Multilayer Technique Research Articles

A Novel Hybrid Intelligent SOPDEL Model with Comprehensive Data Preprocessing for Long-Time-Series Climate Prediction

Long-time-series climate prediction is of great significance for mitigating disasters; promoting ecological civilization; identifying climate change patterns and preventing floods, drought and typhoons. However, the general public often struggles with the complexity and extensive temporal range of meteorological data when attempting to accurately forecast climate extremes. Sequence disorder, weak robustness, low characteristics and weak interpretability are four prevalent shortcomings in predicting long-time-series data. In order to resolve these deficiencies, our study gives a novel hybrid spatiotemporal model which offers comprehensive data preprocessing techniques, focusing on data decomposition, feature extraction and dimensionality upgrading. This model provides a feasible solution to the puzzling problem of long-term climate prediction. Firstly, we put forward a Period Division Region Segmentation Property Extraction (PD-RS-PE) approach, which divides the data into a stationary series (SS) for an Extreme Learning Machine (ELM) prediction and an oscillatory series (OS) for a Long Short-term Memory (LSTM) prediction to accommodate the changing trend of data sequences. Secondly, a new type of input-output mapping mode in a three-dimensional matrix was constructed to enhance the robustness of the prediction. Thirdly, we implemented a multi-layer technique to extract features of high-speed input data based on a Deep Belief Network (DBN) and Particle Swarm Optimization (PSO) for parameter searching of a neural network, thereby enhancing the overall system’s learning ability. Consequently, by integrating all the above innovative technologies, a novel hybrid SS-OS-PSO-DBN-ELM-LSTME (SOPDEL) model with comprehensive data preprocessing was established to improve the quality of long-time-series forecasting. Five models featuring partial enhancements are discussed in this paper and three state-of-the-art classical models were utilized for comparative experiments. The results demonstrated that the majority of evaluation indices exhibit a significant optimization in the proposed model. Additionally, a relevant evaluation system showed that the quality of “Excellent Prediction” and “Good Prediction” exceeds 90%, and no data with “Bad Prediction” appear, so the accuracy of the prediction process is obviously insured.

Modeling and Design of Full Electromagnetic Integration of a Symmetrical EMI Filtering Circuit With Flexible Multi-Layer Foil Technique

In a high-frequency power electronic converter with wide-bandgap device, electromagnetic interference (EMI) filter is an essential module for mitigating the conducted EMI issues. However, traditional discrete EMI filter will significantly increase total size and weight of the system. In this article, an UU-core based fully integrated symmetrical EMI filter is proposed using flexible multilayer foil technique, all the common-mode (CM) and differential-mode (DM) filtering components are integrated in the same unit for a more compact design. Moreover, a function-decoupling state is realized between the CM and DM elements, which contributes to predigesting the lumped equivalent CM and DM circuits. Then the parameter design procedure can be simplified. Prototypes of the proposed and other typical types of EMI filters are built for a 100 kHz SiC- <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mosfet</small> voltage source inverter, contrastive experiments have verified the feasibility and validity of the full electromagnetic integration approach.

Long-term Outcomes of Non-vascularized Multilayer Fascial Closure Technique for Dural Repair in Endoscopic Transnasal Surgery: Efficacy, Durability, and Limitations

