Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

A mobile terminal including a body; a touchscreen provided to a front and extending to side of the body and configured to display content; and a controller configured to detect one side of the body comes into contact with one side of an external terminal, display a first area on the touchscreen corresponding to a contact area of the body and the external terminal and a second area including the content, receive an input of moving the content displayed in the second area to the first area, display the content in the first area, and share the content in the first area with the external terminal.

Mobile terminal and method for controlling the same

Journal of the American Statistical Association: William S. Cleveland, Marylyn E. McGill and Robert McGill, “The shape parameter for a two variable graph” 83 (1988) 289–300

Robotics and autonomous systems

https://www.jstage.jst.go.jp/article/jrsj/31/7/31_31_676/_pdf

Incremental Noise Estimation in Outdoor Auditory Scene Analysis using a Quadrocopter with a Microphone Array

This paper investigates Sound Source Localization (SSL) for a robot in a real world. Previously, we focused on one-dimensional SSL for azimuth and assumed that target sources are distributed close to a horizontal plane. Without this assumption, the SSL performance is drastically degraded. Thus, three-dimensional SSL is essential to improve the localization for sound sources distributed in a three-dimensional space. Compared to one-dimensional SSL, three-dimensional SSL mainly has the following problems: 1) a massive number of Transfer Function (TF) measurements for microphone array calibration are required for three dimensions to maintain the spatial resolution of SSL sufficiently-high, 2) the computational cost for searching for sound sources drastically increases in high-dimensional spaces. For the first issue, we extend the previously-proposed one-dimensional TF interpolation method, integrating time-domain-based and frequency-domain-based interpolation, to three dimensions. The interpolation achieves three-dimensional super-resolution SSL and reduction of the number of TF measurements while maintaining the spatial resolution of SSL. For the second issue, we propose optimal hierarchical SSL, which reduces computational cost for searching for sound sources by introducing a hierarchical search algorithm instead of using greedy search in localization. We previously proposed the concept of the algorithm. This paper additionally discusses theoretical optimality in hierarchization to minimize the total computational cost of SSL. The method determines the number of hierarchies and the resolution of each hierarchy depending on desired spatial resolution. These techniques are integrated into an SSL system using a robot. The experimental result showed: 1) the proposed interpolation method achieved super-resolution SSL working better than that with pre-measured TFs, 2) the optimal hierarchical SSL drastically reduced computational cost by approximately 97%.

Real-time super-resolution three-dimensional sound source localization for robots

Smart home technology is receiving significant attention. This is largely in response to an increase in the size of demographic those who require assistance due to reduced mobility, in particular, older adults. Smart home technology enables the assistance individuals with limited mobility need for their daily routines: these limitations can be addressed using modern ambient assisted living technologies. In particular we discuss the benefits of using electromyography (EMG) sensors to capture gestural input that would normally be difficult to sense in the absence of such sensors. With EMG, we can provide user control of a smart environment through the use of gestures based on muscle activity of the hands. This paper will focus on presenting the benefits of EMG technologies that can potentially assist individuals with hand mobility issues. We will describe the current state of EMG sensory technologies and their role in shaping gesture-based interaction techniques. We present our approach using such EMG signals and demonstrate their value in a smart home scenario. Finally we introduce the concept of subtle EMG gestures and build a better understanding of how we might improve accessibility for those with limited upper limb motion.

Smart Home Interactions for People with Reduced Hand Mobility Using Subtle EMG-Signal Gestures.

This paper tackles speaker localization in meeting recognition using a flexible microphone array whose microphone location is not given in advance. The existing microphone-array-based blind meeting recognition approaches including our previous work could estimate the number and activity periods of speakers. However, they have difficulties in estimating speaker location since location of microphones is not given. Thus, this paper proposes a novel self-calibration technique by introducing an array of acoustic signal emitters connected to the uncalibrated microphone array and proposes a probabilistic estimation of microphone location using the time-of-arrival of emitted signals, which can finally estimate location of speakers. The evaluation showed the proposed algorithm can estimate location of each speaker using meeting conversation recorded in a real reverberant meeting room.

Self-Calibration of Flexible Microphone Array for Speaker Localization in Meeting Conversations Using Emitters

In this paper, we present a method in suppressing speech degradation affecting human-robot communication in real reverberant environment condition. The novelty of the proposed method is the mechanism to indirectly incorporate language information in the enhancement process. This is achieved by considering the effects of the acoustic energy transfer of two consecutive words. The proposed method is categorized into two namely, a one-time computation of the smearing coefficients (offline mode) and the actual enhancement (online mode). In the offline mode, word pair smearing coefficients reflective of the inter-word energy transfer within a word pair are calculated and stored, creating a pool of smearing priors database. Then, the online robust enhancement process integrates this information to the conventional framewise enhancement method. In theory, the proposed method outperforms the conventional framewise-only enhancement since it is able to dynamically update the enhancement parameters based on the actual acoustic energy transfer between successive words during testing. Experiments using a humanoid robot inside a reverberant room confirms the effectiveness of the proposed method. Our method renders human-robot speech communication robust to the effect of reverberation as opposed to the conventional method.

Keisuke Nakamura

Papers

Incremental Noise Estimation in Outdoor Auditory Scene Analysis using a Quadrocopter with a Microphone Array

Real-time super-resolution three-dimensional sound source localization for robots

Smart Home Interactions for People with Reduced Hand Mobility Using Subtle EMG-Signal Gestures.

Self-Calibration of Flexible Microphone Array for Speaker Localization in Meeting Conversations Using Emitters

Mitigating the effects of reverberation for effective human-robot interaction in the real world