Optimal Band Research Articles

Theoretical exploration of the structure and physical properties of YbZn2X2 (X = N, P, As, Sb)

In this study, we conduct a comprehensive theoretical analysis of the structural parameters, dynamic stability, elastic properties, and optoelectronic characteristics of YbZn2X2 (X = N, P, As, Sb). The phonon dispersion calculations imply that YbZn2N2 is dynamically stable. For the first time, we investigate the elastic constants of YbZn2X2, and our findings show that the obtained elastic constants meet the mechanical stability criteria. The analysis of electronic properties shows that YbZn2X2 (X = N, Sb) and YbZn2X2 (X = P, As) are direct and indirect band gap semiconductors, respectively. The band gaps of these compounds vary between 0.3 and 1.8 eV, and the energy gap is decreased from N to Sb. The results imply that YbZn2As2 displays an optimal band gap of approximately 1.2 eV and a high optical absorption coefficient with an order of 105, making it a promising candidate for optoelectronic devices. These findings offer valuable insights for further exploration of the performance of these compounds in optoelectronic applications.

Evaluation and optimization of the three-band spectral indices for oil type identification using reflection spectrum

Oil type identification can help determine the source of leakage and decide a plan of post-accident treatment. Visible spectroscopy is a promising way for rapid oil type identification. Choosing the appropriate three-band spectral index (TBSI) and corresponding optimal band combination is the essential basis to improve the accuracy of the identification model. In order to determine the TBSIs that are available for oil type identification, as well as the corresponding optimal spectral band combination, this study proposed a novel algorithm for the optimization of spectral band combination for classification problems by evaluating the distinguishability of TBSI with statistical parameters from paired t-test. Heavy diesel, refined diesel, and the crude oil originated from two different places were used in the experiments, in which the spectra of the oil samples were collected using high-resolution hyperspectral sensor. Four different TBSIs that are commonly-used in the reflection spectrum analysis were tested using the proposed optimal band combination algorithm. According to the results, three out of the four TBSIs tested in the experiment are proved to be applicable for oil type identification. The optimal spectral band combinations are determined for each TBSI, and their distribution patterns in the three-dimensional tensor of spectral band combinations are studied and discussed. The optimal spectral combination algorithm proposed in this study can not only determine the spectral bands for rapid detection of oil spills with smaller number of calculations, but also provide the theoretical basis for other target classification tasks using reflection spectrum.

Pressure-induced tuning of structure and electronic properties in lead-free hybrid halide perovskite HC(NH2)2SnI3 for photovoltaic solar cells

Pressure effect on structural parameters and band gaps for different phases of lead-free photovoltaic hybrid halide perovskite formamidinium tin iodide was studied using density functional theory accounting for van der Waals interactions. The lowest compressibility of formamidinium tin iodideis along C–H bonds of tetragonal and orthorhombic phases, while cubic phase is more compressible(less stable with respect to compression)than tetragonal(the most stable)and orthorhombic ones. It has been established that Sn-I bonds have partially covalent character and their energies were calculated. Electron density and energies for Sn-I bonds increase with pressure. The band gap for tetragonal phase is smaller than that for orthorhombic and cubic phases. Pressure increase causes the band gap, especially for cubic phase, to decrease significantly to the values optimal for the maximum power conversion efficiency of solar cells. The cubic phase reached the optimal band gap values at pressures less than 1.1 GPa.

X-aggregation-induced emission in newly fabricated Pullulan/3-Hydroxyflavone derivative composite electrospun nanofiber mat for optical applications

A fascinating optically important 3-Hydroxyflavone derivative 2-(2,5-dimethoxyphenyl)-3‑hydroxy-4H-chromen-4-one was synthesized and its single-crystal structure was studied. This compound was used as a dopant and incorporated into the pullulan matrix by electrospinning technique. Functionalized pullulan nanofiber mat was found to possess dopant molecules organized in an X-aggregated fashion accounting for the twisted structure of the dopant molecules. The diameter of the nanofiber mat was reduced from 250 nm to 120 nm upon fabrication with dopant due to the nanofiber mat's increased crystallinity. Dopant molecules imparted absorption and emission properties into the fabricated nanofiber mat and turned it to be highly fluorescent triggering yellowish-green emission with a large Stokes shift of 193 nm due to X-aggregation. The improved water resistance of the fabricated pullulan nanofiber mat was witnessed by an increased water contact angle from 27.3° to 62.5° due to the incorporation of hydrophobic dopant molecules. The thermal and mechanical stability of the fabricated nanofiber mat was improved upon fabrication. The predicted absolute quantum yield was obtained in the 34.1- 40.3% range. The optimum indirect optical band gap of 2.25–2.50 eV and refractive index of 2.1–3.4 for the designed nanofiber mat suggested the potential application as OLED material.

