In this paper, we combined hyperspectral imaging techniques and deep neural networks (DNN) to detect Fusarium wilt on Phalaenopsis. Spectral angle mapper (SAM) and constrained energy minimization (CEM) were used to find abnormal areas. Band selection (BS) methods include Harsanyi-Farrand-Chang (HFC), band priority (BP) and band decorrelation (BD) were applied to get effective bands. The results showed that, on the fifth day of Phalaenopsis infection, the best accuracy rates for detecting Fusarium wilt using VNIR and SWIR hyperspectral imaging were 93.5% and 94.9%, respectively. In most cases, the accuracy of using DNN is better than using support vector machine (SVM).

Food safety and quality examination has received close attention from general public in recent years. One of examples is the freshness of pleurotus eryngii, which plays an important role in its economic values. The estimation of its freshness could not be based on the number of storage days because fungi could normally keep alive for a while after harvest depending on storage environment. With advances of hardware and software, hyperspectral technologies shed some light on prediction of its nonlinear decay trend. This paper proposed a spectral derivative analysis to improve the temporal accuracy of previous works [5] from weeks to days. Then, the long short-term memory neural network was utilized to predict the decay trend based on the data of beginning few days. The experimental studies demonstrated that the prediction trends were close to the real ones.

In this paper, we propose a method to inspect the quality of Phalaenopsis by using hyperspectral imaging techniques. Phalaenopsis is easy to get infected with Fusarium wilt. We use the k-means clustering method to find out that the reflection spectrum of Phalaenopsis stem changes. The methods of the Spectral Angle Mapper (SAM) and Constrained Energy Minimization (CEM) are then used to find the area of the infected area. The Harsanyi, Farrand and Chang (HFC) methods and virtual dimensions (VD) are used to estimate the amount of spectrum required for band selection (BS). Band priority (BP) is used to calculate the priority of each band, and band de-correlation (BD) will remove band data with high correlation with each other. Then use the support vector machine (SVM) to detect Phalaenopsis wilt. The detection accuracy of VNIR and SWIR is 0.81 and 0.86, respectively, with band selection.

N-finder algorithm (N-FINDR) has been widely used for finding endmembers in hyperspectral imagery. Since N-FINDR must find all endmembers simultaneously, it requires exhausting all possible p-endmember combinations among the entire data samples with p being the number of endmembers required to be found. Accordingly, directly implementing N-FINDR is practically infeasible. To mitigate this dilemma, two recently developed algorithms called sequential N-FINDR (SQ N-FINDR) and successive N-FINDR (SC N-FINDR) were developed. However, even such an exhaustive search issue can be resolved numerically, another challenging issue for N-FINDR, which remains unsolved, is spectral dimensionality reduction. Because a p-vertex simplex is embedded in a (p-1)-dimensional spectral data space, N-FINDR does not require full spectral dimensionality to calculate simplex volume (SV). This article presents a compressive sensing (CS) approach to N-FINDR that can find a p-vertex simplex with the maximal SV by SQ/SC N-FINDR in a compressively sensed band domain (CSBD). In particular, to make this idea work, a new CS-based property called restricted SV property (RSVP) can be shown to be preserved in CSBD via a sensing matrix. It is this property that allows what N-FINDR and SQ/SC N-FINDR can achieve in the original data space (ODS) to be also achieved in CSBD. To further show the utility of SQ/SC N-FINDR in both ODS and CSBD as well as SV preserved by RSVP, a series of experiments are conducted for performance analysis.

Fusarium wilt on Phalaenopsis is a disease that makes farmers suffer seriously. Although Phalaenopsis does not die immediately with Fusarium wilt, it seriously decreases the quality that buyers cannot accept. In this paper, we introduce an emerging method to detect Fusarium wilt at the base of Phalaenopsis stems. The detection model divides Phalaenopsis samples into two categories, healthy and infection. The band selection (BS) processing technique based on band prioritization (BP) is applied to extract significant bands and eliminate redundant bands. Subsequently, some algorithms which are constrained energy minimization (CEM), spectral information divergence(SID) and SeQuential N-FINDER to detect the Fusarium wilt, and we hope the research would help farmers decrease their losses.

