Revolving Scanning on Tagged Objects: 3D Structure Detection of Logistics Packages via RFID Systems

Nowadays, detecting and evaluating the internal structure of packages becomes a crucial task for logistics systems to guarantee the reliability and security. However, prior solutions such as X-ray diffraction and WiFi-based detection are not suitable for this purpose. X-ray-based methods usually require manual analysis or image processing algorithms with high complexity, while WiFi-based solutions may fail to detect complex structures due to the significant error of the RF-signal features. In this paper, we propose RF-Detector, a low-cost RFID solution for performing 3D structure detection of items contained in the packages, including the item orientations and relative locations. We thoroughly investigate a brand-new sensing model for RFID-based 3D structure detection, i.e., revolving scanning. We propose not only the fundamental revolving model but also a novel calibration method towards the undesired deployment. We have implemented a prototype system to evaluate the performance of RF-Detector. Extensive evaluations in real settings show the effectiveness of RF-Detector, achieving very high accuracy of the internal 3D structure detection.

Recognizing early cardiac sarcoidosis (CS) imaging phenotypes can help identify opportunities for effective treatment before irreversible myocardial pathology occurs. We aimed to characterize regional CS myocardial remodeling features correlating with future adverse cardiac events by coupling automated image processing and data analysis on cardiac magnetic resonance (CMR) imaging datasets. A deep convolutional neural network (DCNN) was used to process a CMR database of a 10-year cohort of 117 consecutive biopsy-proven sarcoidosis patients. The maximum relevance-minimum redundancy method was used to select the best subset of all the features-24 (from manual processing) and 232 (from automated processing) left ventricular (LV) structural/functional features. Three machine learning (ML) algorithms, logistic regression (LogR), support vector machine (SVM) and multi-layer neural networks (MLP), were used to build classifiers to categorize endpoints. Over a median follow-up of 41.8 (inter-quartile range 20.4-60.5) months, 35 sarcoidosis patients experienced a total of 43 cardiac events. After manual processing, LV ejection fraction (LVEF), late gadolinium enhancement, abnormal segmental wall motion, LV mass (LVM), LVMI index (LVMI), septal wall thickness, lateral wall thickness, relative wall thickness, and wall thickness of 9 (out of 17) individual LV segments were significantly different between patients with and without endpoints. After automated processing, LVEF, end-diastolic volume, end-systolic volume, LV mass and wall thickness of 92 (out of 216) individual LV segments were significantly different between patients with and without endpoints. To achieve the best predictive performance, ML algorithms selected lateral wall thickness, abnormal segmental wall motion, septal wall thickness, and increased wall thickness of 3 individual segments after manual image processing, and selected end-diastolic volume and 7 individual segments after automated image processing. LogR, SVM and MLP based on automated image processing consistently showed better predictive accuracies than those based on manual image processing. Automated image processing with a DCNN improves data resolution and regional CS myocardial remodeling pattern recognition, suggesting that a framework coupling automated image processing with data analysis can help clinical risk stratification.

Designing affective Human Computer-Interfaces such as Embodied Conversational Agents requires modeling the relations between spontaneous emotions and behaviors in several modalities. There have been a lot of psychological researches on emotion and nonverbal communication. Yet, these studies were based mostly on acted basic emotions. This paper explores how manual annotation and image processing might cooperate towards the representation of spontaneous emotional behavior in low resolution videos from TV. We describe a corpus of TV interviews and the manual annotations that have been defined. We explain the image processing algorithms that have been designed for the automatic estimation of movement quantity. Finally, we explore several ways to compare the manual annotations and the cues extracted by image processing.

There have been a lot of psychological researches on emotion and nonverbal communication. Yet, these studies were based mostly on acted basic emotions. This paper explores how manual annotation and image processing can cooperate towards the representation of spontaneous emotional behavior in low-resolution videos from TV. We describe a corpus of TV interviews and the manual annotations that have been defined. We explain the image-processing algorithms that have been designed for the automatic estimation of movement quantity. Finally, we explore how image processing can be used for the validation of manual annotations.

We report a new method for automated identification and measurement of primary particles within soot aggregates as well as the sizes of the aggregates and discuss its application to high-resolution transmission electron microscope (TEM) images of the aggregates. The image processing algorithm is based on an optimized Hough transform, applied to the external border of the aggregate. This achieves a significant data reduction by decomposing the particle border into fragments, which are assumed to be spheres in the present application, consistent with the known morphology of soot aggregates. Unlike traditional techniques, which are ultimately reliant on manual (human) measurement of a small sample of primary particles from a subset of aggregates, this method gives a direct measurement of the sizes of the aggregates and the size distributions of the primary particles of which they are composed. The current version of the algorithm allows processing of high-resolution TEM images by a conventional laptop computer at a rate of 1-2 ms per aggregate. The results were validated by comparison with manual image processing, and excellent agreement was found.

