In most supervised learning problems, the labelling quality of datasets plays a paramount role in the learning of high-performance classifiers. The performance of a classifier can significantly be degraded if it is trained with mislabeled data. Therefore, identification of such examples from the dataset is of critical importance. In this study, we proposed an improved majority filtering algorithm, which utilized the ability of a support vector machine in terms of capturing potentially mislabeled examples as support vectors (SVs). The key technical contribution of our work, is that the base (or component) classifiers that construct the ensemble of classifiers are trained using non-SV examples, although at the time of testing, the examples captured as SVs were employed. An example can be tagged as mislabeled if the majority of the base classifiers incorrectly classifies the example. Experimental results confirmed that our algorithm not only showed high-level accuracy with higher F1 scores, for identifying the mislabeled examples, but was also significantly faster than the previous methods.

Unlike Radio Frequency Identification (RFID), emerging Computational RFID (CRFID) integrates the RF front-end and MCU with multiple sensors. CRFIDs need to transmit data within the interrogator range, so when the tags moved rapidly or the contact duration with interrogator is limited, the sensor data collected by CRFID must be transferred to interrogator quickly. In this paper, we focus on throughput optimization for backscatter link, take physical and medium access control (MAC) layers both into consideration, put forward our scheme called ORRIS. On physical layer, we propose Cluster Gather Degree (CGD) indicator, which is the clustering degree of signal in IQ domain. Then CGD is regarded as the criterion to adaptively adjust the rate encoding mode and link frequency, accordingly achieve adaptive rate transmission. On MAC layer, based on the idea of asynchronous transfer, we utilize the the number of clusters in IQ domain to select the optimal Q value as much as possible. So that achieve burst transmission or bulk data transmission. Experiments and analyses on the static and mobile scenarios show that our proposal has significantly better mean throughput than BLINK or CARA, which demonstrate the effectiveness of our scheme.

In this paper, we propose multidimensional stochastic modeling of priority broadcast in Vehicular Ad hoc Networks (VANET). We focus on the channel switching operation of IEEE 1609.4 in systems that handle different types of safety messages, such as event-driven urgent messages and periodic beacon messages. The model considers the constraints imposed by the channel switching operation. The model also reflects differentiated services that handle different types of messages. We carefully consider the delivery time limit and the number of transmissions of the urgent messages. We also consider the hidden node problem, which has an increased impact on broadcast communications. We use the model in analyzing the relationship between system variables and performance metrics of each message type. The analysis results include confirming that the differentiated services work effectively in providing class specific quality of services under moderate traffic loads, and that the repeated transmission of urgent message is a meaningful countermeasure against the hidden node problem. It is also confirmed that the delivery time limit of urgent message is a crucial factor in tuning the channel switching operation.

Dynamic sharing of limited radio spectrum resources is expected to satisfy the increasing demand for spectrum resources in the upcoming 5th generation mobile communication system (5G) era and beyond. Distributed real-time spectrum sensing is a key enabler of dynamic spectrum sharing, but the costs incurred in observed-data transmission are a critical problem, especially when massive numbers of spectrum sensors are deployed. To cope with this issue, the proposed spectrum sensors learn the ambient radio environment in real-time and create a time-spectral model whose parameters are shared with servers operating in the edge-computing layer. This process makes it possible to significantly reduce the communication cost of the sensors because frequent data transmission is no longer needed while enabling the edge servers to keep up on the current status of the radio environment. On the basis of the created time-spectral model, sharable spectrum resources are dynamically harvested and allocated in terms of geospatial, temporal, and frequency-spectral domains when accepting an application for secondary-spectrum use. A web-based prototype spectrum management system has been implemented using ten servers and dozens of sensors. Measured results show that the proposed approach can reduce data traffic between the sensors and servers by 97%, achieving an average data rate of 10 kilobits per second (kbps). In addition, the basic operation flow of the prototype has been verified through a field experiment conducted at a manufacturing facility and a proof-of-concept experiment of dynamic-spectrum sharing using wireless local-area-network equipment.

