Affinity Propagation Clustering Method Research Articles

An improved differential evolution algorithm for multi-modal multi-objective optimization.

Multi-modal multi-objective problems (MMOPs) have gained much attention during the last decade. These problems have two or more global or local Pareto optimal sets (PSs), some of which map to the same Pareto front (PF). This article presents a new affinity propagation clustering (APC) method based on the Multi-modal multi-objective differential evolution (MMODE) algorithm, called MMODE_AP, for the suit of CEC'2020 benchmark functions. First, two adaptive mutation strategies are adopted to balance exploration and exploitation and improve the diversity in the evolution process. Then, the affinity propagation clustering method is adopted to define the crowding degree in decision space (DS) and objective space (OS). Meanwhile, the non-dominated sorting scheme incorporates a particular crowding distance to truncate the population during the environmental selection process, which can obtain well-distributed solutions in both DS and OS. Moreover, the local PF membership of the solution is defined, and a predefined parameter is introduced to maintain of the local PSs and solutions around the global PS. Finally, the proposed algorithm is implemented on the suit of CEC'2020 benchmark functions for comparison with some MMODE algorithms. According to the experimental study results, the proposed MMODE_AP algorithm has about 20 better performance results on benchmark functions compared to its competitors in terms of reciprocal of Pareto sets proximity (rPSP), inverted generational distances (IGD) in the decision (IGDX) and objective (IGDF). The proposed algorithm can efficiently achieve the two goals, i.e., the convergence to the true local and global Pareto fronts along with better distributed Pareto solutions on the Pareto fronts.

A Novel Hybrid Protocol and Code Related Information Reconciliation Scheme for Physical Layer Secret Key Generation

Wireless networks are vulnerable to various attacks due to their open nature, making them susceptible to eavesdropping and other security threats. Eavesdropping attack takes place at the physical layer. Traditional wireless network security relies on cryptographic techniques to secure data transmissions. However, these techniques may not be suitable for all scenarios, especially in resource-constrained environments such as wireless sensor networks and adhoc networks. In these networks having limited power resources, generating cryptographic keys between mobile entities can be challenging. Also, the cryptographic keys are computationally complex and require key management infrastructure. Physical Layer Key Generation (PLKG) is an emerging solution to address these challenges. It establishes secure communication between two users by taking advantage of the wireless channel's inherent features. PLKG process involves channel probing, quantization, information reconciliation (IR) and privacy amplification to generate symmetric secret key. The researchers have used various PLKG techniques to get the secret key, sTop of Form
 till they face problems in the IR scheme to obtain symmetric keys between the users who share the same channel for communication. Both the code based and protocol based methods proposed in the literature have advantages and limitations related to their performance parameters such as information leakage, interaction delay and computation complexity. This research work proposes a novel IR mechanism that combines the protocol and code-based error correction methods to obtain reduced Bit Mismatch Rate (BMR), reduced information leakage, reduced interaction delay, and reduced computational time to enhance physical layer secret key's quality. In the proposed research work, the channel samples are generated using the Received Signal Strength (RSS) and Channel Impulse Response (CIR) parameters. These samples are quantized using Vector Quantization with Affinity Propagation Clustering (VQAPC) method to generate the preliminary key. The samples collected by the two users who wish to communicate, (for example Alice and Bob) will be different due to noise in the channel and hardware limitations. Hence their preliminary keys will be different. Removing this discrepancy between Bob's and Alice's initial keys, using novel Hybrid Protocol and Code related Information Reconciliation (HPC-IR) scheme to generate error corrected key, is the most important contribution of this research work. This key is further encoded by the MD5 hash function to generate a final secret key for exchanging information between two users over the wireless channel. It is observed that the proposed HPC-IR scheme achieves BMR of 19.4%, information leakage is 0.002, interaction delay is 0.001 seconds and computation time is 0.02 seconds.

