Deep Targets Research Articles

High-precision real-time UAV target recognition based on improved YOLOv4

In recent years, unmanned aerial vehicles (UAVs) have gained widespread use in both military and civilian fields with the advancement of aviation technology and improved communication capabilities. However, the phenomenon of unauthorized UAV flights, or “black flying”, poses a serious threat to the safe flight of aircraft in airspace and public safety. To effectively interfere with and attack UAV targets, it is crucial to enhance the detection and identification of “low, slow and small” UAVs. This study focuses on achieving high-precision and lightweight detection and identification of four-rotor, six-rotor, and fixed-wing UAVs in low-altitude complex environments. By combining deep learning target detection with superresolution feature enhancement, a lightweight UAV detection model is designed and field-tested for verification. To address the challenge of detecting small UAV targets with limited information, the feature fusion network is enhanced based on the traditional YOLOv4 algorithm to improve the detection ability of small targets via small target enhancement and candidate box adjustment. The feasibility of the improved network is quantitatively and qualitatively analyzed. Channel pruning and layer pruning are then applied to the network, significantly reducing its depth and width and realizing a lightweight network. Finally, reasoning quantification is conducted on the embedded platform to enable end-side deployment of the target detection algorithm.

Deep Brain Stimulation of the Subthalamic Nucleus in a Patient With X-Linked Dystonia-Parkinsonism. (P11-11.001)

<h3>Objective:</h3> N/A <h3>Background:</h3> X-linked dystonia-parkinsonism (XDP) is one of the genetic causes of generalized dystonia. Both dystonia and parkinsonism components of the disease are frequently resistant to pharmacologic treatment. Deep brain stimulation (DBS) of the globus pallidus pars interna (GPi) is an effective treatment modality, especially for dystonic manifestations of XDP. The subthalamic nucleus (STN) is a known DBS target in Parkinson disease but it is less frequently used for treatment of dystonia. In our case report we describe a patient with XDP who underwent bilateral STN DBS with notable improvement in parkinsonism and dystonia. <h3>Design/Methods:</h3> N/A <h3>Results:</h3> Our patient is a right-handed Filipino man from the island of Panay. He developed bilateral parkinsonism, blepharospasm, oromandibular and cervical dystonia at the age of 51. Diagnosis of XDP was confirmed with genetic testing. Marked improvement of Unified Parkinson Disease Rating Scale (UPDRS) motor score in response to levodopa administration was demonstrated (65 off and 36 on). His pre-DBS Burke-Fahn-Marsden Dystonia Rating Scale (BFMDRS) was 27.5. Bilateral GPi were initially selected as a target for DBS lead placement based on previously published data. Surgical target was subsequently changed to bilateral STN due to distortion in GPi anatomy likely secondary to long-standing disease. Medtronic Percept PC neurostimulator with Sensight DBS leads were used. There was no surgical complications. Patient had an immediate improvement in tremor, bradykinesia and rigidity after his first programming visit; antidystonic effects of stimulation became evident over the next few weeks. There was substantial improvement in limb and oromandibular dystonia and mild effect on cervical dystonia and blepharospasm. His speech clarity became better as well. His motor UPDRS and BFMDRS decreased to 21 and 19, respectively. Gait, posture, ability to perform activities of daily living significantly improved. <h3>Conclusions:</h3> The subthalamic nucleus may be considered an alternative deep brain stimulation target in patients with X-linked dystonia-parkinsonism. <b>Disclosure:</b> Dr. Redko has nothing to disclose. Brian Kopell has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Medtronic. Brian Kopell has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Abbott Neuromodulation. Brian Kopell has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Enspire DBS. Dr. Tse has nothing to disclose.

