Reduce Background Noise Research Articles

A turn-on fluorescence strategy for hypochlorous acid detection based on DNAzyme-assisted cyclic signal amplification

Hypochlorous acid (HClO) is a crucial active oxygen component and one of the innate immunity's barrier substances in the body. Abnormal fluctuations in HClO concentration can lead to increased oxidative stress, cellular dysfunction, and the onset of various diseases. Thus, developing convenient, affordable, efficient, and sensitive methods to monitor HClO concentration in healthcare and pathophysiology research is highly significant. In this study, we developed a novel fluorescence strategy for HClO detection based on nucleic acid oxidative cleavage and Pb2+-dependent DNAzyme. By introducing a phosphorothioate site in the hairpin-structured nucleic acid sequence, the nucleic acid probe specifically recognized HClO and underwent oxidative cleavage. Upon cleavage, the enzyme strand is liberated, forming DNAzyme. This DNAzyme then cleaves the substrate strand, liberating the initially quenched fluorescent dyes and generating a turn-on fluorescent signal. The enzyme strand produced by the oxidative cleavage of HClO can be repeatedly utilized, thus realizing the cyclic signal amplification to reduce background noise. We verified the detection mechanism of this strategy through stepwise fluorescence spectroscopy analysis and electrophoresis. Under optimal experimental conditions, the method achieved a detection limit of 5.38 nM and a linear range of 1 nM-800 nM. This method demonstrated exceptional performance in actual biological sample testing and presented an exciting opportunity for expanded utilization in clinical diagnosis and medical research.

A highly sensitive and robust electrochemical biosensor for microRNA detection based on PNA-DNA hetero-three-way junction formation and target-recycling catalytic hairpin assembly amplification

Robust and sensitive methods for the detection of microRNAs (miRNAs) are crucial in the clinical diagnosis of cancers. In this study, a novel electrochemical biosensor with high sensitivity for miRNA-21 detection is developed, which relies on the formation of a peptide nucleic acid (PNA)-DNA hetero-three-way junction (H3WJ) and target-recycling catalytic hairpin assembly (CHA) amplification. The electroneutral PNA probes are initially immobilized onto a gold electrode to construct the sensor. Upon introduction of miRNA-21, target-recycling CHA is initiated, resulting in abundant double-stranded CHA products. Subsequently, association between the PNA probes and these products leads to the formation of PNA-DNA H3WJs. Consequently, the electrode surface is densely populated with numerous electroactive Ferrocene (Fc) groups, resulting in a significantly amplified current response for highly sensitive detection of miRNA-21 at concentrations as low as 0.15 fM. This approach demonstrates remarkable specificity towards target miRNAs and can be utilized for quantitative monitoring of miRNA-21 expression in human cancer cells. More importantly, the sensor exhibits exceptional stability and shows a significant reduction in background noise during miRNA detection, making this method a highly promising sensing platform for monitoring various miRNA biomarkers to facilitate the diagnosis of diverse cancers.

EA-ConvNeXt: An Approach to Script Identification in Natural Scenes Based on Edge Flow and Coordinate Attention

In multilingual scene text understanding, script identification is an important prerequisite step for text image recognition. Due to the complex background of text images in natural scenes, severe noise, and common symbols or similar layouts in different language families, the problem of script identification has not been solved. This paper proposes a new script identification method based on ConvNext improvement, namely EA-ConvNext. Firstly, the method of generating an edge flow map from the original image is proposed, which increases the number of scripts and reduces background noise. Then, based on the feature information extracted by the convolutional neural network ConvNeXt, a coordinate attention module is proposed to enhance the description of spatial position feature information in the vertical direction. The public dataset SIW-13 has been expanded, and the Uyghur script image dataset has been added, named SIW-14. The improved method achieved identification rates of 97.3%, 93.5%, and 92.4% on public script identification datasets CVSI-2015, MLe2e, and SIW-13, respectively, and 92.0% on the expanded dataset SIW-14, verifying the superiority of this method.