Optimization Algorithms for UAV-and-MUV Cooperative Data Collection in Wireless Sensor Networks

The deployment of unmanned aerial vehicles (UAVs) has significantly improved the efficiency of data collection for wireless sensor networks (WSNs). The freshness of collected information from sensors can be measured by the age of information (AoI), which is an important factor to consider in data collection. For data collection during long-term mission, the energy limitation of UAVs may cause mission interruption, which makes supplementation of the UAVs’ energy more necessary. To this end, we introduce the mobile unmanned vehicle (MUV) to guarantee the UAVs’ energy supplementation. In this paper, we investigate the problem of multi-UAVs and single-MUV cooperative trajectory planning (MUSM-CTP) for data collection in WSNs with consideration for the AoI the collected data and the limited battery capacity of UAVs. The objective of this problem is to find cooperative flight trajectories for multiple UAVs and to determine the MUV’s travel plan to replace batteries for the UAVs, such that the average AoI of all collected data is minimized. We prove the NP-hardness of the problem and design the algorithm via three phases to solve this: determining candidate hover points based on the affinity propagation (AP) clustering method, constructing the flight trajectories of multiple UAVs based on the genetic algorithm (GA), and designing a travel plan for the MUV. The simulation results verify the effectiveness of the proposed algorithm in improving the freshness of the information collected from all of the sensors.

Toward Recognition of Easily Confused TCM Herbs on the Smartphone Using Hierarchical Clustering Convolutional Neural Network

Background and Objective. The use of Chinese herbal medicines (CHMs) for treatment plays an important role in traditional Chinese medicine (TCM). However, some herbs are easily confused with the others because their shapes/textures look similar and they could have totally different utilities. Recently, deep learning has attracted great attention for the application of image recognition and could be useful for TCM herb identification. Methods. For recognizing easily-confused TCM herbs on a smartphone, we propose a CHM recognition system using hierarchical clustering convolutional neural networks (HCNNs) based on the affinity propagation clustering method. Results. We implement our system on the smartphone and show recognition accuracy close to 98%, based on a dataset of 65 kinds of herbs (including 12 easy-confused herbs pairs). We also investigate the effect of different parameters (e.g., selection of clustering algorithms for HCNNs, types of smartphone, and number of layers in the neural network) on the system performance. Conclusions. In this work, we proposed a hierarchical clustering convolutional neural network (HCNN) method to distinguish similar TCM herbs with a high accuracy. We also showed the usefulness of applying the data augmentation techniques when implementing the proposed system for a variety of smartphones.

Lithology identification using graph neural network in continental shale oil reservoirs: A case study in Mahu Sag, Junggar Basin, Western China

The continental shale oil reservoir of Fengcheng Formation in the northern slope area of Mahu Sag, Junggar Basin, Western China is very heterogeneous in lithology. Thus, the complex response characteristics of conventional logging and limited core availability in the study area has led to major challenges in lithology identification. Therefore, to resolve lithology identification by well logs in continental shale oil reservoirs, a graph neural network (GNN) method named GraphSAGE is used to train the lithology identification model based on a constructed graph, which connects the samples with adjacent depth and similar log response features on operator intention. The identification process is divided into two parts: first, based on the formation depth sequence and affinity propagation clustering method, the vertical distribution of the stratum and nodes logging curve similarity information are integrated into the graph structure, which structurally represents the conventional logging curves as graph instead of well logs as input data; Second, the nodes of the constructed graph are classified by GraphSAGE, which naturally supports combination generalization and improves sample complexity accompanied by strong relational inductive bias. To examine the effectiveness of GraphSAGE for lithology identification, a conventional log dataset labelled by direct core observations from two separate wells in Muhu Sag are used. The identification results showed that the accuracy of GraphSAGE for the lithologies exceeds 90% of the testing data, especially for transitional lithology such as dolomitic mudstone, silty mudstone and tuffaceous fine sandstone. Compared with the commonly used machine learning methods such as SVM, RF and XGBoost, GraphSAGE was more accurate in lithology identification, matching core observations. Collectively, this reflects the superiority of graph neural network in conventional logging lithology identification and effective means provided for lithology identification of continental shale oil reservoir in the Mahu Sag.