Phalaenopsis is a significant agriculture product with high economic value in Taiwan. However, the fusarium wilt causes Phalaenopsis leaves turning yellow, thinning, water loss, and finally died. This paper presents an emerging method to detect fusarium wilt on Phalaenopsis stem base. In order to build the detection models, the hyperspectral databases are generated form two statues of Phalaenopsis samples, which are health and disease sample. We applied band selection (BS) processing base on band prioritization (BP) and band de-correlation (BD) to extract the significant bands and eliminate the redundant bands. Then, three algorithms were used, orthogonal subspace projection (OSP), constrain energy minimization (CEM), and support vector machine (SVM) to detect the fusarium wilt.

One of the most powerful ideas in deep learning is the transfer learning technique. Transfer learning can be utilized to take a knowledge from what a deep neural network has learned from a particular task and apply that knowledge to a different task. Transfer learning is very useful when the size of the training samples of interest is small to train a neural network from scratch. This research focuses on the concept of transfer learning where the Convolutional Neural Network (CNN) power can be utilized as a features extractor to help with classifying benign from malignant breast cancer images. In addition, Support Vector Machine (SVM) classifier based on Radial Basis Function (RBF) was adapted for its flexibility in fitting the data dimension space adequately by tuning the kernel width. The hybridization between CNN and RBF-Based SVM showed robust results for both the dataset and the application task of this research. The contribution of this paper can be summarized in three major parts. First, a CNN was implemented from scratch on a large number of available spine images to classify images of two different spine views (sagittal and axial) in order to transfer the learning process to the CNN of breast images. Second, retrain the spine CNN on the images of breast cancer to classify between benign and malignant cases by fine-tuning. Finally, the features were extracted from the retrained CNN and fed to RBF-Based SVM to classify benign from malignant breast mammogram images.

This research method is motivated by Rat Grimace Scale(RGS) method in [1]. Their approach indicates the utility of quantifying spontaneous pain in mice via blinded coding of facial expression, but there is a general concern about rating with subjective criteria of mice experts. Therefore, this research utilizes a supervised parameter linear SVM classifier for long-term monitor of pain face. The contributions are summarized in two points. First, a statistical analysis of pain face has been done for exploring facial patterns before training SVM classifier. Second, a blind test has been implemented to evaluate the rating performance of the mice experts versus linear SVM classifier. Surprisingly, SVM-based approach is much more reliable than the experts. In addition, the hypothesis does not rely on the subjective determination, this manuscript approach further automates whole process by implementing haar cascade for extracting the facial patterns. All in all, we believe that SVM-based pain face detection can be used as a comprehensive and no human interventions index for developing chronic pain scoring system in the future.

Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.

Pollock model was one of the popular template matching algorithms, which constructs a three-dimensional description of each individual tree-crown envelope. Unfortunately, it is always challenging to determine parameters since each tree has different grown condition. This paper proposed an iterative least square fitting algorithm to form a Pollock model best fitting each individual tree for tree detection and crown delineation. The proposed algorithm provides a solution to avoid difficulties of finding the best set of parameters for each tree crown. As a result, it improves the detection rate and decreases the computing time as shown in the experimental studies. The proposed least square fitting algorithm is more suitable for practical applications.

Multi-level morphological active contour algorithm (MMAC), was proposed in [3-4], to incorporate mathematical morphology for tree detection and crown delineation with the average prediction error around 4% in mountainous areas. However, two major drawbacks come with the design of MMAC algorithm, which are huge computational complexity and certain level of false alarm or omission rate. The paper provides a solution for two major problems by proposing a gradient vector flow (GVF) snake based MMAC algorithm. The GVF snake model took advantage of the gradient vector force of the LiDAR image and expand the boundary of each blob to approximate the real crown of each forest candidate. According to the experimental studies, the proposed algorithm could help improve the computational complexity and detection rate of the original MMAC algorithm effectively.

Forests in mountainous areas normally contain a diverse variety, including tropical rain forests, subtropical evergreen forests, temperate forests, and alpine cold forests. These forests distribute vertically along the central region and can be categorized into broadleaved, mixed, and conifer forests. Terrain features in mountainous areas make manual inspection of forests both labor-intensive and time-consuming if not impossible. By utilizing remote sensing techniques the efforts of field sampling could be effectively reduced.

Development of agriculture has shifted its emphasis from increasing of quantity to quality. Pesticides have been commonly used as plant protection products to increase gains of agricultural products for decades. Generally speaking, a pesticide is a chemical or biological agent to prevent damage influences from pests. Since application of pesticides has been so successful, nowadays most agricultural products available in the consumer markets were raised with at least a few pesticides. Nevertheless, the negative effects of pesticide exposure have been continuously found in many studies, including cancers[1], neurological diseases[2], reproductive effects[3], etc. The health effects of pesticides has caused public concerns for level of pesticide residues on food. Currently there are several methods available to examine pesticide residues, such as mass spectroscopy, Raman spectroscopy, FTIR Analysis, and infrared absorption spectroscopy. However, each of them has their own constraints in sample preparation, examination environments, or light sources. These limitations make current examinations very time-consuming and cost-ineffective.

Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Until recently, the machine learning algorithms had been investigated in [5-7] for an automatic classification system. The automatic classification system exploited the luminance of cerebrospinal fluid (CSF) as the major features. Unfortunately, the limited sequences of magnetic resonance images, which included only T1and T2sequences, produced certain level of false alarm and reduced the classification rate. The band expansion process(BEP) proposed in [8] shed light on this issue by generating additional bands with non-linear functions. The idea of BEP unveils the non-linear relationship among sequences to increase the classification rate. The utilities of BEP had been evaluated in brain MR images [9]. This paper would like to extend the applications of BEP for classification of CSF. The experimental studies further demonstrated the benefits of the BEP.

This paper develops band weighting spectral methods, which are wSAM and wSID, for detection of pesticide residues on vegetables. Since the water content of vegetables has significant impact on the measured spectrum, the proposed band weighting measures are able to suppress the effect of water content to enhance detectability of of pesticide residue detection. Compared to the traditional band selection techniques, there are three advantages. First of all, it does not require determining the number of bands to be selected. Second, the proposed methods assigned a weight to each band based on the amount of pesticide information. Third, the band weighting method could help reduce the effect of undesired signal, which is the water content in our case. The experimental study further demonstrates the utilities of our proposed band weighting methods.

Aerobics is one of the best exercises for a full-body or functional workout. However, the flexibility of aerobics also makes it difficult to estimate calories consumption. The single accelerometer method developed in [20] failed to provide an accurate model due to the complicated movement of aerobics. This manuscript proposed a method to accurately estimate the calories consumption. The proposed method took advantage of Microsoft Kinect to track 10 body joints of exercisers. Since each node could be considered as a 3-axis accelerometer mounting the corresponding joint, so the multiple regression model was exploited to form an estimation model. The accuracy and robustness of the estimation model was evaluated in the experimental studies. The results indicated that the calories consumption of aerobics could be estimated accurately with 14 times of training.

Multi-level Morphological Active Contour algorithm (MMAC) had been proposed to effectively increase recognition rate of individual tree in mountainous areas. However, it was specifically designed for LiDAR CHM data only, which make the algorithm incompatible with any other type of remote sensing data. To relieve constraints of MMAC this manuscript proposed a spectral-based MMAC (SB-MMAC), which retains the framework of MMAC by replacing height information from LiDAR CHM model with spectral information from multispectral images. The proposed SB-MMAC is comprised of two stages, seed blobs detection and modified active contour model. The experimental study further demonstrated the utility of SB-MMAC.

One key issue encountered in endmember extraction is to determine the number of endmembers, p, required to be extracted. Virtual dimensionality (VD) has been widely used for this purpose. However, VD was originally developed and defined as the number of spectrally distinct signatures which are not necessarily pure signatures. So, on some occasions the VD estimated value for p may not be accurate to be used for the number of endmembers. This paper develops an endmember-specified VD (ES-VD) which makes use of data sample vectors generated by a specific endemember finding algorithm (EFA) as target signal sources and then determine if these signal sources are indeed true endmember by a binary composite hypothesis testing to determine endmembers. As a result, ES-VD varies with different target signal sources produced by EFAs. Most importantly, ES-VD not only determines the value of VD and in the mean time it also finds desired endmembers.

Forests in Taiwan contain a diverse variety. Remote sensing data could offer information of large area sampling, but it is very challenging to automatically detect tree and delineate three crown in remote sensing data. Recently a algorithm, called multi-level morphological active contour algorithm (MMAC), has been proposed to address these issues in [1]. It combines a multi-level morphological approach with the active contour model. However, this algorithm comes with a price, which is huge computational complexity, to prevent it from being implemented practically in medium- or large-scale images. This manuscript aimed to accelerate MMAC by developing a parallel processing approach using reconfigurable computing platform with field-programmable gate arrays (FPGA). The experimental evaluation indicated that the proposed architecture could provide around 40% acceleration with simple implementation in hardware.