Use of polarization properties of seismic waves to improve Fresnel Volume Migration of three-component subsurface seismic data

Long-range exploration in mines contributes significantly to work safety, raw material extraction and storage of materials in the subsurface. The distribution and number of source and receiver points for seismic surveys depend on the available gallery passages in the mine or underground buildings. Due to the resulting limited aperture, migration artifacts, spatial ambiguities, and geometrically induced amplitude focusing can occur in migration images. In addition, background noise is often very interfering, and reflectors smear in migration images. It has been shown that along drifts that have directional changes and thus corners or chambers, the signal-to-noise ratio is low due to scattered waves. We have incorporated directional and polarization filters into the workflow for pre-processing subsurface seismic data before starting Fresnel Volume Migration (FVM). This significantly reduces background noise and geometrically induced amplitude focusing as well as migration amplitude smearing effects. By applying directional and polarization filters beforehand, we improve the 3D seismic imaging. This allows us to highlight previously hidden or smeared reflectors when calculating migrations of reflected P and S waves and suppress amplitude focusing effects along drifts. In this paper, we present step-by-step this novel methodological approach that improves 3D seismic imaging for large-scale structure exploration in mining.

Effect of Sub-Surface Damage Layer Removal by Sublimation Etching of 4H-SiC Bulk Wafers on PL Imaging of Crystal Defect Visibility

Improving the visibility of defects in nitrogen-doped 4H-SiC (0001) bare wafers by photoluminescence imaging (PLI) is essential for improving the epitaxial growth process and device yields. This study proposes sub-surface damage (SSD) introduced during the mechanical process of SiC wafers as a new factor in reducing defect visibility in PL images. To verify the effect of SSD, we observed the surface of a SiC wafer, which was thermally etched at about 3 μm. As a result, dramatic defect visibility improvement was observed when the surface roughness was sufficiently flat (Ra < 0.3 nm) after thermal etching. Thus, the results suggest that defect visibility in PL images can be improved by controlling SSD and surface roughness. Using the background noise reduction effect of the SSD removal, not only PLI but also many other wafer surface inspections are expected to be improved.

Sustainable and Rapid Determination of Two Halogenated Pesticides in a Commercial Formulation by Solid Phase Microextraction and Liquid Phase Chemical Ionization Mass Spectrometry

This work presents a sustainable and rapid method for halogenated pesticide analysis without chromatographic separation. The system is composed of a microfluidic open interface (MOI) for solid-phase microextraction (SPME) liquid phase desorption, connected to a liquid electron ionization mass spectrometry interface (LEI-MS). Either a triple quadrupole mass spectrometer (QQQ-MS/MS, (low-resolution) or a quadrupole-time-of-flight tandem MS (QTOF-MS/MS, high-resolution) were employed, each operating in negative chemical ionization (NCI) conditions. The flow rate used (100 µL/min) to rapidly empty the MOI chamber (approximately 2.5 µL) is reduced to the working flow rate of the LEI interface (500 nL/min) by a passive flow splitter (PFS). NCI is an appropriate ionization technique for electrophilic compounds, increasing specificity and reducing background noise. Two halogenated pesticides, dicamba and tefluthrin, were extracted simultaneously from a commercial formulation matrix (CF) using a C18 fiber by direct immersion (3 min under vortex agitation). Analyte desorption occurred in static conditions inside MOI filled with acidified acetonitrile (ACN) (0.2% phosphoric acid, PA). Extraction and desorption steps were optimized to increase efficiency and accelerate the process. No chromatographic separation was involved; therefore, the system fully exploited MS/MS selectivity and HRMS accuracy demonstrating good linearity, repeatability and limits of detection (LODs) and limits of quantification (LOQs) in the pg/mL range (50 and 500 pg/mL, respectively). Low-resolution experiments showed that matrix effects (ME) did not affect the results. The fast workflow (5 min) makes the system suitable for high-throughput analysis observing the principles of green analytical chemistry (GAC).

