Baijian Yang

• Doctor of Philosophy
• Professor at Purdue University West Lafayette

Spatial transcriptomics (ST) technologies have revolutionized our understanding of cellular ecosystems. However, these technologies face challenges such as sparse gene signals and limited gene detection capacities, which hinder their ability to fully capture comprehensive spatial gene expression profiles. To address these limitations, we propose le...

Remote sensing scene classification (RSSC) is a critical task with diverse applications in land use and resource management. While unimodal image-based approaches show promise, they often struggle with limitations such as high intra-class variance and inter-class similarity. Incorporating textual information can enhance classification by providing...

Tree species classification using unmanned aerial vehicle (UAV) images has gained increasing attention due to recent advancements in deep learning algorithms and UAV technology. Recent studies have primarily focused on the use of UAV images captured during the growing seasons. Despite the fact that winter is a critical and convenient period for for...

A 3D point cloud is an unstructured, sparse, and irregular dataset, typically collected by airborne LiDAR systems over a geological region. Laser pulses emitted from these systems reflect off objects both on and above the ground, resulting in a dataset containing the longitude, latitude, and elevation of each point, as well as information about the...

Forests play a critical role in the provision of ecosystem services, and understanding their compositions, especially tree species, is essential for effective ecosystem management and conservation. However, identifying tree species is challenging and time-consuming. Recently, unmanned aerial vehicles (UAVs) equipped with various sensors have emerge...

Human state recognition is a critical topic with pervasive and important applications in human-machine systems. Multi-modal fusion, which entails integrating metrics from various data sources, has proven to be a potent method for boosting recognition performance. Although recent multi-modal-based models have shown promising results, they often fall...

Modern clinical studies collect longitudinal and multimodal data about participants, treatments and responses, biospecimens, and molecular and multiomics data. Such rich and complex data requires new common data models (CDM) to support data dissemination and research collaboration. We have developed the ARDaC CDM for the Alcoholic Hepatitis Network...

The interaction and collaboration between humans and multiple robots represent a novel field of research known as human multirobot systems. Adequately designed systems within this field allow teams composed of both humans and robots to work together effectively on tasks, such as monitoring, exploration, and search and rescue operations. This articl...

Spatial cellular authors heterogeneity contributes to differential drug responses in a tumor lesion and potential therapeutic resistance. Recent emerging spatial technologies such as CosMx, MERSCOPE and Xenium delineate the spatial gene expression patterns at the single cell resolution. This provides unprecedented opportunities to identify spatiall...

Recent advances in high-throughput molecular imaging have pushed spatial transcriptomics technologies to subcellular resolution, which surpasses the limitations of both single-cell RNA-seq and array-based spatial profiling. The multichannel immunohistochemistry images in such data provide rich information on the cell types, functions, and morpholog...

Spatial cellular heterogeneity contributes to differential drug responses in a tumor lesion and potential therapeutic resistance. Recent emerging spatial technologies such as CosMx SMI, MERSCOPE, and Xenium delineate the spatial gene expression patterns at the single cell resolution. This provides unprecedented opportunities to identify spatially l...

As many as 80% of critically ill patients develop delirium increasing the need for institutionalization and higher morbidity and mortality. Clinicians detect less than 40% of delirium when using a validated screening tool. EEG is the criterion standard but is resource intensive thus not feasible for widespread delirium monitoring. This study evalua...

The interaction and collaboration between humans and multiple robots represent a novel field of research known as human multi-robot systems. Adequately designed systems within this field allow teams composed of both humans and robots to work together effectively on tasks such as monitoring, exploration, and search and rescue operations. This paper...

Video object segmentation (VOS) plays an important role in video analysis and understanding, which in turn facilitates a number of diverse applications, including video editing, video rendering, and augmented reality / virtual reality. However, existing deep learning-based approaches rely heavily on a large number of pixel-wise annotated video fram...

italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Contribution: A novel proactive and collaborative learning paradigm was proposed to engage learners with different backgrounds and enable effective retention and transfer of the multidisciplinary artificial intelligence (AI)-cybersecurity knowledge. Sp...

