for Journals by Title or ISSN for Articles by Keywords help

Publisher: Springer-Verlag (Total: 2573 journals)

Similar Journals
 Artificial Life and RoboticsJournal Prestige (SJR): 0.226 Number of Followers: 10      Hybrid journal (It can contain Open Access articles) ISSN (Print) 1614-7456 - ISSN (Online) 1433-5298 Published by Springer-Verlag  [2573 journals]
• Neural network-based construction of inverse kinematics model for serial
redundant manipulators
• Abstract: Abstract Solving the inverse kinematics of redundant manipulators is difficult, because knowledge of the manipulators and their evaluation functions is required. To solve this problem, we propose a novel method of enabling a neural network model to learn the inverse kinematics. The method achieves learning independent of the structure of the evaluation function, by combining multiple neural network models. The method can obtain the neural network models of the inverse kinematics via an automatic calculation process using only training data, which consist of the postures, end-points, and evaluation values. In this paper, the algorithm used by the method and its background is explained, and the effectiveness of the method is validated by a numerical simulation.
PubDate: 2019-12-01

• Spike-timing-dependent plasticity model for low-frequency pulse waveform
• Abstract: Abstract The authors are studying pulse-type hardware neural networks (P-HNN) for generating the driving waveform of the robot. The P-HNN generates a driving waveform by the oscillatory pulse waveform. Oscillating frequency depends on the time constant of the oscillator. In the case of implementing into the integrated circuit (IC), a large time constant cannot construct to the limited space. This paper is discussing the generation of low-frequency pulse waveform without using a large time constant. Two cell body models pre-synaptic neuron (Pre) and post-synaptic neuron (Post) generate the high-frequency pulse (637 kHz). A slight time difference of both pulse waveform converts to the small voltage difference of spike-timing-dependent plasticity (STDP) model. The small voltage difference indicates the coupling coefficient of Pre and Post. The value of the coupling coefficient changing slowly, thus, the output neuron (Out) generates the burst-like waveform which can use as a low-frequency pulse waveform (37 Hz).
PubDate: 2019-12-01

• Skin color image analysis for evaluating wetness on palm with reducing
influence of sharp highlights
• Abstract: Abstract In this study, we analyzed color changed by wetness in various areas on palm to clarify the influence of highlights. To improve the accuracy of emotion estimation, it is necessary to suggest other modalities combined with the conventional modalities. Therefore, we focused on emotional sweating, which is reliable modality of contact methods but not used in non-contact methods. We analyzed the color change in images containing a few highlights to clarify the influence of sharp highlights because the highlights can be noise for the analysis of internal reflection change by getting wet. The sharp highlight means the bright pixels in images of gloss material. We also analyzed areas separated from pixels representing sharp highlights to unveil the influence of the sharp highlights. As a result, we found that sharp highlights have a little influence on the analysis and better detection can be performed on pixels not containing sharp highlight area.
PubDate: 2019-12-01

• Analysis of push-forward model for swarm-like collective motions
• Abstract: Abstract A system that operates as a whole through interactions between its constituent individuals, each of which operates autonomously, is called an autonomous decentralized system. This type of system is increasingly attracting attention in the fields of biology and engineering as a system that flexibly adapts to changes in external environments. In this paper, a push-forward model is proposed as a simple model to generate various collective motions in groups. The push-forward model can be used to generate four types of collective motions, including one where “if an individual flies out of the group, the direction in which the entire group is heading changes accordingly.” This motion could not be generated using conventional group models. In this study, the group collective motions obtained from the push-forward model are classified using evaluation indices, and the mechanisms of their development are discussed. Moreover, an evaluation is conducted using scale-free correlation, an index that expresses “group likeness,” which is derived from actual observations of bird flocks.
PubDate: 2019-12-01

• Technology for visualizing the local change in shape of edema using a
depth camera
• Abstract: Abstract The change in the edema condition is visualized considering the three-dimensional shape. Continuous treatment and observation are indispensable for patients with edema. The measurement and evaluation of the three-dimensional shape of the leg are thus important in evaluating edema of the leg. Such an evaluation can confirm the therapeutic effect and assist in the planning of treatment by confirming the change in local capacity. Additionally, the depth camera of Structure Sensor used this study is feasible for use in home care systems due to its very low cost compared with other depth cameras. We obtain a point cloud of the leg and register shape models. We conducted an experiment to measure legs swathed and not swathed in bandages, with the former representing a leg with edema. In addition, for visualization of the edema condition, the change in shape was color coded according to the change obtained in the proposed analysis of the three-dimensional shape. Our experimental results show that our proposed visualization technique is effective in conveying the change in shape visually and clearly.
PubDate: 2019-12-01