Exploring the spatiotemporal characteristics of intracity travels by time series clustering: A case study of Beijing

AbstractExploring spatiotemporal characteristics of residents' travel is a fundamental task in the field of urban studies. Time series clustering is one of the useful methods to distinguish those characteristics of intracity travel. However, previous studies focused more on exploring the spatiotemporal characteristics in urban centers. For understanding the spatiotemporal characteristics in suburbs, we combined the Shape Based Distance (SBD) based on the Discrete Fourier Transformation (DFT) similarity measurement method and the Affinity Propagation (AP) clustering method to cluster time series of each Traffic Analyze Zone (TAZ). The method performed well both in urban centers and suburbs. There are nine clusters on weekdays and seven clusters on weekends. These clusters reflect different travel characteristics. To further understand the difference between these travel characteristics, Points of Interest (POI) data were employed to analyze attractors of travel. Work‐oriented, Residence‐oriented and Attraction‐oriented are three main attractors on weekdays. Meanwhile, there are four attractors on weekends which are Recreation‐oriented, Residence‐oriented, Attraction‐oriented and Work‐oriented. This research has a certain theoretical and practical value for understanding urban formation evolution and urban planning.

Bioregionalization of the coastal and open oceans of British Columbia and Southeast Alaska based on Sentinel-3A satellite-derived phytoplankton seasonality

Classifying the ocean into regions with distinct biogeochemical or physical properties may enhance our interpretation of ocean processes. High-resolution satellite-derived products provide valuable data to address this task. Notwithstanding, no regionalization at a regional scale has been attempted for the coastal and open oceans of British Columbia (BC) and Southeast Alaska (SEA), which host essential habitats for several ecologically, culturally, and commercially important species. Across this heterogeneous marine domain, phytoplankton are subject to dynamic ocean circulation patterns and atmosphere-ocean-land interactions, and their variability, in turn, influences marine food web structure and function. Regionalization based on phytoplankton biomass patterns along BC and SEA’s coastal and open oceans can be valuable in identifying pelagic habitats and representing a baseline for assessing future changes. We developed a two-step classification procedure, i.e., a Self-Organizing Maps (SOM) analysis followed by the affinity propagation clustering method, to define ten bioregions based on the seasonal climatology of high-resolution (300 m) Sentinel-3 surface chlorophyll-a data (a proxy for phytoplankton biomass), for the period 2016-2020. The classification procedure allowed high precision delineation of the ten bioregions, revealing separation between off-shelf bioregions and those in neritic waters. Consistent with the high-nutrient, low-chlorophyll regime, relatively low values of phytoplankton biomass (< 1 mg/m3) distinguished off-shelf bioregions, which also displayed, on average, more prominent autumn biomass peaks. In sharp contrast, neritic bioregions were highly productive (>> 1 mg/m3) and characterized by different phytoplankton dynamics. The spring phytoplankton bloom onset varied spatially and inter-annually, with substantial differences among bioregions. The proposed high-spatial-resolution regionalization constitutes a reference point for practical and more extensive implementation in understanding the spatial dynamics of the regional ecology, data-driven ocean observing systems, and objective regional management.

Application of Affinity Propagation Clustering Method in Medium and Extended Range Forecasting of Heavy Rainfall Processes in China

