitrogen and general air), with 98.5% recognition accuracy.
The team repeatedly tested the SWISE sensing system and its applications, such as wireless soft keyboards and smart wristbands. The results fully proved that it has huge application potential in wireless sensing and remote control. It is expected to further the evolution of smart sensing and remote-control technologies and the development of the smart city in Hong Kong.
This project was funded by the HKSAR Government’s Research Grants Council Early Career Scheme, General Research Fund, HKSAR Innovation and Technology Fund, and Tencent University Relations Programme.
Novel triboelectric nanogenerator with high power output
TENG empowers SWISE to generate displacement current during the discharge process to achieve self-powered wireless sensing. Not only a finger touch can generate power by TENG. Mechanical motions in the environment, such as water waves, wind, rain droplets, and biomechanical motions can also be harvested by TENG to produce clean and renewable energy. However, TENG suffers from two fundamental limitations: the low charge transfer and the high output impedance, which result in low output power and limited application.
Recently, Professor Zi and his team have developed an opposite-charge-enhanced transistor-like triboelectric nanogenerator (OCT-TENG) that is capable of delivering instantaneous power density over 10 MW/m2 at a low frequency of about 1 Hz, far beyond the previous reports.
For demonstrating the high performance of this new invention, the team lit up a 180 W commercial lamp using an OCT-TENG device, as well as a vehicle LED bulb rated 30 W being wirelessly powered. These results set a record for the high-power output of TENG. The related output was published in the prestigious journal of Nature Communications.