Non-vascularized multilayer fascial closure technique (NMFCT) can be used instead of nasoseptal flap reconstruction for dural repair in endoscopic transnasal surgery (ETS); however, due to the lack of blood supply, its long-term durability and possible limitations need to be clarified. This was a retrospective study on patients who underwent ETS with intraoperative cerebrospinal fluid (CSF) leakage. We assessed the postoperative and delayed CSF leakage rates and the associated risk factors. Among 200 ETSs with intraoperative CSF leakage, 148 (74.0%) ETSs were performed for skull base pathologies other than pituitary neuroendocrine tumor. The mean follow-up period was 34.4 months. Esposito grade 3 leakage was confirmed in 148 (74.0%) cases. NMFCT was used either with (67 [33.5%]) or without (133 [66.5%]) lumbar drainage. There were 10 cases (5.0%) of postoperative CSF leakage that necessitated reoperation. In 4 other cases (2.0%), CSF leakage was suspected but lumbar drainage alone successfully restored the condition. Multivariate logistic regression analyses revealed that posterior skull base location (P < 0.01, odds ratio 11.5, 95% CI 1.99-2.17× 102) and craniopharyngioma pathology (P= 0.03, odds ratio 9.4, 95% CI 1.25-1.92× 102) were significantly associated with postoperative CSF leakage. No delayed leakage occurred during the observation period except for 2 patients who underwent multiple radiotherapies. NMFCT is a reasonable alternative with long-term durability, though vascularized flap may be a better choice for cases in which vascularity of the surrounding tissues is significantly impaired due to interventions including multiple radiotherapies.

Conformable Electrode Arrays for Wearable Neuroprostheses.

Wearable electrode arrays can selectively stimulate muscle groups by modulating their shape, size, and position over a targeted region. They can potentially revolutionize personalized rehabilitation by being noninvasive and allowing easy donning and doffing. Nevertheless, users should feel comfortable using such arrays, as they are typically worn for an extended time period. Additionally, to deliver safe and selective stimulation, these arrays must be tailored to a user's physiology. Fabricating customizable electrode arrays needs a rapid and economical technique that accommodates scalability. By leveraging a multilayer screen-printing technique, this study aims to develop personalizable electrode arrays by embedding conductive materials into silicone-based elastomers. Accordingly, the conductivity of a silicone-based elastomer was altered by adding carbonaceous material. The 1:8 and 1:9 weight ratio percentages of carbon black (CB) to elastomer achieved conductivities between 0.0021-0.0030 S cm-1 and were suitable for transcutaneous stimulation. Moreover, these ratios maintained their stimulation performance after several stretching cycles of up to 200%. Thus, a soft, conformable electrode array with a customizable design was demonstrated. Lastly, the efficacy of the proposed electrode arrays to stimulate hand function tasks was evaluated by in vivo experiments. The demonstration of such arrays encourages the realization of cost-effective, wearable stimulation systems for hand function restoration.

Bonding performance between distinct layers of cast-in-situ self-compacting concrete and ordinary concrete

The issue of concrete vibration in the continuous beam 0# block is resolved by using a combination of self-compacting concrete (SCC) and ordinary concrete (OC). As a consequence of the multi-layer casting technique, SCC-OC structures consist of two layers and a bonding interlayer, so the bonding performance is crucial to guarantee the reliability of the structure. This paper studies the bonding performance between distinct layers of SCC and OC and attempts to establish the relationship between the two parameters (i.e., casting time interval and curing age) and the bonding strength (i.e., spitting strength and shearing strength). The results indicate that the casting time interval between SCC and OC has a stronger effect on the failure mode than that of curing age, and the shearing test can better characterize the weakly bonded interface than the splitting test. A shorter casting time interval and a longer curing age lead to higher bonding strength. Based on the bonding micro-mechanism and failure modes of SCC-OC interfaces, a mechanical model is proposed to predict the shear strength of the SCC-OC composite. The innovative approach of combining SCC and OC is promising to solve the problem of concrete vibration in the continuous beam 0# block at a low cost.

Classification of HEp-2 Staining Pattern Images Using Adapted Multilayer Perceptron Neural Network-Based Intra-Class Variation of Cell Shape.