Comparison of speech recognition performance with and without a face mask between a basic and a premium hearing aid in hearing-impaired listeners

BackgroundThe mask mandate during the COVID-19 pandemic leads to communication challenges as sound energy gets reduced and the visual cues are lost due to the face mask. This study examines the impact of a face mask on sound energy and compares speech recognition performance between a basic and a premium hearing aid. MethodsParticipants watched four video clips (a female and a male speaker with and without a face mask) and repeated the target sentences in various test conditions. Real-ear measurement was performed to investigate the changes in sound energy in no mask, surgical, and N95 mask conditions. ResultsWith the face mask on, sound energy significantly decreased for all types of masks. For speech recognition, the premium hearing aid showed significant improvement in the mask condition. ConclusionThe findings emphasize and encourage health care professionals to actively use communication strategies, such as speaking slowly and reducing background noise, when interacting with individuals with hearing loss.

Objective Assessment of Binaural Benefit from Acoustical Treatment in Real Primary School Classrooms.

Providing students with an adequate acoustic environment is crucial for ensuring speech intelligibility in primary school classrooms. Two main approaches to control acoustics in educational facilities consist of reducing background noise and late reverberation. Prediction models for speech intelligibility have been developed and implemented to evaluate the effects of these approaches. In this study, two versions of the Binaural Speech Intelligibility Model (BSIM) were used to predict speech intelligibility in realistic spatial configurations of speakers and listeners, considering binaural aspects. Both versions shared the same binaural processing and speech intelligibility backend processes but differed in the pre-processing of the speech signal. An Italian primary school classroom was characterized in terms of acoustics before (reverberation, T20 = 1.6 ± 0.1 s) and after (T20 = 0.6 ± 0.1 s) an acoustical treatment to compare BSIM predictions to well-established room acoustic measures. With shorter reverberation time, speech clarity and definition improved, as well as speech recognition thresholds (SRTs) (by up to ~6 dB), particularly when the noise source was close to the receiver and an energetic masker was present. Conversely, longer reverberation times resulted (i) in poorer SRTs (by ~11 dB on average) and (ii) in an almost non-existent spatial release from masking at an angle (SRM).

Attention-induced semantic and boundary interaction network for camouflaged object detection

The high intrinsic similarity between camouflaged objects and the background makes camouflaged object detection (COD) more challenging than traditional salient object detection (SOD). Existing deep-learning methods often fall into the following shortcomings: (1) When dealing with high-level features, it is difficult to fully and accurately extract semantic information, which is crucial for locating camouflaged targets. (2) The camouflaged targets identified by existing methods in complex scenes have rough boundaries and incomplete spatial information. (3) Existing methods cannot effectively exert the uniqueness and complementarity of multiple features when integrating multiple features. To this end, we propose an attention-induced semantic and boundary interaction network for accurately identifying camouflaged objects. Specifically, we propose a contrastive positioning module (CPM), which adopts a contrastive learning way to separate the camouflaged object from the background, thereby obtaining the exact location of the camouflaged target and retaining more semantic information. Then, we design a boundary exploration module (BEM), which can reduce background noise interference, focus on the structural details of camouflaged targets, and explore rich fine-grained spatial information. Finally, we propose an attention-induced interaction module (AIM) to fuse multivariate information (i.e., semantic location information, boundary information, and the side output information of the backbone), and multivariate information is complementarily fused under attention guidance to generate more powerful camouflaged target features. Extensive experiments show that the proposed method on the different backbones (i.e., ResNet-50, Res2Net-50, PVTv2-B2, EfficientNet-B1) produces state-of-the-art results on several camouflaged benchmarks. The code is available https://github.com/zhangqiao970914/ASBI.

