DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment.

Recent advancements in deep learning techniques have accelerated the growth of robotic vision systems. One way this technology can be applied is to use a mobile robot to automatically generate a 3D map and identify objects within it. This paper addresses the important challenge of labeling objects and generating 3D maps in a dynamic environment. It explores a solution to this problem by combining Deep Object Pose Estimation (DOPE) with Real-Time Appearance-Based Mapping (RTAB-Map) through means of loose-coupled parallel fusion. DOPE's abilities are enhanced by leveraging its belief map system to filter uncertain key points, which increases precision to ensure that only the best object labels end up on the map. Additionally, DOPE's pipeline is modified to enable shape-based object recognition using depth maps, allowing it to identify objects in complete darkness. Three experiments are performed to find the ideal training dataset, quantify the increased precision, and evaluate the overall performance of the system. The results show that the proposed solution outperforms existing methods in most intended scenarios, such as in unilluminated scenes. The proposed key point filtering technique has demonstrated an improvement in the average inference speed, achieving a speedup of 2.6× and improving the average distance to the ground truth compared to the original DOPE algorithm.

Synthesizing Rolling Bearing Fault Samples in New Conditions: A Framework Based on a Modified CGAN.

Bearings are vital components of rotating machines that are prone to unexpected faults. Therefore, bearing fault diagnosis and condition monitoring are essential for reducing operational costs and downtime in numerous industries. In various production conditions, bearings can be operated under a range of loads and speeds, which causes different vibration patterns associated with each fault type. Normal data are ample as systems usually work in desired conditions. On the other hand, fault data are rare, and in many conditions, there are no data recorded for the fault classes. Accessing fault data is crucial for developing data-driven fault diagnosis tools that can improve both the performance and safety of operations. To this end, a novel algorithm based on conditional generative adversarial networks (CGANs) was introduced. Trained on the normal and fault data on actual fault conditions, this algorithm generates fault data from normal data of target conditions. The proposed method was validated on a real-world bearing dataset, and fault data were generated for different conditions. Several state-of-the-art classifiers and visualization models were implemented to evaluate the quality of the synthesized data. The results demonstrate the efficacy of the proposed algorithm.

A Camera Intrinsic Matrix-Free Calibration Method for Laser Triangulation Sensor.

Laser triangulation sensors (LTS) are widely used to acquire depth information in industrial applications. However, the parameters of the components, e.g., the camera, of the off-the-shelf LTS are typically unknown. This makes it difficult to recalibrate the degenerated LTS devices during regular maintenance operations. In this paper, a novel one-dimensional target-based camera intrinsic matrix-free LTS calibration method is proposed. In contrast to conventional methods that calibrate the LTS based on the precise camera intrinsic matrix, we formulate the LTS calibration as an optimization problem taking all parameters of the LTS into account, simultaneously. In this way, many pairs of the camera intrinsic matrix and the equation of the laser plane can be solved and different pairs of parameters are equivalent for displacement measurement. A closed-form solution of the position of the one-dimensional target is proposed to make the parameters of the LTS optimizable. The results of simulations and experiments show that the proposed method can calibrate the LTS without knowing the camera intrinsic matrix. In addition, the proposed approach significantly improves the displacement measurement precision of the LTS after calibration. In conclusion, the proposed method proved that the precise camera intrinsic matrix is not the necessary condition for LTS displacement measurement.

High Throughput Screening of Cell Mechanical Response Using a Stretchable 3D Cellular Microarray Platform.

Cells in vivo are constantly subjected to multiple microenvironmental mechanical stimuli that regulate cell function. Although 2D cell responses to the mechanical stimulation have been established, these methods lack relevance as physiological cell microenvironments are in 3D. Moreover, the existing platforms developed for studying the cell responses to mechanical cues in 3D either offer low-throughput, involve complex fabrication, or do not allow combinatorial analysis of multiple cues. Considering this, a stretchable high-throughput (HT) 3D cell microarray platform is presented that can apply dynamic mechanical strain to cells encapsulated in arrayed 3D microgels. The platform uses inkjet-bioprinting technique for printing cell-laden gelatin methacrylate (GelMA) microgel array on an elastic composite substrate that is periodically stretched. The developed platform is highly biocompatible and transfers the applied strain from the stretched substrate to the cells. The HT analysis is conducted to analyze cell mechano-responses throughout the printed microgel array. Also, the combinatorial analysis of distinct cell behaviors is conducted for different GelMA microenvironmental stiffnesses in addition to the dynamic stretch. Considering its throughput and flexibility, the developed platform can readily be scaled up to introduce a wide range of microenvironmental cues and to screen the cell responses in a HT way.

Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review.

Autonomous vehicles (AV) are expected to improve, reshape, and revolutionize the future of ground transportation. It is anticipated that ordinary vehicles will one day be replaced with smart vehicles that are able to make decisions and perform driving tasks on their own. In order to achieve this objective, self-driving vehicles are equipped with sensors that are used to sense and perceive both their surroundings and the faraway environment, using further advances in communication technologies, such as 5G. In the meantime, local perception, as with human beings, will continue to be an effective means for controlling the vehicle at short range. In the other hand, extended perception allows for anticipation of distant events and produces smarter behavior to guide the vehicle to its destination while respecting a set of criteria (safety, energy management, traffic optimization, comfort). In spite of the remarkable advancements of sensor technologies in terms of their effectiveness and applicability for AV systems in recent years, sensors can still fail because of noise, ambient conditions, or manufacturing defects, among other factors; hence, it is not advisable to rely on a single sensor for any of the autonomous driving tasks. The practical solution is to incorporate multiple competitive and complementary sensors that work synergistically to overcome their individual shortcomings. This article provides a comprehensive review of the state-of-the-art methods utilized to improve the performance of AV systems in short-range or local vehicle environments. Specifically, it focuses on recent studies that use deep learning sensor fusion algorithms for perception, localization, and mapping. The article concludes by highlighting some of the current trends and possible future research directions.

Graphene-Coated Spandex Sensors Embedded into Silicone Sheath for Composites Health Monitoring and Wearable Applications.

This study presents a low-cost, tunable, and stretchable sensor fabricated based on spandex (SpX) yarns coated with graphene nanoplatelets (GnP) through a dip-coating process. The SpX/GnP is wrapped into a stretchable silicone rubber (SR) sheath to protect the conductive layer against harsh conditions, which allows for fabricating washable wearable sensors. Dip-coating parameters are optimized to obtain the maximum GnP coating rate. The covering sheath is tailored to achieve high stretchability beyond the sensing limit of 104% for SpX/GnP/SR sensors. Adjustable sensitivity is attained by manipulating SpX immersion times broadening its application for a wide range of strains: Gauge factors as high as two orders of magnitude are achieved at tensile strains greater than ≈40%. The fabricated sensors are tested for two applications: First, the SpX/GnP sensors are integrated into composite fabrics (with no negative impact on the structural integrity of the part) for screening the yarn displacements, resin flow, solidification during the hot press forming process, and structural health monitoring under mechanical loads with minimal cross-sensitivity to temperature/humidity. Second, the capability of SpX/GnP/SP sensors in detection of a wide range of bodily motions (from the joint motion to arterial blood pressure) is demonstrated.

Label-Free Capacitive Biosensor for Detection of Cryptosporidium.

Cryptosporidium, an intestinal protozoan pathogen, is one of the leading causes of diarrhea in healthy adults and death in children. Detection of Cryptosporidium oocysts has become a high priority to prevent potential outbreaks. In this paper, a label-free interdigitated-based capacitive biosensor has been introduced for the detection of Cryptosporidium oocysts in water samples. Specific anti-Cryptosporidium monoclonal antibodies (IgG3) were covalently immobilized onto interdigitated gold electrodes as the capture probes, and bovine serum albumin was used to avoid non-specific adsorption. The immobilization of the antibodies was confirmed by measuring the change in the contact angle. The detection was achieved by measuring the relative change in the capacitive/dielectric properties due to the formation of Cryptosporidium-antibody complex. The biosensor has been tested for different concentrations of Cryptosporidium. The results show that the biosensor developed can accurately distinguish different numbers of captured cells and densities on the surface of the biosensor. The number of Cryptosporidium oocysts captured on the electrode surface was confirmed using a fluorescein isothiocyanate (FITC) immunofluorescence assay. The response from the developed biosensor has been mainly dependent on the concentration of Cryptosporidium under optimized conditions. The biosensor showed a linear detection range between 15 and 153 cells/mm² and a detection limit of 40 cells/mm². The label-free capacitive biosensor developed has a great potential for detecting Cryptosporidium in environmental water samples. Furthermore, under optimized conditions, this label-free biosensor can be extended for detection of other biomarkers for biomedical and environmental analyses.