There exists a growing interest from the clinical practice research communities in the development of methods to automate HEp-2 stained cells classification procedure from histopathological images. Challenges faced by these methods include variations in cell densities and cell patterns, overfitting of features, large-scale data volume and stained cells. In this paper, a multi-class multilayer perceptron technique is adapted by adding a new hidden layer to calculate the variation in the mean, scale, kurtosis and skewness of higher order spectra features of the cell shape information. The adapted technique is then jointly trained and the probability of classification calculated using a Softmax activation function. This method is proposed to address overfitting, stained and large-scale data volume problems, and classify HEp-2 staining cells into six classes. An extensive experimental analysis is studied to verify the results of the proposed method. The technique has been trained and tested on the dataset from ICPR-2014 and ICPR-2016 competitions using the Task-1. The experimental results have shown that the proposed model achieved higher accuracy of 90.3% (with data augmentation) than of 87.5% (with no data augmentation). In addition, the proposed framework is compared with existing methods, as well as, the results of methods using in ICPR2014 and ICPR2016 competitions.The results demonstrate that our proposed method effectively outperforms recent methods.

A Software Framework for Predicting the Maize Yield Using Modified Multi-Layer Perceptron

Predicting crop yields is one of agriculture’s most challenging issues. It is crucial in making national, provincial, and regional choices and estimates the government to meet the food demands of its citizens. Crop production is anticipated based on various factors such as soil conditions and meteorological, environmental, and crop variables. This study intends to develop an effective model that can accurately anticipate agricultural production in advance, assisting farmers in better planning. In the current study, the Crop Yield Prediction Dataset is normalized initially, and then feature engineering is performed to determine the significance of the feature in assessing the crop yield. Crop yield forecasting is performed using the Multi-Layer Perceptron model and the Spider Monkey Optimization method. The Multi-Layer Perceptron technique is efficient in dealing with the non-linear relations among the features in the data, and the Spider Monkey Optimization technique would assist in optimizing the corresponding feature weights. The current study uses data from the Food and Agriculture Organization and the World Data Bank to forecast maize yield in the Saudi Arabia region based on factors such as average temperature, average rainfall, and Hg/Ha production in past years. The suggested MLP-SMO model’s prediction effectiveness is being evaluated using several evaluation metrics such as Root-Mean-Square Error, R-Squared, Mean Absolute Error, and Mean Bias Error, where the model has outperformed in the prediction process with a Root-Mean-Square Error value of 0.11, which is lowest among all the techniques that are considered in the statical analysis in the current study.

Thermal performance improvement of multilayer insulation technique

Thermal performance improvement of multilayer insulation technique

Evaporation in thin film region of water at ambient temperature under reduced pressure conditions: Flow and interface characteristics

In this paper, the flow and interface characteristics of the thin liquid film region near the contact line of water under reduced pressure conditions are experimentally observed by using a multilayer nanoparticle image velocimetry technique. The results demonstrate that the flow in this region is promoted by reducing the pressure. The average velocities in the top layer of this region are 57.99, 61.52, 65.20, 66.00, and 68.25 μm/s at the degree of reduced pressure of 10–50 kPa with an interval of 10 kPa. Reducing the pressure shortens the evaporation time and advances the depinning time in the constant contact radius mode. Entering the constant contact angle mode, the initial height of the film increases, the critical height is elevated, and the decrease rate of film thickness increases, which leads to the shortening of the overall evaporation time. This work provides insight into the microscopic transport mechanisms of coolant under reduced pressure conditions.

Development of a multilayer biodegradable active packaging based on nano emulsions, for the bio preservation of food

Multi-layer biodegradable active packaging is a new class of innovative food packaging containing bioactive compounds that are able to maintain food quality and extend shelf life preservation by releasing an active agent during storage. In this context, this study aims to develop and characterize three-layer biodegradable active films: 2 outer layers of ethylcellulose (EC) and a layer internal pectin containing nanoemulsions (NE) of trans-cinnamaldehyde (TC) as an antimicrobial agent. Trans-cinnamaldehyde (NE) nanoemulsions were prepared with soy lecithin as an agent. emulsifier to stabilize the TC and protect it for the duration of the film manufacturing. The average size and the zeta potential of the nanoemulsion droplets were 103.93 nm and -46 mV, respectively. The opacity of samples of monolayer and multilayer films decreased by 15.19 (A*mm-1) for the monolayer film of pectin incorporated by nanocapsules at 2.02 for multilayer films. In addition, the multilayer technique has made it possible to improve the mechanical properties of the films compared to monolayers with greater resistance breakage and greater extensibility. Inhibition tests on four bacteria representatives of bacteria pathogens and spoilage found in food industries have confirmed the antimicrobial activity, both, mono and multilayers. The work presented in this study offers perspectives for the fabrication packaging based on antimicrobial and biodegradable multilayer films.

