Multiplex imaging is revolutionizing pathology by enabling the simultaneous visualization of multiple biomarkers within tissue samples, providing molecular-level insights that traditional hematoxylin and eosin (H&E) staining cannot provide. However, the complexity and cost of multiplex data acquisition have hindered its widespread adoption. Additionally, most existing large repositories of H&E images lack corresponding multiplex images, limiting opportunities for multi-modal analysis. To address these challenges, we leverage recent advances in latent diffusion models (LDMs), which excel at modeling complex data distributions by utilizing their powerful priors for fine-tuning to a target domain. In this paper, we introduce a novel framework for virtual multiplex staining that utilizes pretrained LDM parameters to generate multiplex images from H&E images using a conditional diffusion model. Our approach enables marker-by-marker generation by conditioning the diffusion model on each marker, while sharing the same architecture across all markers. To tackle the challenge of varying pixel value distributions across different marker stains and to improve inference speed, we fine-tune the model for single-step sampling, enhancing both color contrast fidelity and inference efficiency through pixel-level loss functions. We validate our framework on two publicly available datasets, notably demonstrating its effectiveness in generating up to 18 different marker types with improved accuracy, a substantial increase over the 2-3 marker types achieved in previous approaches. This validation highlights the potential of our framework, pioneering virtual multiplex staining. Finally, this paper bridges the gap between H&E and multiplex imaging, potentially enabling retrospective studies and large-scale analyses of existing H&E image repositories.

Lost and stolen phone reporting services are widely deployed to prevent unauthorized device use by blacklisting International Mobile Equipment Identities (IMEIs). However, through an extensive experimental study across three major U.S. carriers and diverse mobile devices, we discover that these services unexpectedly introduce severe and previously unexplored security risks. Specifically, we identify six new vulnerabilities spanning the device, carrier, and cross-carrier domains, which together enable attackers to arbitrarily block cellular devices from accessing carrier networks. Building on these findings, we design and validate two practical denial-of-service (DoS) attacks: Home Security System Freezing, which disables cellular-based home security gateways and blocks alarm delivery, and Zero-Day Flagship Phone Ambush, which preemptively blocks brand-new flagship phones from accessing mobile services at launch. Both attacks are experimentally validated on operational 5G/4G networks. Finally, we propose practical, backward-compatible countermeasures and implement a prototype to evaluate their effectiveness.

Blind and Visually Impaired (BVI) people find challenges in navigating unfamiliar environments, even using assistive tools such as white canes or smart devices. Increasingly affordable quadruped robots offer us opportunities to design autonomous guides that could improve how BVI people find ways around unfamiliar environments and maneuver therein. In this work, we designed RDog, a quadruped robot guiding system that supports BVI individuals’ navigation and obstacle avoidance in indoor and outdoor environments. RDog combines an advanced mapping and navigation system to guide users with force feedback and preemptive voice feedback. Using this robot as an evaluation apparatus, we conducted experiments to investigate the difference in BVI people’s ambulatory behaviors using a white cane, a smart cane, and RDog. Results illustrated the benefits of RDog-based ambulation, including faster and smoother navigation with fewer collisions and limitations, and reduced cognitive load. We discuss the implications of our work for multi-terrain assistive guidance systems.

Calcaneus fracture is the most common fracture in all types of Tarsal fracture. Early and accurate diagnosis is essential for prompt treatment. This study aims to develop an automatic detection and classification system for calcaneal fracture with deep learning techiques, in which the X-ray images of calcaneal fractures can be detected and classified clearly. In this study, we collected the X-ray image dataset of calcaneal, which was categorized as either fracture or non-fracture, and employed data augmentation techniques to expand the volume and variety of the dataset. In this work, a Deep Residual Neural Network (ResNet) model has been trained for binary fracture classification. To enhance the model interpret-ability and help non-deep learning experts understand how the model predicts. We've utilized the Grad-CAM method to generate the heatmaps. With the heatmaps, the range of calcaneal fracture can be highligted and realized more clearly and intuitively.

Tensor decomposition has emerged as an essential means for applications with multidimensional signals such as data compression and feature extraction. However, due to the enormous amount of signal processing and storage, it is challenging to design a low-latency tensor decomposition processor with high hardware efficiency. This paper presents a low-latency algorithm and VLSI architecture for a tensor decomposition processor. The designed circuit is implemented based on the FPGA platform. The estimation results demonstrate that the proposed architecture achieves a low-latency performance and high hardware efficiency.