Based on the precipitation data of an ensemble forecast from the European Centre for Medium-Range Weather Forecasts, we establish a clustering model named EOF_AP by using the empirical orthogonal function decomposition and the affinity propagation clustering method. Then, using EOF_AP, we conducted research on the identification and classification of the characteristics of medium and extended range forecasts on 11 heavy rainfall events in the middle–lower reaches of the Yangtze River, North China, and the Huanghuai region, from June to September in 2021. We then selected two representative cases to analyze the common characteristics in detail to evaluate the effect of the model. The results show that the EOF_AP clustering model can better identify and classify the main rainfall pattern characteristics, and their corresponding occurrence probability of heavy rainfall processes, on the basis of comprehensively retaining the main forecast information of ensemble members with a few representative types. The rainfall pattern characteristics of some types with low occurrence probability can be identified, such as the extreme type. The distributions of rainfall patterns of the same type are basically consistent, whereas those among different types are distinct. Moreover, through the comparison of the forecast results with different starting times, we analyze the forecast performance of ensemble members and the variation trend of forecast results. We hope this study can provide a reference for the probability forecast of medium and extended range heavy rainfall process.

A niching backtracking search algorithm with adaptive local search for multimodal multiobjective optimization

• Propose a niching backtracking search algorithm with adaptive local search. • Backtracking search algorithm is applied in this field for the first time. • Develop a novel mutation based on the affinity propagation clustering. • Develop an adaptive local search strategy for the proposed algorithm. Multimodal multiobjective optimization problems,which widely exist in real-world applications, have multiple Pareto optimal sets in decision space corresponding to the same Pareto front in objective space. The key to handling such problems is locating and maintaining all Pareto optimal solutions in decision space simultaneously. The distribution of Pareto optimal solutions obtained by some existing multimodal multiobjective evolutionary algorithms is still not satisfactory. This paper proposes a niching backtracking search algorithm with adaptive local search to solve such problems. In the proposed algorithm, the affinity propagation clustering method as a parameter-free automatic niching technique is adopted to form multiple niches. A novel mutation based on affinity propagation clustering is then developed to search for more Pareto solutions within each niche. In addition, an adaptive local search strategy is designed in each niche to improve the search efficiency and the accuracy of Pareto optimal solutions. The proposed algorithm is compared with seven state-of-the-art multimodal multiobjective evolutionary algorithms on a multimodal multiobjective optimization test suite with 22 benchmark functions from CEC 2019 competition and a map-based practical application problem. The experimental results show that the proposed algorithm outperforms its competitors on 14 out of 22 benchmark functions in terms of the reciprocal of Pareto sets proximity and inverted generational distance in decision space metrics. Also, the proposed method is more effective and competitive than its competitors when solving the map-based practical application problem.

Deep learning-based optimal segmentation of 3D printed product for surface quality improvement and support structure reduction

Large-sized product cannot be printed as one piece by a 3D printer because of the volume limitation of most 3D printers. Some products with the complex structure and high surface quality should also not be printed into one piece to meet requirement of the printing quality. For increasing the surface quality and reducing support structure of 3D printed models, this paper proposes a 3D model segmentation method based on deep learning. Sub-graphs are generated by pre-segmenting 3D triangular mesh models to extract printing features. A data structure is proposed to design training data sets based on the sub-graphs with printing features of the original 3D model including surface quality, support structure and normal curvature. After training a Stacked Auto-encoder using the training set, a 3D model is pre-segmented to build an application set by the sub-graph data structure. The application set is applied by the trained deep-learning system to generate hidden features. An Affinity Propagation clustering method is introduced in combining hidden features and geometric information of the application set to segment a product model into several parts. In the case study, samples of 3D models are segmented by the proposed method, and then printed using a 3D printer for validating the performance.

Definition of customer requirements in big data using word vectors and affinity propagation clustering.

Customer requirements (CRs) have a significant impact on product design. The existing methods of defining CRs, such as customer surveys and expert evaluations, are time-consuming, inaccurate and subjective. This paper proposes an automatic CRs definition method based on online customer product reviews using the big data analysis. Word vectors are defined using a continuous bag of words (CBOW) model. Online customer reviews are searched by a crawling method and filtered by the parts of speech and frequency of words. Filtered words are then clustered into groups by an affinity propagation (AP) clustering method based on trained word vectors. Exemplars in each clustering group are finally used to define CRs. The proposed method is verified by case studies of defining CRs for product design. Results show that the proposed method has better performance to determine CRs compared to existing CRs definition methods.

