Department of Electrical and Computer Engineering Works
Permanent URI for this collection
Browse
Recent Submissions
Item Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation(IEEE, 2021) Jing, Taotao; Ding, Zhengming; Electrical and Computer Engineering, School of Engineering and TechnologyUnsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features through deep adversarial networks. However, most of them seek to match the different domain feature distributions, without considering the task-specific decision boundaries across various classes. In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD 2 CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment. Moreover, we naturally design two different structure classifiers to identify the unlabeled target samples over the supervision of the labeled source domain data. Such dual distinct classifiers with various architectures can capture diverse knowledge of the target data structure from different perspectives. Extensive experimental results on several cross-domain visual benchmarks prove the model's effectiveness by comparing it with other state-of-the-art UDA.Item RCNN-SliceNet: A Slice and Cluster Approach for Nuclei Centroid Detection in Three-Dimensional Fluorescence Microscopy Images(IEEE, 2021) Wu, Liming; Han, Shuo; Chen, Alain; Salama, Paul; Dunn, Kenneth W.; Delp, Edward J.; Electrical and Computer Engineering, School of Engineering and TechnologyRobust and accurate nuclei centroid detection is important for the understanding of biological structures in fluorescence microscopy images. Existing automated nuclei localization methods face three main challenges: (1) Most of object detection methods work only on 2D images and are difficult to extend to 3D volumes; (2) Segmentation-based models can be used on 3D volumes but it is computational expensive for large microscopy volumes and they have difficulty distinguishing different instances of objects; (3) Hand annotated ground truth is limited for 3D microscopy volumes. To address these issues, we present a scalable approach for nuclei centroid detection of 3D microscopy volumes. We describe the RCNN-SliceNet to detect 2D nuclei centroids for each slice of the volume from different directions and 3D agglomerative hierarchical clustering (AHC) is used to estimate the 3D centroids of nuclei in a volume. The model was trained with the synthetic microscopy data generated using Spatially Constrained Cycle-Consistent Adversarial Networks (SpCycle-GAN) and tested on different types of real 3D microscopy data. Extensive experimental results demonstrate that our proposed method can accurately count and detect the nuclei centroids in a 3D microscopy volume.Item SymptomGraph: Identifying Symptom Clusters from Narrative Clinical Notes using Graph Clustering(ACM, 2023) Tahabi, Fattah Muhammad; Storey, Susan; Luo, Xiao; Electrical and Computer Engineering, School of Engineering and TechnologyPatients with cancer or other chronic diseases often experience different symptoms before or after treatments. The symptoms could be physical, gastrointestinal, psychological, or cognitive (memory loss), or other types. Previous research focuses on understanding the individual symptoms or symptom correlations by collecting data through symptom surveys and using traditional statistical methods to analyze the symptoms, such as principal component analysis or factor analysis. This research proposes a computational system, SymptomGraph, to identify the symptom clusters in the narrative text of written clinical notes in electronic health records (EHR). SymptomGraph is developed to use a set of natural language processing (NLP) and artificial intelligence (AI) methods to first extract the clinician-documented symptoms from clinical notes. Then, a semantic symptom expression clustering method is used to discover a set of typical symptoms. A symptom graph is built based on the co-occurrences of the symptoms. Finally, a graph clustering algorithm is developed to discover the symptom clusters. Although SymptomGraph is applied to the narrative clinical notes, it can be adapted to analyze symptom survey data. We applied Symptom-Graph on a colorectal cancer patient with and without diabetes (Type 2) data set to detect the patient symptom clusters one year after the chemotherapy. Our results show that SymptomGraph can identify the typical symptom clusters of colorectal cancer patients’ post-chemotherapy. The results also show that colorectal cancer patients with diabetes often show more symptoms of peripheral neuropathy, younger patients have mental dysfunctions of alcohol or tobacco abuse, and patients at later cancer stages show more memory loss symptoms. Our system can be generalized to extract and analyze symptom clusters of other chronic diseases or acute diseases like COVID-19.Item Peek into the Future Camera-based Occupant Sensing in Configurable Cabins for Autonomous Vehicles(IEEE Xplore, 2021-09-19) Prabu, Avinash; Tian, Renran; Li, Lingxi; Le, Jialiang; Sundararajan, Srinivasan; Barbat, Saeed; Electrical and Computer Engineering, School of Engineering and TechnologyThe development of fully autonomous vehicles (AVs) can potentially eliminate drivers and introduce unprecedented seating design. However, highly flexible seat configurations may lead to occupants' unconventional poses and actions. Understanding occupant behaviors and prioritize safety features become eye-catching topics in the AV research frontier. Visual sensors have the advantages of cost-efficiency and high-fidelity imaging and become more widely applied for in-car sensing purposes. Occlusion is one big concern for this type of system in