Ictal Thalamic Recordings in Patients with Deep Brain Stimulation Targeting Thalamic NucleiIdentify whether ictal thalamic EEG signals could be derived from ambulatory recordings in patients with pharmacoresistant epilepsy treated with deep brain stimulation (DBS) targeting either bilateral anterior thalamic nuclei (ATN) or centromedian nuclei (CMN). (P5-1.008)

<h3>Objective:</h3> Identify whether ictal thalamic EEG signals could be derived from ambulatory recordings in patients with pharmacoresistant epilepsy treated with deep brain stimulation (DBS) targeting bilateral anterior thalamic nuclei (ATN) or centromedian nuclei (CMN). <h3>Background:</h3> The DBS system is one modality that can target thalamic nuclei for neuromodulation. The most recently available model features the capability to record live streamed intracranial EEG (local field potentials, or LFP). <h3>Design/Methods:</h3> We selected four patients who had habitual electroclinical and electrographic seizures during live streaming (based on the simultaneous scalp EEG). All the devices were Percept^™ PC (by Medtronic^®), utilizing the BrainSense^® feature to record bipolar LFP signals between two contacts of each of the bilateral four-contact leads. LFP time series were extracted using MATLAB and exported as EEG for review and visualization. <h3>Results:</h3> Three patients were adults (mean age 43, median age 37), and one was a child (10 years). Two had generalized forms of epilepsy (acquired Lennox-Gastaut Syndrome due to diffuse bilateral polymicrogyria; generalized non-lesional epilepsy characterized by absence and myoclonic seizures). One patient had unilateral hemispheric epilepsy due to dual pathology (adult-onset Rasmussen’s encephalitis and focal cortical dysplasia) and prior frontal topectomy. The last patient presented with non-lesional multifocal epilepsy and a history of left parietal topectomy. The DBS for two types of generalized epilepsy targeted bilateral CMN, while the other two targeted bilateral ATN. Generalized ictal patterns involving the four contacts of both thalamic nuclei have been identified as ictal patterns. In contrast, in hemispheric or multifocal epilepsies, only unilateral thalamic nuclei exhibited ictal EEG changes. Ictal EEG alterations consisted of a combination of rhythmic activity and sharp waves or rhythmic spiking activity. Our figures depict the ictal thalamic recordings with the corresponding ictal thalamic waves. <h3>Conclusions:</h3> Our observations call for a more systematic investigation of ictal thalamic signature in various types of epilepsy. <b>Disclosure:</b> Miss Saab has nothing to disclose. Ms. Jiang has nothing to disclose. The institution of Dr. Quraishi has received research support from NeuroPace. The institution of Dr. Quraishi has received research support from Biogen. The institution of Dr. Quraishi has received research support from Praxis Precision Medicines. Dr. Herlopian has nothing to disclose.

Ensemble scenario‐based inversion: A new approach for estimating the uncertainty of resistivity models derived from 3D controlled source electromagnetic data

AbstractNon‐linear inversion of controlled source electromagnetic data is non‐unique. Inversion ambiguity and uncertainty grow with model complexity and limitations in sensitivity, for example when imaging deep targets. Uncertainties should be estimated. The best way to do that is by statistical inversion techniques. Because of the large number of parameters of 3D models, these methods are too costly for 3D applications. But neglecting or underestimating uncertainties often leads to erroneous interpretation and poor exploration decisions. The number of inversion parameters can be dramatically reduced while still being able to describe a complex 3D subsurface. To obtain that, I represent prior information by an input ensemble of geologically reasonable prior models. The model space is defined by the principal directions of this ensemble, where the inversion parameters are the coefficients of the different components. In this model space, inversion becomes much more efficient and can produce an updated ensemble of posterior models at the same computational cost as a controlled‐source electromagnetic inversion project using conventional non‐linear inversion techniques. I present examples where unique Gauss–Newton inversions lead to difficult interpretations and poor conclusions about hydrocarbon presence and saturation. The new approach provides a quantitative estimation of resistivity ambiguities and uncertainties leading to better interpretation and safer decisions. The examples use 2D synthetic controlled‐source electromagnetic data and 3D controlled‐source electromagnetic field data.

Sustained modulation of primate deep brain circuits with focused ultrasonic waves