• A high-performance haptic rendering system for virtual reality molecular
modeling
• Abstract: Purpose To provide a virtual reality 3D user interface with comprehensive molecular modeling, we have developed a novel haptic rendering system with a fingertip haptic rendering device and a hand-tracking Leap Motion controller. Methods The system handles virtual molecular objects with real hands motion captured by the Leap Motion controller in a virtual reality environment. The fingertip haptic rendering device attached on each finger and a wrist gives haptic display, when virtual hands manipulating virtual molecular objects. Results Based on preliminary software development studies using existing 3D graphics toolkit such as CHAI3D and Unity, the fingertip haptic rendering device works with a reasonable performance for a polygon surface model and a ribbon model, but not for an atomic model due to the low rendering performance. On the other hand, the device provides us a grasping feeling of a large molecule represented by an atomic model, when used with the particle simulation system running on graphics library, DirectX 12. The haptic rendering performances, among the three software systems are discussed.
PubDate: 2019-12-01

• Merging trajectory generation method using real-time optimization with
enhanced robustness against sensor noise
• Abstract: Abstract To reduce drivers’ mental load and traffic congestion caused by merging maneuver, a merging trajectory generation method aiming for practical automatic driving was proposed in the past research by the authors. In this paper, the robustness of the method against sensor noises is enhanced. The robustness is improved by the dummy optimization variables that relax the equality constraints and the barrier functions. The stage costs composed by these introduced dummy variables are designed to generate safe and smooth merging maneuver. The effectiveness of the proposed method for a typical case is observed in the simulation results. To check if the proposed method works well under different initial conditions, 116 initial conditions are generated randomly. The proposed method solves all the cases of merging problem, while the conventional method fails in 80% of the cases.
PubDate: 2019-12-01

• Wireless sensor monitoring system of Canadian Poplar Forests based on
Internet of Things
• Abstract: Abstract In the current ecological measurement of commonweal forest, there are many problems such as high intensity of operation and continuous measurement of environmental factors. In this paper, the technology of Internet of Things is applied to the automatic measurement of ecological cultivation of public-welfare forest, and the structure of automatic monitoring system of ecological cultivation based on Internet of Things is put forward. Implementation in production practice: according to the basic flow of the ecological cultivation of commonweal forest, the cultivation environment of the ecological cultivation link of the Canadian Poplar Forests was analyzed. The environmental factors influencing the growth of trees in the Canadian Poplar Forests were summarized and the best environment for the ecological cultivation was established. The preliminary experiments show that the system has the advantages of low power consumption, flexible networking, scalable and friendly human–machine interface, and can meet the application requirements of ecological cultivation information monitoring of Canadian Poplar Forests.
PubDate: 2019-12-01

• The effect of different types of acupuncture manipulations on shoulder
pain and cardiovascular circulation dynamics
• Abstract: Abstract This study is to compare the effect of contacting needle technique (CNT) and insertion needle technique (INT) on cardiovascular dynamics and visual analogue scale (VAS) in patients with shoulder pain. A total of 11 patients (9 females, 2 males, average age 32.27) were recruited and divided into two groups (CNT group and INT group). The treatment was performed once a week and a total of 4 weeks. The changes in cardiovascular circulation dynamics were detected at baseline, during the treatment and after the treatment. Pain was assessed before and after acupuncture therapy. There was significant difference in VAS within each group. There was no significant difference between the two groups on CO, SV, BPs, BPd and VAS, and had significant difference on PR (P < 0.05). PR significantly decreased in both groups, the rate of decrease was significantly higher in the CNT group than that in the INT group.
PubDate: 2019-12-01

• Effects of individual and social learning on the evolution of co-creative
linguistic communication
• Abstract: Abstract The effects of learning have been regarded as important factors of the evolutionary process of human linguistic abilities. Our purpose is, by use of computer simulations, to examine the effects of individual and social learning on the evolution of cognitive (e.g., building language hierarchy) and communicative (e.g., intention sharing) abilities of language based on the interplay between biological and cultural evolution of language. In particular, we focus on a co-creative aspect of linguistic communication, which is a synergy of both cognitive and communicative aspects of language. Our simulation results show that roles of individual and social learning can work together and contribute to the evolution of co-creative aspect of linguistic abilities. It is also implied that the stable evolutionary process of cognitive abilities is based on repeated occurrences of the Baldwin effect, and dynamic and less assimilated evolution of communicative traits can work together, contributing to the co-creative communication.
PubDate: 2019-12-01