Simplest synthesis and characterization study of flower-like Cu2ZnSnS4 thin films

Nowadays Cu2ZnSnS4 (CZTS) thin film is most reliable as economical and eco-friendly semiconductor material due to having advantageous properties likes high absorption coefficient and optimum band gap. Addition to these CZTS has nontoxic elements and naturally abundant readily available. Here we report economical and simplest chemical bath deposition method to synthesis of Cu2ZnSnS4 thin films which were studied by characterization techniques like XRD, Raman, UV–Visible spectroscopy, electrical conductivity, scanning electron microscopy techniques by which we report poly-crystalline CZTS thin films having stable kasterite structure in a excellent stoichiometric with 1.45 eV as an ideal band gap and its SEM reports uniform typical flower -like morphology.

Design of Lead Hybrid Halide Perovskite for Solar Cells

Hybrid organic-inorganic halide perovskites solar cells have attracted extensive interest because of their outstanding properties, including an optimal band gap, high carrier mobility, and excellent optoelectronic merits. We study the electronic and crystal structural properties of hybrid organic-inorganic halide APbX3 (A = Cs, methylammonium (MA), formamidinium (FA), X = I, Br) perovskites using first-principles calculations based on density functional theory. We find that halide atoms and A-site cations strongly affect their structural and electronic properties. The radius of a halide atom and the size of an organic molecule determine their lattice parameters and bond length. A relatively large halide atom can increase the value of the lattice parameters (a and b). Meanwhile, the electronic properties (band gap & carrier effective mass) of the Pb-based hybrid halide APbX3 can be effectively modified by adopting appropriate A- and X-site atoms or organic sections. We predict that HOIPs may have outstanding potential in solar light harvesting with promoted power conversion efficiency due to a tunable band gap and excellent electronic properties.

A dataset of spatial distribution of highland barley planting area on the Qinghai-Tibet Plateau (2019)

Highland barley is the dominant crop that can best adapt to the natural environment of the Qinghai-Tibet Plateau characterized by Alpine low temperature, hypoxia and strong radiation. In order to obtain the spatial distribution of the highland barley planting areas on the Qinghai-Tibet Plateau, we adopted a highland barley extraction method based on multi-element fusion of partition classification. First, we impose restrictions on the range of highland barley map spots of different agricultural partitions in terms of altitude, slope, precipitation and hydrological factors. Second, we optimized the optimal band for highland barley extraction through the OIF index partition. Finally, we used the object-oriented classification method to extract the planting areas of highland barley on the Qinghai-Tibet Plateau. The accuracy test of confusion matrix shows that the overall accuracy is 91.74% and Kappa coefficient is 0.83. According to the extraction results of highland barley on the Qinghai-Tibet Plateau, the total planting area of highland barley is about 2.74×105 hm2. The dataset improves the understanding of the existing highland barley spatial distribution pattern from the administrative unit scale to the patch scale. And it can provide data reference for optimizing the spatial distribution pattern of highland barley planting in the future.

Effects of spectral variability due to sediment and bottom characteristics on remote sensing for suspended sediment in shallow rivers