Edge computing has been determined as a key feature for achieving low-latency performance in 5G networks. It enables application servers to be deployed next to base stations, thus offering services without experiencing Internet delays or congestion. Thanks to the O-RAN (Open Radio Access Network) architecture, the edge server can obtain RAN information at run time and employ it to enhance the quality of edge-based services. In this work, we develop a proactive adaptation solution, designated as IPA-DASH (Intelligent Proactive Adaptation for Dynamic Adaptive Streaming over HTTP), for DASH video streaming services. By utilizing the radio access information for each UE (User Equipment), IPA-DASH applies deep reinforcement learning to estimate the best video quality at present, while enabling video segment reselection along with an in-band, low-overhead segment cancellation method. This allows IPA-DASH to proactively adapt video streaming before its quality suffers, in contrast to conventional video adaptation solutions that reactively adapt video streaming based solely on application-layer performance. These solutions have no access to radio access conditions, so the adaptation is triggered after the video quality degrades. We implement and evaluate IPA-DASH on both a simulator and an emulated 5G edge platform. The results demonstrate that IPA-DASH outperforms other video adaptation solutions, achieving gains of 1.1% to 55.6% in terms of average QoE (Quality of Experience) and reducing rebuffering time by 35.0% to 97.3%.

A streaming-based Indoor Positioning System (IPS) is developed for beam-based cellular networks that apply directional beam patterns for communications and sensing. The proposed IPS is designed to provide a real-time positioning service by leveraging the computing framework and the streaming modules of Apache Spark streaming. Under the Spark Streaming framework, a beam and model-based location tracking method is designed and optimized for positioning precision and resource utilization. Experiments show that the average positioning error of the proposed user tracking method is about 0.4 meters, which achieves 56.2% improvements over static locating methods. More importantly, a static timing analysis is carried out to evaluate the throughput and bottlenecks of the proposed IPS system. Based on the analysis, our proposed architecture is capable and promising for low-latency IPS provisioning under the O-RAN framework.

This paper presents a novel method for object-level unknown obstacle detection in driving scenes that reduces false positives. The proposed method combines existing anomaly detectors, depth estimation, and object detection techniques to achieve object-level predictions. Our method can predict anomalies as bound-box instance detections. These bounding boxes can then be used to refine anomaly detection by suppressing false positives outside of the bounding boxes. The proposed method has several advantages, including object-level detections that are more practical than pixel-level detections, and the ability to find and refine region proposals for obstacle detection. The paper provides a detailed explanation of all components of the system and includes an ablation study on the usage of depth estimation, as well as execution time averages on different hardware. The proposed method is evaluated using different metrics and benchmarks, demonstrating the effectiveness and relevance of the existing proposed methods. Overall, our proposed method has the potential to significantly improve object-level anomaly detection making it suitable for real-world applications.

MOTIVATION: Stitching microscope images into a mosaic is an essential step in the analysis and visualization of large biological specimens, particularly human and animal tissues. Recent approaches to highly multiplexed imaging generate high-plex data from sequential rounds of lower-plex imaging. These multiplexed imaging methods promise to yield precise molecular single-cell data and information on cellular neighborhoods and tissue architecture. However, attaining mosaic images with single-cell accuracy requires robust image stitching and image registration capabilities that are not met by existing methods. RESULTS: We describe the development and testing of ASHLAR, a Python tool for coordinated stitching and registration of 103 or more individual multiplexed images to generate accurate whole-slide mosaics. ASHLAR reads image formats from most commercial microscopes and slide scanners, and we show that it performs better than existing open-source and commercial software. ASHLAR outputs standard OME-TIFF images that are ready for analysis by other open-source tools and recently developed image analysis pipelines. AVAILABILITY AND IMPLEMENTATION: ASHLAR is written in Python and is available under the MIT license at https://github.com/labsyspharm/ashlar. The newly published data underlying this article are available in Sage Synapse at https://dx.doi.org/10.7303/syn25826362; the availability of other previously published data re-analyzed in this article is described in Supplementary Table S4. An informational website with user guides and test data is available at https://labsyspharm.github.io/ashlar/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Recent state-of-the-art multiplex imaging techniques have expanded the depth of information that can be captured within a single tissue sample by allowing for panels with dozens of markers. Despite this increase in capacity, space on the panel is still limited due to technical artifacts, tissue loss, and long imaging acquisition time. As such, selecting which markers to include on a panel is important, since removing important markers will result in a loss of biologically relevant information, but identifying redundant markers will provide a room for other markers. To address this, we propose computational approaches to determine the amount of shared information between markers and select an optimally reduced panel that captures maximum amount of information with the fewest markers. Here we examine several panel selection approaches and evaluate them based on their ability to reconstruct the full panel images and information within breast cancer tissue microarray datasets using cyclic immunofluorescence as a proof of concept. We show that all methods perform adequately and can re-capture cell types using only 18 of 25 markers (72% of the original panel size). The correlation-based selection methods achieved the best single-cell marker mean intensity predictions with a Spearman correlation of 0.90 with the reduced panel. Using the proposed methods shown here, it is possible for researchers to design more efficient multiplex imaging panels that maximize the amount of information retained with the limited number of markers with respect to certain evaluation metrics and architecture biases.

