Enhanced Detection Efficiency Research Articles

Exploiting Drone Images for Forest Fire Detection using Metaheuristics with Deep Learning Model

<p>Forest fires are a global natural calamity causing significant economic damage and loss of lives. Professionals forecast that forest fires would raise in the future because of climate change. Early prediction and identification of fire spread would enhance firefighting and reduce affected zones. Several systems have been advanced to detect fire. In recent times, Unmanned Aerial Vehicles (UAVs) are used for tackling this issue because of their ability, high flexibility, and their cheap price to cover vast areas during the nighttime or daytime. But still they are limited by difficulties like image degradation, small fire size, and background complexity. This study develops an automated Forest Fire Detection using Metaheuristics with Deep Learning (FFDMDL-DI) model. The presented FFDMDL-DI technique exploits the DL concepts on drone images to identify the occurrence of fire. To accomplish this, the FFDMDL-DI technique makes use of the Capsule Network (CapNet) model for feature extraction purposes with a biogeography-based optimization (BBO) algorithm-based hyperparameter optimizer. For accurate forest fire detection, the FFDMDL-DI technique uses a unified deep neural network (DNN) model. Finally, the tree growth optimization (TGO) technique is utilized for the parameter adjustment of the DNN method. To depict the enhanced detection efficiency of the FFDMDL-DI approach, a series of simulations were performed. The outcomes reported improvements in the FFDMDL-DI method over other DL models.</p>

Global and Local Context-Aware Ship Detector for High-Resolution SAR Images

Due to the large sizes of synthetic aperture radar (SAR) images, traditional deep learning-based ship detection methods usually utilize the sliding window preprocessing strategy to obtain the small-sized sub-images. However, there are amounts of background clutter areas without ships in SAR images. Thus, traditional sliding window-based methods may generate numerous sub-images without ships, which can bring high computation redundancy and numerous false alarms. To deal with the above problems, in this paper, a novel detection method called global and local context-aware ship detector (GLC-Det) for high-resolution SAR images is proposed. The proposed method mainly contains three parts: the global context-aware based sub-images selection (GCSS) module, the deep learning module, and the local context-aware based false alarms suppression (LCFS) module. The GCSS module employs the global context information to eliminate the sub-images without ships, which can enhance detection efficiency and avoid generating numerous false alarms. The deep learning module is used to further obtain the preliminary detection boxes. The LCFS module is a postprocessing step, which employs the local context information around the detection boxes to further eliminate the false alarms. The experimental results on the measured data of AIR-SARShip-1.0 and 2.0 high-resolution SAR images demonstrate that the proposed method has higher precision and efficiency than the original deep learning methods.

Portrait of intense communications within microfluidic neural networks

In vitro model networks could provide cellular models of physiological relevance to reproduce and investigate the basic function of neural circuits on a chip in the laboratory. Several tools and methods have been developed since the past decade to build neural networks on a chip; among them, microfluidic circuits appear to be a highly promising approach. One of the numerous advantages of this approach is that it preserves stable somatic and axonal compartments over time due to physical barriers that prevent the soma from exploring undesired areas and guide neurites along defined pathways. As a result, neuron compartments can be identified and isolated, and their interconnectivity can be modulated to build a topological neural network (NN). Here, we have assessed the extent to which the confinement imposed by the microfluidic environment can impact cell development and shape NN activity. Toward that aim, microelectrode arrays have enabled the monitoring of the short- and mid-term evolution of neuron activation over the culture period at specific locations in organized (microfluidic) and random (control) networks. In particular, we have assessed the spike and burst rate, as well as the correlations between the extracted spike trains over the first stages of maturation. This study enabled us to observe intense neurite communications that would have been weaker and more delayed within random networks; the spiking rate, burst and correlations being reinforced over time in terms of number and amplitude, exceeding the electrophysiological features of standard cultures. Beyond the enhanced detection efficiency that was expected from the microfluidic channels, the confinement of cells seems to reinforce neural communications and cell development throughout the network.

Adaptive dynamic inferential analytic stationary subspace analysis: A novel method for fault detection in blast furnace ironmaking process

Detecting faults in blast furnace ironmaking process (BFIP) remains a challenging task due to the hybrid properties involving dynamics and nonstationarity. To address this problem, this paper develops a novel method called adaptive dynamic interpretable analytic stationary subspace analysis (DiASSA). The method employs an inferential observation decomposition strategy to distinguish dynamic, static, and nonstationary components from BFIP data. It then implements an iterative modeling algorithm to estimate dynamic consistent features within a closed region and effectively isolates the dynamics and statics. The static part is further modeled by ordinary analytic stationary subspace analysis (ASSA) to construct static consistent features and eliminate the interference of nonstationary information. Moreover, an adaptive fault detection strategy is developed, using exponentially weighted statistic structures and adaptive threshold settings to enhance detection efficiency and robustness. Theoretical investigations and case studies confirm the advantages of the proposed method over traditional methods.