Cell-cell communications are vital for biological signalling and play important roles in complex diseases. Recent advances in single-cell spatial transcriptomics (SCST) technologies allow examining the spatial cell communication landscapes and hold the promise for disentangling the complex ligand-receptor (L-R) interactions across cells. However, d...

In order to operate in a regulated world, researchers need to ensure compliance with ever-evolving landscape of information security regulations and best practices. This work explains the concept of Controlled Unclassified Information (CUI) and the challenges it brings to the research institutions. Survey from the user perceptions showed that most...

The Indiana University Data Coordinating Center is developing ARDaC, the Alcoholic Hepatitis Network (AlcHepNet) Research Data Commons, to facilitate the effective use of the rich and complex AlcHepNet multimodal data and synergize efforts and expertise within the consortium and beyond. ARDaC provides a comprehensive solution for representing, quer...

Delirium occurs in as many as 80% of critically ill older adults and is associated with increased long-term cognitive impairment, institutionalization, and mortality. Less than half of delirium cases are identified using currently available subjective assessment tools. Electroencephalogram (EEG) has been identified as a reliable objective measure b...

As many as 80% of critically ill patients develop delirium increasing the need for institutionalization and higher morbidity and mortality. Clinicians detect less than 40% of delirium when using a validated screening tool. EEG is the criterion standard but is resource intensive thus not feasible for widespread delirium monitoring. This study evalua...

Human state recognition is a critical topic with pervasive and important applications in human-machine systems.Multi-modal fusion, the combination of metrics from multiple data sources, has been shown as a sound method for improving the recognition performance. However, while promising results have been reported by recent multi-modal-based models,...

The recent advances in high throughput molecular imaging push the spatial transcriptomics technologies to the subcellular resolution, which breaks the limitations of both single cell RNA seq and array based spatial profiling. The latest released single cell spatial transcriptomics data from NanoString CosMx and MERSCOPE platforms contains multi cha...

Tensor decompositions, including CANDECOMP/PARAFAC decomposition (CPD), Tucker decomposition (TKD), and tensor train decompositions (TTD), are extensions of singular value decomposition (SVD) for matrices. They are frameworks to decompose images or videos data into bases and coefficients. Due to recent developments in artificial intelligence (AI),...

Identifying brain abnormalities in autism spectrum disorder (ASD) is critical for early diagnosis and intervention. To explore brain differences in ASD and typical development (TD) individuals by detecting structural features using T1-weighted magnetic resonance imaging (MRI), we developed a deep learning-based approach, three-dimensional (3D)-ResN...

Dear Editor, Visual localization relies on local features and searches a pre-stored GPS-tagged image database to retrieve the reference image with the highest similarity in feature spaces to predict the current location [1]–[3]. For the conventional methods [4]–[6], local features are generally explored by multiple-stage feature extraction which fi...

Traditional principal component analysis (PCA) is well known in high-dimensional data analysis, but it requires to express data by a matrix with observations to be continuous. To overcome the limitations, a new method called flexible PCA (FPCA) for exponential family distributions is proposed. The goal is to ensure that it can be implemented to arb...

Core failure inspection is an important issue in die casting. The inspection process is often carried out by manually examining X-ray images. However, human visual inspection suffers from individual biases and eye fatigues. Computer-vision-based automatic inspection, if it can achieve equal to or better than human performance, is favored to assist...

In this work, we introduce a Denser Feature Network(DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more key...

Tensor decompositions are becoming increasingly important in processing images and videos. Previous methods, such as ANDECOMP/PARAFAC decomposition (CPD), Tucker decomposition (TKD), or tensor train decomposition (TTD), treat individual modes (or coordinates) equally. Their results do not contain a natural and hierarchical connection between a give...