Inspection of tissues using a light microscope is the primary method of diagnosing many diseases, notably cancer. Highly multiplexed tissue imaging builds on this foundation, enabling the collection of up to 60 channels of molecular information plus cell and tissue morphology using antibody staining. This provides unique insight into disease biology and promises to help with the design of patient-specific therapies. However, a substantial gap remains with respect to visualizing the resulting multivariate image data and effectively supporting pathology workflows in digital environments on screen. We, therefore, developed Scope2Screen, a scalable software system for focus+context exploration and annotation of whole-slide, high-plex, tissue images. Our approach scales to analyzing 100GB images of 109or more pixels per channel, containing millions of individual cells. A multidisciplinary team of visualization experts, microscopists, and pathologists identified key image exploration and annotation tasks involving finding, magnifying, quantifying, and organizing regions of interest (ROIs) in an intuitive and cohesive manner. Building on a scope-to-screen metaphor, we present interactive lensing techniques that operate at single-cell and tissue levels. Lenses are equipped with task-specific functionality and descriptive statistics, making it possible to analyze image features, cell types, and spatial arrangements (neighborhoods) across image channels and scales. A fast sliding-window search guides users to regions similar to those under the lens; these regions can be analyzed and considered either separately or as part of a larger image collection. A novel snapshot method enables linked lens configurations and image statistics to be saved, restored, and shared with these regions. We validate our designs with domain experts and apply Scope2Screen in two case studies involving lung and colorectal cancers to discover cancer-relevant image features.

We study the XAI (explainable AI) on the face recognition task, particularly the face verification. Face verification has become a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, and automatic personal log-on for mobile devices. With the increasing amount of data, deep convolutional neural networks can achieve very high accuracy for the face verification task. Beyond exceptional performances, deep face verification models need more interpretability so that we can trust the results they generate. In this article, we propose a novel similarity metric, called explainable cosine ( xCos ), that comes with a learnable module that can be plugged into most of the verification models to provide meaningful explanations. With the help of xCos , we can see which parts of the two input faces are similar, where the model pays its attention to, and how the local similarities are weighted to form the output xCos score. We demonstrate the effectiveness of our proposed method on LFW and various competitive benchmarks, not only resulting in providing novel and desirable model interpretability for face verification but also ensuring the accuracy as plugging into existing face recognition models.

Deaf and hard-of-hearing (DHH) individuals encounter difficulties when engaged in group conversations with hearing individuals, due to factors such as simultaneous utterances from multiple speakers and speakers whom may be potentially out of view. We interviewed and co-designed with eight DHH participants to address the following challenges: 1) associating utterances with speakers, 2) ordering utterances from different speakers, 3) displaying optimal content length, and 4) visualizing utterances from out-of-view speakers. We evaluated multiple designs for each of the four challenges through a user study with twelve DHH participants. Our study results showed that participants significantly preferred speechbubble visualizations over traditional captions. These design preferences guided our development of SpeechBubbles, a real-time speech recognition interface prototype on an augmented reality head-mounted display. From our evaluations, we further demonstrated that DHH participants preferred our prototype over traditional captions for group conversations.