Band selection (BS) has advantages over data dimensionality in satellite communication and data transmission. However, several issues regarding real time processing need to be addressed, (1) how many bands required for BS, (2) how to select appropriate bands, (3) how to take advantage of previously selected bands without re-implementing BS, and finally and most important, (4) how to tune bands to be selected in real time as number of bands varies. This paper presents a new approach, called progressive band processing (PBP) for Modified Fully Abundance-Constrained Spectral Unmixing (MFCLS) without actually implementing BS. When spectral unmixing is performed, BS must be done prior to data unmixing in which case real time implementation in data communication is infeasible. The proposed PBP-MFCLS allows users to incorporate new incoming bands into data unmixing currently being processed. Accordingly, PBP-MFCLS can be carried out band by band in a real time and progressive fashion with unmixed data updated recursively band by band in the same way that data is processed by a Kalman filter.

Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenos is (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.

N-finder algorithm (N-FINDR) has been widely used for endmember extraction in hyperspectral imagery. Due to its high computational complexity, developing fast computing N-FINDR has received considerable interest, specifically to take advantage of field-programmable gate array (FPGA) architecture in hardware implementation to realize N-FINDR. However, there are two severe drawbacks arising in the nature of N-FINDR design, the number of endmembers,p, which must be fixed once its value is determined in FPGA design and inconsistency in final extracted endmembers caused by different selections of initial endmembers. This paper investigates a progressive version of N-FINDR, previously known as simplex growing algorithm for its FPGA implementation which can resolve these two issues.

The cross section area of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, this region can only be defined by doctors manually and calculated the amount of area by commercial software at present. The solution for reliable and robust classification and measurement remains open. This manuscript utilized kernel-based support vector machine to provide an automatically classification and measurement of the cross-section area of spinal canal. This kernel-based SVM classifier is compared with the linear SVM proposed in [1] and the present method. The experiments showed that the kernel based-SVM classifier could provide a better performance and robust classification result for the cross section area of spinal canal.

Two of the most challenging issues in the unsupervised linear spectral mixture analysis (ULSMA) are: 1) determining the number of signatures to form a linear mixing model; and 2) finding the signatures used to unmix data. These two issues do not occur in supervised LSMA since the target signatures are assumed to be known a priori. With recent advances in hyperspectral sensor technology, many unknown and subtle signal sources can now be uncovered and revealed and such signal sources generally cannot be identified by prior knowledge. Even when they can, the obtained knowledge may not be reliable, accurate, or complete. As a consequence, the resulting unmixed results may be misleading. This paper addresses these issues by introducing a new concept of inter-band spectral information (IBSI), which can be used to categorize signatures into background and target classes in terms of their sample spectral statistics. It then develops a component analysis (CA)-based ULSMA where two classes of signatures can be extracted directly from the data by two different CA-based transforms without requiring prior knowledge. In order to substantiate the utility of the proposed approach, synthetic images are used for experiments and real images are further used for validation.

N-finder algorithm (N-FINDR) has been widely used in endmember extraction. When it comes to implementation several issues need to be addressed. One is determination of endmembers, p required for N-FINDR to generate. Another is its computational complexity resulting from an exhaustive search. A third one is its requirement of dimensionality reduction. A fourth and probably the most critical issue is its use of random initial endmembers which results in inconsistent final endmember selection and results are not reproducible. This paper re-invents the wheel by re-designing the N-FINDR in such a way that all the above-mentioned issues can be resolved while making the last issue an advantage. The idea is to implement the N-FINDR as a random algorithm, called random N-FINDR (RN-FINDR) so that a single run using one set of random initial endmembers is considered as one realization. If there is an endmember present in the data, it should appear in any realization regardless of what random set of initial endmembers is used. In this case, the N-FINDR is terminated when the intersection of all realizations produced by two consecutive runs of RN-FINDR remains the same in which case the p is then automatically determined by the intersection set without appealing for any criterion. In order to substantiate the proposed RN-FINDR custom-designed synthetic image experiments with complete knowledge are conducted for validation and real image experiments are also performed to demonstrate its utility in applications.

Endmember extraction has received increasing interest in hyperspectral image analysis. One widely used endmember extraction algorithm is pixel purity index (PPI), which finds endmembers via a set of random vectors, called skewers. Several issues arise in its implementation. One is the prior knowledge of the number of skewersKrequired to be used. Second, due to random nature in skewers, the final results are inconsistent and unreproducible. Third, it needs to know the number of dimensions to be retained after dimensionality reduction. Fourth, it needs to preset a cutoff threshold to extract potential endmembers. Finally, it involves human intervention to manually select final endmembers. This letter derives a random PPI (RPPI) to resolve the aforementioned issues. It considers the result produced by PPI using a random set of initial vectors as skewers as a realization of a random algorithm. From a statistical signal processing view point, if endmembers are crucial in terms of information, they should occur in realizations produced by PPI regardless of what set is chosen for skewers. By virtue of this assumption, the proposed RPPI is developed and validated by experiments.

The simplex growing algorithm (SGA) was recently developed as an alternative to the N-finder algorithm (N-FINDR) and shown to be a promising endmember extraction technique. This paper further extends the SGA to a versatile real-time (RT) processing algorithm, referred to as RT SGA, which can effectively address the following four major issues arising in the practical implementation for N-FINDR: (1) use of random initial endmembers which causes inconsistent final results; (2) high computational complexity which results from an exhaustive search for finding all endmembers simultaneously; (3) requirement of dimensionality reduction because of large data volumes; and (4) lack of RT capability. In addition to the aforementioned advantages, the proposed RT SGA can also be implemented by various criteria in endmember extraction other than the maximum simplex volume.

Virtual dimensionality (VD) is a new concept which was originally developed for estimating the number of spectrally distinct signatures present in hyperspectral data. The effectiveness of the VD is determined by the technique used for VD estimation. This paper develops an orthogonal subspace projection (OSP) technique to estimate the VD. The idea is derived from linear spectral mixture analysis where a data sample vector is modeled as a linear mixture of a finite set of what is called as virtual endmembers in this paper. A similar idea was also previously investigated by the signal subspace estimate (SSE) and was later improved by hyperspectral signal subspace identification by minimum error (HySime), where the minimum mean squared error is used as a criterion to determine the VD. Interestingly, with an appropriate interpretation, the proposed OSP technique includes the SSE/HySime as its special case. In order to demonstrate its utility, experiments using synthetic images and real image data sets are conducted for performance analysis.

Simplex growing algorithm (SGA) was recently developed as an alternative to the N-finder algorithm (N-FINDR) which is shown to be a promising endmember extraction technique. This paper further extends the SGA to a real-time processing algorithm, referred to as real-time SGA (RT SGA) that can effectively address four major issues arising in practical implementation for N-FINDR, (1) use of random initial endmembers which causes inconsistent final results, (2) very high computational complexity which results from an exhaustive search for finding all endmembers simultaneously, (3) requirement of dimensionality reduction because of enormous data volumes to be processed and (4) lack of real-time capability.

A recent paper by Changdevelops a new algorithm, called the simplex growing algorithm, which has shown promise in endmember extraction. There is an erroneous description made for one of synthetic image experiments. While making a simple correction would have sufficed, a series of studies has led to interesting and intriguing results on how to determine an appropriate number of endmembers$p$, how to design a better endmember extraction algorithm, and how to use an effective technique to perform dimensionality reduction.

One of commonly used criteria for finding an endmember set is to assume that for a given number of endmembers, p, a p-vertex simplex with its vertices specified by p endmembers always yields the maximum volume. Since there are also other criteria which have been widely used for endmember extraction, the issue of interest is "does an endmember set really produce a simplex with maximum volume?" In other words, using the criterion of a simplex with maximum volume is a better and more effective measure than other criteria currently being used by endmember extraction such as orthogonal projection-based pixel purity index (PPI), fully constrained least squares-based spectral unmixing, etc. This paper explores this issue by investigating a number of popular endmember extraction algorithms which are designed by different criteria. An extensive experiment-based study is also conducted for comparative analysis.

A new growing method for simplex-based endmember extraction algorithms (EEAs), called simplex growing algorithm (SGA), is presented in this paper. It is a sequential algorithm to find a simplex with the maximum volume every time a new vertex is added. In order to terminate this algorithm a recently developed concept, virtual dimensionality (VD), is implemented as a stopping rule to determine the number of vertices required for the algorithm to generate. The SGA improves one commonly used EEA, the N-finder algorithm (N-FINDR) developed by Winter, by including a process of growing simplexes one vertex at a time until it reaches a desired number of vertices estimated by the VD, which results in a tremendous reduction of computational complexity. Additionally, it also judiciously selects an appropriate initial vector to avoid a dilemma caused by the use of random vectors as its initial condition in the N-FINDR where the N-FINDR generally produces different sets of final endmembers if different sets of randomly generated initial endmembers are used. In order to demonstrate the performance of the proposed SGA, the N-FINDR and two other EEAs, pixel purity index, and vertex component analysis are used for comparison.