3D Printing-Based Integrated Water Quality Sensing System.

The online and accurate monitoring of drinking water supply networks is critically in demand to rapidly detect the accidental or deliberate contamination of drinking water. At present, miniaturized water quality monitoring sensors developed in the laboratories are usually tested under ambient pressure and steady-state flow conditions; however, in Water Distribution Systems (WDS), both the pressure and the flowrate fluctuate. In this paper, an interface is designed and fabricated using additive manufacturing or 3D printing technology-material extrusion (Trade Name: fused deposition modeling, FDM) and material jetting-to provide a conduit for miniaturized sensors for continuous online water quality monitoring. The interface is designed to meet two main criteria: low pressure at the inlet of the sensors and a low flowrate to minimize the water bled (i.e., leakage), despite varying pressure from WDS. To meet the above criteria, a two-dimensional computational fluid dynamics model was used to optimize the geometry of the channel. The 3D printed interface, with the embedded miniaturized pH and conductivity sensors, was then tested at different temperatures and flowrates. The results show that the response of the pH sensor is independent of the flowrate and temperature. As for the conductivity sensor, the flowrate and temperature affect only the readings at a very low conductivity (4 µS/cm) and high flowrates (30 mL/min), and a very high conductivity (460 µS/cm), respectively.

Microfluidics Integrated Biosensors: A Leading Technology towards Lab-on-a-Chip and Sensing Applications.

A biosensor can be defined as a compact analytical device or unit incorporating a biological or biologically derived sensitive recognition element immobilized on a physicochemical transducer to measure one or more analytes. Microfluidic systems, on the other hand, provide throughput processing, enhance transport for controlling the flow conditions, increase the mixing rate of different reagents, reduce sample and reagents volume (down to nanoliter), increase sensitivity of detection, and utilize the same platform for both sample preparation and detection. In view of these advantages, the integration of microfluidic and biosensor technologies provides the ability to merge chemical and biological components into a single platform and offers new opportunities for future biosensing applications including portability, disposability, real-time detection, unprecedented accuracies, and simultaneous analysis of different analytes in a single device. This review aims at representing advances and achievements in the field of microfluidic-based biosensing. The review also presents examples extracted from the literature to demonstrate the advantages of merging microfluidic and biosensing technologies and illustrate the versatility that such integration promises in the future biosensing for emerging areas of biological engineering, biomedical studies, point-of-care diagnostics, environmental monitoring, and precision agriculture.

Empirical validation of Conformal Prediction for trustworthy skin lesions classification.

BACKGROUND AND OBJECTIVE: Uncertainty quantification is a pivotal field that contributes to realizing reliable and robust systems. It becomes instrumental in fortifying safe decisions by providing complementary information, particularly within high-risk applications. existing studies have explored various methods that often operate under specific assumptions or necessitate substantial modifications to the network architecture to effectively account for uncertainties. The objective of this paper is to study Conformal Prediction, an emerging distribution-free uncertainty quantification technique, and provide a comprehensive understanding of the advantages and limitations inherent in various methods within the medical imaging field. METHODS: In this study, we developed Conformal Prediction, Monte Carlo Dropout, and Evidential Deep Learning approaches to assess uncertainty quantification in deep neural networks. The effectiveness of these methods is evaluated using three public medical imaging datasets focused on detecting pigmented skin lesions and blood cell types. RESULTS: The experimental results demonstrate a significant enhancement in uncertainty quantification with the utilization of the Conformal Prediction method, surpassing the performance of the other two methods. Furthermore, the results present insights into the effectiveness of each uncertainty method in handling Out-of-Distribution samples from domain-shifted datasets. Our code is available at: github.com/jfayyad/ConformalDx. CONCLUSIONS: Our conclusion highlights a robust and consistent performance of conformal prediction across diverse testing conditions. This positions it as the preferred choice for decision-making in safety-critical applications.