crowded car cabins. It is important but largely unknown about how a visual-sensing framework will look like to support 2-D and 3-D human pose tracking towards highly configurable seats. As one of the first studies to touch this topic, we peek into the future camera-based sensing framework via a simulation experiment. Constructed representative car-cabin, seat layouts, and occupant sizes, camera coverage from different angles and positions is simulated and calculated. The comprehensive coverage data are synthesized through an optimization process to determine the camera layout and overall occupant coverage. The results show the needs and design of a different number of cameras to fully or partially cover all the occupants with changeable configurations of up to six seats.Item GNRFET-Based DC-DC Converters for Low Power Data Management in ULSI System, a Feasibility Study(IEEE, 2021) Mekhael, George; Morgan, Nathaniel; Patnala, Mounica; Ytterdal, Trond; Rizkalla, Maher; Electrical and Computer Engineering, School of Engineering and TechnologyLow power data management is an approach that distribute the supply power on the various modules in the chip, following certain algorithms such as dynamic voltage sharing (DVS), single input multiple data (SIMD) among others with a coil-less circuit design. The key factors for reducing the power and enhancing the efficiency is attributed to the lower feeding power supply, high device mobility for low power consumption, the device size, and the architecture used in the design. Graphene Nano Ribbon Field Effect Transistors (GNRFET) based Buck and Boost converters were designed for single input/multiple outputs conversion. The design features very high efficiency that exceeds 90% at very high frequencies. The input was 0.7V with outputs of 0.35V and 1.4V for buck and boost converters respectively. The design gains from the high mobility feature of the nano scale GNRFET devices, and the low supply power applied to the various modules in the chip. A 10nm scale channel device with 4 ribbons were considered, and the switch capacitor (SC) approach was utilized. The study of the transient analysis, the static power, dynamic power, and ripple voltages at different design constraints were investigated versus the conversion parameters including the frequency, load, and duty cycles. The efficiency at a high load was estimated to be near 97%, while at low load and lower switching frequencies, the efficiency was estimated to be near 85%.Item Social relation and physical lane aggregator: Integrating social and physical features for multimodal motion prediction(Emerald Publishing, 2022-10-11) Chen, Qiyuan; Wei, Zebing; Wang, Xiao; Li, Lingxi; Lv, Yisheng; Electrical and Computer Engineering, School of Engineering and TechnologyPurpose The purpose of this paper aims to model interaction relationship of traffic agents for motion prediction, which is critical for autonomous driving. It is obvious that traffic agents’ trajectories are influenced by physical lane rules and agents’ social interactions. Design/methodology/approach In this paper, the authors propose the social relation and physical lane aggregator for multimodal motion prediction, where the social relations of agents are mainly captured with graph convolutional networks and self-attention mechanism and then fused with the physical lane via the self-attention mechanism. Findings The proposed methods are evaluated on the Waymo Open Motion Dataset, and the results show the effectiveness of the proposed two feature aggregation modules for trajectory prediction. Originality/value This paper proposes a new design method to extract traffic interactions, and the attention mechanism is used in each part of the model to extract and fuse different relational features, which is different from other methods and improves the accuracy of the LSTM-based trajectory prediction method.Item Flux estimation analysis systematically characterizes the metabolic shifts of the central metabolism pathway in human cancer(Frontiers Media, 2023-06-12) Yang, Grace; Huang, Shaoyang; Hu, Kevin; Lu, Alex; Yang, Jonathan; Meroueh, Noah; Dang, Pengtao; Wang, Yijie; Zhu, Haiqi; Cao, Sha; Zhang, Chi; Electrical and Computer Engineering, School of Engineering and TechnologyIntroduction: Glucose and glutamine are major carbon and energy sources that promote the rapid proliferation of cancer cells. Metabolic shifts observed on cell lines or mouse models may not reflect the general metabolic shifts in real human cancer tissue. Method: In this study, we conducted a computational characterization of the flux distribution and variations of the central energy metabolism and key branches in a pan-cancer analysis, including the glycolytic pathway, production of lactate, tricarboxylic acid (TCA) cycle, nucleic acid synthesis, glutaminolysis, glutamate, glutamine, and glutathione metabolism, and amino acid synthesis, in 11 cancer subtypes and nine matched adjacent normal tissue types using TCGA transcriptomics data. Result: Our analysis confirms the increased influx in glucose uptake and glycolysis and decreased upper part of the TCA cycle, i.e., the Warburg effect, in almost all the analyzed cancer. However, increased lactate production and the second half of the TCA cycle were only seen in certain cancer types. More interestingly, we failed to detect significantly altered glutaminolysis in cancer tissues compared to their adjacent normal tissues. A systems biology model of metabolic shifts through cancer and tissue types is further developed and analyzed. We observed that (1) normal tissues have distinct metabolic phenotypes; (2) cancer types have