BackgroundTranscranial focused ultrasound has the potential to noninvasively modulate deep brain circuits and impart sustained, neuroplastic effects. ObjectiveBring the approach closer to translations by demonstrating sustained modulation of deep brain circuits and choice behavior in task-performing non-human primates. MethodsLow-intensity transcranial ultrasound of 30 s in duration was delivered in a controlled manner into deep brain targets (left or right lateral geniculate nucleus; LGN) of non-human primates while the subjects decided whether a left or a right visual target appeared first. While the animals performed the task, we recorded intracranial EEG from occipital screws. The ultrasound was delivered into the deep brain targets daily for a period of more than 6 months. ResultsThe brief stimulation induced effects on choice behavior that persisted up to 15 minutes and were specific to the sonicated target. Stimulation of the left/right LGN increased the proportion of rightward/leftward choices. These effects were accompanied by an increase in gamma activity over visual cortex. The contralateral effect on choice behavior and the increase in gamma, compared to sham stimulation, suggest that the stimulation excited the target neural circuits. There were no detrimental effects on the animals' discrimination performance over the months-long course of the stimulation. ConclusionThis study demonstrates that brief, 30-s ultrasonic stimulation induces neuroplastic effects specifically in the target deep brain circuits, and that the stimulation can be applied daily without detrimental effects. These findings encourage repeated applications of transcranial ultrasound to malfunctioning deep brain circuits in humans with the goal of providing a durable therapeutic reset.

153 Utilizing a 32-Channel System for Treatment of Complex Movement Disorders: Initial Case Series

INTRODUCTION: Complex, mixed movement disorders affecting multiple pathways (e.g., Holme’s Tremor (HT) or comorbid essential tremor (ET) with dystonia, among others) represent significant challenges for surgical treatment. These disease states are likely the result of combined or complex network pathologies, requiring multi-nodal targeting for DBS. METHODS: Multiple simultaneous deep targets were implanted using four 8-contact, directional leads placed through 2 burr-holes, which were connected to a 32-channel pulse generator. Targets were chosen based on disorders and comorbidities. RESULTS: Seven complex movement disorder patients were operated on at Stanford University using the approach described above. All seven patients in the series reported significant improvement in symptoms, and four patients also had objective metrics recorded demonstrating significant improvements. In these four patients, patient A presented with DBS-refractory Parkinsonian tremor and showed additional 17% reduction in UPDRS after addition of a third lead from an existing burr hole, utilizing the 32-channel system. Similarly patient C with HT and patients D and E with ET/dystonia all demonstrated significant improvement in TRS (p &lt; 0.01) and dystonic symptoms after bilateral dual targeting of VIM and GPi through two burr-holes. Programming utilized tailored fractionation and stimulation parameters to achieve optimal results. CONCLUSIONS: We present the largest initial case series demonstrating the feasibility of a 32-channel multi-target DBS strategy for treating complex movement disorders. This approach warrants further investigation for treating complex, multi-circuit neuropsychiatric disorders.

Reduced-Parameter YOLO-like Object Detector Oriented to Resource-Constrained Platform

Deep learning-based target detectors are in demand for a wide range of applications, often in areas such as robotics and the automotive industry. The high computational requirements of deep learning severely limit its ability to be deployed on resource-constrained and energy-first devices. To address this problem, we propose a class YOLO target detection algorithm and deploy it to an FPGA platform. Based on the FPGA platform, we can make full use of its computational features of parallel computing, and the computational units such as convolution, pooling and Concat layers in the model can be accelerated for inference.To enable our algorithm to run efficiently on FPGAs, we quantized the model and wrote the corresponding hardware operators based on the model units. The proposed object detection accelerator has been implemented and verified on the Xilinx ZYNQ platform. Experimental results show that the detection accuracy of the algorithm model is comparable to that of common algorithms, and the power consumption is much lower than that of the CPU and GPU. After deployment, the accelerator has a fast inference speed and is suitable for deployment on mobile devices to detect the surrounding environment.

Potential drilling hazards for wells targeting the Cane Creek shale, Pennsylvanian Paradox Formation, Paradox fold and fault belt, southeastern Utah and southwestern Colorado