Food volume estimation by multi-layer superpixel.

Estimating the volume of food plays an important role in diet monitoring. However, it is difficult to perform this estimation automatically and accurately. A new method based on the multi-layer superpixel technique is proposed in this paper to avoid tedious human-computer interaction and improve estimation accuracy. Our method includes the following steps: 1) obtain a pair of food images along with the depth information using a stereo camera; 2) reconstruct the plate plane from the disparity map; 3) warp the input image and the disparity map to form a new direction of view parallel to the plate plane; 4) cut the warped image into a series of slices according to the depth information and estimate the occluded part of the food; and 5) rescale superpixels for each slice and estimate the food volume by accumulating all available slices in the segmented food region. Through a combination of image data and disparity map, the influences of noise and visual error in existing interactive food volume estimation methods are reduced, and the estimation accuracy is improved. Our experiments show that our method is effective, accurate and convenient, providing a new tool for promoting a balanced diet and maintaining health.

Narrative within a Narrative: Blogging as an Embedded Narrative Strategy in Adichie’s Americanah

In the world of storytelling, authors employ multilayered narrative techniques for various reasons. This study aims to explore the narrative levels, the relationships between them, and the functions of the embedded texts in Adichie’s novel “Americanah.” Unlike the previous works that mostly focused on the thematic concerns raised in the novel, this study is originally approached from a narratological perspective. Applying narrative theory, it mainly focuses on analyzing the novel’s use of blogs as an embedded narrative strategy. A narrative strategy here refers to a device or technique that a real author uses to communicate the themes of a novel. The study employs a qualitative research method since it is a textual analysis. Since blogs can reach a wide audience as a mouth of many diasporas, the author strategically used them to explain the external narration. Critical diaspora concerns are juxtaposed in the blogs by the major character, Ifemelu, for having the effect of intimacy with the readers. Overall, blogs are effectively used by the author as an embedded narrative strategy. The primary (embedding) narrative justifies the embedded narrative in it. They do not just present the text rather they provide a context for the embedded narrative. The functions identified are actional, explicative, aesthetic, and advancement of oral storytelling. The second degree narratives (blogs) are also used for aesthetic purposes as a means of creating suspense and introducing new plot lines. Keywords: blogging, narrative embedding, narrative levels, narrative strategies, narrator. DOI: https://doi.org/10.55463/hkjss.issn.1021-3619.60.77

IMPROVING EFFICIENT STUDENT CAREER RECOMMENDATIONS USING MACHINE LEARNING

This research aims to develop and improve the model’s efficacy for student career recommendations using feature selection, data sampling, and machine learning techniques. The results showed that the wrapper approach improved the model’s performance when applied to over-sampling techniques. In particular, a model combining k-mean, Synthetic Minority Over-sampling Technique, and Edited Nearest Neighbor methods will significantly improve model performance. Additionally, the model developed based on machine learning showed that the model using the Multi-Layer Perceptron Neural Network technique had a higher efficiency than other classifiers in this experiment. Finally, when developing the model using the wrapper, k-mean, Synthetic Minority Over-sampling Technique, Edited Nearest Neighbor, and Multi-Layer Perceptron Neural Network, the model is suitable predicts student careers. This model has a prediction accuracy of 95.88% and a root mean squared error of 2.0968. The most accurate models using the classifier are Support Vector Machine, k-Nearest Neighbors, Random Forest, Decision Tree, Naïve Bayes, and Logistic Regression. Keywords: Career Recommendations, Machine Learning, SMOTE-ENN, Resampling, Wrapper DOI： https://doi.org/10.35741/issn.0258-2724.58.2.49