Optimal symbolic entropy: An adaptive feature extraction algorithm for condition monitoring of bearings

Due to their effectiveness in vibration-based fault feature extraction from bearings, entropy-based methods have become a hot research topic. Symbolic dynamic filtering reduces background noise in bearing signals, making it ideal for entropy analysis. However, the partitioning approach selection of symbolic dynamic filtering mainly depends on experience, which may bring over-track and under-track phenomena. The optimal symbolic entropy (OSE) method proposes a solution by using mean spectral kurtosis to evaluate the symbolization performance of partitioning approaches. This method improves the identification of bearing faults through steps such as evaluating frequency and amplitude preservation, selecting the optimal symbolization approach, and using the OSE method with multiscale analysis. Simulative and experimental data analysis demonstrates its superior ability to extract bearing fault characteristics, with better performance and robustness than existing methods.

Causal speech enhancement using dynamical-weighted loss and attention encoder-decoder recurrent neural network.

Speech enhancement (SE) reduces background noise signals in target speech and is applied at the front end in various real-world applications, including robust ASRs and real-time processing in mobile phone communications. SE systems are commonly integrated into mobile phones to increase quality and intelligibility. As a result, a low-latency system is required to operate in real-world applications. On the other hand, these systems need efficient optimization. This research focuses on the single-microphone SE operating in real-time systems with better optimization. We propose a causal data-driven model that uses attention encoder-decoder long short-term memory (LSTM) to estimate the time-frequency mask from a noisy speech in order to make a clean speech for real-time applications that need low-latency causal processing. The encoder-decoder LSTM and a causal attention mechanism are used in the proposed model. Furthermore, a dynamical-weighted (DW) loss function is proposed to improve model learning by varying the weight loss values. Experiments demonstrated that the proposed model consistently improves voice quality, intelligibility, and noise suppression. In the causal processing mode, the LSTM-based estimated suppression time-frequency mask outperforms the baseline model for unseen noise types. The proposed SE improved the STOI by 2.64% (baseline LSTM-IRM), 6.6% (LSTM-KF), 4.18% (DeepXi-KF), and 3.58% (DeepResGRU-KF). In addition, we examine word error rates (WERs) using Google's Automatic Speech Recognition (ASR). The ASR results show that error rates decreased from 46.33% (noisy signals) to 13.11% (proposed) 15.73% (LSTM), and 14.97% (LSTM-KF).

Behavior-Based Video Summarization System for Dog Health and Welfare Monitoring

The popularity of dogs has been increasing owing to factors such as the physical and mental health benefits associated with raising them. While owners care about their dogs' health and welfare, it is difficult for them to assess these, and frequent veterinary checkups represent a growing financial burden. In this study, we propose a behavior-based video summarization and visualization system for monitoring a dog's behavioral patterns to help assess its health and welfare. The system proceeds in four modules: (1) a video data collection and preprocessing module; (2) an object detection-based module for retrieving image sequences where the dog is alone and cropping them to reduce background noise; (3) a dog behavior recognition module using two-stream EfficientNetV2 to extract appearance and motion features from the cropped images and their respective optical flow, followed by a long short-term memory (LSTM) model to recognize the dog's behaviors; and (4) a summarization and visualization module to provide effective visual summaries of the dog's location and behavior information to help assess and understand its health and welfare. The experimental results show that the system achieved an average F1 score of 0.955 for behavior recognition, with an execution time allowing real-time processing, while the summarization and visualization results demonstrate how the system can help owners assess and understand their dog's health and welfare.