Detection of the Pin Defects of Power Transmission Lines Based on Improved TPH-MobileNetv3

Pins are essential connecting components in power transmission lines. Their extensive use yet leads to frequent defects. Given the small size of a pin and many similar components, the detection of such defects is not ideal, which is a technological problem in the identification and diagnosis of power defects. In response to the large size, complex background, and on-site requirements, such as real-time detection, of power transmission lines, this paper proposes a method to detect pin defects based on TPH-MobileNetv3 (Transformer prediction Head Mobilenetv3). This paper modifies and adds a self-attention layer to MobilNetV3-Small to improve the feature extraction capability of small targets after downsampling. A feature fusion structure with layers of self-attention and a convolutional block attention module (CBAM) is added to the neck network, and a transformer prediction head are added to the head network so that different scale characteristics can be fused and focused from space and channels to strengthen the detection of small targets. Compared with the traditional MobileNetV3, the detection accuracy of the algorithm in this paper has been raised by 24%, as shown in the detection results of measured data. Moreover, compared with the mainstream algorithms with the same detection accuracy, this algorithm not only reduces the model size and significantly enhances detection efficiency but also satisfies the requirement of edge image processing of power inspection.

Advancing in situ single-cell microbiological analysis through a microwell droplet array with a gradual open sidewall.

The utilization of microfluidic analysis technology has resulted in the advancement of fast pathogenic bacteria detection, which can accurately provide information on biochemical reactions in a single cell and enhance detection efficiency. Nevertheless, the achievement of rapid and effective in situ detection of single-bacteria arrays remains a challenge due to the complexity of bacterial populations and low Reynolds coefficient fluid, resulting in insufficient diffusion. We develop microwell droplet array chips from the lateral hydrodynamic wetting approach to address this issue. The sidewall of the microwell gradually opens which aids in advancing the liquid-air interface and facilitates the impregnation of the solid microwells, preserving the Wenzel state and assisting in resisting the liquid force to separation from the drop. The feasibility of preparing cell arrays and identifying them inside the microwells was demonstrated through the simulated streamlined distribution of gradual and traditional microwells with different sizes. The water-based ink diffusion experiment examined the relationship between diffusion efficiency and flow velocity, as well as the position of the microwell relative to the channel. It showed that the smaller gradual microwell still has a good diffusion efficiency rate at a flow velocity of 2.1 μL min-1 and that the infiltration state is easier to adjust. With this platform, we successfully isolated a mixed population containing E. coli and S. aureus, obtained single-bacteria arrays, and performed Gram assays after in situ propagation. After 20 hours of culture, single bacteria reproduced demonstrating the capability of this platform to isolate, cultivate, and detect pathogenic bacteria.

Icing wind tunnel measurements of supercooled large droplets using the 12 mm total water content cone of the Nevzorov probe

Abstract. Supercooled large droplet (SLD) icing can occur behind the protected surfaces of an aircraft and create severe aerodynamic disturbances, which represent a safety hazard for aviation. Liquid water content (LWC) measurements in icing conditions that contain SLDs require instruments that are able to sample unimodal and bimodal droplet size distributions with droplet diameters from 2 to 2000 µm. No standardized detection method exists for this task. A candidate instrument, which is currently used in icing wind tunnel (IWT) research, is the Nevzorov probe. In addition to the standard 8 mm total water content (TWC) collector cone, a novel instrument version also features a 12 mm diameter cone, which might be advantageous for collecting the large droplets characteristic of SLD conditions. In the scope of the two EU projects, SENSors and certifiable hybrid architectures for safer aviation in ICing Environment (SENS4ICE) and ICE GENESIS, we performed measurement campaigns in SLD icing conditions in IWTs in Germany, Austria and the USA. We obtained a comprehensive data set of measurements from the LWC sensor, the 8 mm cone sensor and the 12 mm cone sensor of the Nevzorov probe, and from the tunnel reference instrumentation. In combination with measurements of the particle size distribution, we experimentally derive a collision efficiency curve that is based on a suitable functional form for the new 12 mm cone for median volume diameters (MVDs) between 12 and 58 µm and wind tunnel speeds from 40 to 85 m s−1. Knowledge of this curve allows us to correct the LWC measurements of the 12 mm cone (LWC12) in particular for the inevitably high decrease in collision efficiency for small droplet diameters. In unimodal SLD conditions, with MVDs between 128 and 720 µm, LWC12 generally agrees within ±20 % with the tunnel LWC reference values from a WCM-2000 and an isokinetic probe. An increase in the difference between LWC12 and the WCM-2000 measurements at larger MVDs indicates better droplet collection properties of the 12 mm cone. Similarly, the favorable detector dimensions of the 12 mm cone explain a 7 % enhanced detection efficiency compared to the 8 mm cone; however this difference falls within the instrumental uncertainties. Data collected in various bimodal SLD conditions with MVDs between 16 and 534 µm and LWCs between 0.22 and 0.72 g m−3 also show an agreement within ±20 % between LWC12 and the tunnel LWC, which demonstrates the suitability of the Nevzorov sensor head with the 12 mm cone for measurements of LWC in Appendix O icing conditions.