Advances in remote sensing techniques for water environments have led to acquisition of abundant data on suspended sediment concentration (SSC). However, confounding factors, such as particle sizes, mineral properties, and bottom materials, have not been fully studied, despite their substantial interference with the detection of intrinsic signals of suspended sediments. Therefore, we investigated the spectral variability arising from the sediment and bottom using laboratory and field-scale experiments. In the laboratory experiment, we focused on measuring spectral characteristics of suspended sediment according to particle size and sediment type. The laboratory experiment was conducted under conditions of completely mixed sediment and non-bottom reflectance using a specially designed rotating horizontal cylinder. To investigate the effects of different channel bottoms under sediment-laden flow conditions, we performed sediment tracer tests in field-scale channels comprising sand and vegetated bottoms. Based on experimental datasets, we performed spectral analysis and multiple endmember spectral mixture analysis (MESMA) to quantify the effect of spectral variability of sediment and bottom on the relationship between hyperspectral data and SSC. The results showed that optimal spectral bands were precisely estimated under non-bottom reflectance conditions, and the effective wavelengths depended on the sediment type. The fine sediments had a higher backscattering intensity compared to the coarse sediments, and the reflectance difference according to the particle size difference increased as the SSC increased. However, in the field-scale experiment, the bottom reflectance substantially decreased the R2 in the relationship between the hyperspectral data and SSC. Nevertheless, MESMA can quantify the contribution of suspended sediment and bottom signals as fractional images. Moreover, the suspended sediment fraction had a clear exponential relationship with SSC in all cases. We conclude that MESMA-driven sediment fractions could be an important alternative for estimating SSC in shallow rivers, as it quantifies the contributions of each factor and then minimizes the bottom effect.

Optimizing Cardiac Wireless Implant Communication: A Feasibility Study on Selecting the Frequency and Matching Medium

Cardiac wireless implantable medical devices (CWIMD) have brought a paradigm shift in monitoring and treating various cardiac conditions, including heart failure, arrhythmias, and hypertension. One of the key elements in CWIMD is the implant antenna which uses radio frequency (RF) technology to wirelessly communicate and transmit data to external devices. However, wireless communication with a deeply implanted antenna using RF can be challenging due to the significant loss of electromagnetic (EM) signal at the air-skin interface, and second, due to the propagation and reflection of EM waves from different tissue boundaries. The air-skin interface loss of the EM wave is pronounced due to the absence of a matching medium. This paper investigates the EM propagation losses in the human body and presents a choice of optimal frequency for the design of the cardiac implant antenna and the dielectric properties of the matching medium. First, the dielectric properties of all tissues present in the human thorax including skin, fat, muscle, cartilage, and heart are analyzed as a function of frequency to study the EM wave absorption at different frequencies. Second, the penetration of EM waves inside the biological tissues is analyzed as a function of frequency. Third, a transmission line (TL) formalism approach is adopted to examine the optimal frequency band for designing a cardiac implant antenna and the matching medium for the air-skin interface. Finally, experimental validation is performed at two ISM frequencies, 433 MHz and 915 MHz, selected from the optimal frequency band (0.4-1.5 GHz) suggested by our analytical investigation. For experimental validation, two off-the-shelf flexible dipole antennas operating at selected ISM frequencies were used. The numerical and experimental findings suggested that for the specific application of a cardiac implant with a penetration depth of 7-17 cm, the most effective frequency range for operation is within 0.4-1.5 GHz. The findings based on the dielectric properties of thorax tissues, the penetration depth of EM waves, and the optimal frequency band have provided valuable information on developing and optimizing CWIMDs for cardiac care applications.

Non hydrazine based chemical synthesis of earth abundant Cu2SnS3 thin film photocatalyst for wastewater treatment

Utilization of renewable solar energy has been a vital achievement for material scientists. The present work represents synthesis of Cu2SnS3 (CTS) thin film photocatalysts by a simple and economical spin coating sol gel method. The films were investigated for their structural, morphological, compositional, optical and chemical properties. Monoethanolamine (MEA) was employed to enhance the age of CTS gel by increasing its stability. X-ray diffraction (XRD) and Raman analysis indicated formation of single phase pristine tetragonal CTS material. Morphological studies showed the films are covered with CTS quantum dots. X-ray photoelectron spectroscopy (XPS) revealed oxidation states of Cu, Sn and S as +1, +4 and −2 respectively. The CTS material exhibited polycrystalline nature determined from the selected area electron diffraction (SAED) patterns of the films. The films has optimum energy band gap (∼1.7 eV) suitable for visible light photocatalysis. The thin films were explored as photocatalysts against methylene blue (MB) dye and it was found that the films degraded most of the dye (∼87%) in just 90 min of visible light illumination. Reusability experiments performed showed the films can be used again and again without considerable loss in the activity.