Most of the previous researchers used manual image processing approach through a public domain tool (ImageJ) to interpret soil surface moisture content. However, the manual processing could not be possible, when the number of images is significantly large. In addition, results could not be reproduced with conventional manual image processing. This technical note introduces a novel technique to automate the quantification process of soil surface moisture content. A stepwise strategy was demonstrated to remove user dependency for soil colour analysis using an autonomous Python script. The images of the compacted soil were captured using a commercially available camera model. The image analysis was conducted using conventional manual image processing approach and newly developed technique. The difference between the mean gray values obtained from the above mentioned two approaches was very low (< 3%). Hence, the newly developed technique is cost-effective and feasible for programming with drones to monitor soil surface moisture content in large areas.

Radio frequency identification (RFID) technology has already been explored for efficient self-localization of indoor mobile robots. A mobile robot equipped with RFID readers detects passive RFID tags installed on the floor in order to locate itself. The Monte-Carlo localization (MCL) method enables the localization of a mobile robot equipped with an RFID system with reasonable accuracy, sufficient robustness and low computational cost. The arrangements of RFID readers and tags and the size of antennas are important design parameters for realizing accurate and robust self-localization using a low-cost RFID system. The design of a likelihood model of RFID tag detection is also crucial for the accurate self-localization. This paper presents a novel design and arrangement of RFID readers and tags for indoor mobile robot self-localization. First, by considering small-sized and large-sized antennas of an RFID reader, we show how the design of the likelihood model affects the accuracy of self-localization. We also design a novel likelihood model by taking into consideration the characteristics of the communication range of an RFID system with a large antenna. Second, we propose a novel arrangement of RFID tags with eight RFID readers, which results in the RFID system configuration requiring much fewer readers and tags while retaining reasonable accuracy of self-localization. We verify the performances of MCL-based self-localization realized using the high-frequency (HF)-band RFID system with eight RFID readers and a lower density of RFID tags installed on the floor based on MCL in simulated and real environments. The results of simulations and real environment experiments demonstrate that our proposed low-cost HF-band RFID system realizes accurate and robust self-localization of an indoor mobile robot.

Simple SummaryFlow cytometric immunophenotyping is critical in detecting minimal residual disease (MRD) in patients with chronic lymphocytic leukemia (CLL). However, flow cytometric analysis is complicated and time-consuming. Herein, we evaluated the performance of a deep neural network (DNN) in detecting CLL MRD and whether it could improve the diagnostic workflow in a clinical laboratory setting. Our findings demonstrated that a hybrid DNN approach had high accuracy in detecting CLL MRD; it standardized the gating strategy and dramatically reduced gating time, and it could be fully integrated into the existing clinical laboratory.Flow cytometric (FC) immunophenotyping is critical but time-consuming in diagnosing minimal residual disease (MRD). We evaluated whether human-in-the-loop artificial intelligence (AI) could improve the efficiency of clinical laboratories in detecting MRD in chronic lymphocytic leukemia (CLL). We developed deep neural networks (DNN) that were trained on a 10-color CLL MRD panel from treated CLL patients, including DNN trained on the full cohort of 202 patients (F-DNN) and DNN trained on 138 patients with low-event cases (MRD < 1000 events) (L-DNN). A hybrid DNN approach was utilized, with F-DNN and L-DNN applied sequentially to cases. “Ground truth” classification of CLL MRD was confirmed by expert analysis. The hybrid DNN approach demonstrated an overall accuracy of 97.1% (95% CI: 84.7–99.9%) in an independent cohort of 34 unknown samples. When CLL cells were reported as a percentage of total white blood cells, there was excellent correlation between the DNN and expert analysis [r > 0.999; Passing–Bablok slope = 0.997 (95% CI: 0.988–0.999) and intercept = 0.001 (95% CI: 0.000–0.001)]. Gating time was dramatically reduced to 12 s/case by DNN from 15 min/case by the manual process. The proposed DNN demonstrated high accuracy in CLL MRD detection and significantly improved workflow efficiency. Additional clinical validation is needed before it can be fully integrated into the existing clinical laboratory practice.

The vision sensor which is based on the optical triangulation theory with the laser as an auxiliary light source can detect not only the seam position but the shape of seam. In this study, a vision sensor using the scanning laser beam was investigated. To design the vision sensor which considers the reflectivity of the sensing object and satisfies the desired resolution and measuring range, the equation of the focused laser beam which has a Gaussian irradiance profile was firstly formulated, Secondly, the image formaing sequence, and thirdly the relation between the displacement in the measuring surface and the displacement in the camera plane was formulated. Therefore, the focused beam diameter in the measuring range could be determined and the influence of the relative location between the laser and camera plane could be estimated. The measuring range and the resolution of the vision sensor which was based on the Scheimpflug's condition could also be calculated. From the results mentioned above a vision sensor was developed, and an adequate calibration technique was proposed. The image processing algorithm which and recognize the center of joint and its shape informaitons was investigated. Using the developed vision sensor and image processing algorithm, the shape informations was investigated. Using the developed vision sensor and image processing algorithm, the shape informations of the vee-, butt- and lap joint were extracted.