Application of Multi-layer Spiral 3D Reconstruction Technique in Orthodontics

Application of Multi-layer Spiral 3D Reconstruction Technique in Orthodontics

An Application of Feature Selection Methods to Compare the Performances of Classification Algorithms

In this study, it is aimed to determine fewer and significant variables with the help of feature selection methods among a large number of variables in the data discussed. Feature selection methods are effective methods that have great importance in statistics in recent years and provide great convenience to researchers. Depending on the technique used in the method, different numbers of variables are included in the model, but the correct classification rates may vary. In this context, being able to express the variables in a data set with a large number of variables of interest with a high classification percentage and fewer new variables makes positive contributions to issues such as time and cost. The variables in the data set discussed in this study were firstly analyzed with different feature selection methods and new data sets were created. Afterwards, these new data sets containing different numbers of variables were analyzed with different machine learning techniques and the best machine learning technique was determined. In this study, chronic kidney disease data were handled and the variables in the data set were classified with different feature selection methods. When the results of the study are examined, the highest classification rate with 99.75% was obtained from the correlation-based feature selection method, which includes the random forest and multilayer perceptron technique, and the filter method, which includes the k-nearest neighbor technique, with the same rate. The results of the study show that the percentage of correct classification obtained from this study is higher than that of other studies, when compared with other studies using the same dataset.

Formation of a 3D Particle Array Actuated by Ultrasonic Traveling Waves in a Regular Polygon Resonator.

Acoustic radiation forces have been extensively studied regarding static particles, cell patterning, and dynamic transportation. Compared with standing wave manipulation, traveling wave manipulation can be more easily modulated in real time and has no matching requirement between the size of the resonant cavity and the sound frequency. In this work, we present an efficient, multi-layer microparticle pattern technique in a 3D polygon cavity with a traveling bulk acoustic wave. There are two types of excitation modes: the interval excitation mode (IEM) and the adjacent excitation mode (AEM). We conducted theoretical and simulation analyses, and our results show that both of these modes can form particle arrays in the resonant cavity, which is in accordance with the experimental results. The array spacings in the IEM and AEM were about 0.8 mm and 1.3 mm, respectively, while the acoustic frequency was 1MHz. Double-layer particle patterns were arrayed by a double in the resonant cavity. The spacing between the two layers was set at 3.0 mm. The line spacings were about 0.4 mm in both layers. The line width was 0.2 mm, which was larger than the single layer. The results show that ultrasonic traveling waves are a feasible method to manipulate particles and cells that form 3D patterns in particle-fluid flows.

Comparison of Graft Materials in Multilayer Reconstruction with Nasoseptal Flap for High-Flow CSF Leak during Endoscopic Skull Base Surgery.

Cerebrospinal fluid (CSF) leak is a crucial complication after endoscopic skull base surgery. Therefore, multilayer reconstruction with grafts is as essential as a reconstruction with pedicled flaps. Although widely used, the multilayer technique with autologous fascia lata has drawbacks, such as additional wound and donor site complications. We compared acellular dermal graft and banked homologous fascia lata graft (alternative grafts) with autologous fascia lata graft for high-flow CSF leak repair. We retrospectively enrolled 193 subjects who underwent endoscopic skull base reconstruction with multilayer fascial grafts and nasoseptal flap for high-flow CSF leaks from November 2014 to February 2020 at a single institution. Acellular dermal matrix (ADM), banked homologous fascia lata, and autologous fascia lata were used in 48 (24.9%), 102 (52.8%), and 43 (22.3%) patients, respectively. Postoperative CSF leaks occurred in 23 (11.9%) patients and meningitis in 8 (4.1%). There was no significant difference in postoperative CSF leak (p = 0.36) and meningitis (p = 0.17) across the graft groups. Additionally, we could not find out contributing risk factors for postoperative CSF leak and meningitis. ADM and banked homologous fascia lata are non-inferior to autologous fascia lata for endoscopic skull base reconstruction in water-tight reconstruction or safety without additional donor site morbidities.