On-chip-based electrochemical biosensor for the sensitive and label-free detection of Cryptosporidium.

Cryptosporidium, an intestinal protozoan pathogen, is one of the leading causes of death in children and diarrhea in healthy adults. Detection of Cryptosporidium has become a high priority to prevent potential outbreaks. In this paper, a simple, easy to fabricate, and cost-effective on-chip-based electrochemical biosensor has been developed for the sensitive and label-free detection of Cryptosporidium oocysts in water samples. The sensor was fabricated using standard lithography using a mask with a 3-electrode design and modified by self-assembling a hybrid of a thiolated protein/G and the specific anti-Cryptosporidium monoclonal antibodies (IgG3). The electrochemical impedance spectroscopy (EIS) was employed to quantitate C. parvum in the range of 0 to 300 oocysts, with a detection limit of approximately 20 oocysts/5 µL. The high sensitivity and specificity of the developed label-free electrochemical biosensor suggest that this novel platform is a significant step towards the development of fast, real-time, inexpensive and label-free sensing tool for early warning and immediate on-site detection of C. parvum oocysts in water samples, as compared to the traditional methods (such as PCR and microscopy). Furthermore, under optimized conditions, this label-free biosensor can be extended to detect other analytes and biomarkers for environmental and biomedical analyses.

A Critical Analysis of Industrial Human-Robot Communication and Its Quest for Naturalness Through the Lens of Complexity Theory.

Human-robot communication is one of the actively researched fields to enable efficient and seamless collaboration between a human and an intelligent industrial robotic system. The field finds its roots in human communication with the aim to achieve the "naturalness" inherent in the latter. Industrial human-robot communication pursues communication with simplistic commands and gestures, which is not representative of an uncontrolled real-world industrial environment. In addition, naturalness in communication is a consequence of its dynamism, typically ignored as a design criterion in industrial human-robot communication. Complexity Theory-based natural communication models allow for a more accurate representation of human communication which, when adapted, could also benefit the field of human-robot communication. This paper presents a perspective by reviewing the state of human-robot communication in industrial settings and then presents a critical analysis of the same through the lens of Complexity Theory. Furthermore, the work identifies research gaps in the aforementioned field, fulfilling which, would propel the field towards a truly natural form of communication. Finally, the work briefly discusses a general framework that leverages the experiential learning of data-based techniques and naturalness of human knowledge.

Comprehensive review of conventional and state-of-the-art detection methods of Cryptosporidium.

Cryptosporidium is a critical waterborne protozoan pathogen found in water resources that have been a major cause of death and serious illnesses worldwide, costing millions of dollars annually for its detection and treatment. Over the past several decades, substantial efforts have been made towards developing techniques for the detection of Cryptosporidium. Early diagnostic techniques were established based on the existing tools in laboratories, such as microscopes. Advancements in fluorescence microscopy, immunological, and molecular techniques have led to the development of several kits for the detection of Cryptosporidium spp. However, these methods have several limitations, such as long processing times, large sample volumes, the requirement for bulky and expensive laboratory tools, and the high cost of reagents. There is an urgent need to improve these existing techniques and develop low-cost, portable and rapid detection tools for applications in the water quality industry. In this review, we compare recent advances in nanotechnology, biosensing and microfluidics that have facilitated the development of sophisticated tools for the detection of Cryptosporidium spp.Finally, we highlight the advantages and disadvantages, of these state-of-the-art detection methods compared to current analytical methodologies and discuss the need for future developments to improve such methods for detecting Cryptosporidium in the water supply chain to enable real-time and on-site monitoring in water resources and remote areas.