Convolutional neural networks (CNNs)-based multi-category damage detection and recognition of high-speed rail (HSR) reinforced concrete (RC) bridges using test images

The fast networking of high-speed rail (HSR) may cause in-service fatigue and ultimate load damage to bridges. This paper investigates the application of deep convolutional neural networks (CNNs) for multi-category damage image classification recognition of HSR-reinforced concrete (RC) bridges. The present study establishes a deep learning (DL) system based on a large amount of HSR bridge test data. When to begin, the damage done to HSR bridge piers may be broken down into three primary categories: concrete cracks, concrete spalling, and reinforcement exposure. These categories are determined by the statistics of HSR bridge pier testing. Secondly, in order to develop an automated recognition model for the damage of HSR piers, AlexNet CNNs were taught a transfer learning approach and then used to train themselves. The correct recognition rate of the three damaged pictures in the actual application of the model is 86% for cracks, 82% for reinforcement exposure, and 70% for concrete spalling, all of which have good recognition rates. The study's accuracy and precision enhance detection efficiency and may be utilized to identify HSR pier deterioration quickly. The research comprises a random selection from the training and validation sets. It also assesses the training model's generalization to out-of-sample pictures for engineering applications. This aspect of the work sets it apart from previous research in the same study area.

Glycerol Additive Boosts 100-fold Sensitivity Enhancement for One-Pot RPA-CRISPR/Cas12a Assay.

CRISPR/Cas12, a highly efficient and specific nucleic acid recognition system, has been broadly employed to detect amplified DNA products. However, most reported methods adopt a two-step detection mode that needs a liquid transfer step, thus complicating the detection procedure and posing a risk of aerosol contamination. A one-pot detection method can obviate these problems, but it suffers from poor detection efficiency due to the loss of amplification templates elicited by CRISPR/Cas12 cleavage. In this study, we discovered that a glycerol additive dramatically promoted the detection efficiency of the one-pot recombinase polymerase amplification (RPA)-CRISPR/Cas12a method. Compared with the glycerol-free version, its sensitivity was nearly 100-fold higher and was close to that of the canonical two-step method. Further investigation displayed that the enhanced detection efficiency was attributed to the phase separation of the RPA and CRISPR/Cas12a system during the initial phase of the RPA reaction caused by the glycerol viscosity. This highly efficient one-pot method has been triumphantly harnessed for the detection of African swine fever virus (ASFV) and SARS-CoV-2, achieving naked-eye readout through a smartphone-equipped device. The currently developed glycerol-enhanced one-pot RPA-CRISPR/Cas12a method can be an advantageous point-of-care nucleic acid detection platform on account of its simplicity, high sensitivity, and universality.