The Cane Creek shale of the Pennsylvanian Paradox Formation represents a major target for oil and gas in the Paradox fold and fault belt of the northern Paradox Basin of southeastern Utah and southwestern Colorado. Early exploration and development attempts resulted in blowouts due to unexpected gas-bearing intervals and casing collapses caused by salt flowage in the Paradox Formation. These problems represent some of the types of drilling hazards that could be expected when planning Cane Creek wells. Horizontal drilling first used in the early 1990s changed the Cane Creek shale play from one of mostly drilling failures to a more successful commercial play. Depending on the location, exploratory Cane Creek wells may penetrate a section that ranges in age from Cretaceous through Pennsylvanian. Drilling in the region often encounters a wide variety of lithologies (carbonates, shale, mudstone, sandstone, and evaporites) and associated potential hazards that may include: (1) swelling clays, (2) high porosity-permeability or fractured zones resulting in lost circulation or excessive mudcake buildup, (3) “kicks” due to the influx of reservoir fluid (oil, water, or gas) into the wellbore, (4) uranium-rich zones, (5) washouts, (6) hole deviation, sticking, and other well-integrity problems, (7) chert, and (8) overpressured intervals. In addition, natural carbon dioxide, which flows from the partially human-made Crystal Geyser near some Cane Creek wellsites, represents an unusual drilling hazard if encountered in the northernmost part of the fold and fault belt. Using the lessons learned from the recently completed research well, State 16-2 (renamed the State 16-2LN-CC, API No. 43-019-50089, after the horizontal leg was drilled), and other wells in the region, drilling engineers and operators can better plan for potential hazards when exploring for hydrocarbons in the Cane Creek shale or deeper targets (Mississippian Leadville Limestone and Devonian Elbert Formation) in the fairly remote, relatively sparsely explored Paradox fold and fault belt. The goal is to de-risk wells, lower expenses, and mitigate problems before they occur. The expected results are safer and more successful drilling of wells to the Cane Creek shale and deeper reservoirs ultimately leading to additional commercial hydrocarbon discoveries in the region.

Foreign Object Shading Detection in Photovoltaic Modules Based on Transfer Learning

As a representative new energy source, solar energy has the advantages of easy access to resources and low pollution. However, due to the uncertainty of the external environment, photovoltaic (PV) modules that collect solar energy are often covered by foreign objects in the environment such as leaves and bird droppings, resulting in a decrease in photoelectric conversion efficiency, power losses, and even the “hot spot” phenomenon, resulting in damage to the modules. Existing methods mostly inspect foreign objects manually, which not only incurs high labor costs but also hinders real-time monitoring. To address these problems, this paper proposes an IDETR deep learning target detection model based on Deformable DETR combined with transfer learning and a convolutional block attention module, which can identify foreign object shading on the surfaces of PV modules in actual operating environments. This study contributes to the optimal operation and maintenance of PV systems. In addition, this paper collects data in the field and constructs a dataset of foreign objects of PV modules. The results show that the advanced model can significantly improve the target detection AP values.

Localization of Lesion Cells and Targeted Mitochondria Via Embedded Hydrogel Microsphere using Heat Transfer Microneedles

AbstractThe localization of lesion cells and targeted regulation of organelle function can promote the lesion repair. However, conventional regulation is difficult to reach deep lesions and target mitochondria. In this study, dynamic spiral Mosaic technology is ued to construct heat transfer microneedles with spiral Mosaic micro/nano hydrogel microspheres (ST‐needle), using molecular chain motion in response to heat stimulation to regulate the adhesion of non‐oriented triblock polymer, as a dual delivery system for heat energy and biological factors. The ST‐needle system use its physical property to accurately reach the deep lesions and transfer heat to the lesion cells. Heat activates the dynamic spiral Mosaic mechanism of the ST‐needle system, removing the Mosaic state of hydrogel microspheres and realizing the arrival of heat and hydrogel microspheres into lesion together. Through the rapid inhibition of mitochondrial apoptosis by heat, and long‐term induce mitophagy by hydrogel microspheres releasing biological factors, finally complete the synergistic targeted regulation of mitochondrial function. In vitro/vivo experiments show that ST‐needle system can inhibit chondrocyte apoptosis more effectively (64.41% lower than conventional regulation). Based on dynamic spiral Mosaic technique and the synergistic regulation of heat and biological factors, the ST‐needle system is a promising method for lesion repair.

Comparing the effects of transcranial alternating current and temporal interference (tTIS) electric stimulation through whole-brain mapping of c-Fos immunoreactivity.