With no need for Road Side Unit (RSU), multi-hop Vehicular Ad Hoc NETworks (VANETs) have drawn more and more attention recently. Considering the safety of vehicles, a Media Access Control (MAC) protocol for reliable transmission is critical for multi-hop VANETs. Most current works need RSU to handle the collisions brought by hidden-terminal problem and the mobility of vehicles. In this paper, we proposed RV-MAC, which is a reliable MAC protocol for multi-hop VANETs based on Time Division Multiple Access (TDMA). First, to address the hidden-terminal under the networks with multi-hop topology, we design a region marking scheme to divide vehicles into different regions. Then a collisions avoidance scheme is proposed to handle the collisions owing to channel competition and the mobility of vehicles. Simulation results show that compared with other protocol, RV-MAC can decrease contention collisions by 30% and encounter collisions by 50% respectively. As a result, RV-MAC achieves higher throughput and lower network delay.

In this research, we propose a novel method to determine fingerprint liveness to improve the discriminative behavior and classification accuracy of the combined features. This approach detects if a fingerprint is from a live or fake source. In this approach, fingerprint images are analyzed in the differential excitation (DE) component and the centralized binary pattern (CBP) component, which yield the DE image and CBP image, respectively. The images obtained are used to generate a two-dimensional histogram that is subsequently used as a feature vector. To decide if a fingerprint image is from a live or fake source, the feature vector is processed using support vector machine (SVM) classifiers. To evaluate the performance of the proposed method and compare it to existing approaches, we conducted experiments using the datasets from the 2011 and 2015 Liveness Detection Competition (LivDet), collected from four sensors. The results show that the proposed method gave comparable or even better results and further prove that methods derived from combination of features provide a better performance than existing methods.

This paper introduces recent trends in video streaming and four methods proposed by the authors for video streaming. Video traffic dominates the Internet as seen in current trends, and new visual contents such as UHD and 360-degree movies are being delivered. MPEG-DASH has become popular for adaptive video streaming, and machine learning techniques are being introduced in several parts of video streaming. Along with these research trends, the authors also tried four methods: route navigation, throughput prediction, image quality assessment, and perceptual video streaming. These methods contribute to improving QoS/QoE performance and reducing power consumption and storage size.

Some of the most serious threats to network security involve malware. One common way to detect malware-infected machines in a network is by monitoring communications based on blacklists. However, such detection is problematic because (1) no blacklist is completely reliable, and (2) blacklists do not provide the sufficient evidence to allow administrators to determine the validity and accuracy of the detection results. In this paper, we propose a malicious DNS query clustering approach for blacklist-based detection. Unlike conventional classification, our cause-based classification can efficiently analyze malware communications, allowing infected machines in the network to be addressed swiftly.

Wireless Full-Duplex (FD) communication can double the point-to-point throughput. To obtain the full benefits of the FD technique in multi-hop networks, its potential throughput performance in multi-hop networks should be clarified qualitatively and quantitatively. Developing an analytical model for FD multi-hop networks is effective and useful for not only clarifying such network dynamics but also developing the optimal protocol design. However, generalized analytical expression for the end-to-end throughput of FD multi-hop networks has not been proposed. This paper proposes analytical expressions for the end-to-end throughput of string-topology wireless FD multi-hop networks. Our approach is to integrate with the analytical model of the airtime expression, which is an effective analytical approach of the throughput analysis for Half-Duplex (HD) multi-hop networks, and the Markov-chain model considering the FD MAC operation. The proposed model clarify the detailed effect of the FD MAC operation on the throughput performance in multi-hop networks. In particular, it can obtain the end-to-end throughput of FD multi-hop networks for arbitrary number of hops, arbitrary payload size and arbitrary value of the minimum contention window. The analytical expressions verified by comparisons with the simulation results. From the comparisons with the results in HD multi-hop networks, we confirm the effectiveness of the FD communication in multi-hop networks.

This paper provides perspectives for future medical healthcare social services and businesses that integrate advanced information and communication technology (ICT) and data science. First, we propose a universal medical healthcare platform that consists of wireless body area network (BAN), cloud network and edge computer, big data mining server and repository with machine learning. Technical aspects of the platform are discussed, including the requirements of reliability, safety and security, i.e., so-called dependability. In addition, novel technologies for satisfying the requirements are introduced. Then primary uses of the platform for personalized medicine and regulatory compliance, and its secondary uses for commercial business and sustainable operation are discussed. We are aiming at operate the universal medical healthcare platform, which is based on the principle of regulatory science, regionally and globally. In this paper, trials carried out in Kanagawa, Japan and Oulu, Finland will be revealed to illustrate a future medical healthcare social infrastructure by expanding it to Asia-Pacific, Europe and the rest of the world. We are representing the activities of Kanagawa medical device regulatory science center and a joint proposal on security in the dependable medical healthcare platform. Novel schemes of ubiquitous rehabilitation based on analyses of the training effect by remote monitoring of activities and machine learning of patient's electrocardiography (ECG) with a neural network are proposed and briefly investigated.