A sub-region Unet for weak defects segmentation with global information and mask-aware loss

In recent years, diverse detection methods have been proposed to achieve highly accurate image segmentation. However, low contrast and background noise interference still pose challenges to defect detection. Existing deep learning-based methods for defect detection mostly learn rich features on the whole image. This can lead to overfitting as the parameters get bigger, and it also loses the spatial connection. In order to solve this problem, we suggest a network based on spatial sub-region feature extraction and mask-aware loss that can detect metal surface defects. In this network framework, we obtain the contextual information of each region through two streams: one branch encodes the spatial sub-region information and reduces the effect of geometric and illumination deformation under u-shape architecture. A skip-connected structure in another stream is designed to learn global information and compensate for boundary features. Next, we propose a mask-aware loss to reduce background noise interference further. Finally, we validate the effectiveness of our method on two challenging datasets, reaching 88.45% and 79.16% on the NEU-Seg and USB-Seg datasets, respectively. Also, our model is only 5.48 MB, and can achieve 172 fps for processing images with 200 × 200 size defects.

Using crowd-sourced data to optimize conversational sound levels in hospitality venues

One of the top complaints about a restaurant is usually related to noise. The sound level in a venue can significantly affect whether or not a customer will return. Statistical analysis of the crowdsourced data collected with the SoundPrint smartphone app at more than 10,000 U.S.-based hospitality venues (restaurants, coffee shops, and bars) provides a comparison of the objective sound level data versus the patrons’ subjective ratings for conversational ability. These insights show a customer's tolerance for noisy environments can be highly dependent on the venue type, specifically when communication is important. The findings can also help venue managers know what interior sound levels to target when optimizing the acoustics for their venue, whether by reducing background noise levels or improving acoustical treatments, in order to attract and keep their patrons happy.

A teacher-student based attention network for fine-grained image recognition

Fine-grained image recognition (FGIR) task is dedicated to distinguishing similar sub-categories that belong to the same super-category, such as bird species and car types. In order to highlight visual differences, existing FGIR works often follow two steps: discriminative sub-region localization and local feature representation. However, these works pay less attention on global context information. They neglect a fact that the subtle visual difference in challenging scenarios can be highlighted through exploiting the spatial relationship among different sub-regions from a global view point. Therefore, in this paper, we consider both global and local information for FGIR, and propose a collaborative teacher-student strategy to reinforce and unity the two types of information. Our framework is implemented mainly by convolutional neural network, referred to Teacher-Student Based Attention Convolutional Neural Network (T-S-ACNN). For fine-grained local information, we choose the classic multi-attention network (MA-Net) as our baseline, and propose a type of boundary constraint to further reduce background noises in the local attention maps. In this way, the discriminative sub-regions tend to appear in the area occupied by fine-grained objects, leading to more accurate sub-region localization. For fine-grained global information, we design a graph convolution based global attention network (GA-Net), which can combine extracted local attention maps from MA-Net with non-local techniques to explore spatial relationship among sub-regions. At last, we develop a collaborative teacher-student strategy to adaptively determine the attended roles and optimization modes, so as to the cooperative reinforcement of MA-Net and GA-Net. Extensive experiments on CUB-200-2011, Stanford Cars and FGVC Aircraft datasets illustrate the promising performance of our framework.© 2022 Published by Elsevier Ltd.

Immobilization and enhancement of a heterodimeric fluorescent biosensor in fibrous protein biomaterials via gene fusion.

Leave-One-Out Green Fluorescent Proteins (LOO_GFPs) unite a peptide sensor and detection method in a single biocompatible molecule. In LOO_GFPs, one β-strand of the GFP protein is removed and the cavity is re-engineered to specifically bind a desired analyte. Unfortunately, LOO_GFPs have a reduced quantum yield relative to the parent protein, and form fluorescent oligomers in the unbound state, reducing signal-to-noise. Immobilizing LOO_GFPs in materials composed of the Drosophila protein Ultrabithorax (Ubx) via gene fusion both increased the fluorescent signal and prevented oligomerization, substantially reducing background noise. These fibers represent the first incorporation of aheterodimeric protein into materials via gene fusion. Interactions between LOO_GFP and Ubx that hampered analyte rebinding were mitigated by optimizing salt and detergent concentrations in the assay. The result is a useful first-generation fluorescent biosensor, immobilized in and stabilized by robust protein fibers. This study highlights the advantages and identifies potential pitfalls associated with protein immobilization in materials.