The analysis of the topography of brain neuromodulation following transcranial alternating current (AC) stimulation is relevant for defining strategies directed to specific nuclei stimulation in patients. Among the different procedures of AC stimulation, temporal interference (tTIS) is a novel method for non-invasive neuromodulation of specific deep brain targets. However, little information is currently available about its tissue effects and its activation topography in in vivo animal models. After a single session (30 min, 0.12 mA) of transcranial alternate current (2,000 Hz; ES/AC group) or tTIS (2,000/2,010 Hz; Es/tTIS group) stimulation, rat brains were explored by whole-brain mapping analysis of c-Fos immunostained serial sections. For this analysis, we used two mapping methods, namely density-to-color processed channels (independent component analysis (ICA) and graphical representation (MATLAB) of morphometrical and densitometrical values obtained by density threshold segmentation. In addition, to assess tissue effects, alternate serial sections were stained for glial fibrillary acidic protein (GFAP), ionized calcium-binding adapter molecule 1 (Iba1), and Nissl. AC stimulation induced a mild superficial increase in c-Fos immunoreactivity. However, tTIS stimulation globally decreased the number of c-Fos-positive neurons and increased blood brain barrier cell immunoreactivity. tTIS also had a stronger effect around the electrode placement area and preserved neuronal activation better in restricted areas of the deep brain (directional stimulation). The enhanced activation of intramural blood vessels' cells and perivascular astrocytes suggests that low-frequency interference (10 Hz) may also have a trophic effect.

Mechanisms underlying capsulotomy for refractory obsessive-compulsive disorder: neural correlates of negative affect processing overlap with deep brain stimulation targets

Ablative procedures such as anterior capsulotomy are potentially effective in refractory obsessive-compulsive disorder (OCD). Converging evidence suggests the ventral internal capsule white matter tracts traversing the rostral cingulate and ventrolateral prefrontal cortex and thalamus is the optimal target for clinical efficacy across multiple deep brain stimulation targets for OCD. Here we ask which prefrontal regions and underlying cognitive processes might be implicated in the effects of capsulotomy by using both task fMRI and neuropsychological tests assessing OCD-relevant cognitive mechanisms known to map across prefrontal regions connected to the tracts targeted in capsulotomy. We tested OCD patients at least 6 months post-capsulotomy (n = 27), OCD controls (n = 33) and healthy controls (n = 34). We used a modified aversive monetary incentive delay paradigm with negative imagery and a within session extinction trial. Post-capsulotomy OCD subjects showed improved OCD symptoms, disability and quality of life with no differences in mood or anxiety or cognitive task performance on executive, inhibition, memory and learning tasks. Task fMRI revealed post-capsulotomy decreases in the nucleus accumbens during negative anticipation, and in the left rostral cingulate and left inferior frontal cortex during negative feedback. Post-capsulotomy patients showed attenuated accumbens-rostral cingulate functional connectivity. Rostral cingulate activity mediated capsulotomy improvement on obsessions. These regions overlap with optimal white matter tracts observed across multiple stimulation targets for OCD and might provide insights into further optimizing neuromodulation approaches. Our findings also suggest that aversive processing theoretical mechanisms may link ablative, stimulation and psychological interventions.

Robot grasping system based on deep learning target detection

The traditional robot grasping system often uses fixed point grasping or demonstrative grasping, but with the increase in the diversity of grasping targets and the randomness of poses, the traditional grasping method is no longer sufficient. A robot grasping method based on deep learning target detection is proposed for a high error rate of target recognition and low success rate of grasping in the robot grasping process. The method investigates the robotic arm hand-eye calibration and the deep learning-based target detection and poses estimation algorithm. The Basler camera is used as the visual perception tool of the robot arm, the AUBO i10 robot arm is used as the main body of the experiment, and the PP-YOLO deep learning algorithm performs target detection and poses estimation on the object. Through the collection of experimental data, several grasping experiments were conducted on the diversity of targets randomly placed in the poses under real scenes. The results showed that the success rate of grasping target detection was 94.93% and the robot grasping success rate was 93.37%.