• A modified cascaded neuro-computational model applied to recognition of
connected spoken Japanese prefecture words
• Abstract: Abstract In this paper, a novel approach of connected spoken word recognition is proposed, based only on a relatively simple artificial neural network model. The model used is a modified version of the previously proposed cascaded neuro-computational model and has a three-layered network structure, where a non-linear metric to each of the second-layer units is newly introduced for performing effectively the pattern matching at the word-feature level. Simulations were conducted using connected speech data sets of a larger lexicon than those used in the previous works; the data sets were comprised of the naturally spoken strings, each string consisting of a varying number of 2–7 words selected from a total of 47 Japanese prefecture names. The simulation results show that the modified model yields the overall recognition performance, i.e., 95.2% in terms of the word accuracy rate, which is comparable to that (98.1%) obtained using a benchmark approach of hidden Markov model with embedded training.
PubDate: 2019-12-01

• Automatic control of mobile robot based on autonomous navigation algorithm
• Abstract: Abstract Autonomous navigation control is the key technology of mobile robot. The navigation algorithm of mobile robot is studied in this paper. A simultaneous localization and mapping (SLAM) algorithm based on particle filter is designed. Then, it is combined with VFH obstacle avoidance algorithm to obtain the navigation algorithm and conduct experiments on it. Through the simulation experiment in MATLAB environment, it is found that the use of SLAM algorithm can reduce the position error of the robot. The average error is 0.003 m, while the average position error without SLAM algorithm is about 0.009 m, which proves the reliability of SLAM algorithm. Then, the simulation experiment of the navigation algorithm also proves that the algorithm can avoid obstacles and reach the destination accurately. The research in this paper provides some theoretical references for the further development of autonomous navigation control of mobile robots.
PubDate: 2019-12-01

• Synergistic attention U-Net for sublingual vein segmentation
• Abstract: Abstract The tongue is one of the most sensitive organs of the human body. The changes in the tongue indicate the changes of the human state. One of the features of the tongue, which can be used to inspect the blood circulation of human, is the shape information of the sublingual vein. Therefore, this paper aims to segment the sublingual vein from the RGB images of the tongue. In traditional segmentation network training based on deep learning, the resolution of the input image is generally resized to save training costs. However, the size of the sublingual vein is much smaller than the size of the tongue relative to the entire image. The resized inputs are likely to cause the network to fail to capture target information for the smaller segmentation and produce an “all black” output. This study first pointed out that the training of the segmentation of the sublingual vein compared to the tongue segmentation is much more difficult through a small dataset. At the same time, we also compared the effects of different input sizes on small sublingual segmentation. In response to the problems that arise, we propose a synergistic attention network. By dismembering the entire encoder–decoder framework and updating the parameters synergistically, the proposed network can not only improve the convergence speed of training process, but also avoid the problem of falling into the optimal local solution and maintains the stability of training without increasing the training cost and additional regional auxiliary labels.
PubDate: 2019-12-01

• El Niño-Southern Oscillation forecasting using complex networks analysis
of LSTM neural networks
• Abstract: Abstract Arguably, El Niño-Southern Oscillation (ENSO) is the most influential climatological phenomenon that has been intensively researched during the past years. Currently, the scientific community knows much about the underlying processes of ENSO phenomenon, however, its predictability for longer horizons, which is very important for human society and the natural environment is still a challenge in the scientific community. Here we show an approach based on using various complex networks metrics extracted from climate networks with long short-term memory neural network to forecast ENSO phenomenon. The results suggest that the 12-network metrics extracted as predictors have predictive power and the potential for forecasting ENSO phenomenon longer multiple steps ahead.
PubDate: 2019-12-01

• Defect detection method using deep convolutional neural network, support
vector machine and template matching techniques
• Abstract: Abstract In this paper, a defect detection method using deep convolutional neural network (DCNN), support vector machine (SVM) and template matching techniques is introduced. First, a DCNN for visual inspection is designed and trained using a large number of images to inspect undesirable defects such as crack, burr, protrusion, chipping, spot and fracture phenomena which appear in the manufacturing process of resin molded articles. Then the trained DCNN named sssNet and well-known AlexNet are, respectively, incorporated with two SVMs to classify sample images with high recognition rate into accept as OK category or reject as NG one, in which compressed feature vectors obtained from the DCNNs are used as inputs for the SVMs. The performances of the two types of SVMs with the DCNNs are compared and evaluated through training and classification experiments. Finally, a template matching technique is further proposed to efficiently extract important target areas from original training and test images. This will be able to enhance the reliability and accuracy for defect detection.
PubDate: 2019-12-01