Drones offer camera angles that are not possible with traditional cameras and are becoming increasingly popular for videography. However, flying a drone and controlling its camera simultaneously requires manipulating 5-6 degrees of freedom (DOF) that needs significant training. We present ARPilot, a direct-manipulation interface that lets users plan an aerial video by physically moving their mobile devices around a miniature 3D model of the scene, shown via Augmented Reality (AR). The mobile devices act as the viewfinder, making them intuitive to explore and frame the shots. We leveraged AR technology to explore three 6DOF video-shooting interfaces on mobile devices: AR keyframe, AR continuous, and AR hybrid, and compared against a traditional touch interface in a user study. The results show that AR hybrid is the most preferred by the participants and expends the least effort among all the techniques, while the users' feedback suggests that AR continuous empowers more creative shots. We discuss several distinct usage patterns and report insights for further design.

Nature is gorgeous for her imbalance. The innate bias from non-human to human results in a wonderful yet mysterious biological foundation towards the inspirational thinking for real application. The vision researchers evidenced that the left gaze bias in humans and non-humans. Nevertheless, the acousticians observed the right ear advantages in both non-humans and humans. Unlike the vision and acoustician researchers investigating the underlying mechanisms of human innate bias, we are more interested in mimicking these characteristics. In this paper, we propose two simple yet effective methods to generate the left eye gaze bias and the right ear advantage. We further discuss the potential applications, e.g., real life driving, from these inherent phenomena. We believe that this paper could bring an inspirational impact for future cognitive transportation, by implementing these human innate biases properly.

Face inpainting aims to restore the corrupted regions of face images due to extreme lighting variations, occlusion, or even disguise. This task becomes especially challenging, when the face images are taken in an unconstrained environment (i.e., with pose, illumination, and expression variations) and the type of corruption is not known in advance. In this paper, we propose a deep-learning based approach of occlusion-aware generative adversarial networks (GAN) for solving this problem. By utilizing GAN pre-trained on occlusion-free images, we are able to detect corrupted image regions automatically with the associated image pixels properly recovered. We produce promising performances on images from the benchmark dataset of LFW, and show that recognition of such face images would be benefited from our proposed approach.

Electric current and voltage are fundamental to learning, understanding, and debugging circuits. Although both can be measured using tools such as multimeters and oscilloscopes, electric current is much more difficult to measure because users have to unplug parts of a circuit and then insert the measuring tools in serial. Furthermore, users need to restore the circuits back to its original state after measurements have been taken. In practice, this cumbersome process poses a formidable barrier to knowing how current flows throughout a circuit. We present CurrentViz, a system that can sense and visualize the electric current flowing through a circuit, which helps users quickly understand otherwise invisible circuit behavior. It supports fully automatic, ubiquitous, and real-time collection of amperage information of breadboarded circuits. It also supports visualization of the amperage data on a circuit schematic to provide an intuitive view into the current state of a circuit.

The rise of Maker communities and open-source electronic prototyping platforms have made electronic circuit projects increasingly popular around the world. Although there are software tools that support the debugging and sharing of circuits, they require users to manually create the virtual circuits in software, which can be time-consuming and error-prone. We present CircuitSense, a system that automatically recognizes the wires and electronic components placed on breadboards. It uses a combination of passive sensing and active probing to detect and generate the corresponding circuit representation in software in real-time. CircuitSense bridges the gap between the physical and virtual representations of circuits. It enables users to interactively construct and experiment with physical circuits while gaining the benefits of using software tools. It also dramatically simplifies the sharing of circuit designs with online communities.

Augmented Reality (AR) provides real-time information by super-imposing virtual information onto users' view of the real world. Our work is the first to explore how peripheral vision, instead of central vision, can be used to read text on AR and smart glasses. We present PeriText+, a multiword reading interface using rapid serial visual presentation (RSVP). This enables users to observe the real world using central vision, while using peripheral vision to read text. We conducted a lab study to compare reading efficiency among 40 different conditions of text transformation. We also conducted a field study to evaluate the information transfer while using PeriText+ in a real-world walking scenario.

Personalizing a music emotion recognition model is needed because the perception of music emotion is highly subjective, but it is a time-consuming process. In this paper, we consider how to expedite the personalization process that begins with a general model trained offline using a general user base and progressively adapts the model to a music listener using the emotion annotations of the listener. Specifically, we focus on reducing the number of user annotations needed for the personalization. We investigate and evaluate four component tying methods: single group tying, quadrantwise tying, hierarchical tying, and random tying. These methods aim to exploit the available annotations by identifying related model parameters on-the-fly and updating them jointly. In the evaluation, we use the AMG1608 dataset, which contains the clip-level valence-arousal emotion ratings of 1608 30-s music clips annotated by 665 listeners. Also, we use the acoustic emotion Gaussians model as the general model that uses a mixture of Gaussian components to learn the mapping between the acoustic feature space and the emotion space. The results show that the model adaptation with component tying requires only 10-20 personal annotations to obtain the same level of prediction accuracy as the baseline model adaptation method that uses 50 personal annotations without component tying.