Milling chatter monitoring under variable cutting conditions based on time series features

Chatter monitoring is an important task while ensuring machining quality and improving machining efficiency. Under variable cutting conditions, cutting parameters often change, and the cutting state and traditional time-frequency domain cutting features will also change significantly. In order to achieve precise monitoring of chatter under such cutting conditions, this article proposes a time series method named recurrence plot (RP) that can reflect the non-stationary characteristics and state differences of the signal system to analyze the cutting force signal in the cutting process. Firstly, reconstruct the phase space, generate RP; then use recurrence quantitative analysis (RQA) to extract statistical features in the RP that reflect the current state of the system; thirdly, use affinity propagation (AP) clustering method to find out the exemplar features from the RQA; finally, train the exemplar features using the light gradient boosting (LGB) method to obtain the classification prediction model. Experimental results show that this method can effectively identify the machining chatter state and stable cutting state under variable cutting conditions.

A Joint Rogue Access Point Localization and Outlier Detection Scheme Leveraging Sparse Recovery Technique

With the pervasive deployments of Access Point (AP) in Wireless Local Area Network (WLAN), rogue AP has emerged as such a large threat to user's privacy, that it is expected to be detected and located accurately. Hence, in this paper, we propose a novel rogue AP localization scheme leveraging sparse recovery technique, which consists of three steps: 1) Coarse localization, which is the result of comparing the online records with clustered fingerprint database. A novel Object Weighting Affinity Propagation (OWAP) clustering method is proposed to group the offline fingerprints. When computing the similarities, unlike traditional affinity propagation clustering method which views each object equally, we utilize the prior physical coordinates information to assign weight to each object. 2) Compressive sensing (CS) kernel optimization, in which the minimum number requirement of monitors in localization system is deduced through analyzing the problem formulation theoretically, and an Equiangular Tight Frame (ETF) based monitors selection scheme is presented to achieve higher location accuracy. 3) Joint fine rogue AP localization and outlier detection through a formulation of an improved CS based sparse recovery model. It could localize the rogue AP and identify the monitors whose readings are either not available or erroneous simultaneously, which increases the localization robustness. We operate simulations as well as experiments to verify the superiority of the proposed scheme both theoretically and practically.

UAV-Aided Data Collection for Information Freshness in Wireless Sensor Networks

In this work, we study the UAV-enabled data collection problem for high information freshness in wireless sensor networks, where one UAV is dispatched to collect information of ground Sensor Nodes (SNs). The information freshness is measured by the Age of Information (AoI) of each SN, which is defined as the sum of the SN's data uploading time and the UAV's flight time after leaving this SN. Two optimization problems of age-optimal data collection are formulated to minimize the SNs' maximal AoI and average AoI, respectively. An iterative SN association and trajectory planning policy is proposed to seek the age-optimal solutions via an iterative two-step procedure. Firstly, SN association is performed based on the affinity propagation clustering method with an appropriate weight to find a set of data Collection Points (CPs) at which the UAV hovers to collect data and schedules which SNs to upload in what order. Based on this result, trajectory planning is performed to find the max-AoI-optimal and ave-AoI-optimal trajectories of the UAV along the CPs using dynamic programming or genetic algorithm. With the optimized clustering weight, the proposed scheme can always strike a balance between the SNs' uploading time and the UAV's flight time in various scenarios. Simulation results show that the proposed strategy can improve the freshness of information collected from all the SNs.