Contrast-specific imaging of histotripsy: Chirp-coded subharmonic imaging combined with Volterra Filtering

Histotripsy is a non-thermal focused ultrasound therapy under development to ablate tissue mechanically via bubble cloud activity. Real-time ultrasound imaging is used for treatment guidance. Bubble cloud hyperechogenicity is reduced in deep abdominal targets, making contrast-specific imaging an active area of research. Subharmonic imaging with chirp-coded excitation can improve bubble cloud detection, though the contrast-to-tissue ratio (CTR) was still limited to nearly 6 dB. Nonlinear components of a signal can be delineated with Volterra filtering, including those associated with bubble oscillations. In this study, we tested Volterra filtering as a means to enhance bubble cloud detection. Histotripsy bubble clouds were generated in scattering tissue-mimicking phantoms. Imaging of the bubble clouds was performed with a chirped pulse (1.9-μs duration, 7–12 MHz bandwidth). The scattered signals were processed with a subharmonic matched filter, followed by a tuned second-order Volterra filter. Volterra filtering improved the CTR for bubble cloud detection two-fold relative to matched filtering alone (12.5 dB vs 5.6 dB). Further improvement in bubble contrast was observed for third-order Volterra filtering (CTR of 20.3 dB) but at the cost of underestimating the bubble cloud area. Overall, these findings indicate the utility of Volterra filtering as a means to improve histotripsy image guidance.

Dynamic Target Tracking Control of Autonomous Underwater Vehicle Based on Trajectory Prediction.

Underwater dynamic target tracking technology has a wide application prospect in marine resource exploration, underwater engineering operations, naval battlefield monitoring, and underwater precision guidance. Aiming at the underwater dynamic target tracking problem, an autonomous underwater vehicle tracking control method based on trajectory prediction is studied. First, a deep learning-based target detection algorithm is developed. For the image collected by the multibeam forward-looking sonar image, this algorithm uses the YOLO v3 network to determine the target in a sonar image and obtain the position of the target. Then, a time profit Elman neural network (TPENN) is constructed to predict the trajectory information of the dynamic target. Compared with an ordinary Elman neural network, its accuracy of dynamic target prediction is increased. Finally, underwater tracking of the dynamic target is realized using the model predictive controller (MPC), and the tracking result is stable and reliable. Through simulations and experiment, the proposed underwater dynamic target tracking control method is demonstrated to be effective and feasible.

Acquisition and near-surface impacts on VSP mini-batch FWI and RTM imaging in desert environment

The SEG Advanced Modeling (SEAM) Arid benchmark model was designed to simulate an extremely heterogeneous low-velocity near surface (NS), which is typical of desert environments and typically not well characterized or imaged. Imaging of land seismic data is highly sensitive to errors in the NS velocity model. Vertical seismic profiling (VSP) partly alleviates the impact of the NS as the receivers are located at depth in the borehole. Deep learning (DL) offers a flexible optimization framework for full-waveform inversion (FWI), often outperforming typically used optimization methods. We investigate the quality of images that can be obtained from SEAM Arid VSP data by acoustic mini-batch reverse time migration (RTM) and full-waveform imaging. First, we focus on the effects of seismic vibrator and receiver array positioning and imperfect knowledge of the NS model when inverting 2D acoustic data. FWI imaging expectedly and consistently outperforms RTM in our tests. We find that the acquisition density is critical for RTM imaging and less so for FWI, while NS model accuracy is critical for FWI and has less effect on RTM imaging. Distributed acoustic sensing along the full length of the well provides noticeable improvement over a limited aperture array of geophones in imaging deep targets in both RTM and FWI imaging scenarios. Finally, we compare DL-based FWI imaging with inverse scattering RTM using the upgoing wavefield from the original SEAM data. Use of significantly more realistic 3D elastic physics for the simulated data generation and simple 2D acoustic inversion engine makes our inverse problem more realistic. We observe that FWI imaging in this case produces an image with fewer artifacts.

A YOLOX-Based Automatic Monitoring Approach of Broken Wires in Prestressed Concrete Cylinder Pipe Using Fiber-Optic Distributed Acoustic Sensors.

Wire breakage is a major factor in the failure of prestressed concrete cylinder pipes (PCCP). In the presented work, an automatic monitoring approach of broken wires in PCCP using fiber-optic distributed acoustic sensors (DAS) is investigated. The study designs a 1:1 prototype wire break monitoring experiment using a DN4000 mm PCCP buried underground in a simulated test environment. The test combines the collected wire break signals with the previously collected noise signals in the operating pipe and transforms them into a spectrogram as the wire break signal dataset. A deep learning-based target detection algorithm is developed to detect the occurrence of wire break events by extracting the spectrogram image features of wire break signals in the dataset. The results show that the recall, precision, F1 score, and false detection rate of the pruned model reach 100%, 100%, 1, and 0%, respectively; the video detection frame rate reaches 35 fps and the model size is only 732 KB. It can be seen that this method greatly simplifies the model without loss of precision, providing an effective method for the identification of PCCP wire break signals, while the lightweight model is more conducive to the embedded deployment of a PCCP wire break monitoring system.