Cloud computing is revolutionizing the information technology field. However, clouds today have not yet addressed real-time applications. Current work has shown that real-time hypervisors are capable of allowing virtual machines to meet real-time requirements. Other work has looked at statically allocating resources to virtual guests, which allow those guests to meet deadlines. In this paper, we present DART-C (Demand-based Allocation for Real-Time Clouds), a dynamic real-time cloud framework that allows automated adaptation to these types of workloads. Many applications follow dynamic multi-modal execution patterns, with varying computational requirements over time. DART-C provides demand-based elasticity to support changing real-time requirements by enabling applications to report mode changes to a resource manager, which reallocates resources based on need. We also describe a prototype and demonstrate up to 62% in system resource utilization savings compared to a static allocation, when running a synthetic application set.

A novel stabilization problem for T-S polynomial fuzzy system with time-delay is investigated in this paper. Firstly, a polynomial fuzzy controller for T-S polynomial fuzzy system with time-delay is proposed. In addition, based on polynomial Lyapunov-Krasovskii function and the developed polynomial slack variable matrices, a novel stabilization condition for T-S polynomial fuzzy system with time-delay is presented in terms of sum-of-square (SOS) form. Lastly, nonlinear system with time-delay and a well-known T-S fuzzy system with time-delay are illustrated to demonstrate the feasibility and effectiveness of the proposed results.

In this paper, the stabilization problems for a class of Takagi-Sugeno (T-S) fuzzy neutral systems are explored. Utilizing Pólya's theorem and some homogeneous polynomials techniques, the delay-dependent stabilization condition for T-S fuzzy neutral systems are proposed in terms of a linear matrix inequality (LMI) to guarantee the asymptotic stabilization of T-S fuzzy neutral systems. Lastly, an example is illustrated to demonstrate the effectiveness and applicability of the proposed method.

Automated recognition of musical emotion from audio signals has received considerable attention recently. To construct an accurate model for music emotion prediction, the emotion-annotated music corpus has to be of high quality. It is desirable to have a large number of songs annotated by numerous subjects to characterize the general emotional response to a song. Due to the need for personalization of the music emotion prediction model to address the subjective nature of emotion perception, it is also important to have a large number of annotations per subject for training and evaluating a personalization method. In this paper, we discuss the deficiency of existing datasets and present a new one. The new dataset, which is publically available to the research community, is composed of 1608 30-second music clips annotated by 665 subjects. Furthermore, 46 subjects annotated more than 150 songs, making this dataset the largest of its kind to date.

Personalization techniques can be applied to address the subjectivity issue of music emotion recognition, which is important for music information retrieval. However, achieving satisfactory accuracy in personalized music emotion recognition for a user is difficult because it requires an impractically huge amount of annotations from the user. In this paper, we adopt a probabilistic framework for valence-arousal music emotion modeling and propose an adaptation method based on linear regression to personalize a background model in an online learning fashion. We also incorporate a component-tying strategy to enhance the model flexibility. Comprehensive experiments are conducted to test the performance of the proposed method on three datasets, including a new one created specifically in this work for personalized music emotion recognition. Our results demonstrate the effectiveness of the proposed method.

Most existing systems recommend songs to the user based on the popularity of songs and singers. However, the system proposed in this paper is driven by an emerging and somewhat different need in the music industry-promoting new talents. The system recommends songs based on the novelty of singers (or artists) and their similarity to the user's favorite artists. Novel artists whose popularity is on the rise have a higher priority to be recommended. Specifically, given a user's favorite artists, the system first determines the candidate artists based on their similarity with the favorite artists and then selects those who have a higher novelty score than the favorite artists. Then, the system outputs a playlist composed of the most popular songs of the selected artists. The proposed system can be integrated into most existing systems. Its performance is evaluated using the Spotify Radio Recommender as a reference and a pool of 100 subjects recruited on campus. Experimental results show that our system achieves a high novelty score and a competitive user-preference score.