Intelligent video surveillance using enhanced deep belief based multilayered convolution neural network classification techniques

AbstractVideo surveillance has undergone numerous changes in the past few years and several pieces of research have been carried out in this field. Object tracking is the significant task in such systems, and hence it is essential to review the standard approaches dealing with object detection, classification and tracking. This work proposes a novel classification technique for a detected object of a moving scene from a video dataset. Initially the dataset has been processed and prepared for data training based on neural networks. The data has been classified using the proposed enhanced deep belief based multilayered convolutional neural network (EBMCNN). The major focus is on deep learning applications involved in estimating the count, total persons involved and the activities in a crowd where all criteria are taken into consideration, thereby achieving security through video analysis. Identifying theft and the detection of violence are some security measures where video is converted to frames which are then processed to analyse the individuals along with their activities. The classification is performed through comparative analysis of a real‐time dataset. Experimental results show the accuracy 97%, precision 93.8%, recall 87.7% and F‐1 score 87.5%.

Study on Co-production compatibility evaluation method of multilayer tight gas reservoir

Tight sandstone gas reservoir normally has a poor pore connectivity and a low productivity of single layer production, and the multilayer co-production technique has received increasing attention to improve its recovery in recent years. However, the range and impact of geological conditions are still unclear, leading to a challenging comprehensive evaluation of multilayer co-production compatibility. In this study, the impact of a series of factors on multilayer tight gas production is discussed by numerical simulation in detail, and their compatibility thresholds are determined. The variable weight based fuzzy comprehensive evaluation (VW-FCE) method is constructed, and a co-production compatibility index (CCI) is further proposed for multilayer tight gas reservoir co-production evaluation, with an application to Daning-jixian tight gas reservoirs for verification. The results show that thickness, permeability, reservoir pressure, and gas saturation are the key factors affecting the co-production, and the 10-year cumulative gas production contribution of the lower sandstone increases with the increase of each parameter ratio between the lower and the upper sandstones. When the properties of two co-production layers are similar, their compatibility is mainly impacted by the formation pressure and gas saturation variations. Otherwise, their compatibility is controlled by the formation thickness and permeability. The CCI values for multilayer co-production is 0.6–1, and the gas production capacity shows a positive exponential relationship with the evaluation index. The proposed method is verified by comparing with the actual production data from typical wells of tight sandstone gas co-production in the Daning-Jixian area, which indicates that the CCI is appropriate to evaluate the co-production compatibility of multiplayer tight gas reservoir, and provide theoretical supports for tight gas co-production.

Human Coronary Plaque Optical Coherence Tomography Image Repairing, Multilayer Segmentation and Impact on Plaque Stress/Strain Calculations.

Coronary vessel layer structure may have a considerable impact on plaque stress/strain calculations. Most current plaque models use single-layer vessel structures due to the lack of available multilayer segmentation techniques. In this paper, an automatic multilayer segmentation and repair method was developed to segment coronary optical coherence tomography (OCT) images to obtain multilayer vessel geometries for biomechanical model construction. Intravascular OCT data were acquired from six patients (one male; mean age: 70.0) using a protocol approved by the local institutional review board with informed consent obtained. A total of 436 OCT slices were selected in this study. Manually segmented data were used as the gold standard for method development and validation. The edge detection method and cubic spline surface fitting were applied to detect and repair the internal elastic membrane (IEM), external elastic membrane (EEM) and adventitia-periadventitia interface (ADV). The mean errors of automatic contours compared to manually segmented contours were 1.40%, 4.34% and 6.97%, respectively. The single-layer mean plaque stress value from lumen was 117.91 kPa, 10.79% lower than that from three-layer models (132.33 kPa). On the adventitia, the single-layer mean plaque stress value was 50.46 kPa, 156.28% higher than that from three-layer models (19.74 kPa). The proposed segmentation technique may have wide applications in vulnerable plaque research.