Cat Swarm Optimization-Based Computer-Aided Diagnosis Model for Lung Cancer Classification in Computed Tomography Images

Lung cancer is the most significant cancer that heavily contributes to cancer-related mortality rate, due to its violent nature and late diagnosis at advanced stages. Early identification of lung cancer is essential for improving the survival rate. Various imaging modalities, including X-rays and computed tomography (CT) scans, are employed to diagnose lung cancer. Computer-aided diagnosis (CAD) models are necessary for minimizing the burden upon radiologists and enhancing detection efficiency. Currently, computer vision (CV) and deep learning (DL) models are employed to detect and classify the lung cancer in a precise manner. In this background, the current study presents a cat swarm optimization-based computer-aided diagnosis model for lung cancer classification (CSO-CADLCC) model. The proposed CHO-CADLCC technique initially pre-process the data using the Gabor filtering-based noise removal technique. Furthermore, feature extraction of the pre-processed images is performed with the help of NASNetLarge model. This model is followed by the CSO algorithm with weighted extreme learning machine (WELM) model, which is exploited for lung nodule classification. Finally, the CSO algorithm is utilized for optimal parameter tuning of the WELM model, resulting in an improved classification performance. The experimental validation of the proposed CSO-CADLCC technique was conducted against a benchmark dataset, and the results were assessed under several aspects. The experimental outcomes established the promising performance of the CSO-CADLCC approach over recent approaches under different measures.

A Study of the Detection of SARS-CoV-2 ORF1ab Gene by the Use of Electrochemiluminescent Biosensor Based on Dual-Probe Hybridization.

To satisfy the need to develop highly sensitive methods for detecting the severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) and further enhance detection efficiency and capability, a new method was created for detecting SARS-CoV-2 of the open reading frames 1ab (ORF1ab) target gene by a electrochemiluminescence (ECL) biosensor based on dual-probe hybridization through the use of a detection model of “magnetic capture probes—targeted nucleic acids—Ru(bpy)32+ labeled signal probes”. The detection model used magnetic particles coupled with a biotin-labeled complementary nucleic acid sequence of the SARS-CoV-2 ORF1ab target gene as the magnetic capture probes and Ru(bpy)32+ labeled amino modified another complementary nucleic acid sequence as the signal probes, which combined the advantages of the highly specific dual-probe hybridization and highly sensitive ECL biosensor technology. In the range of 0.1 fM~10 µM, the method made possible rapid and sensitive detection of the ORF1ab gene of the SARS-CoV-2 within 30 min, and the limit of detection (LOD) was 0.1 fM. The method can also meet the analytical requirements for simulated samples such as saliva and urine with the definite advantages of a simple operation without nucleic acid amplification, high sensitivity, reasonable reproducibility, and anti-interference solid abilities, expounding a new way for efficient and sensitive detection of SARS-CoV-2.

An inimitable and ecological pleasant technique for the assessment of trace amount of copper (II) in tangible samples with new complexing reagent

A simple and rapid spectrophotometric technique has been designed for the trace copper analysis employing 1-(2-Thiazolylazo)-2-naphthol (TAN) reagent in aqueous micellar solution of cetyl trimethylammonium bromide (CTAB) as a surfactant. Copper complexed with 1-(2-Thiazolylazo)-2-naphthol to form bis[1-(2-Thiazolylazo)-2-naphthol]copper. The present spectrophotometric technique was very important since the micellar system was used in place of the toxic, high cost and time-consuming solvent extraction steps. The technique showed an enhanced detection efficiency, specificity, and molar absorptivity. It was found that the molar absorption coefficient and sensitivity of Sandel were ε 2.45 × 104 L mol−1cm−1 and 2.6 ngcm−2 at λmax 578.4 nm. A linear calibration plot in the range 0.12–5.0 μg mL−1 was obtained; a stoichiometric metal ligand ratio [M:L] of 1:2 was found for the formation of Cu-[TAN]2. The complex was formed at pH 9.5 and was stable up to 24 h. The proposed technique has been employed to study copper from different alloys, biological, environmental and pharmaceutical samples.

Simple but effective: strong efficiency boost for a linear variable filter-based spectrometer

A method to drastically enhance detection efficiency of a linear variable filter (LVF) sensor across an extended and continuous wavelength range is presented. The efficiency is increased by a wavelength preselection concept, where the incoming light is divided into partial spectra to reduce otherwise unavoidable reflection losses of filter-based spectrometers. The simple but effective setup uses selected and successively arranged dichroic beamsplitters, which ensures an optimized compromise between efficiency enhancement and minimum increasing complexity. When connected to a two-dimensional camera and combined with a tilted LVF, this compact optical system allows the continuous recording of the full wavelength range between 450 and 850 nm with a resolution of ∼19 nm at 508.6 nm. An efficiency enhancement factor of up to 5.7 is achieved in comparison to a conventional LVF setup. The working principle was verified by measuring the reflection spectra of different natural and artificial green leaves. The proposed approach for increasing the efficiency can be miniaturized and applied to a broad range of other filter-based sensors.

2.5D microscopy with polarization independent SLM for enhanced detection efficiency and aberration correction.

