Jerry Gao

Jerry Gao
San Jose State University | SJSU · Department of Computer Engineering and Department of Applied Data Science

Ph.D.

About

288
Publications
277,436
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,703
Citations
Introduction
Jerry Zeyu Gao is a professor at the Department of Computer Engineering at San Jose State University. Now, he is the director of SJSU research center on Smart Technology, Computing, and Complex Systems. He has over 20 years of academic research and teaching experience and over 10 years of industry working and management experience on software engineering and IT development applications. He has published three technical books and over hundreds (280) publications in IEEE/ACM and achieved journals.
Additional affiliations
October 2016 - present
San Jose State University
Position
  • Managing Director
Description
  • His current research interest includes smart cities, big data analytics & machine learning, cloud and mobile cloud computing, software testing and automation.
August 1998 - present
San Jose State University
Position
  • Professor (Full)
August 1998 - present
San Jose State University
Position
  • Professor
Description
  • One Washington Square San Jose, CA 95192-0180

Publications

Publications (288)
Article
According to Business Wire, the global market for Autonomous Vehicles estimated at 6.1 thousand Units fpsin the year 2020, is projected to reach a revised size of 110.1 thousand Units by 2026, growing at a CAGR of 60.6% over the analysis period. This strong demand brings more research interests in autonomous vehicle systems. One of the hot topics i...
Conference Paper
Full-text available
Autonomous driving has received much attention in academia and industries in recent years. Researchers incorporate different perceptions to detect vehicles, objects, routes, and lighting. However, few publications focus on road signs on pavement surface. This paper aims at creating a dataset with 10,000 images of U.S. road markings from similar dat...
Conference Paper
Full-text available
Development of autonomous vehicles is seen as a solution to many of today's societal and everyday issues such as traffic congestion, road accidents, and air pollution. Unmanned autonomous vehicles are complex systems and testing such systems raises many challenges. This paper, written in a position paper to review main aspects of testing of unmanne...
Article
Full-text available
There are many models presented that assess water quality. However, the applications of the models are limited due to the difficulty of preparing input data and interpreting model output. In this paper, we developed a Web-based platform to assist researchers in analyzing water quality. The data from sensors can be automatically imported to the plat...
Presentation
Full-text available
This presentation covers the following topics: a) the state-of-the-art AI Testing and Automation, including basic concepts, challenges and issues, as well as needs. b) AI Testing Modeling and Analysis c) Testing and automation for intelligent chat mobile apps d) AI Test Experience e) Test Automation
Presentation
Full-text available
Title: Real-Time Intelligent Wildfire Platform – Wildfire Big Data and Machine Learning Abstract: Wildfires in recent years have destroyed communities, caused server damage to property and human life, and living environment. There were 3,356 fires during the last decade (2009 – 2018), which is 1.4 times greater than the per-decade average number o...
Conference Paper
Full-text available
According to the PRNewswire research report, Cloud Robotics Market will witness a YOY growth of 21.19% in 2022 at a CAGR of 22.26% during the forecast period. This strong demand has brought more research interest in cloud platforms for robotics integration services. Most of the available research results and commercial application technology soluti...
Conference Paper
Due to the shortage of electricity, there is a strong demand on new technology and solutions in production of renewable green energy, including green energy AI, renewable energy infrastructure, green energy trading and management. Rapid advance of green energy technology and AI techniques provide many researchers with many opportunities and new ide...
Conference Paper
Full-text available
The global population is expected to reach 9.7 billion in 2050, according to the UN News. This suggests that food, agriculture, and global commodity trading are essential and critical to human beings. To stabilize food price and better understand and predict the market trend, people need a real-time efficient online platform as an intelligent tradi...
Conference Paper
Full-text available
With the fast advance of artificial intelligence technology and data-driven machine learning techniques, more and more AI approaches are applied in software engineering activities, such as coding, testing and etc.. Conventionally, test engineers use manual testing tools to test mobile apps and deliver products. Object detection technology like YOLO...