Security presents itself as one of the biggest threats to the enabling and the deployment of the Internet of Things (IoT). Security challenges are evident in light of recent cybersecurity attacks that targeted major internet service providers and crippled a significant portion of the entire Internet by taking advantage of faulty and ill-protected e...

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more key...

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kin...

Unmanned Aerial Systems, hereafter referred to as UAS, are of great use in hazard events such as wildfire due to their ability to provide high-resolution video imagery over areas deemed too dangerous for manned aircraft and ground crews. This aerial perspective allows for identification of ground-based hazards such as spot fires and fire lines, and...

Aerial imagery has been increasingly adopted in mission-critical tasks, such as traffic surveillance, smart cities, and disaster assistance. However, identifying objects from aerial images faces the following challenges: 1) objects of interests are often too small and too dense relative to the images; 2) objects of interests are often in different...

The CHEESE project supplements and enhances traditional cybersecurity education with hands-on, practical experience in common cybersecurity flaws and solutions. CHEESE requires only a web browser, allowing users to develop cybersecurity skills without compromising their own computer or spending hours setting up a complex virtual machine (VM) or san...

Both the public sector and private sector have strong demand for qualified cybersecurity professionals. It is therefore imperative that higher education institutions can fill the gap by producing more skilled graduates that have deep understanding of cybersecurity. Cryptography is one of those fundamental subjects that is difficult to learn and err...

Water pollution has caused increased incidence of algal growth around the globe. Harmful algae blooms result in massive economic losses. In this paper, a multi-robot based task planner is designed to remove excessive algae from water bodies and to identify algae build-up so that prompt action can be taken against its accumulation. Computer vision i...

Regression problems that have closed-form solutions are well understood and can be easily implemented when the dataset is small enough to be all loaded into the RAM. Challenges arise when data is too big to be stored in RAM to compute the closed form solutions. Many techniques were proposed to overcome or alleviate the memory barrier problem but th...

A disconcerting ramification of water pollution caused by burgeoning populations, rapid industrialization and modernization of agriculture, has been the exponential increase in the incidence of algal growth across the globe. Harmful algal blooms (HABs) have devastated fisheries, contaminated drinking water and killed livestock, resulting in economi...

Internet of Things (IoT) devices present different security challenges that have not been addressed yet and there is no clear commitment from stakeholders to do so. Such problems have become evident and IoT devices are targets of malicious actors that employ them as instruments to fulfill their nefarious purposes. Recent attacks to major Internet s...

Over the past few decades, radio frequency identification (RFID) technology has been an important factor in securing products along the agri-food supply chain. However, there still exist security vulnerabilities when registering products to a specific RFID tag, particularly regarding the ease at which tags can be cloned. In this paper, a potential...

To enhance and improve cryptography instructions, this study investigated how representational fluency is related to the cognitive process through a set of eye-tracking studies and interview questions. The results showed that multiple representations were helpful for students to comprehend a concept because the different representations supported e...

This paper describes our initial effort in applying supervised machine learning approaches to analyze data collected at a FCA casting plant during the production of crossmember castings. The data contain results of X-ray inspection on castings and processing variables such as alloy compositions, cooling conditions of the shot tooling and die, and t...

Dimension reduction is aimed at reducing the dimension of a high dimensional vector-valued explanatory variables and simultaneously preserves its relationship with a univariate or low-dimensional real-valued response. As one of the oldest and most well-known dimension reduction approaches, principal component analysis (PCA) has been extensively use...

As crimes, along with nearly every aspect of life, continue to transit into cyberspace, network traffic becomes an increasingly important source of evidence for forensic investigators. Network forensics is most commonly used in analyzing network traffic, identifying suspicious patterns and tracing the source of attack. This paper takes a different...

The increasing use of web applications for tasks such as banking, social media, and travel reservations and the frequent news of hacker attacks has brought cybersecurity to the forefront of public discussion. It is vital to ensure that the new generation of programmers is aware of the importance of cybersecurity and the various solutions in existen...