drastically different metabolic shifts compared to their adjacent normal controls; and (3) the different shifts in tissue-specific metabolic phenotypes result in a converged metabolic phenotype through cancer types and cancer progression. Discussion: This study strongly suggests the possibility of having a unified framework for studies of cancer-inducing stressors, adaptive metabolic reprogramming, and cancerous behaviors.Item Real-Time Embedded Implementation of Improved Object Detector for Resource-Constrained Devices(MDPI, 2022-04-13) Ravi, Niranjan; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and TechnologyArtificial intelligence (A.I.) has revolutionised a wide range of human activities, including the accelerated development of autonomous vehicles. Self-navigating delivery robots are recent trends in A.I. applications such as multitarget object detection, image classification, and segmentation to tackle sociotechnical challenges, including the development of autonomous driving vehicles, surveillance systems, intelligent transportation, and smart traffic monitoring systems. In recent years, object detection and its deployment on embedded edge devices have seen a rise in interest compared to other perception tasks. Embedded edge devices have limited computing power, which impedes the deployment of efficient detection algorithms in resource-constrained environments. To improve on-board computational latency, edge devices often sacrifice performance, creating the need for highly efficient A.I. models. This research examines existing loss metrics and their weaknesses, and proposes an improved loss metric that can address the bounding box regression problem. Enhanced metrics were implemented in an ultraefficient YOLOv5 network and tested on the targeted datasets. The latest version of the PyTorch framework was incorporated in model development. The model was further deployed using the ROS 2 framework running on NVIDIA Jetson Xavier NX, an embedded development platform, to conduct the experiment in real time.Item Road Condition Detection and Classification from Existing CCTV Feed(Purdue e-Pubs, 2022) Chien, Stanley; Chen, Yaobin; Christopher, Lauren; Qiu, Mei; Ding, Zhengming; Electrical and Computer Engineering, School of Engineering and TechnologyThe Indiana Department of Transportation (INDOT) has approximately 500 digital cameras along highways in populated areas of Indiana. These cameras are used to monitor traffic conditions around the clock, all year round. Currently, the videos from these cameras are observed one-by-one by human operators looking for traffic conditions and incidents. The main objective of this research was to develop an automatic, real-time system to monitor traffic conditions and detect incidents automatically. The Transportation and Autonomous Systems Institute (TASI) of the Purdue School of Engineering and Technology at Indiana University-Purdue University Indianapolis (IUPUI) and the Traffic Management Center of INDOT developed a system that monitors the traffic conditions based on the INDOT CCTV video feeds. The proposed system performs traffic flow estimation, incident detection, and classification of vehicles involved in an incident. The research team designed the system, including the hardware and software components added to the existing INDOT CCTV system; the relationship between the added system and the currently existing INDOT system; the database structure for traffic data extracted from the videos; and a user-friendly, web-based server for showing the incident locations automatically. The specific work in this project includes vehicle-detection, road boundary detection, lane detection, vehicle count over time, flow-rate detection, traffic condition detection, database development, web-based graphical user interface (GUI), and a hardware specification study. The preliminary prototype of some system components has been implemented in the Development of Automated Incident Detection System Using Existing ATMS CCT (SPR-4305).Item Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction(MDPI, 2023-06-19) Zhang, Qingxue; Zhou, Dian; Electrical and Computer Engineering, School of Engineering and TechnologyBackground: Internet-of-things technologies are reshaping healthcare applications. We take a special interest in long-term, out-of-clinic, electrocardiogram (ECG)-based heart health management and propose a machine learning framework to extract crucial patterns from noisy mobile ECG signals. Methods: A three-stage hybrid machine learning framework is proposed for estimating heart-disease-related ECG QRS duration. First, raw heartbeats are recognized from the mobile ECG using a support vector machine (SVM). Then, the QRS boundaries are located using a novel pattern recognition approach, multiview dynamic time warping (MV-DTW). To enhance robustness with motion artifacts in the signal, the MV-DTW path distance is also used to quantize heartbeat-specific distortion conditions. Finally, a regression model is trained to transform the mobile ECG QRS duration into the commonly used standard chest ECG QRS durations. Results: With the proposed framework, the performance of ECG QRS duration estimation is very encouraging, and the correlation coefficient, mean error/standard deviation, mean absolute error, and root mean absolute error are 91.2%, 0.4 ± 2.6, 1.7, and 2.6 ms, respectively, compared with the traditional chest ECG-based measurements. Conclusions: Promising experimental results are demonstrated to indicate the effectiveness of the framework. This study will greatly advance machine-learning-enabled ECG data mining towards smart medical decision support.