Deep learning-based circular disk type radar target detection in complex environment

Target identification is one of the most popular radar uses in real life. Target identification is a classifier that analyzes whether a signal contains an echo from a target (target-present) or is merely noise (target-absent). Deep learning techniques are a popular topic in classification, and they have evinced to be effective in a range of applications. In this paper, a 64 layers Circular Disk type RADAR Target Detection (CDRTD) model is proposed based on Transfer Learning using the SqueezeNet architecture of Convolutional Neural Network (CNN) that functions directly with processed radar target return eco signal and minimize the requirement of conventional laborious radar signal processing. Further, the proposed 64 layers SqueezeNet-based CNN CDRTD model was then implemented to identify circular disk type targets in complex environment. Finally, the target return eco data was tested to identify the circular disk type radar target in complex environments. We further analyzed target detection probability, false alarm rate, precision, recall, F1 in a complex environment and compared it with the ideal case. We found that our proposed CDRTD model can classify 83.3% of the test samples correctly with an overall accuracy of 94.59% in a noisy and cluttered environment whereas 100% of the test samples are classified correctly with an overall accuracy of 100% in an ideal environment.

Reflectivity Cross Plot of Modified Zoeppritz Equation

Beside the complexities and not readily practical applications resulting from the full Zoeppritz equation, the seismic amplitude reflection does not give enough information beyond the critical angle. Consequently, there are breakdown of the Zoeppritz equation approximations at angle of incidence beyond (Shuey’s approximation). More so, the validity is only for slight contrast in elastic parameters across the formations and small angle of incidence is assumed. In an attempt to address these inaccuracies and enhance understanding of seismic reservoir responses and prediction of fluid and lithology, a modified form of the Zoeppritz equation is derived using relations between elastic constants and velocities in terms of Pseudo Poisson’ ratio reflectivity, rigidity reflectivity, density reflectivity in linearized forms devoid of the complexities associated with the original Zoeppritz equation with practical applications in hydrocarbon exploration, exploitation and production. These properties are lithology and fluid discriminators. The modified Zoeppritz equation was analyzed using well data from oil field in a sedimentary basin, onshore of Niger Delta area. Reflectivity crossplot was carried out and comparison with the exact and other approximations was done to validate the derived equation. The results showed that the modified equation can be applied in exploration beyond the critical angle than the shuey’s and Aki &amp; Richards’ approximations especially for deep targets and wide angle acquisition for accurate estimation of intercept and gradient attributes. The modified Zoeppritz equation in this study gives higher accuracy at far offset than the two foremost approximations.

Poverty Reduction In Bojonegoro Regency Based On Regional Autonomy Implementation

Poverty Becomes a must problem quick completed , where problem poverty in the District Bojonegoro still many occur especially in regions with difficult access for reached. There is autonomy area (OTODA) is expected could strengthen power competitive with consider potential and diversity Indonesian region , as well democracy , equity , and justice , as well privileges and specialties. So that study this aim for review effectiveness application autonomy area to level poverty in the District Bojonegoro . Method research used is a mix of methods that is qualitative descriptive and quantitative equality regression . Research results this explain that Policy used in countermeasures poverty that exists in society is at level or level certain in accordance with criteria poverty experienced by the community . Government Regency Bojonegoro in To do countermeasures poverty To do cooperation with TNP2K (National Team for Management and Management poverty ). Decline poverty this no regardless with role government in take policy or use authority for welfare . As perpetrator in activity economy , society related tightly with achievements or deep targets growth economy . In accordance with results equality regression state that in the simultaneous test poverty influential significant on growth economy.. Based on conditions Regency Bojonegoro moment this accompanied with take into account strengths , opportunities , challenges , and more problems big that will faced in the future . Realization sustainable development is the main spirit that underlies it development area districts Bojonegoro in a manner evenly.