Malignant versus normal breast tissue: Optical differentiation exploiting hyperspectral imaging system

Breast malignancy is a critical problem that severely affects women’s health globally with a high-frequency rate, necessitating fast, effective, and early diagnostic methods. The present study aims to measure the breast tissue’s optical properties by capturing the spectral signatures from malignant and normal breast tissue for therapeutic and diagnostic applications. The optical imaging system incorporates a hyperspectral (HS) camera to capture the spectral signatures for both the malignant and normal breast tissues within 400 ~ 1000 nm. The system was subdivided into two exploratory (reflection/transmission) to measure the tissue’s diffuse reflectance (Rd) and light transmission (Tr), respectively. The study involved 30 breast tissue (normal/tumor) samples from 30 females in the age range of 46 ~ 72 years, who were optically inspected in the visible and near-infrared (VIS-NIR) spectra. Then, the inverse adding doubling (IAD) method for breast tissue characterization and descriptive analysis (T-test) was exploited to verify the significant difference between the various types of breast tissues and select the optimum wavelength. Finally, comparing the study outcome with the histopathological examination to evaluate the system’s effectiveness by calculation (sensitivity, specificity, and accuracy). The average outcome values demonstrated that the optimal spectral bands distinguishing between the normal and the tumor tissues regarding the reflectance approach were 600 ~ 680 nm and 750 ~ 960 nm at the VIS and NIR spectrum, respectively. Then, for the transmission technique, the optimal spectral bands were 560 ~ 590 nm and 760 ~ 810 nm at the VIS and NIR spectra, respectively. Later, the T-test and the IAD verified that the highest Rd values for discrimination were 600 ~ 640 nm and 800 ~ 840 nm at the VIS and NIR spectra, respectively. On the other side, the highest Tr values were 600 ~ 640 nm and 760 ~ 800 nm at the VIS and NIR spectra, respectively. The investigation’s average reading accuracy, sensitivity, and specificity were 85%, 81.88%, and 88.8%, respectively. The experimental trials revealed that the system could identify the optimal wavelength for therapeutic and diagnostic applications through the light interaction behavior of the breast tissue’s optical properties.

An effective strategy of indium half-doping to stabilize the structure and improve optoelectronic characteristics of Tl-Co based double perovskite: First principles study

Doping can improve the structural stability and photoelectric properties of perovskite materials. In this study, indium element was added into Tl-Co double based perovskite material to stabilize its structure and improve its photoelectric performance. The results show that the doped material Cs2In0.5Tl0.5CoX6(X = I, Br, Cl) has better ductility and stability than the original Cs2TlCoI6 by elastic constants and phonon spectra. Moreover, indium doping can improve the band structure of Tl-Co double-base perovskite materials, such as changing the band value to the optimal band gap value of solar energy absorber and transforming from indirect band structure to quasi-direct band structure. In terms of optical properties, indium doping can expand the wavelength range of the material's light absorption, making its absorption spectrum more matching with the simulated AM1.5 spectrum. Cs2In0.5Tl0.5CoCl6 is proposed to be a promising candidate for optoelectronic applications based on its structural stability, bandgap value and optical absorption spectrum.

Investigating the rate of turbidity impact on underwater spectral reflectance detection

Spectral reflectance detection of the targeted object is considered a vital inherent optical property for its potential to provide abundant spectral information, which is crucial in underwater spectral imaging. However, the coarse condition of the underwater environment due to turbidity causes extreme distortions in spectral reflectance detection due to the high absorption and scattering of light. To cope with the effects of light degradation on underwater spectral reflectance detection accuracy, the rate of the impacts of turbidity on spectral reflectance should be examined thoroughly. Therefore, we utilize a stare-type underwater spectral imaging system based on a liquid crystal tunable filter (LCTF) to study the effects of turbidity in underwater spectral imaging of various colored bodies. To examine the accuracy of underwater spectral reflectance detection based on escalating turbidity, the paper models the rate of increase in scattering intensity of the water body. Results show that, based on the non-linear increase in the pixel response of the black and white board, the rapid upsurge in scattering intensity occurs between 400nm to 500nm at different turbidity levels. Additionally, the spectral reconstruction of color bodies relative to the black and white board shows the maximum absolute deviation of 5.3% in spectral reflectance detection accuracy under varying turbidity. While employing underwater spectral imaging, the above findings of optimal band selection can find significant applications to improve the quality of underwater object detection.