Fast, volumetric imaging by fluorescence microscopy is essential in studying biological phenomena and cellular functions. Recently, single-shot 2.5D microscopy showed promising results for high-throughput quantitative subcellular analysis via extended depth of field imaging without sequential z-scanning; however, the detection efficiency was limited and it lacked depth-induced aberration correction. Here we report that a spatial light modulator (SLM) in a polarization insensitive configuration can significantly improve the detection efficiency of 2.5D microscopy, while also compensating for aberrations at large imaging depths caused by the refractive index mismatch between the sample and the immersion medium. We highlight the improved efficiency via quantitative single-molecule RNA imaging of mammalian cells with a 2-fold improvement in the fluorescence intensity compared to a conventional SLM-based microscopy. We demonstrate the aberration correction capabilities and extended depth of field by imaging thick specimens with fewer z-scanning steps.

SPAD-based asynchronous-readout array detectors for image-scanning microscopy

Fluorescence microscopy and derived techniques are continuously looking for photodetectors able to guarantee increased sensitivity, high spatial and temporal resolution, and ease of integration into modern microscopy architectures. Recent advances in single-photon avalanche diodes (SPADs) fabricated with industry-standard microelectronic processes allow the development of new detection systems tailored to address the requirements of advanced imaging techniques (such as image-scanning microscopy). To this aim, we present the complete design and characterization of two bidimensional SPAD arrays composed of 25 fully independent and asynchronously operated pixels, both having fill factor of about 50% and specifically designed for being integrated into existing laser scanning microscopes. We used two different microelectronics technologies to fabricate our detectors: the first technology exhibiting very low noise (roughly 200 dark counts per second at room temperature) and the second one showing enhanced detection efficiency (more than 60% at a wavelength of 500 nm). Starting from the silicon-level device structures and moving towards the in-pixel and readout electronics description, we present performance assessments and comparisons between the two detectors. Images of a biological sample acquired after their integration into our custom image-scanning microscope finally demonstrate their exquisite on-field performance in terms of spatial resolution and contrast enhancement. We envisage that this work can trigger the development of a new class of SPAD-based detector arrays able to substitute the typical single-element sensor used in fluorescence laser scanning microscopy.

Detection properties of photoconductive antennas fabricated on low-temperature-grown GaAs and ErAs:GaAs at subterahertz band

Terahertz (THz) spectroscopy with high sensitivity is essential for biological application considering the strong absorption and scattering effects therein. As the most commonly used THz detector, the photoconductive antenna’s (PCA) response greatly relies on the properties of the substrate’s material. THz detection properties of the PCAs fabricated on low-temperature-grown GaAs (LT-GaAs) and ErAs:GaAs superlattices were compared at the sub-THz band. The detection efficiency of the PCAs with regard to incident laser power was characterized. In addition, using the PCAs as detectors, the signal-to-noise ratio (SNR) and dynamic range (DR) of a terahertz time-domain spectroscopy were quantified. The result indicates that the PCA detector with LT-GaAs has higher efficiency than the one with ErAs:GaAs. Consequently, the corresponding THz spectrometer has better SNR and DR. This result is contrary to the previous report, in which enhanced detection efficiency was observed with ErAs:GaAs-based PCA, which is probably due to the different structures of ErAs:GaAs superlattices used in the experiment.

Analytical model of DOI-induced time bias in ultra-fast scintillation detectors for TOF-PET

In positron emission tomography (PET), long crystals (20 mm) are used to enhance detection efficiency and increase scanner sensitivity. However, for fast time-of-flight (TOF) scanners, this may affect the achievable coincidence time resolution (CTR) due to depth-of-interaction (DOI) induced blur on timing. Currently, the effect of DOI on CTR evaluation with analytical modeling is incorporated using the probability density function (PDF) for attenuation of the annihilation photons with the PDFs of the other scintillation processes. However, we show that the resulting PDF would not describe accurately the variation in timestamps distribution at different DOIs. We propose a new analytical model for the CTR evaluation, which consists of computing a DOI dependent CTR weighted by the DOI probability in coincidence. The CTR was thus defined as the weighted root-mean-square error (RMSE) of the DOI-wise variance and bias in order to explicitly describe the positioning bias induced by coincident annihilation photons at different DOIs. The effect of DOI bias on CTR was investigated by using four classic estimators found in the literature, each applied on contemporary scintillation detectors and nearly ideal detectors. A limited difference in the calculated CTR was found for typical scintillation detectors when assessing RMSE with and without DOI time offset correction. This was expected since the DOI bias remains negligible against other phenomena in such case. However, the difference becomes significant for nearly ideal scintillation detectors, where optimal CTR would only be attainable with DOI correction. For these nearly ideal cases, the revised model has better predictive power since the DOI time offset correction is included. Investigation with analytical approaches for realistically achievable ultra-fast CTR in TOF-PET detectors should be performed with a model that genuinely takes into account the DOI effect. We show that the proposed model is a valid candidate for such a task.