SPAD-Based LiDAR With Real-Time Accuracy Calibration and Laser Power Regulation

This brief reports a light detection and range (LiDAR) imager which incorporates an image sensor based on a single-photon avalanche diode (SPAD) with the resolution of 32 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {\times }$ </tex-math></inline-formula> 32, a VCSEL-based laser emission system with the same resolution as image sensor as well as the pixel spacing, and a field programmable logic gate array (FPGA) used to realize the calibration algorithm and control the working time of the LiDAR imager. A gating high-voltage driver circuit drives the image sensor to reduce background noise interference and realize real-time accuracy calibration for the time-to-digital converter (TDC) with the resolution of 200 ps. The common-cathode driver circuit with the narrow pulse, adaptive frequency and power regulation drives different channels of VCSEL based on the time-division multiplexing method to improve the signal-to-noise ratio and reduce power consumption of the LiDAR imager. The LiDAR imager based on the proposed circuit architecture and calibration algorithm can achieve depth imaging up to 10 m revealing a repeatability error of 10 cm at 10 frames/s.

Reducing Noise in Restaurants: Feasibility and Recommendations

A recent study investigated the negative effects of loud background noise in restaurants for adults over the age of 60. 1 The researchers simulated a restaurant in a sound booth with 31 older adults with varying levels of hearing loss. They found that in certain levels of background noise, the speakers raised their voices, reported increased communication disturbances, and described less willingness to spend time and money in the restaurant.Restaurants, noise, acoustics.These negative outcomes occurred due to a cycle of bothersome noise generated by the Lombard effect, which is the unconscious tendency to increase one’s voice in a noisy environment. In restaurants, patrons act as sources and receivers of noise, which results in a noisy environment that is challenging to manage. 2 The researchers concluded with two main findings: 1) that the negative cycle of the Lombard effect is reduced when background noise is less than 60 dB(A), and 2) that restaurant owners should try to keep their background noise levels between 50-55 dB(A) to be inclusive of older adults with hearing loss, allowing them to understand the speech of their dining partners. Given the fact that restaurants have a variety of noise sources (e.g., kitchen noise, background music, patrons’ conversations, etc.), 3 it is difficult to achieve background noise between 50-55 dB(A). Yet, background noise in restaurants is a well-documented problem 4,5 and has been rated the most irritating component of dining out. 6 Here, we offer feasible solutions for restaurant owners to reduce disturbing background noise and improve the dining experience of restaurant goers, both old and young. ACOUSTIC RECCOMENDATIONS The negative cycle of noise in restaurants can be eliminated when the level of the background noise remains below 60 dB(A). There are three main avenues to achieve this level of noise: acoustical capacity, absorbent materials, and screens. Acoustical capacity. We have all seen signs in public spaces stating the required maximum capacity. These are safety-standards based on the physical size of the room. However, for restaurants aiming to provide a positive dining experience for their patrons, another relevant consideration should be acoustical capacity. 7 Acoustical capacity considers the number of people within a restaurant, as opposed to its physical size. This effectively limits the number of talkers within the restaurant at a given point in time, which results in a reduction in background noise. Restaurant owners may not be enthusiastic about reducing the number of people who can eat at their restaurant. But given the fact that irritating noise in restaurants is directly linked to the number of people seated, following a preset acoustical capacity is a strong way to improve the dining experience. Absorbent materials. A more realistic acoustic treatment for restaurants is installing absorbent materials on the ceilings. This approach to reducing background noise is more common than adhering to an acoustical capacity, and although it may not result in the lowest levels of noise, it is a viable option for restaurant owners. Specifically, suspended acoustic ceiling baffles absorb bothersome noise in restaurants. 8 These baffles hang vertically to scatter sound that decreases speech intelligibility between talkers/receivers. Screens. Another practical option for reducing noise in restaurants is installing screens between tables. The screens increase customers’ privacy and reduce their volume levels by increasing the spatial energy decay. 9 Many restaurant owners installed similar screens as a health measure due to the COVID-19 pandemic, but these screens serve a dual purpose by acoustically treating dining rooms as well. WHERE TO START? Acoustical consultants are available as resources to improve the overall quality of the dining experience through sound treatment. We recommend that restaurant owners collaborate with acoustical consultants early when designing, renovating, or refurbishing their businesses. A proper sound treatment may contribute about 5%-10% to the total cost of renovation, which is a small expense to eliminate customers’ irritation stemming from noise. “HEALTH IS WEALTH” One answer to the complex problem of noise in restaurants is sound treatment. Some Michelin-starred restaurants are among the eating establishments with the lowest background noise levels, as their design-process considered the acoustic experiences of their patrons, 10 resulting in easily intelligible conversations and customers who are willing to spend long periods at the dining table. Acoustic consultants contributed to the design of these top-tier eateries, but they are also available to support any restaurant owner with a desire to facilitate positive dining experiences in their space. It is commonly said that “time is money” and, even more importantly, “health is wealth.” With the proper sound treatment, why not have both?