This study proposes a novel machine learning architecture and various learning algorithms to build-in anti-phishing services for avoiding cyber-phishing attack. For the rapid develop of information technology, hackers engage in cyber-phishing attack to steal important personal information, which draws information security concerns. The prevention of phishing website involves in various aspect, for example, user training, public awareness, fraudulent phishing, etc. However, recent phishing research has mainly focused on preventing fraudulent phishing and relied on manual identification that is inefficient for real-time detection systems. In this study, we used methods such as ANOVA, X2, and information gain to evaluate features. Then, we filtered out the unrelated features and obtained the top 28 most related features as the features to use for the training and evaluation of traditional machine learning algorithms, such as Support Vector Machine (SVM) with linear or rbf kernels, Logistic Regression (LR), Decision tree, and K-Nearest Neighbor (KNN). This research also evaluated the above algorithms with the ensemble learning concept by combining multiple classifiers, such as Adaboost, bagging, and voting. Finally, the eXtreme Gradient Boosting (XGBoost) model exhibited the best performance of 99.2%, among the algorithms considered in this study.

Intrusion detection system (IDS) is a device or software to monitor a network system for malicious activity. In terms of detection results, there could be two types of false, namely, the false positive (FP) which incorrectly detects normal traffic as abnormal, and the false negative (FN) which incorrectly judges malicious traffic as normal. To protect the network system, we expect that FN should be minimized as low as possible. However, since there is a trade-off between FP and FN when IDS detects malicious traffic, it is difficult to reduce the both metrics simultaneously. In this paper, we propose a sequential classifiers combination method to reduce the effect of the trade-off. The single classifier suffers a high FN rate in general, therefore additional classifiers are sequentially combined in order to detect more positives (reduce more FN). Since each classifier can reduce FN and does not generate much FP in our approach, we can achieve a reduction of FN at the final output. In evaluations, we use NSL-KDD dataset, which is an updated version of KDD Cup'99 dataset. WEKA is utilized as a classification tool in experiment, and the results show that the proposed approach can reduce FN while improving the sensitivity and accuracy.

The GUINNESS (GUI based binarized neural network synthesizer) is an open-source tool flow for a binarized deep neural network toward FPGA implementation based on the GUI including both the training on the GPU and inference on the FPGA. Since all the operation is done on the GUI, the software designer is not necessary to write any scripts to design the neural network structure, training behavior, only specify the values for hyperparameters. After finishing the training, it automatically generates C++ codes to synthesis the bit-stream using the Xilinx SDSoC system design tool flow. Thus, our tool flow is suitable for the software programmers who are not familiar with the FPGA design. In our tool flow, we modify the training algorithms both the training and the inference for a binarized CNN hardware. Since the hardware has a limited number of bit precision, it lacks minimal bias in training. Also, for the inference on the hardware, the conventional batch normalization technique requires additional hardware. Our modifications solve these problems. We implemented the VGG-11 benchmark CNN on the Digilent Inc. Zedboard. Compared with the conventional binarized implementations on an FPGA, the classification accuracy was almost the same, the performance per power efficiency is 5.1 times better, as for the performance per area efficiency, it is 8.0 times better, and as for the performance per memory, it is 8.2 times better. We compare the proposed FPGA design with the CPU and the GPU designs. Compared with the ARM Cortex-A57, it was 1776.3 times faster, it dissipated 3.0 times lower power, and its performance per power efficiency was 5706.3 times better. Also, compared with the Maxwell GPU, it was 11.5 times faster, it dissipated 7.3 times lower power, and its performance per power efficiency was 83.0 times better. The disadvantage of our FPGA based design requires additional time to synthesize the FPGA executable codes. From the experiment, it consumed more three hours, and the total FPGA design took 75 hours. Since the training of the CNN is dominant, it is considerable.

We examine the feasibility of Deutsch-Jozsa Algorithm, a basic quantum algorithm, on a machine learning-based logistic regression problem. Its major property to distinguish the function type with an exponential speedup can help identify the feature unsuitability much more quickly. Although strict conditions and restrictions to abide exist, we reconfirm the quantum superiority in many aspects of modern computing.