Improved Viola-Jones face detection algorithm based on HoloLens

The current face detection in Microsoft HoloLens can only be achieved by remote call of face detection interface algorithm which is, however, restricted by network, resulting in slow detection and failing to meet real-time detection demand. This paper proposes an improved Viola-Jones algorithm of face detection based on HoloLens upgrading classical Viola-Jones face detection algorithm relying on Haar-like rectangle feature expansion to enhance detection efficiency, and accelerating detection building on two-dimensional convolution separation and image re-sampling technique. The detection efficiency of improved face detection algorithm is 12% on average higher than that of existing face detection interface algorithm, and its detection speed is four-folded. Moreover, HoloLens depth camera enables 3D face detection and location, and its unique gaze, voice, and gesture interacting techniques free the hands, thereby realizing easier and less-burdened man-computer interaction. HoloLens furnished with real-time video face detection algorithm as detailed in this paper can be applied in such fields as social contact, public security, and business management.

Copy-Move Forgeries Detection and Localization Using Two Levels of Keypoints Extraction

Copy-move offense is considerably used to conceal or hide several data in the digital image for specific aim, and onto this offense some portion of the genuine image is reduplicated and pasted in the same image. Therefore, Copy-Move forgery is a very significant problem and active research area to check the confirmation of the image. In this paper, a system for Copy Move Forgery detection is proposed. The proposed system is composed of two stages: one is called the detection stages and the second is called the refine detection stage. The detection stage is executed using Speeded-Up Robust Feature (SURF) and Binary Robust Invariant Scalable Keypoints (BRISK) for feature detection and in the refine detection stage, image registration using non-linear transformation is used to enhance detection efficiency. Initially, the genuine image is picked, and then both SURF and BRISK feature extractions are used in parallel to detect the interest keypoints. This gives an appropriate number of interest points and gives the assurance for finding the majority of the manipulated regions. RANSAC is employed to find the superior group of matches to differentiate the manipulated parts. Then, non-linear transformation between the best-matched sets from both extraction features is used as an optimization to get the best-matched set and detect the copied regions. A number of numerical experiments performed using many benchmark datasets such as, the CASIA v2.0, MICC-220, MICC-F600 and MICC-F2000 datasets. With the proposed algorithm, an overall average detection accuracy of 95.33% is obtained for evaluation carried out with the aforementioned databases. Forgery detection achieved True Positive Rate of 97.4% for tampered images with object translation, different degree of rotation and enlargement. Thus, results from different datasets have been set, proving that the proposed algorithm can individuate the altered areas, with high reliability and dealing with multiple cloning.

A novel integrated microfluidic platform based on micro-magnetic sensor for magnetic bead manipulation and detection

We present a novel integrated microfluidic platform based on micro-magnetic sensor for manipulating and detecting magnetic beads (MB). A micro-spiral planar coil in MB manipulating system microfabricated by micro-electro-mechanical system technology is implemented to manipulate MB, and a giant magnetoimpedance (GMI) based micro-magnetic sensor is employed to detect the trapped MB. In our work, MB can be efficiently trapped by trapping force generated from micro-coil in microchannel. Next, trapped MB are detected by the changing ratio of impedance, as well as the variation of resistance and reactance in GMI sensor for trapped MB induce weak stray magnetic field under the magnetization by external magnetic field. The maximum difference of GMI ratio between with beads condition and without beads condition is 4.0% at the optimum driving frequency of 20 MHz under the external magnetic field of 15 Oe, and resistance ratio varies more significantly than reactance ratio. In comparison with traditional MB detecting methods by GMI sensor, the integrated microfluidic platform based on GMI sensor can not only manipulate and detect MB signal sensitively, but also enhance detection efficiency and decrease the experiment errors. Furthermore, this platform avoids contamination from the solutions in chemically reactive layers and reduces assay time in future biomarker detection. In our work, the microfluidic platform based on GMI sensor has potential applications in biomarker detection via MB manipulation and detection.