Ridge regression is an important approach in linear regression when explanatory variables are highly correlated. Although expressions of estimators of ridge regression parameters have been successfully obtained via matrix operation after observed data are standardized, they cannot be used to big data since it is impossible to load the entire data s...

The Internet of Things (IoT) is intended for ubiquitous connectivity among different entities or "things". While its purpose is to provide effective and efficient solutions, security of the devices and network is a challenging issue. The number of devices connected along with the ad-hoc nature of the system further exacerbates the situation. Theref...

The Internet of Things (IoT) is intended for ubiquitous connectivity among different entities or "things". While its purpose is to provide effective and efficient solutions, security of the devices and network is a challenging issue. The number of devices connected along with the ad-hoc nature of the system further exacerbates the situation. Theref...

Near Field Communication (NFC) is a convenient short range contactless communication method that is receiving more and more attentions for its simplicity to support mobile payment. Influential industry players, such as Apple, Google and Samsung have integrated NFC technology in their mobile payment applications, i.e. Apple Pay, Android Pay and Sams...

As the world is becoming more and more connected, managing security of the network system is becoming more difficult. One of the ways to ensure security is by encrypting the data and in order to do so, the encryption key needs to be exchanged between the devices trying to communicate with each other. The key exchange that happens today use only a s...

NetFlowMatrix is a visual analytics system design that adopts small multiple charts to help analysts monitor NetFlow data of a computer network. This design provides an overview and drill-down interactions that allow analysts to see and analyse traffic data from a computer network of thousands of computers and millions of flow records. Various netw...

An experimental setup of 32 honeypots reported 17M login attempts originating from 112 different countries and over 6000 distinct source IP addresses. Due to decoupled control and data plane, Software Defined Networks (SDN) can handle these increasing number of attacks by blocking those network connections at the switch level. However, the challeng...

Over the past decade, the Advanced Persistent Threat (APT) has risen to forefront of cybersecurity threats. APTs are a major contributor to the billions of dollars lost by corporations around the world annually. The threat is significant enough that the Navy Cyber Power 2020 plan identified them as a “must mitigate” threat in order to ensure the se...

The IEEE Cybersecurity Initiative developed a user-friendly, cloud-based, interactive platform for hosting tools and demonstrations: Try-CybSI. The goal is to help practitioners and students gain practical familiarity with tools and widespread attacks' behavior.

A major requirement of cloud block storage services is guaranteed performance and high availability. However, offering guaranteed Service Level Agreements (SLAs) in cloud block storage services is often not straightforward. Cloud block storage performance may be affected by physical disk background operations, like garbage collection, storage clust...

This paper proposes a highly scalable framework that can be applied to detect network anomaly at per flow level by constructing a meta-model for a family of machine learning algorithms or statistical data models. The approach is scalable and attainable because raw data needs to be accessed only one time and it will be processed, computed and transf...

The Box-Cox transformation is an important technique in linear regression when assumptions of a regression model are seriously violated. The technique has been widely accepted and extensively applied since it was first proposed. Based on the maximum likelihood approach, previous methods and algorithms for the Box-Cox transformation are mostly devel...

This paper adopts a method to retrieve graphic data stored in the global memory of an NVIDIA GPU. Experimentation shows that a 24-bit TIFF formatted graphic can be retrieved from the GPU in a forensically sound manner. However, like other types of Random Access Memory, acquired data cannot be verified due to the volatile nature of the GPU memory. I...

Botnets represent a major and formidable threat in modern computing, and security researchers are engaged in constant and escalating battle with the writers of such malware to detect and mitigate it. Current advanced malware behaviors include encryption of communications between the botmaster and the bot machines as well as various strategies for r...

In this paper, we investigated the vulnerabilities surrounding software-defined networking (SDN). Specifically, we examined the vulnerabilities of OpenDayLight SDN controller. Among all the possible attack vectors, a man-in-the-middle attack using ARP poisoning was successfully launched to intercept the traffic between a client and the OpenDayLight...