Abstract 2111: Transfer learning for tumor mutation burden prediction and spatial heterogeneity analysis from histopathology slides in bladder cancer

Abstract Backgrounds: Tumor mutation burden (TMB) is an emerging potential genomic biomarker, which may help in identifying patients likely to benefit from immunotherapy. DNA sequencing has been used to determine the TMB, but its utility is limited due to time-consuming preparation and relative high cost. In addition, while tumor might carry a mixture of TMB high/low cells, bulk DNA sequencing is limited to provide a full spectrum of TMB heterogeneity landscape. On the other hand, recent studies have shown that deep learning on pathology slides can predict tumor molecular subtypes and genetic changes and provide landscape of spatial heterogeneity of tumor. In this work, we apply transfer learning for predicting bladder cancer patient TMB and the spectrum of spatial heterogeneity of TMB within tumor using H&E stained whole slide images (WSIs). Methods: We present a general computational and deep learning framework to extract histological image features in WSIs and predicts patient TMB level with the machine learning model. Our method mainly consists of four steps. (1) we trained the tumor detector based on convolutional neural networks (CNN) to detect bladder cancer regions in WSIs. (2) we applied affinity propagation clustering method to select a subset of representative tumor tiles. (3) transfer learning based on Xception model is applied to extract features from representative tumor tiles. (4) the WSI is characterized by integrating feature vectors of representative tumor tiles. The SVM classifier is then trained to predict patient with either low or high TMB level. Finally, the spatial heterogeneity analysis of TMB is performed and incorporated with predicted TMB status to identify patient subgroups with distinct survival outcomes. Results: Experiments have been performed on 253 different patient pathology slides selected from The Cancer Genome Atlas (TCGA) bladder cancer cohort. Evaluations show that the trained CNN-based tumor detector provides over 90% sensitivity and precision in detecting cancer regions from WSIs. The trained SVM classifier can provide over 0.75 AUC value (95% CI, 0.683-0.802) in distinguishing low and high TMB patients. Using the spatial heterogeneity analysis of TMB status, we found that bladder cancer patients with more homogeneous TMB high status across tumor regions show significantly better survival outcomes compared to other patients carrying mixtures of TMB high/low status across tumor regions (log rank test p<0.05). Conclusion: Our study indicates that TMB levels and the spatial heterogeneity of TMB levels within tumors could be predicted using digitized H&E stained WSIs for bladder cancer patients. To the best of our knowledge, this is the first work to predict TMB status and its spatial heterogeneity to stratify patients in bladder cancer. Our method is extensible to histopathology images of other organs for predicting TMB or other clinical outcomes implying the broad and economical aspects of clinical utility of TMB prediction using WSIs. Citation Format: Hongming Xu, Sung Hak Lee, Tae Hyun Hwang. Transfer learning for tumor mutation burden prediction and spatial heterogeneity analysis from histopathology slides in bladder cancer [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2111.

Fingerprinting Based Indoor Localization Considering the Dynamic Nature of Wi-Fi Signals

Current localization techniques in the outdoors cannot work well in indoors. The Wi-Fi fingerprinting technique is an emerging localization technique for indoor environments. However, in this technique, the dynamic nature of WiFi signals affects the accuracy of the measurements. In this paper, we use the affinity propagation clustering method to decrease the computation complexity in location estimation. Then, we use the least variance of Received Signal Strength (RSS) measured among Access Points (APs) in each cluster. Also, we assign lower weights to alter APs for each point in a cluster, to represent the level of similarity to Test Point (TP) by considering the dynamic nature of signals in indoor environments. A method for updating the radio map and improving the results is then proposed to decrease the cost of constructing the radio map. Simulation results show that the proposed method has 22.5% improvement in average in localization results, considering one altering AP in the layout, compared to the case when only RSS subset sampling is considered for localization because of altering APs.

From edit distance to augmented space-time-weighted edit distance: Detecting and clustering patterns of human activities in Puget Sound region