• A degradable NoC router for the improvement of fault-tolerant routing
performance
• Abstract: Abstract Network-on-chip (NoC) provides high computation performance for a wide range of applications including robotics and artificial intelligence. This paper deals with the issue of improving the fault-tolerant routing performance for realizing high-performance NoCs. The major drawbacks of the conventional fault-tolerant routing methods are low node utilization efficacy and high communication latency. To solve these problems, we propose a novel NoC router which enables to logically reconstruct faulty input buffers. In contrast to most conventional methods, where routers with partially faulty input buffers are regarded as faulty, the proposed method regards them as fault-free routers with degraded input buffers. Simulation results obtained by a cycle accurate custom simulator show that the proposed method reduces the number of faulty and unused nodes and improves communication latency by up to 93% and 87%, respectively, compared with the conventional methods.
PubDate: 2019-11-30

• A construction of simple and smaller-state real-time generator for
exponential sequences
• Abstract: Abstract A model of cellular automata ($${\mathrm {CA}}$$) is considered to be a well-studied non-linear model of complex systems in which an infinite one-dimensional array of finite state machines (cells) updates itself in a synchronous manner according to a uniform local rule. A sequence generation problem on the $${\mathrm {CA}}$$s was studied and many scholars proposed real-time sequence generation algorithms for a variety of non-regular sequences such as $$\{2^n \, \,n = 1, 2, 3,\ldots \}$$, prime, and Fibonacci sequences. In this paper, we show that sequence $$\{ k^n n=1, 2, 3, \ldots \}$$ can be generated in real-time by a k-state $${\mathrm {CA}}$$, when $$k \ge 3$$, and give a mathematical proof of the correctness of the implementation.
PubDate: 2019-11-29

• Motor control mechanism underlying pedaling skills: an analysis of
bilateral coordination in the lower extremities
• Abstract: Abstract In the field of competitive cycling, non-traumatic injuries arising from muscle fatigue have been recognized as a significant problem. Although muscle coordination of the lower extremities is key to achieve high efficiency in pedaling, only a few prior studies have quantified the bilateral coordination of both legs. This quantification could contribute to the understanding of how enhanced pedaling skills may help to reduce muscle fatigue. The aim of this study was to investigate the mechanism underlying inter-lower limb coordination, which should serve to extend the understanding of pedaling skills further. First, 11 healthy males were instructed to pedal for 30 s under a 150-W exercise load and at cadences of 70, 90, and 110 rpm. Next, we investigated the synergistic activity—known as muscle synergy—of both the left and right legs based on the time frequency components of surface electromyography, along with the crank rotation angle during the pedaling exercise. The results indicate that the muscle synergy of bilateral muscle coordination reflects the motor adaptation to pedaling rate during cycling, and the functional roles of the left and right legs differ with changes in cadence and cycling experience. In conclusion, the motor control mechanism underlying pedaling skills is explained by the bilateral muscle coordination related to actions, such as pushing a pedal down using one leg, while pulling the other pedal up using the other leg during pedaling. This conclusion casts doubt on investigations into the efficiency of the pedaling done by a single leg.
PubDate: 2019-11-29

• Duplicating same argument of function to realize efficient hardware for
high-level synthesis
• Abstract: Abstract High-level synthesis (HLS) automatically converting software into hardware is a promising technology to reduce the design burden significantly. However, to use HLS technology efficiently, software program must be described considering the hardware organization that HLS tool will generate. We are developing the HLS image processing library. However, some caution is required when using HLS for programs that read images. When the same image is read through an argument of the function, the input port corresponding to this argument on the hardware generated by HLS tool may cause the port conflict. As a result, the image reading is made serialized and this serialization disturbs the performance of the data path well pipelined by the HLS tool. This paper shows how to write a software program to avoid this problem. In addition, we adapt this method to two image processing and evaluate the effect of our proposal to them.
PubDate: 2019-11-28

• Complex systems approaches to temporal soundspace partitioning in bird
communities as a self-organizing phenomenon based on behavioral plasticity

• Abstract: Abstract This paper introduces our several preliminary approaches toward understanding temporal soundspace partitioning in bird communities as a self-organizing phenomenon based on behavioral plasticity. First, we describe this phenomenon from our recordings, and show there are asymmetric relationships and the diversity in the temporal avoidance behaviors among the species, using transfer entropy analysis. Then, we consider the evolutionary significance of such a diversity using a computational experiment of the coevolution of the temporal overlap avoidance of singing behaviors among sympatric species with different species-specific song lengths, implying that diversity in the behavioral plasticity in bird communities can contribute to the more efficient establishment of the soundspace partitioning. Finally, we introduce our preliminary works on extracting the temporal dynamics of interaction processes among multiple birds from recordings with a microphone array using an open-source software system for robot audition called HARK.
PubDate: 2019-09-23

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327

Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs