Decision Templates Research Articles

Model observer design for multi-signal detection in the presence of anatomical noise

As psychophysical studies are resource-intensive to conduct, model observers are commonly used to assess and optimize medical imaging quality. Model observers are typically designed to detect at most one signal. However, in clinical practice, there may be multiple abnormalities in a single image set (e.g. multifocal multicentric (MFMC) breast cancer), which can impact treatment planning. Prevalence of signals can be different across anatomical regions, and human observers do not know the number or location of signals a priori. As new imaging techniques have the potential to improve multiple-signal detection (e.g. digital breast tomosynthesis may be more effective for diagnosis of MFMC than mammography), image quality assessment approaches addressing such tasks are needed. In this study, we present a model observer to detect multiple signals in an image dataset. A novel implementation of partial least squares (PLS) was developed to estimate different sets of efficient channels directly from the images. The PLS channels are adaptive to the characteristics of signals and the background, and they capture the interactions among signal locations. Corresponding linear decision templates are employed to generate both image-level and location-specific scores on the presence of signals. Our results show that: (1) the model observer can achieve high performance with a reasonably small number of channels; (2) the model observer with PLS channels outperforms that with benchmark modified Laguerre–Gauss channels, especially when realistic signal shapes and complex background statistics are involved; (3) the tasks of clinical interest, and other constraints such as sample size would alter the optimal design of the model observer.

Ontology-based executable design decision template representation and reuse

AbstractIn decision-based design, the principal role of a designer is to make decisions. Decision support is crucial to augment this role. In this paper, we present an ontology that provides decision support from both the “construct” and the “information” perspectives that address the gap that existing research focus on these two perspectives separately and cannot provide effective decision support. The decision support construct in the ontology is the compromise decision support problem (cDSP) that is used to make multiobjective design decisions. The information for decision making is archived as cDSP templates and represented using frame-based ontology for facilitating reuse, consistency maintaining, and rapid execution. In order to facilitate designers’ effective reuse of the populated cDSP templates ontology instances, we identified three types of modification that can be made when design consideration evolves. In our earlier work, part of the utilization (consistency checking) of the ontology has been demonstrated through a thin-walled pressure vessel redesign example. In this paper, we comprehensively present the ontology utilization including consistency checking, trade-off analysis, and design space visualization based on the pressure vessel example.

High resolution multisensor fusion of SAR, optical and LiDAR data based on crisp vs. fuzzy and feature vs. decision ensemble systems

Synthetic Aperture Radar (SAR) data are of high interest for different applications in remote sensing specially land cover classification. SAR imaging is independent of solar illumination and weather conditions. It can even penetrate some of the Earth’s surface materials to return information about subsurface features. However, the response of radar is more a function of geometry and structure than a surface reflection occurs in optical images. In addition, the backscatter of objects in the microwave range depends on the frequency of the band used, and the grey values in SAR images are different from the usual assumption of the spectral reflectance of the Earth’s surface. Consequently, SAR imaging is often used as a complementary technique to traditional optical remote sensing. This study presents different ensemble systems for multisensor fusion of SAR, multispectral and LiDAR data. First, in decision ensemble system, after extraction and selection of proper features from each data, crisp SVM (Support Vector Machine) and Fuzzy KNN (K Nearest Neighbor) are utilized on each feature space. Finally Bayesian Theory is applied to fuse SVMs when Decision Template (DT) and Dempster Shafer (DS) are applied as fuzzy decision fusion methods on KNNs. Second, in feature ensemble system, features from all data are applied on a cube. Then classifications were performed by SVM and FKNN as crisp and fuzzy decision making system respectively. A co-registered TerrraSAR-X, WorldView-2 and LiDAR data set form San Francisco of USA was available to examine the effectiveness of the proposed method. The results show that combinations of SAR data with different sensor improves classification results for most of the classes.

P12CDK2-AP1 interacts with CD82 to regulate the proliferation and survival of human oral squamous cell carcinoma cells.

p12 cyclin-dependent kinase2 (CDK2)-associating protein1 (p12CDK2-AP1) has been demonstrated to negatively regulate the activity of CDK2. However, the underlying molecular mechanism remains largely unknown. We aimed to determine the potential binding proteins of p12CDK2-AP1 and to elucidate the role of p12CDK2-AP1 in the regulation of the proliferation, invasion, apoptosis, and invivo growth of human oral squamous cell carcinoma cells. The protein-protein interaction was predicted using computational decision templates. The predicted p12CDK2‑AP1 interacting proteins were overexpressed in human oral squamous cell carcinoma OSCC-15 cells, and the protein binding was examined using co-precipitation (Co-IP). Cell proliferation and invasion were determined via MTT assay and Transwell system, respectively. Cell apoptosis was evaluated using AnnexinV-FITC/PI double staining followed by flow cytometric analysis. The invivo growth of OSCC-15 cells was examined in nude mouse tumor xenografts. We found that overexpression of either p12CDK2-AP1 or CD82 significantly suppressed the proliferation and invasion but promoted the apoptosis of OSCC-15 cells (P<0.05). Importantly, combined overexpression of p12CDK2-AP1 and CD82 showed synergistic antitumor activity compared with the overexpression of a single protein alone (P<0.05). Additionally, the simultaneous overexpression of p12CDK2-AP1 and CD82 significantly suppressed the invivo tumor growth of OSCC-15 cells in nude mice compared with the negative control (P<0.05). Our findings indicate that p12CDK2-AP1 interacts with CD82 to play a functional role in suppressing the invitro and invivo growth of OSCC-15 cells.

Bio-Inspired Computational Algorithms for Improved Image Steganalysis

Acquiring the best image features that best distinguishes a stego and clean image is a challenge in image steganalysis. Though higher order models acquire all these features, they pose problems due to computational complexity in terms of time and space. This demands optimization of the feature sets. Compared to the existing statistical feature optimization techniques, genetic algorithm based optimization techniques are evolving to be more promising. The existing deterministic methods of optimization have the limitation of converging into local minima as compared to the evolutionary methods which tend to converge to the global minima. Objectives: This paper intends to review the various genetic algorithm based feature optimization techniques applicable for image steganalysis of JPEG images and identify the best algorithm that converges to global minima. Method/Analysis: The methods analysed include the stochastic (metaheuristic) algorithms that make use of the random behaviour of plants and animals. The Antlion behaviour based optimization technique (ALO) has been implemented and analysed for JPEG stego images. The movement of ants are modelled as random walk and the traps built by antlions are assumed proportional to their fitness. The antlions shoot sand outwards to pull the ants inside the pits. This causes sliding down of the ants into the pits to the most minimum position. The coding of the optimization is implemented in Matlab with images taken from the standard BOSS database. Findings: The feature set after feature extraction has a dimension of 2000 × 48600 with 1000 cover and 1000 clean images. Considering these vectors as the initial positions of the ants in the Ant Lion Optimizer, for a payload of 0.5 in embedding logic the classification accuracies are studied. The convergence of this optimizer is proved according to the convergence curve for 300 iterations. After optimization, the reduced feature set is used to classify the image as cover or stego image. SVM, MLP and the fusion classifiers - Bayes, Decision template and Dempster Schafer are used. For low levels of embedding changes, the classification by MLP and Fusion schemes is good. For medium and high levels of embedding changes, the classification by Fusion schemes alone is good. It has been identified that the proposed steganalyser gives best results for Bayes fusion classification (69%) scheme when Antlion behaviour is used as optimizer. Applications/Improvements: This research has implemented a novel method of image feature optimization that improves steganalysis. The optimized feature set is 100 times less in dimension assuring reduced computational complexity in time and space. Improved version of this research may include a different selection mechanism or using a different optimization function.

A Multiple Classifier Fusion Algorithm Using Weighted Decision Templates

Fusing classifiers’ decisions can improve the performance of a pattern recognition system. Many applications areas have adopted the methods of multiple classifier fusion to increase the classification accuracy in the recognition process. From fully considering the classifier performance differences and the training sample information, a multiple classifier fusion algorithm using weighted decision templates is proposed in this paper. The algorithm uses a statistical vector to measure the classifier’s performance and makes a weighed transform on each classifier according to the reliability of its output. To make a decision, the information in the training samples around an input sample is used by thek-nearest-neighbor rule if the algorithm evaluates the sample as being highly likely to be misclassified. An experimental comparison was performed on 15 data sets from the KDD’99, UCI, and ELENA databases. The experimental results indicate that the algorithm can achieve better classification performance. Next, the algorithm was applied to cataract grading in the cataract ultrasonic phacoemulsification operation. The application result indicates that the proposed algorithm is effective and can meet the practical requirements of the operation.

Fusion of hyperspectral and LIDAR data using decision template-based fuzzy multiple classifier system

Regarding to the limitations and benefits of remote sensing sensors, fusion of remote sensing data from multiple sensors such as hyperspectral and LIDAR (light detection and ranging) is effective at land cover classification. Hyperspectral images (HSI) provide a detailed description of the spectral signatures of classes, whereas LIDAR data give height detailed information. However, because of the more complexities and mixed information in LIDAR and HSI, traditional crisp classification methods could not be more efficient. In this situation, fuzzy classifiers could deliver more satisfactory results than crisp classification approaches. Also, referring to the limitation of single classifiers, multiple classifier system (MCS) may exhibit better performance in the field of multi-sensor fusion. This paper presents a fuzzy multiple classifier system for fusions of HSI and LIDAR data based on decision template (DT). After feature extraction and feature selection on each data, all selected features of both data are applied on a cube. Then classifications were performed by fuzzy k-nearest neighbour (FKNN) and fuzzy maximum likelihood (FML) on cube of features. Finally, a fuzzy decision fusion method is utilized to fuse the results of fuzzy classifiers. In order to assess fuzzy MCS proposed method, a crisp MCS based on support vector machine (SVM), KNN and maximum likelihood (ML) as crisp classifiers and naive Bayes (NB) as crisp classifier fusion method is applied on selected cube feature. A co-registered HSI and LIDAR data set from Houston of USA was available to examine the effect of proposed MCSs. Fuzzy MCS on HSI and LIDAR data provide interesting conclusions on the effectiveness and potentialities of the joint use of these two data.

Vehicle identification by improved stacking via kernel principal component regression

Purpose – Many applications in intelligent transportation demand accurate categorization of vehicles. The purpose of this paper is to propose a working image-based vehicle classification system. The first component vehicle detection is implemented by applying Dalal and Triggs's histograms of oriented gradients features and linear support vector machine (SVM) classifier. The second component vehicle classification, which is the emphasis of this paper, is accomplished by an improved stacked generalization. As an effective ensemble learning strategy, stacked generalization has been proposed to combine multiple models using the concept of a meta-learner. However, it was found that the well-known meta-learning scheme multi-response linear regression (MLR) for stacked generalization performs poorly on the vehicle classification. Design/methodology/approach – A new meta-learner is then proposed based on kernel principal component regression (KPCR). The stacked generalization scheme consists of a heterogeneous classifier ensemble with seven base classifiers, i.e. linear discriminant classifier, fuzzy k-nearest neighbor, logistic regression, Parzen classifier, Gaussian mixture model, multiple layer perceptron and SVM. Findings – Experimental results using more than 2,500 images from four types of vehicles (bus, light truck, car and van) demonstrated the effectiveness of the proposed approach. The improved stacked generalization produced consistently better results when compared to any of the single base classifier used and four other beta learning algorithms, including MLR, majority voting, logistic regression and decision template. Originality/value – With the seven base classifiers, the KPCR-based stacking offers a performance of 96 percent accuracy and 95 percent κ coefficient, thus exhibiting promising potentials for real-world applications.

Combining localized fusion and dynamic selection for high-performance SVM

To resolve class-ambiguity in real world problems, we previously presented two different ensemble approaches with support vector machines (SVMs): multiple decision templates (MuDTs) and dynamic ordering of one-vs.-all SVMs (DO-SVMs). MuDTs is a classifier fusion method, which models intra-class variations as subclass templates. On the other hand, DO-SVMs is an ensemble method that dynamically selects proper SVMs to classify an input sample based on its class probability. In this paper, we newly propose a hybrid scheme of those two approaches to utilize their complementary properties. The localized fusion approach of MuDTs increases variance of the classification models while the dynamic selection scheme of DO-SVMs reduces the unbiased-variance, which causes incorrect prediction. We show the complementary properties of MuDTs and DO-SVMs with several benchmark datasets and verify the performance of the proposed method. We also test how much our method could increase its baseline accuracy by comparing with other combinatorial ensemble approaches.

MSLoc-DT: A new method for predicting the protein subcellular location of multispecies based on decision templates

Revealing the subcellular location of newly discovered protein sequences can bring insight to their function and guide research at the cellular level. The rapidly increasing number of sequences entering the genome databanks has called for the development of automated analysis methods. Currently, most existing methods used to predict protein subcellular locations cover only one, or a very limited number of species. Therefore, it is necessary to develop reliable and effective computational approaches to further improve the performance of protein subcellular prediction and, at the same time, cover more species. The current study reports the development of a novel predictor called MSLoc-DT to predict the protein subcellular locations of human, animal, plant, bacteria, virus, fungi, and archaea by introducing a novel feature extraction approach termed Amino Acid Index Distribution (AAID) and then fusing gene ontology information, sequential evolutionary information, and sequence statistical information through four different modes of pseudo amino acid composition (PseAAC) with a decision template rule. Using the jackknife test, MSLoc-DT can achieve 86.5, 98.3, 90.3, 98.5, 95.9, 98.1, and 99.3% overall accuracy for human, animal, plant, bacteria, virus, fungi, and archaea, respectively, on seven stringent benchmark datasets. Compared with other predictors (e.g., Gpos-PLoc, Gneg-PLoc, Virus-PLoc, Plant-PLoc, Plant-mPLoc, ProLoc-Go, Hum-PLoc, GOASVM) on the gram-positive, gram-negative, virus, plant, eukaryotic, and human datasets, the new MSLoc-DT predictor is much more effective and robust. Although the MSLoc-DT predictor is designed to predict the single location of proteins, our method can be extended to multiple locations of proteins by introducing multilabel machine learning approaches, such as the support vector machine and deep learning, as substitutes for the K-nearest neighbor (KNN) method. As a user-friendly web server, MSLoc-DT is freely accessible at http://bioinfo.ibp.ac.cn/MSLOC_DT/index.html.

Combining classifiers using nearest decision prototypes

We present a new classifier fusion method to combine soft-level classifiers with a new approach, which can be considered as a generalized decision templates method. Previous combining methods based on decision templates employ a single prototype for each class, but this global point of view mostly fails to properly represent the decision space. This drawback extremely affects the classification rate in such cases: insufficient number of training samples, island-shaped decision space distribution, and classes with highly overlapped decision spaces. To better represent the decision space, we utilize a prototype selection method to obtain a set of local decision prototypes for each class. Afterward, to determine the class of a test pattern, its decision profile is computed and then compared to all decision prototypes. In other words, for each class, the larger the numbers of decision prototypes near to the decision profile of a given pattern, the higher the chance for that class. The efficiency of our proposed method is evaluated over some well-known classification datasets suggesting superiority of our method in comparison with other proposed techniques.

Learning Optimizes Decision Templates in the Human Visual Cortex

Translating sensory information into perceptual decisions is a core challenge faced by the brain. This ability is understood to rely on weighting sensory evidence in order to form mental templates of the critical differences between objects. Learning is shown to optimize these templates for efficient task performance, but the neural mechanisms underlying this improvement remain unknown. Here, we identify the mechanisms that the brain uses to implement templates for perceptual decisions through experience. We trained observers to discriminate visual forms that were randomly perturbed by noise. To characterize the internal stimulus template that observers learn when performing this task, we adopted a classification image approach (e.g., [5-7]) for the analysis of both behavioral and fMRI data. By reverse correlating behavioral and multivoxel pattern responses with noisy stimulus trials, we identified the critical image parts that determine the observers' choice. Observers learned to integrate information across locations and weight the discriminative image parts. Training enhanced shape processing in the lateral occipital area, which was shown to reflect size-invariant representations of informative image parts. Our findings demonstrate that learning optimizes mental templates for perceptual decisions by tuning the representation of informative image parts in higher ventral cortex.

Drug Shortage: A Transdisciplinary Team Approach to Injectable Vitamin K Shortage for Newborns

Purpose for the Program The 2011 American Hospital Association survey found 100% of responding hospitals (N = 800) experienced a drug shortage in the past 6 months. The proposed presentation will present a model of care developed in response to a critical shortage of injectable vitamin K to newborns at a tertiary regional hospital. The implemented management strategy, developed by a transdisciplinary team, considered issues of safety, ethics, communication, collaboration, education, and evaluated published, evidence‐based data on the use of alternative formulations of vitamin K. Proposed Change In an immediate response to a critical injectable vitamin K shortage at a children's hospital, a transdisciplinary team was formed and an action plan developed, which currently serves as a response model for drug shortage management. Inclusion of the voice of patients was a cornerstone to addressing their needs during this drug shortage crisis. Implementation, Outcomes, and Evaluation The response included availability assessment of alternative drug formulations; development of evidence‐based clinical guidelines; electronic point of care decision‐making tools for physicians; education materials for patients/families; education materials for healthcare providers on management plans; ethical considerations for rationing of supplies; and communication strategies for all administrators, healthcare providers, and patients. The success of the program was linked to working with a local pharmacy to compound oral vitamin K for administration to the infants who met the criteria for that route of administration. Injectable vitamin K was reserved for infants in the neonatal intensive care unit and high‐risk infants. Tools developed to support the model of drug shortage response include color coding system of drug supply for pharmacy and healthcare providers, process flow diagrams, published literature classification system, point of care decision templates, lists of ethical principles to consider, pharmacy policies guiding evaluation of alternative suppliers, and educational guides. As a result of the collaborative response to the injectable vitamin K shortage, 100% of the infants, whose parents consented to receive vitamin K, were given the correct oral dosage while in the hospital. Continued development and system‐wide dissemination of the drug shortage response model is underway. Implications for Nursing Practice By proactively addressing the drug shortage, safety, evidence‐based clinical practice, ethical decision making, efficiency, and cost have the potential to be affected. The response to drug shortages is best conducted with a proactive, rather than reactive, approach to have the necessary elements in place for an appropriate controlled response. The 2011 American Hospital Association survey found 100% of responding hospitals (N = 800) experienced a drug shortage in the past 6 months. The proposed presentation will present a model of care developed in response to a critical shortage of injectable vitamin K to newborns at a tertiary regional hospital. The implemented management strategy, developed by a transdisciplinary team, considered issues of safety, ethics, communication, collaboration, education, and evaluated published, evidence‐based data on the use of alternative formulations of vitamin K. In an immediate response to a critical injectable vitamin K shortage at a children's hospital, a transdisciplinary team was formed and an action plan developed, which currently serves as a response model for drug shortage management. Inclusion of the voice of patients was a cornerstone to addressing their needs during this drug shortage crisis. The response included availability assessment of alternative drug formulations; development of evidence‐based clinical guidelines; electronic point of care decision‐making tools for physicians; education materials for patients/families; education materials for healthcare providers on management plans; ethical considerations for rationing of supplies; and communication strategies for all administrators, healthcare providers, and patients. The success of the program was linked to working with a local pharmacy to compound oral vitamin K for administration to the infants who met the criteria for that route of administration. Injectable vitamin K was reserved for infants in the neonatal intensive care unit and high‐risk infants. Tools developed to support the model of drug shortage response include color coding system of drug supply for pharmacy and healthcare providers, process flow diagrams, published literature classification system, point of care decision templates, lists of ethical principles to consider, pharmacy policies guiding evaluation of alternative suppliers, and educational guides. As a result of the collaborative response to the injectable vitamin K shortage, 100% of the infants, whose parents consented to receive vitamin K, were given the correct oral dosage while in the hospital. Continued development and system‐wide dissemination of the drug shortage response model is underway. By proactively addressing the drug shortage, safety, evidence‐based clinical practice, ethical decision making, efficiency, and cost have the potential to be affected. The response to drug shortages is best conducted with a proactive, rather than reactive, approach to have the necessary elements in place for an appropriate controlled response.

Improving the diagnostic accuracy of dysplastic and melanoma lesions using the decision template combination method

Melanoma is the most dangerous type of skin cancer, and early detection of suspicious lesions can decrease the mortality rate of this cancer. In this article, we present a multi-classifier system for improving the diagnostic accuracy of melanoma and dysplastic lesions based on the decision template combination rule. First, the lesion is differentiated from the surrounding healthy skin in an image. Next, shape, colour and texture features are extracted from the lesion image. Different subsets of these features are fed to three different classifiers: k-nearest neighbour (k-NN), support vector machine (SVM) and linear discriminant analysis (LDA). The decision template method is used to combine the outputs of these classifiers. The proposed method has been evaluated on a set of 436 dermatoscopic images of benign, dysplastic and melanoma lesions. The final classifier ensemble delivers a total classification accuracy of 80.46%, with 67.73% of dysplastic lesions correctly classified and 83.53% of melanoma lesions correctly classified. The results show that the proposed method significantly increases the diagnostic accuracy of dysplastic and melanoma lesions compared with a single classifier. The total classification rate is also improved.

Voice of the customer: Customer satisfaction ratio based analysis

Voice of the customer (VOC) is a critical analysis procedure that provides precise information regarding customer input requirements for a product/service output. The ability to conduct a voice of the customer analysis, which could be gained through direct and indirect questioning, will enable engineers and other decision makers to successfully understand customer needs, wants, perceptions, and preferences. The information obtained from the customers is then translated into critical targets that will be used to ultimately satisfy the customer requirements. During this research project, different forms of customer input, including qualitative and quantitative data, were transformed to a common data format to develop a correlation between design input requirements and product/service outputs. We have developed a new method for measuring customer satisfaction ratio (CSR) by considering the following: mining both textual and quantitative data, multiple design parameters, mapping output on a scale of 0–1, and a decision template for means of measure. Previous measures of CSR fail to incorporate the cost implication of fixing customer complaints/issues; however, we include this important and unique measure in our research. The implication of this research will reduce Things Gone Wrong (TGW’s) and engineering development time and will achieve improvements in JD Power ratings, quality perception, marketing tools, and customer satisfaction.

Peace Operation Success: The Evaluation Framework

This article outlines and summarizes the Diehl and Druckman evaluation framework that is used in the case studies that follow. An overview of the decision template is given and the three sets of goals (core, beyond traditional peacekeeping, and peacebuilding) are introduced. Two sample framework entries (violence abatement, and restoration, reconciliation and transformation respectively) are provided as illustrations. Application to peace operations in Bosnia is also used for illustrative purposes.

Improving ECG classification accuracy using an ensemble of neural network modules.

This paper illustrates the use of a combined neural network model based on Stacked Generalization method for classification of electrocardiogram (ECG) beats. In conventional Stacked Generalization method, the combiner learns to map the base classifiers' outputs to the target data. We claim adding the input pattern to the base classifiers' outputs helps the combiner to obtain knowledge about the input space and as the result, performs better on the same task. Experimental results support our claim that the additional knowledge according to the input space, improves the performance of the proposed method which is called Modified Stacked Generalization. In particular, for classification of 14966 ECG beats that were not previously seen during training phase, the Modified Stacked Generalization method reduced the error rate for 12.41% in comparison with the best of ten popular classifier fusion methods including Max, Min, Average, Product, Majority Voting, Borda Count, Decision Templates, Weighted Averaging based on Particle Swarm Optimization and Stacked Generalization.

Soft computing methods applied to combination of one-class classifiers

The paper shows the possibilities of generalizing the two-class classification into multi-class classification by means of a fuzzy inference system. Fuzzy combiner harnesses the support values from classifiers to provide final response having no other restrictions on their structure. We compare proposed combination methods with ECOC and two variations of decision templates, based on Euclidean and symmetric distance. The effectiveness of the proposed combination method based on the fuzzy logic theory is also evaluated via computer experiments carried out on benchmark datasets.

Extended decision template presentation for combining classifiers

In this paper, a new method in classifier fusion is introduced for decision making based on internal structure of base classifiers. Amongst methods used in combining classifiers, there are some methods which work on decision template as a tool for modeling behavior of base classifiers in order to label data. This tool models their behavior only based on their final outputs. Our new method, introduces a special structure for decision template such that internal behavior of a neural network base classifier can be modeled in a proper manner suitable for classifiers fusion. The new method builds decision template for each layer of the neural network including all hidden layers. Therefore, the process of making decision in each base classifier is also available for classifiers fusion. Efficiency of the new method is compared with some known benchmark datasets to show how it can improve efficiency of classifiers fusion.

Prediction of protein–protein interaction types using the decision templates based on multiple classier fusion

Protein–protein interactions (PPIs) play a key role in many cellular processes, such as the regulation of enzymes, signal transduction or mediating the adhesion of cells. Knowing about the multitude of PPIs that allow the cell to function can help the biological scientist understand the molecular machinery of the cell. Unfortunately, it is both time-consuming and expensive to do so solely based on experiments due to the nature of the problem whose complexity is obviously overwhelming, just like the fact that “life is complicated”. Therefore, developing computational approaches for predicting PPIs, binding sites and interaction types would be of significant value in this regard. In this paper, we propose a novel method for predicting the types of PPIs based on decision templates. First, we introduce the concept of the tensor product to construct three kinds of feature vectors which are the amino acid composition tensor product, the residue multi-scale conservation energy tensor product and the secondary structure content tensor product, then the correlation-based feature selection method was also introduced to reduce the dimensionality of these feature vectors. So, the protein pair can be represented by our three new kinds of feature vectors and Zhu’s six kinds of feature vectors. The nine kinds of feature vectors are further taken as the inputs of individual support vector machine classifier respectively, and the outputs of these classifiers are aggregated with decision templates. The overall success rate obtained by jackknife cross-validation was 90.95%, indicating our method is very promising for predicting PPI types, might become a useful vehicle for studying the network biology in the post-genomic era.