Considering and measuring the similarity of human activities remains challenging. Existing studies of similarity measures based on traditional edit distance (ED), specifically on activity patterns, do not reflect the spatiotemporal characteristics in the measurement model. Additionally, interdependence between activities is ignored in existing multidimensional sequence alignment methods. To address the gap, we initially extend the traditional edit distance to a space-time-weighted edit distance (STW-ED). Specifically, differences in distance and time between activities are considered cost functions in the operation cost calculation (insertion, deletion, and substitution). We advance STW-ED to an augmented space-time-weighted edit distance method (ASTW-ED) that integrates an optimum-trajectory-based multidimensional sequence alignment method (OT-MDSAM) with STW-ED, treating the nonspatiotemporal dimensions as augment factors. In addition, ontology is considered for the similarity measure for nonspatiotemporal dimensions.To show the feasibility of our proposed approach, we conduct an empirical study based on an activity-based travel survey in the Puget Sound Region. Eight clusters (homemakers, regular workers with a colorful life, regular workers with a monotonous life, part-time workers, recreation travelers, senior travelers, no-job travelers, and night owl adventurers) are identified based on ASTW-ED and ontology. To cluster the similarity matrix derived from the introduced methods, the affinity propagation (AP) clustering method is employed because it is free of prior knowledge for clustering and can produce exemplars of the clusters. The empirical study indicates that, relative to existing methods for multidimensional activity similarity measurement and clustering, ASTW-ED performs better in terms of within-group homogeneity and between-group heterogeneity of clusters. In addition, the results reveal that ontology can improve clustering performance if it is considered for nonspatiotemporal dimensions provide better understanding of human behavior for urban governance..

A New Knowledge-Based System for Diagnosis of Breast Cancer by a combination of the Affinity Propagation and Firefly Algorithms

Breast cancer has become a widespread disease around the world in young women. Expert systems, developed by data mining techniques, are valuable tools in diagnosis of breast cancer and can help physicians for decision making process. This paper presents a new hybrid data mining approach to classify two groups of breast cancer patients (malignant and benign). The proposed approach, AP-AMBFA, consists of two phases. In the first phase, the Affinity Propagation (AP) clustering method is used as instances reduction technique which can find noisy instance and eliminate them. In the second phase, feature selection and classification are conducted by the Adaptive Modified Binary Firefly Algorithm (AMBFA) for selection of the most related predictor variables to target variable and Support Vectors Machine (SVM) technique as classifier. It can reduce the computational complexity and speed up the data mining process. Experimental results on Wisconsin Diagnostic Breast Cancer (WDBC) datasets show higher predictive accuracy. The obtained classification accuracy is 98.606%, a very promising result compared to the current state-of-the-art classification techniques applied to the same database. Hence this method will help physicians in more accurate diagnosis of breast cancer.

A Bibliometric Review of Natural Language Processing Empowered Mobile Computing

Natural Language Processing (NLP) empowered mobile computing is the use of NLP techniques in the context of mobile environment. Research in this field has drawn much attention given the continually increasing number of publications in the last five years. This study presents the status and development trend of the research field through an objective, systematic, and comprehensive review of relevant publications available from Web of Science. Analysis techniques including a descriptive statistics method, a geographic visualization method, a social network analysis method, a latent dirichlet allocation method, and an affinity propagation clustering method are used. We quantitatively analyze the publications in terms of statistical characteristics, geographical distribution, cooperation relationship, and topic discovery and distribution. This systematic analysis of the field illustrates the publications evolution over time and identifies current research interests and potential directions for future research. Our work can potentially assist researchers in keeping abreast of the research status. It can also help monitoring new scientific and technological development in the research field.

Equilibrium Selection and Strategy: Experimental Evidence from an Infinitely Repeated Transboundary Public Goods Game

We design a transboundary public goods (TPG) game, in which participants have simultaneous interaction within and between groups. We design the TPG game under an infinitely repeated situation in order to explore the types of strategies that participants employ in infinitely repeated games. We theoretically identify a condition in which the grim-trigger strategy is supported as a strategy minimizing strategic risk in the TPG game. We experimentally investigate the types of strategies by eliciting all possible one-period-ahead strategy choices using the strategy method. We replicate the history of the game by simulation and classify the strategies using the affinity propagation clustering method. We find that the frequency of strategies in cooperative clusters is higher in the treatment with high continuation probability than that with low continuation probability. We find that participants employ strategies minimizing strategic risk in an infinitely repeated TPG game.