Although Radio Frequency Identification (RFID) is poised to displace barcodes, security vulnerabilities pose serious challenges for global adoption of the RFID technology. Specifically, RFID tags are prone to basic cloning and counterfeiting security attacks. A successful cloning of the RFID tags in many commercial applications can lead to many serious problems such as financial losses, brand damage, safety and health of the public. With many industries such as pharmaceutical and businesses deploying RFID technology with a variety of products, it is important to tackle RFID tag cloning problem and improve the resistance of the RFID systems. To this end, we propose an approach for detecting cloned RFID tags in RFID systems with high detection accuracy and minimal overhead thus overcoming practical challenges in existing approaches. The proposed approach is based on consistency of dual hash collisions and modified count-min sketch vector. We evaluated the proposed approach through extensive experiments and compared it with existing baseline approaches in terms of execution time and detection accuracy under varying RFID tag cloning ratio. The results of the experiments show that the proposed approach outperforms the baseline approaches in cloned RFID tag detection accuracy.

The quantification of soil surface cracks is important, as it is useful in analyzing water infiltration and overall water balance in any green infrastructure, such as slopes, agricultural fields, green roofs, etc. In previously reported studies, the approaches for quantifying cracks mainly used manual processing of images through the public domain image analysis tool ImageJ. Such software is not customized for quantifying cracks in an unsaturated soil surface, as this results in relatively higher noise (i.e., lower resolution) in the processed image. Furthermore, manual processing makes processing of images in large quantities (usually captured through unmanned aerial vehicle (UAV) surveying) cumbersome. This technical note introduces an autonomous novel image analysis method for characterizing surface crack patterns that develop in unsaturated soils. A simple experimental setup was developed using a 1-D column containing red soil. The soil was compacted by hand to the desired state of compaction and placed in an environment-controlled chamber where it was allowed to dry. A series of images of the soil sample was captured using a commercially available camera model (Canon EOS 700D) to have photographic representation of the cracking process. A step-by-step strategy using a script coded in Python was developed to analyze the images captured during the laboratory tests. It outlines how image analysis can be automated to remove observer-dependent subjectivity (involved in manual processing of images) and introduces reproducibility of results. In addition, it effectively quantifies cracks in unsaturated soils with a much lower processing time and higher accuracy (less noise).

Understanding the structures of noncoding RNAs (ncRNAs) is important for the development of RNA-based therapeutics. There are inherent challenges in employing current experimental techniques to determine the tertiary (3D) structures of RNAs with high complexity and flexibility in folding, which makes computational methods indispensable. In this study, we compared the utilities of three advanced computational tools, namely RNAComposer, Rosetta FARFAR2, and the latest AlphaFold 3, to predict the 3D structures of various forms of RNAs, including the small interfering RNA drug, nedosiran, and the novel bioengineered RNA (BioRNA) molecule showing therapeutic potential. Our results showed that, while RNAComposer offered a malachite green aptamer 3D structure closer to its crystal structure, the performances of RNAComposer and Rosetta FARFAR2 largely depend upon the secondary structures inputted, and Rosetta FARFAR2 predictions might not even recapitulate the typical, inverted "L" shape tRNA 3D structure. Overall, AlphaFold 3, integrating molecular dynamics principles into its deep learning framework, directly predicted RNA 3D structures from RNA primary sequence inputs, even accepting several common post-transcriptional modifications, which closely aligned with the experimentally determined structures. However, there were significant discrepancies among three computational tools in predicting the distal loop of human pre-microRNA and larger BioRNA (tRNA fused pre-miRNA) molecules whose 3D structures have not been characterized experimentally. While computational predictions show considerable promise, their notable strengths and limitations emphasize the needs for experimental validation of predictions besides characterization of more RNA 3D structures.

The width of the emission spectrum of a common fluorophore allows only for a limited number of spectral distinct fluorescent markers in the visible spectrum, which is also the regime where CCD-cameras are used in microscopy. For imaging of cells or tissues, it is required to obtain an image from which the morphology of the whole cell can be extracted. This is usually achieved by differential interference contrast (DIC) microscopy. These images have a pseudo-3D appearance, easily interpreted by the human brain. In the age of high throughput and high content screening, manual image processing is not an option. Conventional algorithms for image processing often use threshold-based criteria to identify objects of interest. These algorithms fail for DIC images as they have a range from dim to bright with an intermediate intensity equal to the background, so as to produce no clear object boundary. In this article we compare different reconstruction methods for up to 100 MB-large DIC images and implement a new iterative reconstruction method based on the Hilbert Transform that enables identification of cell boundaries with standard threshold algorithms.

Habitat-Net: Segmentation of habitat images using deep learning

An image-processing algorithm for morphological characterisation of soot agglomerates from TEM micrographs: Development and functional description