Conference Paper
Full-text available
With the development of machine learning and big data technology, dialogue systems have been applied in many fields, including aerospace, banking and other scenarios that require high accuracy of answers. This has prompted a great deal of research on quality verification and assurance of dialogue systems. Testing and evaluation, as two means to ens...
Article
Full-text available
A natural experiment conducted on the shrinking Salton Sea, a saline lake in California, showed that each one foot drop in lake elevation resulted in a 2.6% average increase in PM2.5 concentrations. The shrinking has caused the asthma rate continues to increase among children, with one in five children being sent to the emergency department, which...
Article
Full-text available
A natural experiment [1] conducted on shrinking Salton Sea, a saline lake in California, showed that each one-foot drop in lake elevation resulted in 2.6% average increase in 〖PM〗_2.5 concentrations. According to the paper [2], the shrinking has caused the asthma rate to keep going up among the kids, one in five children being sent to emergency dep...
Article
Chaotic maps have been widely used in image encryption due to their complexity, pseudorandomness and high sensitivity to initial values. In this paper, an image encryption algorithm based on a 4D chaotic map and steganography is proposed. The algorithm consists of two rounds of encryption and one operation of embedding hash. In the first round of e...
Article
Full-text available
According to the World Health Organization (WHO), wearing a face mask is one of the most effective protections from airborne infectious diseases such as COVID-19. Since the spread of COVID-19, infected countries have been enforcing strict mask regulation for indoor businesses and public spaces. While wearing a mask is a requirement, the position an...
Conference Paper
Full-text available
Wildfires are the most deadly and dangerous accidents across the United States, especially in California. Many lives are lost, and billions of dollars worth of property damages occur in wildfire every year. Wildfires are fueled and accelerated by several different factors, such as weather, climate, vegetation types, land cover, and human activities...
Article
Water accounts for about 70% of the earth’s surface and is one of the most important sources of life. The degradation of the Salton Sea’s water quality due to excessive usage of fertilisers and pesticides in agriculture has posed serious risks to biodiversity, human health, and the local economy. As a result, it is necessary to establish effective...
Presentation
Full-text available
This is an invited Keynote Presentation from 2021 IEEE Future Technology Summit. It discussed our smart wildfire prediction machine learning platform with detailed data engineering process, machine learning models and demo videos for wildfire detection, risk prediction, and progress prediction. The videos shows an on-going system development suppor...
Conference Paper
Full-text available
Functionalities of AI-powered mobile Apps or systems heavily depend on the given training dataset. The challenge in this case is that a learning system will change its behavior due to a slight change of dataset. While current alternative approaches for evaluating these apps either focus on individual performance measurement such as accuracy etc. In...
Conference Paper
Full-text available
With the advancement of machine learning algorithms, different models are being used in agriculture monitoring and food industries. Due to the significant growth in sensor technologies, a great deal of data has been made available in the public domain. The potential of machine learning models in satellite remote sensing data has earned a significan...
Conference Paper
Full-text available
According to the World Health Organization (WHO), wearing a face mask is one of the most effective protections from airborne infectious diseases such as COVID-19. Since the spread of COVID-19, infected countries have been enforcing strict mask regulation for indoor businesses and public spaces. While wearing a mask is a requirement, the position an...
Conference Paper
Full-text available
In this paper, a reversible data hiding scheme based on multiple residual histogram shifting is proposed. As is known to all, there is a prediction technology which can improve the hiding ability under the premise of ensuring good stego-image quality. It studies the similarity between image pixels and uses the residual histogram of the original cov...
Preprint
Wildfires are the most deadly and dangerous accidents across the United States, especially in California. Many lives are lost, and billions of dollars worth of property damages occur in wildfire every year. Wildfires are fueled and accelerated by several different factors, such as weather, climate, vegetation types, land cover, and human activities...
Preprint
With the advancement of machine learning algorithms, different models are being used in agriculture monitoring and food industries. Due to the significant growth in sensor technologies, a great deal of data has been made available in the public domain. The potential of machine learning models in satellite remote sensing data has earned a significan...