Adaptive multi-layer empirical Ramanujan decomposition and its application in roller bearing fault diagnosis

Traditional signal processing methods cannot effectively segment the optimal frequency band, resulting in the fault characteristics are not obvious. Therefore, this paper proposes a multi-layer empirical Ramanujan decomposition (MLERD) method. In MLERD, the number of decomposed components is gradually increased through multi-level decomposition to ensure that the optimal frequency band can be obtained in the spectrum segmentation stage. Subsequently, the adaptive spectral weight kurtosis (ASWK) is defined to adaptively identify the optimal mode component. Compared with kurtosis, ASWK is more sensitive to periodic pulses and can better evaluate fault feature information. Based on this, this paper further proposes an adaptive multi-layer empirical Ramanujan decomposition (AMLERD) method, which can realize adaptive identification of the optimal frequency band and extract the optimal mode component of complex signals. The analysis results of roller bearing simulation and experimental signals show that AMLERD can effectively extract fault feature information and has excellent noise robustness.

Axial stress measurement for tightened bolt based on the effect of stress on ultrasonic wave attenuation

ABSTRACT Accurate assessment and monitoring of axial stress during the service life of the bolt connection is of great significance in ensuring the stability and reliability of the aerospace structure. The current acoustoelastic method requires both transverse and longitudinal mode waves and is less sensitive to small-size bolts, resulting in relatively larger errors in the evaluation of axial stress. In this paper, an axial stress measurement method with only a single longitudinal/transverse transducer for tightened bolts based on a novel attenuation-based model is introduced. The ultrasonic responses under axial preload in different frequency bands are comprehensively reflected through the energy attenuation coefficient matrix. In addition, an experimental method for selecting the optimal frequency band is given. Furthermore, the semi-permanent coupling method is proposed to provide a stable coupling condition to verify the feasibility of the attenuation-based model. Loading tests and ultrasonic tests were conducted on two kinds of strength-grade materials to obtain the calibration curves of both the longitudinal and transverse attenuation models. The experimental results show that the energy attenuation coefficient is positively correlated with the axial stress in a specific frequency range and the calibrated curve has a high fitting rate with a quadratic fitting function. The average relative error of the prediction results is less than 7.5%, which is better than the conventional acoustoelastic effect model.

Development of Rural Social Governance Intelligent System Based on Multi-Data Integration Algorithm and Realization of Multi-Platform Interaction of Mobile Terminals

This paper needs to uphold the concept of governance community "according to the times", "according to local conditions" and "according to people's conditions", and by improving the integration ability of rural social governance resources, building an embedded rural social governance ecology, and promoting the rational layout of rural social organizations, the application of the most The optimal band combination is obtained by the optimal band index method, and the above optimal bands are classified and studied by using unsupervised classification, maximum likelihood method, support vector machine classification method, and decision tree classification method. 's research and development.

An unsupervised learning damage diagnosis method based on virtual impulse response function and time series models

As it contains the inherent properties of the structure and is insensitive to variation of the input, the transmissibility function (TF) is widely used for structural damage detection under ambient excitation. However, in TF-based methods, the selection of the optimal damage sensitivity band often requires access to vibration data under different operating conditions, which is not conducive to unsupervised learning. In order to accommodate unsupervised learning and extract more damage information, this paper proposes a data-driven unsupervised damage detection method based on the virtual impulse response function (VIRF) and time series model (TSM). In this method, the VIRF is used as a damage-sensitive feature (DSF), the TSM is used for low-dimensional feature extraction of the VIRF, and the distance metric of the model coefficients is used to detect the occurrence of anomalies. The study analyses the type of TSM applied to VIRF and uses the parameter adjusted cosine similarity (PACS) as a more accurate statistical distance tool for the model coefficients. The application of two well-known benchmark structure experiments verifies the accuracy and practicality of the proposed method in damage detection under minor operational variations and ambient excitations. The comparative analysis and detection results indicate that the proposed method is advantageous in qualitatively quantifying the extent of the damage. Structural anomalies can be detected in both linear and nonlinear damage scenarios.

Estimation of soil salt content in the Bosten Lake watershed, Northwest China based on a support vector machine model and optimal spectral indices.