To recognize transportation modes without any additional sensor devices, we demonstrate that the transportation modes can be recognized from communication quality factors. In the demonstration, instead of using global positioning system (GPS) and accelerometer sensors, we collect mobile TCP throughputs, received-signal strength indicators (RSSIs), and cellular base-station IDs (Cell IDs) through in-line network measurement when the user enjoys mobile services, such as video streaming. In accuracy evaluations, we conduct two different field experiments to collect the data in six typical transportation modes (static, walking, riding a bicycle, riding a bus, riding a train and riding a subway), and then construct the classifiers by applying a support-vector machine (SVM), k-nearest neighbor (k-NN), random forest (RF), and convolutional neural network (CNN). Our results show that these transportation modes can be recognized with high accuracy by using communication quality factors as well as the use of accelerometer sensors.

Femtocell has been considered as a key promising technology to improve the capacity of a cellular system. However, the femtocells deployed inside a macrocell coverage are potentially suffered from excessive interference. This paper proposes a novel radio resource optimization in closed access femtocell networks based on bat algorithm. Bat algorithm is inspired by the behavior of bats in their echolocation process. While the original bat algorithm is designed to solve the complex optimization problem in continuous search space, the proposed modified bat algorithm extends the search optimization in a discrete search space which is suitable for radio resource allocation problem. The simulation results verify the convergence of the proposed optimization scheme to the global optimal solution and reveal that the proposed scheme based on modified bat algorithm facilitates the improvement of the femtocell network capacity.

We developed a high-frequency and integrated design based on a flip-chip interconnection technique (Hi-FIT) as a wire-free interconnection technique that provides a high modulation bandwidth. The Hi-FIT can be applied to various high-speed (>100 Gbaud) optical devices. The Hi-FIT EA-DFB laser module has a 3-dB bandwidth of 59 GHz. And with a 4-intensity-level pulse amplitude modulation (PAM) operation at 107 Gbaud, we obtained a bit-error rate (BER) of less than 3.8×10-3, which is an error-free condition, by using a 7%-overhead (OH) hard-decision forward error correction (HD-FEC) code, even after a 10-km SMF transmission. The 3-dB bandwidth of the Hi-FIT employing an InP-MZM sub-assembly was more than 67 GHz, which was the limit of our measuring instrument. We also demonstrated a 120-Gbaud rate IQ modulation.

Word order is one of the most significant differences between the Chinese and Vietnamese. In the phrase-based statistical machine translation, the reordering model will learn reordering rules from bilingual corpora. If the bilingual corpora are large and good enough, the reordering rules are exact and coverable. However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. This leads to the quality of reordering in Chinese-Vietnamese machine translation is not high. In this paper, we have combined Chinese dependency relation and Chinese-Vietnamese word alignment results in order to pre-order Chinese word order to be suitable to Vietnamese one. The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.

This paper presents an approach to analyze and model tasks of machines being operated. The executions of the tasks were captured through egocentric vision. Each task was decomposed into a sequence of physical hand-machine interactions, which are described with touch-based hotspots and interaction patterns. Modeling the tasks was achieved by integrating the experiences of multiple experts and using a hidden Markov model (HMM). Here, we present the results of more than 70 recorded egocentric experiences of the operation of a sewing machine. Our methods show good potential for the detection of hand-machine interactions and modeling of machine operation tasks.

The Game of Life, a two-dimensional computationally universal cellular automaton, is known to exhibits 1/f noise in the evolutions starting from random configurations. In this paper we perform the spectral analysis on the computation process by a Turing machine constructed on the array of the Game of Life. As a result, the power spectrum averaged over the whole array has almost flat line at low frequencies and a lot of sharp peaks at high frequencies although some regions in which complicated behavior such as frequent memory rewriting occurs exhibit 1/f noise. This singular power spectrum is, however, easily turned into 1/f by slightly deforming the initial configuration of the Turing machine. These results emphasize the peculiarity of the computation process on the Game of Life that is never shared with the evolutions from random configurations. The Lyapunov exponents have positive values in three out of six trials and zero or negative values in other three trails. That means the computation process is essentially chaotic but it has capable of recovering a slight error in the configuration of the Turing machine.