Preprint
Full-text available
According to the World Health Organization (WHO), wearing a face mask is one of the most effective protections from airborne infectious diseases such as COVID-19. Since the spread of COVID-19, infected countries have been enforcing strict mask regulation for indoor businesses and public spaces. While wearing a mask is a requirement, the position an...
Conference Paper
Full-text available
High-quality Artificial intelligence (AI) software in different domains, like image recognition, has been widely emerged in our lives. They are built on machine learning models to implement intelligent features. However, the current research on image recognition software rarely discusses test questions, clear quality requirements, and verification...
Chapter
The development of autonomous vehicles is seen as a solution to many of today’s societal problems such as traffic congestion, road accidents, theft prevention and air pollution. Radio technology offers a great contribution to these developments but continues to suffer from several shortcomings such as security breaches, radio interference, heteroge...
Article
Full-text available
Business process speci¯ed in Business Process Execution Language (BPEL), which integrates existing services to develop composite service for o®ering more complicated function, is error-prone. Veri¯cation and testing are necessary to ensure the correctness of business processes. SPIN, for which the input language is PROcess MEtaLAnguage (Promela), i...
Article
Full-text available
The Salton Sea, a saline lake in California, is becoming an environmental disaster. With a receding lakeshore, severe dust emission, and toxic water and soil, Salton Sea ecosystem is on a continuous decline for a long time. Many studies and research have been performed to understand the characteristics of soil and sediments present in Salton Sea re...
Article
Full-text available
Artificial intelligence applications provide tremendous opportunities to improve human life and drive innovation. AI systems/applications which operate in a real-world environment have to encounter an infinite set of feasible scenarios. Conventional testing approach to test the AI application allows only limited testing and does not allow taking th...
Article
Full-text available
Over the years, rampant wildfires have plagued the state of California, creating economic and environmental loss. In 2018, wildfires cost nearly 800 million dollars in economic loss and claimed more than 100 lives in California. Over 1.6 million acres of land has burned and caused large sums of environmental damage. Although, recently, researchers...
Conference Paper
Full-text available
Forecasting novel daily cases of COVID-19 is crucial for medical, political, and other officials who handle day to day, COVID-19 related logistics. Current machine learning approaches, though robust in accuracy, can be either black boxes, specific to one region, and/or hard to apply if the user has nominal knowledge in machine learning and programi...
Conference Paper
Full-text available
Hemp is a multipurpose plant that has industrial as well as medicinal value. The plant is easy to grow, maintain, and suitable under any climate. However, just like other plants, Hemp diseases affect plant growth and cause a significant economic loss in hemp production. With the rapid advancement of artificial intelligence and machine learning tech...
Article
Full-text available
Artificial intelligence applications provide tremendous opportunities to improve human life and drive innovation. AI systems/applications which operate in a real-world environment have to encounter an infinite set of feasible scenarios. Conventional testing approach to test the AI application allows only limited testing and does not allow taking th...
Conference Paper
Full-text available
Grape leaf diseases cause significant damage to the grapes and bring financial losses to the farmers if not detected and treated early. Computer vision and deep learning algorithms can be applied to detect the diseases with high efficiency if high accuracy is achieved. In this paper, four deep learning models, Vanilla CNN, improved VGG16, MobileNet...
Conference Paper
Full-text available
Abstract— Grapevine diseases and pets could cause significant financial losses to grape production and farmers if not detected and treated early. With the recent advance of artificial intelligence techniques and machine learning technologies, people start to use computer vision and deep learning algorithms to detect and classify grapevine diseases...
Conference Paper
Full-text available
In smart agriculture, disease detection and classification for diverse plants in farm fields is very important and critical in agriculture quality production. According to industry reports in the United States, the HEMP market is growing an annual rate of 34 percent, from $4.6 billion in 2019 to $26.6 billion in 2025. In hemp production, diseases a...
Conference Paper
The traditional encryption algorithms such as DES, AES are considered too slow for image encryption, which cannot meet the real-time requirements. Therefore, this paper proposes a parallel image encryption algorithm based on cellular automaton and chaotic map. In the scrambling stage, the keystream generated by 2D-LASM is used to scramble the rows...