Low-cost and efficient dynamic monitoring of surface salinization information is critical in arid and semi-arid regions, we conducted a remote sensing inversion exercise for soil salinity in the Bosten Lake watershed in Xinjiang, Northwest China, with a total area of about 43,930 km2, a typical watershed in an arid area. Sentinel MSI and Landsat OLI data were combined with measured soil salinity data in July 2020, and optimal combination bands were selected based on characteristic bands to create a grid search-support vector machine (GS-SVM) inversion model of soil salt content. The maximum value of soil salt content in the Bosten Lake watershed was 11.8 g/kg. The minimum value was 0.41 g/kg, and the average value was 4.77 g/kg, soil salinization is serious. The results of previous studies were applied to the estimation of salt content in Bosten Lake watershed and could not meet the monitoring requirements of the study area, R2 < 0.3. The GS-SVM soil salinity monitoring model was established based on the optimal DI, RI, and NDI remote sensing indexes for the Bosten Lake watershed. After model verification, it was found that the optimal model of image data was the Landsat OLI first-derivative model with R2 of 0.64, RMSE of 3.12, and RPD of 1.64, indicating that the prediction ability of the model was high. We used the first-order derivative model of Landsat OLI data to map the soil salt content in the Bosten Lake watershed in arid area, and found that soil salt content in most of the study area was between 10 and 20 g/kg, indicating severe salinization. This study not only reveals the distribution characteristics of salinization in Bosten Lake watershed, but also provides a scientific basis for soil salinization monitoring in Central Asia to lay a foundation for further soil salinization monitoring in arid areas.

Evaluation of Eutrophication in Jiaozhou Bay via Water Color Parameters Determination with UAV-Borne Hyperspectral Imagery

The continued increase in greenhouse gas emissions as a result of unprecedented eutrophication has resulted in a rising trend of red tides in the sea, which may be responsible for ecological degradation in the surrounding environment. Studies rarely investigate the accurate concentration of seawater eutrophication substances in offshore aquaculture areas, which may lead to the exacerbated pollution of inshore aquaculture. We examined whether offshore seawater quality monitoring can be effectively performed through unmanned aerial vehicles’ (UAVs) airborne hyperspectral remote sensing technique at Jiaozhou Bay, a water body associated with eutrophication. We used the UAV airborne hyperspectral imager to detect and measure typical marine aquaculture areas in Jiaozhou Bay and selected the key parameters of seawater quality, chlorophyll-a (Chl-a) concentrations, and total suspended matter (TSM) concentrations as indicators of seawater eutrophication. The hyperspectral inversion model of the Jiaozhou Bay seawater (JZBZ) was established with the optimal sensitive band of parameters. Results showed that in comparison with the traditional inversion model, the inversion R2 of the Chl-a was 0.712, the RPD was 3.72, and the inversion R2 of the TSM concentration was 0.756 while the RPD was 5.83. We found that this model is more suitable for the retrieval of water color parameters in Jiaozhou Bay. Additionally, by actual measurement, it can be seen that the concentration ranges of Chl-a in the observation area are 0.380–1.74 mg/m3, and the concentration range of TSM is 12.6–131 mg/L. The results of this study indicate that the Jiaozhou Bay Water Quality Translation Model (JZBM), based on the UAV airborne hyperspectral imager, performs well in the inversion of the concentration of chlorophyll and suspended particulate matter in offshore water, which advances our understanding with a new method to assess the degree of eutrophication in coastal waters.

Unsupervised Hyperspectral Band Selection via Multimodal Evolutionary Algorithm and Subspace Decomposition.

Unsupervised band selection is an essential task to search for representative bands in hyperspectral dimension reduction. Most of existing studies utilize the inherent attribute of hyperspectral image (HSI) and acquire single optimal band subset while ignoring the diversity of subsets. Moreover, the ordered property in HSI is expected to be focused in order to avoid choosing redundant bands. In this paper, we proposed an unsupervised band selection method based on the multimodal evolutionary algorithm and subspace decomposition to alleviate the problems. To explore the diversity of band subsets, the multimodal evolutionary algorithm is first employed in spectral subspace decomposition to seek out multiple global or local solutions. Meanwhile, in view of ordered property, we concentrate more on increasing the difference between neighbor band subspaces. Furthermore, to utilize the obtained multiple diverse band subsets, an integrated utilization strategy is adopted to improve the predicted performance. Experimental results on three popular hyperspectral remote sensing datasets and one collected composition prediction dataset show the effectiveness of the proposed method, and the superiority over state-of-the-art methods on predicted accuracy.