A Robust Phenotypic Screening Assay Utilizing Human Podocytes to Identify Agents that Modulate Lipid Droplets.

Lipid droplets (LDs), initially thought to be mere lipid storage structures, are highly dynamic organelles with complex functions that control cell fate and behavior. In recent years, their relevance as therapeutic targets for a wide array of human diseases has been well established. Consequently, efforts to develop tools to study them have intensified, including assays that can accurately track LD levels in clinically relevant cell-based models. We previously reported that LD accumulation destines podocytes for lipotoxicity and cell death in renal diseases of metabolic and nonmetabolic origin. We also showed that LD accumulation in those cells serves as both a marker for disease progression and as a therapeutic target. Here, we describe a robust phenotypic screening method, using differentiated human podocytes, for identifying small-molecule compounds that rescue podocytes from LD accumulation and lipotoxicity under cellular stress. Major assay advances include 1) the use of a solvatochromic dye to improve LD staining, reduce background noise, and improve detection accuracy, 2) use of confocal imaging to reduce vertical overlap of LDs and enable accurate counting, 3) combining membrane and cytoskeleton stains to improve cell segmentation in confocal mode, and 4) use of an optimized spot detection algorithm that requires minimal configuration per individual run. The assay is robust and yields a Z-factor that is consistently >0.5.

Fourier Series Model for Facial Feature Point Land-Marking

The field of digital health apps, combined with intelligent learning systems, is new and expanding to incorporate a wide range of possibilities in different domains. An application in the field of digital therapy is for the incorporation of emotion recognition systems as a tool for therapeutic interventions. Adopting an individually tailored virtual world combined with a novel reward system in a gaming scenario, complemented with the technical affinity of most autism spectrum disorder (ASD) children makes a suitable atmosphere for therapeutic intervention. In this paper the use of image processing techniques coupled with Fourier models is used to generate point land-mark annotations on facial features in an image. The OULU-CASIA database was used for the analysis process. The images were first pre-processed based on previous work to reduce background noise and focus on the face. Afterwards a de-correlation stretch was executed to separate different features. A series of morphological, region detections and boundary traces followed. Fourier series models were used to transition the rough segmented pixel data into a smooth geometric representation. Twenty evenly distributed land-mark points are then selected from a fine mesh. Results showed that the geometric representation adhered to the segmented pixel data with a mean of 81.88% Dice similarity. The positive outlook highlighted the effectiveness of such a technique in automating the land-mark annotation process, which is tedious and time consuming. This method leads to explainable machine learning feature representations, which lead to more robust emotion recognition models.