Presentation
Full-text available
Presentation
This is an invited speech presentation on 6/30/2020 for IEEE BPIT webinar on "Smart CIty: Big Data and Machine Learning", which is organized by BPIT in india.
Article
Full-text available
In many supervised computer vision tasks such as object detection, manual annotation crowdsourcing platforms are widely used for acquiring large-scale labeled data. However, the annotation quality may suffer low quality that can severely affect the training of models. As a result, the evaluation of the annotations within the dataset is critical, ye...
Article
Full-text available
Fully black-box robotic testing is urgently needed given the popularity of mobile applications. A critical constraining issue for generating graphical user interface (GUI) models is identifying isomorphic GUIs. In this study, we present a deep learning-based end-to-end trainable model to determine the similarity between GUIs and subsequently identi...
Article
Full-text available
Cleanliness of city streets has an important impact on city environment and public health. Conventional street cleaning methods involve street sweepers going to many spots and manually confirming if the street needs to be clean. However, this method takes a substantial amount of manual operations for detection and assessment of street’s cleanliness...
Preprint
Full-text available
Cleanliness of city streets has an important impact on city environment and public health. Conventional street cleaning methods involve street sweepers going to many spots and manually confirming if the street needs to clean. However, this method takes a substantial amount of manual operations for detection and assessment of street's cleanliness wh...
Presentation
Full-text available
Advances in big data technology and machine learning have led to a surge in artificial intelligence (AI) applications in building smart cities with substantial investment from industry and governments. Since 2016, many US city governments, university and schools, and industry have teamed up to work on diverse smart city projects to diverse city cha...
Conference Paper
Full-text available
Graffiti on buildings and bridges are oftentimes an eyesore. Those on road symbol signs can even pose safety risks to motorists. Not only is graffiti cleaning costly, it also disrupts normal traffic. Graffiti is a widespread problem in many cities in the U.S. This paper proposes a machine learning approach to unmanned aerial vehicle (UAV) graffiti...
Article
Full-text available
With the fast growth of artificial intelligence and big data computing technologies, more and more software service systems have been developed using diverse machine learning models and technologies to make business and intelligent decisions based on their multimedia input to achieve intelligent features, such as image recognition, recommendation,...
Conference Paper
Full-text available
Growing amount of graffiti on buildings, bridges, and even freeway signs always damage the beauty of a city. People always put curse words and appropriate images in their graffiti, which often harm the appearance of the city and distracts from the beauty and successes of the city. Traditional cleaning methods not only cost a lot of labor, but also...
Article
Full-text available
During the process of smart city construction, city managers always spend a lot of energy and money cleaning street garbage due to the random appearances of street garbage. Consequently, visual street cleanliness assessment is particularly important. However, existing assessment approaches have some clear disadvantages, such as the collection of st...
Conference Paper
Full-text available
Human dynamic behavior detection and classification based on video plays an important role in understanding human motion, and it has many interesting applications in crime watch, security surveillance monitoring, sports, and so on. This paper reports our initial research work on dynamic human behavior pattern detection and classification based on r...
Conference Paper
Full-text available
With the fast advance of artificial intelligence technology and data-driven machine learning techniques, building high-quality AI-based software in different application domains is becoming a very hot research topic in both academic and industry communities. Today, many machine learning models and artificial technologies have been developed to buil...
Article
Full-text available
Recently, compressive sensing (CS) and visual security (VS) have caught researchers attention in information security field. However, the measurement matrix is often reused in CS, which makes it vulnerable to chosen plaintext attack (CPA). In addition, when generating meaningful cipher images, the size of the carrier image is usually not less than...
Article
Full-text available
Advancement in mobile, cloud computingand other techniques has made the world even smaller and connected like never before. It has become a challenge and an opportunity for cities to leverage these growing technologies to solve real city administration problems. Citiesare in the transformation to become state-of-the-art smartcitiesusing these techn...