Experimental comparison of direct and indirect aptamer-based biochemical functionalization of electrolyte-gated graphene field-effect transistors for biosensing applications.

Aptamer-based electrolyte-gated graphene field-effect transistor (EGFET) biosensors have gained considerable attention because of their rapidity and accuracy in terms of quantification of a wide range of biomarkers. Functionalization of the graphene channel of EGFETs with aptamer biorecognition elements (BREs) is a crucial step in fabrication of EGFET aptasensors. This paper presents a comprehensive comparison of commonly used biochemical functionalization approaches applied for preparation of sensing films in EGFET aptasensors, namely indirect and direct immobilization of BREs. This study is the first of its kind to experimentally compare the two BREs immobilization approaches in terms of their effects on the carrier mobility of the monolayer graphene channel and their suitability for sensing applications. Both approaches can preserve and even improve the carrier mobility of bare graphene channel and hence the sensitivity of the EGFET; however, the direct BREs immobilization method was selected to develop an aptameric EGFET biosensor as this method enables simpler and more efficient preparation of the graphene-based aptameric sensing film. The utility of the prepared EGFET aptasensor is demonstrated through detection of tumor necrosis factor-α (TNF-α), an important inflammatory biomarker. The direct BREs immobilization approach is applied to develop an EGFET aptasensor to measure TNF-α in a detection range from 10 pg/ml to 10 ng/ml, representative of its physiological level in human sweat, as a non-invasively accessible biofluid. The outstanding sensing performance of the developed TNF-α EGFET aptasensor based on direct BREs immobilization can pave the way for development of graphene biosensors.

Portable on-chip colorimetric biosensing platform integrated with a smartphone for label/PCR-free detection of Cryptosporidium RNA.

Cryptosporidium, a protozoan pathogen, is a leading threat to public health and the economy. Herein, we report the development of a portable, colorimetric biosensing platform for the sensitive, selective and label/PCR-free detection of Cryptosporidium RNA using oligonucleotides modified gold nanoparticles (AuNPs). A pair of specific thiolated oligonucleotides, complementary to adjacent sequences on Cryptosporidium RNA, were attached to AuNPs. The need for expensive laboratory-based equipment was eliminated by performing the colorimetric assay on a micro-fabricated chip in a 3D-printed holder assembly. A smartphone camera was used to capture an image of the color change for quantitative analysis. The detection was based on the aggregation of the gold nanoparticles due to the hybridization between the complementary Cryptosporidium RNA and the oligonucleotides immobilized on the AuNPs surface. In the complementary RNA's presence, a distinctive color change of the AuNPs (from red to blue) was observed by the naked eye. However, in the presence of non-complementary RNA, no color change was observed. The sensing platform showed wide linear responses between 5 and 100 µM with a low detection limit of 5 µM of Cryptosporidium RNA. Additionally, the sensor developed here can provide information about different Cryptosporidium species present in water resources. This cost-effective, easy-to-use, portable and smartphone integrated on-chip colorimetric biosensor has great potential to be used for real-time and portable POC pathogen monitoring and molecular diagnostics.

Micron-sized particle separation with standing surface acoustic wave-Experimental and numerical approaches.

Traditional cell/particle isolation methods are time-consuming and expensive and can lead to morphology disruptions due to high induced shear stress. To address these problems, novel lab-on-a-chip-based purification methods have been employed. Among various methods introduced for the separation and purification of cells and synthetics particles, acoustofluidics has been one of the most effective methods. Unlike traditional separation techniques carried out in clinical laboratories based on chemical properties, the acoustofluidic process relies on the physical properties of the sample. Using acoustofluidics, manipulating cells and particles can be achieved in a label-free, contact-free, and highly biocompatible manner. To optimize the functionality of the platform, the numerical study should be taken into account before conducting experimental tests to save time and reduce fabrication expenses. Most current numerical studies have only considered one-dimensional harmonic standing waves to simulate the acoustic pressure distribution. However, one-dimensional simulations cannot calculate the actual acoustic pressure distribution inside the microchannel due to its limitation in considering longitudinal waves. To address this limitation, a two-dimensional numerical simulation was conducted in this study. Our numerical simulation investigates the effects of the platform geometrical and operational conditions on the separation efficiency. Next, the optimal values are tested in an experimental setting to validate these optimal parameters and conditions. This work provides a guideline for future acoustofluidic chip designs with a high degree of reproducibility and efficiency.

In situ characterization of microdroplet interfacial properties in digital microfluidic systems.

Real-time characterization of digital microfluidic lab-on-a-chip devices is important for biological and chemical applications in which the properties of the microdroplet are time variant. In this paper, a method for in situ characterization of microdroplet interfacial properties is introduced. The proposed characterization method relies on two submodules, namely the contact angle and capacitance sampling submodules, in a digital microfluidic system. In the contact angle measurement submodule, the microdroplet profile is acquired and an accurate contact angle is determined. In the capacitance sampling submodule, the capacitance of the system is measured by means of an activation voltage signal. For verification purposes, the results obtained from the proposed method are compared to the Lippmann-Young equation. The results are in excellent agreement with previously reported values. Finally, the proposed submodules are used to characterize the interfacial properties of a microdroplet containing an aqueous solution of bovine serum albumin (BSA) in which adsorption is a predominant effect. The results show the temporal behaviour of both microdroplet interfacial properties and dielectric characteristics.

Droplet position control in digital microfluidic systems.

Research on so called digital microfluidic systems (DMS) capable of manipulating individual microdroplets on a cell-based structure has enormously increased in the past few years, mainly due to the demand of the technology-dependent biomedical applications. Significant research in this area has been related to the simulation and modeling of droplet motion, demonstration of different drop actuation techniques on laboratory-scale prototypes, and droplet routing and scheduling for more efficient assay procedures. This paper introduces the basics of the control analysis and design of a DMS, which is a relatively unexplored area in digital microfluidics. This paper starts with a discussion on a simplified dynamic model of droplet motion in a planar array of cells, and continues with more complicated dynamic models that are necessary to realize the structure of an appropriate closed-loop control system for the DMS. The control analysis and design includes both the transient and steady-state responses of the DMS under external driving forces. The proposed control analysis and design approach is implemented into SIMULINK models to demonstrate the performance of the DMS through simulation using the system parameters previously reported in the literature.

Decision making under uncertainty--an example for seismic risk management.

Decision-making techniques are used to select the "best" alternatives under multiple and often conflicting criteria. Multicriteria decision making (MCDM) necessitates to incorporate uncertainties in the decision-making process. The major thrust of this article is to extend the framework proposed by Yager for multiple decisionmakers and fuzzy utilities (payoffs). In addition, the concept of expert credibility factor is introduced. The proposed approach is demonstrated for an example of seismic risk management using a heuristic hierarchical structure. A step-by-step formulation of the proposed approach is illustrated using a hypothetical example and a three-story reinforced concrete building.

Low-Cost Graphene-Based Digital Microfluidic System.

In this work, the laser-scribing technique was used as a low-cost, rapid and facile method for fabricating digital microfluidic (DMF) systems. Laser-scribed graphene (LSG) electrodes are directly synthesized on flexible substrates to pattern the DMF electrode arrays. This facilitates the DMF electrodes' fabrication process by eliminating many microfabrication steps. An electrowetting test was performed to investigate the effectiveness of the LSG DMF electrodes in changing the contact angles of droplets. Different DMF operations were successfully performed using the proposed LSG DMF chips in both open and closed DMF systems. The quality and output resolution were examined to assess the performance of such patterned electrodes in the DMF systems. To verify the efficacy of the LSG DMF chips, a one-step direct assay for the detection of Legionellapneumophila deoxyribonucleic acid (DNA) was performed on the chip without the need for any washing step. The high specificity in distinguishing a single-nucleotide mismatch was achieved by detecting target DNA concentrations as low as 1 nM. Our findings suggest that the proposed rapid and easy fabrication method for LSG DMF electrodes offers a great platform for low-cost and easily accessible point-of-care diagnostic devices.